Method, device, vehicle and medium for processing driving experience data

Abstract

The present invention discloses a method, device, vehicle and medium for processing driving experience data, wherein the method comprises obtaining a user portrait and experience data of the user during driving a vehicle, wherein the experience data comprises human-computer interaction data and driving scene data; obtaining emotional data corresponding to a driving scene during the user's driving process based on the human-computer interaction data, analyzing the emotional data together with the driving scene data and vehicle configuration data in combination with the user portrait, wherein the user portrait is used to characterize the user's personal information characteristics; predicting the user's demand behavior based on the analysis result, and producing corresponding performance configuration optimization results according to the predicted user's demand behavior.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a method, device, vehicle and medium for processing driving experience data. Background Art

[0002] The automotive industry is transforming towards intelligence and networking. The new era of smart cars is also placing increasing demands on the vehicle manufacturing industry. How to improve the in-car human-machine interaction experience, improve driving safety, and meet the needs of different users in different scenarios has become a serious issue that engineers and designers in the automotive industry are thinking about together. With the increase in intelligent functions in the car, technological changes are driving changes in user behavior. The vehicle manufacturing industry urgently needs a way to quickly iterate and test the logic and functional perfection of the human-machine interface in the car, and to reasonably integrate the impact of the three dimensions of people, vehicles, and environment on the functions, as well as the vehicle machine requirements in different weather, road conditions, regions, and networking.

[0003] Therefore the prior art needs further development. Summary of the invention

[0004] In response to the above technical problems, the present invention provides a method, device, vehicle and medium for processing driving experience data.

[0005] A first aspect of an embodiment of the present invention provides a method for processing driving experience data, comprising:

[0006] Obtaining user portraits and user experience data during driving a vehicle, wherein the experience data includes human-computer interaction data and driving scenario data;

[0007] Acquire emotional data corresponding to a driving scene during the user's driving process based on the human-computer interaction data, and analyze the emotional data, the driving scene data, the vehicle model configuration data, and the user portrait, where the user portrait is used to characterize the user's personal information characteristics;

[0008] Based on the analysis results, the user's demand behavior is predicted, and the corresponding performance configuration optimization results are produced according to the predicted user's demand behavior.

[0009] Optionally, the acquiring, based on the human-computer interaction data, emotion data corresponding to a driving scene during the user's driving process includes:

[0010] Obtain voice, user expression images, user sitting posture data, and health data from human-computer interaction data;

[0011] The emotional data of the user during driving the vehicle is calculated based on the voice, user expression image, user sitting posture data, and health data, and the emotional data is classified according to driving scene tags.

[0012] Optionally, obtaining the user portrait and the user's experience data during driving the vehicle includes:

[0013] Obtain or collect data about the user based on user input or associated account information to form the user portrait;

[0014] Human-computer interaction data and driving scene data are obtained based on the human-computer interaction operations, driving environment, driving purpose, driving path, and user's driving status during driving, and the frequency of the human-computer interaction data and driving scene data is counted.

[0015] Optionally, analyzing the emotion data, the driving scenario data, the vehicle model configuration data and the user portrait includes:

[0016] Based on the driving scene data and vehicle model configuration data, the degree of correlation between the emotion type represented by the emotion data during driving and the driving scene is statistically analyzed to determine whether the emotion data is related to the vehicle model configuration data; if so, a user emotion curve is established, and the emotion curve is associated with the driving scene data, vehicle model configuration data and the user portrait for correlation analysis.

[0017] Optionally, if relevant, establishing a user emotion curve, and performing correlation analysis on the emotion curve, the driving scenario data, the vehicle model configuration data and the user portrait, including:

[0018] The user emotion curve is classified and processed according to the user type based on the user portrait, and the corresponding driving scene data and vehicle model configuration data are counted for different categories of user emotion curves. The driving scene data and vehicle model configuration data with large emotional fluctuations in the user emotion curve are classified and analyzed to form correlation data between function points and emotions.

[0019] Optionally, predicting the user's demand behavior based on the analysis result includes:

[0020] The user's acceptance of the function point is analyzed according to the association data between the function point and the emotion, and the user's demand behavior is predicted based on the acceptance degree.

[0021] Optionally, the method for processing driving experience data further includes: forming storyboard data with story symbols including vehicle functional points, vehicle configuration, and advantages and disadvantages labels, and presenting the performance configuration optimization results in the form of a storyboard.

[0022] A second aspect of an embodiment of the present invention provides a device for processing driving experience data, including:

[0023] An acquisition module is used to acquire a user portrait and user experience data during driving a vehicle, wherein the experience data includes human-computer interaction data and driving scenario data;

[0024] An analysis module, used to obtain emotional data corresponding to a driving scene during the user's driving process based on the human-computer interaction data, and analyze the emotional data with the driving scene data, vehicle configuration data and the user portrait, where the user portrait is used to characterize the user's personal information characteristics;

[0025] The prediction module is used to predict the user's demand behavior based on the analysis results, and produce corresponding performance configuration optimization results according to the predicted user's demand behavior.

[0026] Optionally, the analysis module includes:

[0027] The analysis subunit is used to obtain voice, user expression images, user sitting posture data, and health data in the human-computer interaction data; and calculate the user's emotional data during driving the vehicle based on the voice, user expression images, user sitting posture data, and health data, and the emotional data is classified according to the driving scene tags.

[0028] Optionally, the acquisition module includes:

[0029] The acquisition subunit is used to acquire or collect data about the user based on the user input or associated account information to form the user portrait; and to acquire human-computer interaction data and driving scene data based on the human-computer interaction operation, driving environment, driving purpose, driving path, and user's driving status during driving, and to perform frequency statistics on the human-computer interaction data and driving scene data.

[0030] Optionally, the analysis module includes:

[0031] The first analysis subunit is used to count the degree of correlation between the emotion type represented by the emotion data and the driving scene during driving based on the driving scene data and the vehicle model configuration data, and to determine whether the emotion data is related to the vehicle model configuration data; if so, a user emotion curve is established, and the emotion curve is associated with the driving scene data, the vehicle model configuration data and the user portrait for correlation analysis.

[0032] Optionally, the first analysis subunit includes:

[0033] The second analysis subunit is used to classify the user emotion curve according to the user type based on the user portrait, count the corresponding driving scene data and vehicle type configuration data for different categories of user emotion curves, classify and analyze the driving scene data and vehicle type configuration data with large emotional fluctuations in the user emotion curve, and form correlation data between function points and emotions.

[0034] Optionally, the prediction module includes:

[0035] The prediction submodule is used to analyze the user's acceptance of the function point according to the association data between the function point and the emotion, and predict the user's demand behavior based on the acceptance degree.

[0036] Optionally, the driving experience data processing device also includes an output module, which is used to form storyboard data with story symbols including vehicle functional points, vehicle configuration, and advantages and disadvantages labels, and present the performance configuration optimization results in the form of a storyboard.

[0037] According to a third aspect of an embodiment of the present invention, a vehicle is provided, comprising a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the method for processing driving experience data as described above are implemented.

[0038] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for processing driving experience data as described above are implemented.

[0039] In the technical solution provided by the present invention, through user portraits and user experience data during driving, the user's experience of vehicle functions can be analyzed and judged based on the user's emotional data combined with driving scenarios and vehicle configurations, thereby quickly collecting the user's impact on the vehicle configuration on the scene, which is convenient for the storyboard development of the scene library. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is an application scenario diagram of a method for processing driving experience data in an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of a method for processing driving experience data according to an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of collecting user portraits in an embodiment of the present invention;

[0043] Figure 4 Schematic diagram of the implementation process of step S200 in an embodiment of the present invention;

[0044] Figure 5 Schematic diagram of a remote automatic parking control device in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0046] With the rapid development of new energy, the domestic smart car industry has been developing rapidly. Technological innovation has changed the way drivers and passengers interact with cars, and new technologies are also driving the rapid iteration of the entire vehicle field. New technology development is based on human-machine touchpoints that are in close contact with drivers and passengers. At the same time, new technologies are also inseparable from multi-dimensional testing of scenarios. Precisely because scenarios play a vital role in the development of the automobile manufacturing industry, various companies are also constantly exploring ways to develop automotive scenarios. Although the industry attaches great importance to scenarios, the industry lacks an integrated scenario development method that can target different models and users and has strong scalability.

[0047] The human-machine interface of automobiles is developing rapidly as the number of in-car screens continues to increase and the screen size continues to increase. While the information presented on the in-car screens is becoming increasingly rich, the functional logic behind the screens is classified as a part that is strongly related to the user experience. The human-machine design of smart cars is an emerging and rapidly developing field in the industry. At present, the in-car human-machine interaction design relies heavily on web pages and APP designs in terms of vision and logic. However, due to the different ways in which users interact with in-car screens and with media such as mobile phones and computers, if the design logic is always used, it is easy to cause hidden dangers to driving safety. Therefore, the research on mobile product design is not necessarily universal in car computers, and it needs to be re-sorted according to different working conditions and vehicle configuration performance.

[0048] The configuration performance of different models varies widely, especially when targeting the usage habits of different drivers and passengers. It is difficult to cover all users, all working conditions, and all scenarios in the process of vehicle design, and the iteration cost of the vehicle testing process is high. The method provided in this application can target the conventional behavior patterns of most users, so that the vehicle body performance configuration and usage logic can meet the usage habits of the target users to the greatest extent, and improve the user experience of the audience.

[0049] The method for processing driving experience data provided in this application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The terminal 102 receives the user instruction and sends it to the server 104, so that the server 104 obtains the user portrait and the user's experience data in the process of driving the vehicle based on the received control instruction. Further, the server 104 can obtain the emotional data of the corresponding driving scene during the user's driving process based on the human-computer interaction data, and analyze the emotional data with the driving scene data and the vehicle configuration data in combination with the user portrait. Then, the server 104 can predict the user's demand behavior based on the analysis results, and produce corresponding performance configuration optimization results according to the predicted user's demand behavior. Among them, the terminal 102 can be but not limited to various vehicle sensors, vehicle controllers, vehicle human-computer interactions, personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0050] In one embodiment, Figure 2 As shown, Figure 2 Schematic diagram of a method for processing driving experience data in an embodiment of the present invention. The method for processing driving experience data comprises the following steps:

[0051] Step S100: Obtain a user portrait and user experience data during driving a vehicle, wherein the experience data includes human-computer interaction data and driving scenario data.

[0052] Specifically, the user profile is formed by obtaining or collecting data about the user from the user input or associated account information. For example, it includes the user's hand-drawn features, age and place of residence, family status, occupation, user classification label, hobbies, consumption concept, purpose of car purchase, car purchase mode and other aspects. There are various APP accounts in the vehicle system that can obtain the user's basic information. For example, the vehicle system logs in through WeChat, Alipay and other accounts, and can obtain the user's consumption concept and other information based on the user's shopping and payment information. Of course, the main information is mainly input by the user to ensure the accuracy of the information. For example, after purchasing a car, the user can enter the user's personal interests, hobbies, address, age, occupation and other information when customizing personal services.

[0053] The experience data described therein includes various kinds of data, which can be understood as all the data that can be collected by the user during the driving process. Of course, in order to complete the technical problem to be solved by this application, only part of the information can be extracted or directly obtained. In one embodiment, the experience data includes human-computer interaction data and driving scene data of the user during the driving process.

[0054] It should be noted that the driving process includes the pre-boarding stage (after entering the parking lot, when the user is 5 meters close to the car, and when the user walks to the side of the car), the post-boarding stage (after the user is seated and the vehicle starts), the driving stage (exiting the parking lot, smooth driving, congested driving, and vehicle jams), the temporary parking stage (temporary parking, start and stop at traffic lights), the arrival stage (about to arrive at the destination, after entering the parking lot, and after the vehicle is turned off), and the stage after the user gets off the vehicle.

[0055] The human-computer interaction data is reflected in the data of the user operating the vehicle, including the motor display screen, voice control, gesture control, stepping on the brake pedal, turning the steering wheel, adjusting the seat, adjusting the air conditioning, adjusting the rearview mirror, opening the sunroof, opening the APP, etc. The driving scene data includes environmental data during driving, driving purpose, weather conditions, road conditions, etc.

[0056] In order to obtain the user's experience during driving, human-computer interaction data and driving scene data can be obtained based on human-computer interaction operations, driving environment, driving purpose, driving path, and user's driving status during driving, and frequency statistics can be performed on human-computer interaction data and driving scene data. Frequency statistics facilitate calculation and analysis of user behavior patterns, such as data on users who often travel by car or drive in and out of airports. The configuration requirements for vehicles for travel and driving in and out of airports will have different focuses and vehicle configuration requirements; therefore, it is necessary to analyze and process user data.

[0057] Step S200: Acquire emotional data corresponding to a driving scenario during the user's driving process based on the human-computer interaction data, and analyze the emotional data together with the driving scenario data, vehicle configuration data, and the user portrait, wherein the user portrait is used to characterize the user's personal information characteristics.

[0058] User experience refers to the degree of recognition of the performance of the vehicle, including the needs in different driving scenarios, the demand for functions, the need for reversing radar configuration when parking, the need for automatic parking function when parking; when traveling, there is a need for the vehicle's intelligent recommendation function that can screen high-quality shopping stores, accommodations, and gas stations. Of course, users of different ages will have different needs. Generally, the needs of people in adjacent age groups are similar. Therefore, users can be classified according to age groups and user portraits can be developed. Developing user portraits based on age is only one implementation method. User portraits can also be developed based on the city where the user is located, such as users in Beijing, Shanghai, Guangzhou, and Shenzhen. For example, users in towns and users in rural areas, and so on. One or more user portraits can be constructed in different ways. The data for user portraits can be Figure 3 Collect and display in the manner shown.

[0059] Specifically, the user's emotion data during driving can be calculated based on the acquired speech, user expression image, user sitting posture data, and health data in the human-computer interaction data, and the emotion data can be classified based on the driving scene tags.

[0060] As an implementation method, the user emotion data can be analyzed and processed by an emotion recognition model, for example, by building an emotion recognition model by model training, wherein the model can adopt a federated learning model, for example, Federated machine learning or Federated Learning.

[0061] The emotional data can be customized by humans, and the model is used to calculate the result of the numerical judgment. In one example, it can be information such as "happy" and "unhappy" that represents the degree of a certain emotion. As quantifiable information, emotions can be represented by numerical values ​​to represent the degree of happiness, or they can be emotional information represented by "happy", "excited", "disappointed", etc.

[0062] Assume that the distribution of emotional data at a certain moment is: happy: -70%, unhappy: -20%, surprised: -7%, disappointed: -13%, and compare it with the original basic emotions. The value with a larger proportion is determined as the current emotion. As a way, matching evaluation data or deviation evaluation data can be the data distribution under a certain total amount of data. Since the total amount of data remains unchanged, the uniformity of the evaluation data scale can be guaranteed.

[0063] For example, if similar data is found, such as happy -40%, surprised -35%, or happy -42%, surprised -38%, and the difference between the two is small and less than the threshold, then it is necessary to confirm based on other data. For example, the above data is judged by video image data, such as micro-expression data, and the user's current emotion can also be judged by the user's voice information. Of course, judging the user's current emotion by voice can also be calculated using the emotion analysis model.

[0064] If the current user uses voice to express something, and the thing is related to the experience, voice recognition of emotions is preferred, and then the user's emotions are recognized in conjunction with images; of course, the recognition of the two can be performed independently. In addition, the user's health data, such as blood pressure, blood oxygen, pulse and other data can also be used as a reference data or correction data for judging the user's emotions. For example, the user's emotions can be monitored through a health bracelet. The bracelet can be used to measure and track the user's biological signals when worn, including skin electrical response, blood volume, pulse and skin temperature (autonomic nervous system).

[0065] After the user's driving emotions are obtained, the user's behavior can be analyzed in combination with the current driving scene, user's purpose and needs, etc. The user's purpose and needs can also be expressed in voice, and the emotional data is analyzed together with the driving scene data, vehicle configuration data and user portrait.

[0066] For example: what tasks do users need to complete during the human-vehicle interaction stage; what needs do users have at a certain stage, what are their demands, and what are their strengths and weaknesses; what pain points and excitement points do users have for vehicle configuration during driving; and what functional points can be explored based on the above information. Of course, these are scenario-based demand experience analyses of vehicle experience, which are specifically implemented in data analysis.

[0067] Step S300: predicting the user's demand behavior based on the analysis result, and producing corresponding performance configuration optimization results according to the predicted user's demand behavior.

[0068] In this step, the related data can be classified and analyzed, and the user's focus can be found using the cluster analysis algorithm. Usually, the location where the user's emotions fluctuate greatly corresponds to the driving scene, which is the scene mining point, and is also the embodiment of the user's needs during the vehicle driving process; the cluster analysis feature data is obtained by summarizing, and the more focused needs are output as the user's demand behavior. According to the user's demand behavior, different performance optimization configurations can be selected according to different models, or existing configurations can be increased, or new functions can be developed.

[0069] For example, according to the basic performance, intelligent driving, safety configuration, entertainment system, chassis system, internal and external configuration of different models, analyze the functions that meet user expectations, the special functions that represent product characteristics, the quality functions with optimization potential, and the additional functions that are not necessary to implement. After mining the user's pain points and improving the corresponding configuration performance, summarize the user emotion curve. And analyze the relationship between the actual cost and the solution effect in the solution. Describe the scene focus from different dimensions, such as safety scenes, emotional scenes, car networking scenes, multi-functional scenes, pre-consumption customization and after-sales service scenes, etc.

[0070] In the technical solution provided by the present invention, through user portraits and user experience data during driving, the user's experience of vehicle functions can be analyzed and judged based on the user's emotional data combined with driving scenarios and vehicle configurations, thereby quickly collecting the user's impact on the vehicle configuration on the scene, which is convenient for the storyboard development of the scene library.

[0071] Furthermore, the solution of this application can solve the problem that there are too many variable factors in the dimensions of people, cars, and environment in the new era of smart cars, which leads to the inability to sort out the logical confusion of the scene. At the same time, it optimizes the collaboration mode caused by the different thinking angles of staff in different fields of the vehicle industry. In the scene development stage, it is necessary to refer to the diagram to fill in and develop from top to bottom. In order to cover the scene perfection, it is not allowed to skip levels. In terms of testing the necessity and redundancy of functions, it is necessary to test from bottom to top, link by link, and analyze whether the emergence of each function optimizes the user's experience at a certain stage, what are the optimization links, how much is the cost, and how many users have the same feeling, and finally provide a basis for the configuration development of the vehicle.

[0072] Furthermore, the storyboard is a visual sketch of the software display effect, which can show the user's needs and the corresponding vehicle configuration data, thereby providing developers with a more intuitive development basis.

[0073] Story symbols including vehicle functional points, vehicle configuration, advantages and disadvantages labels can be assembled into storyboard data in advance. For example, a data group can be constructed with symbols related to vehicle configuration, such as automatic parking icons, chassis icons, advantages icons, disadvantages icons, display configuration icons, intelligent icons, etc. Then, based on the user demand behavior results analyzed above, the corresponding vehicle configuration can be predicted, and the performance configuration optimization results can be presented in the form of a storyboard by connecting story lines.

[0074] like Figure 4 As shown, Figure 4 The specific implementation process steps in the above step S200 specifically include the following contents:

[0075] Step S201: Based on the driving scene data and the vehicle model configuration data, statistics are collected on the degree of correlation between the emotion type represented by the emotion data during driving and the driving scene.

[0076] This step mainly analyzes whether the driving scene and vehicle configuration cause the user's emotional fluctuations, or have an impact on the user's needs, such as the process of obtaining the user's emotional data during driving through the artificial intelligence model in the above step S200.

[0077] Step S202: Determine whether the emotion data is related to the vehicle model configuration data.

[0078] Because the user's emotions are changeable, they are not necessarily caused by changes in driving scenarios or insufficient vehicle configuration. It may also be caused by the user's emotional fluctuations after answering a phone call. Therefore, it can be confirmed by obtaining the user's human-computer interaction data on the vehicle, such as judging whether the user is on a call through video images, call records, etc., and judging by the user's operation of the vehicle's center console, clicking on the center control screen, etc.

[0079] Step S203: If relevant, a user emotion curve is established, and the emotion curve is combined with the driving scenario data, vehicle configuration data and the user portrait for correlation analysis.

[0080] Specifically, the user emotion curve can be classified and processed according to the user type based on the user portrait, and the corresponding driving scene data and vehicle configuration data of different categories of user emotion curves can be counted. The driving scene data and vehicle configuration data with large emotional fluctuations in the user emotion curve can be classified and analyzed to form the correlation data between function points and emotions. For example, users of different age groups can be classified and counted, and of course, the user's personal historical data can also be counted. It is preferred to analyze the experience data during the user's emotional fluctuations.

[0081] Then, the user's acceptance of the function point is analyzed based on the association data between the function point and the emotion, and the user's demand behavior is predicted based on the acceptance degree. The vehicle configuration data is known, and the user's emotional expression of the vehicle function point is analyzed to determine whether the user is satisfied or has new needs.

[0082] For example, if the current traffic is congested and the user needs to find the nearest charging station to charge, the user uses voice to wake up the intelligent driving system to query the data of surrounding charging stations, but the location of the queried charging station is far away and cannot be reached in time due to the current traffic conditions. This will cause dissatisfaction among users, and users will have emotional fluctuations, such as unhappiness.

[0083] If the vehicle has a battery swap configuration, the need for charging at a charging station can be eliminated, and the user's needs can be met directly by replacing the battery. Therefore, data on the vehicle model configuration that users need to have a battery swap function in congested road conditions can be mined.

[0084] Through the analysis of the above steps, we can get the relationship between the user's driving experience and the user's different driving scenarios and different vehicle configurations, so as to analyze and judge the user's demands, and then judge whether the vehicle configuration is reasonable, whether it needs to be optimized, and whether new user needs can be discovered, so as to develop better driving scenarios and configure better functions. Based on the analysis results, scenarios can be developed according to different dimensions, such as safety scenarios, emotional scenarios, Internet of Vehicles scenarios, multi-functional scenarios, pre-consumption customization and after-sales service scenarios, etc.

[0085] like Figure 5 As shown, the present application also provides a device for processing driving experience data, including:

[0086] An acquisition module 510 is used to acquire a user portrait and user experience data during driving a vehicle, wherein the experience data includes human-computer interaction data and driving scene data;

[0087] An analysis module 520 is used to obtain emotional data corresponding to a driving scene during the user's driving process based on the human-computer interaction data, and analyze the emotional data with the driving scene data, vehicle configuration data and the user portrait, where the user portrait is used to characterize the user's personal information characteristics;

[0088] The prediction module 530 is used to predict the user's demand behavior based on the analysis results, and produce corresponding performance configuration optimization results according to the predicted user's demand behavior.

[0089] The analysis module 520 includes:

[0090] The analysis subunit is used to obtain voice, user expression images, user sitting posture data, and health data in the human-computer interaction data; and calculate the user's emotional data during driving the vehicle based on the voice, user expression images, user sitting posture data, and health data, and the emotional data is classified according to the driving scene tags.

[0091] The acquisition module 510 includes:

[0092] The acquisition subunit is used to acquire or collect data about the user based on the user input or associated account information to form the user portrait; and to acquire human-computer interaction data and driving scene data based on the human-computer interaction operation, driving environment, driving purpose, driving path, and user's driving status during driving, and to perform frequency statistics on the human-computer interaction data and driving scene data.

[0093] The analysis module 520 includes:

[0094] The first analysis subunit is used to count the degree of correlation between the emotion type represented by the emotion data and the driving scene during driving based on the driving scene data and the vehicle model configuration data, and to determine whether the emotion data is related to the vehicle model configuration data; if so, a user emotion curve is established, and the emotion curve is associated with the driving scene data, the vehicle model configuration data and the user portrait for correlation analysis.

[0095] The first analysis subunit comprises:

[0096] The second analysis subunit is used to classify the user emotion curve according to the user type based on the user portrait, count the corresponding driving scene data and vehicle type configuration data for different categories of user emotion curves, classify and analyze the driving scene data and vehicle type configuration data with large emotional fluctuations in the user emotion curve, and form correlation data between function points and emotions.

[0097] The prediction module 530 includes:

[0098] The prediction submodule is used to analyze the user's acceptance of the function point according to the association data between the function point and the emotion, and predict the user's demand behavior based on the acceptance degree.

[0099] The driving experience data processing device also includes an output module, which is used to form storyboard data with story symbols including vehicle functional points, vehicle configuration, and advantages and disadvantages labels, and present the performance configuration optimization results in the form of a storyboard.

[0100] The present invention also provides a vehicle, comprising a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the steps of the above-mentioned method for processing driving experience data when executed by the processor.

[0101] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for processing driving experience data are implemented.

[0102] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0103] It can be understood that computer-readable storage media may include: any entity or device capable of carrying a computer program, recording media, USB flash drives, mobile hard disks, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc. A computer program includes computer program code. The computer program code may be in source code form, object code form, executable file, or some intermediate form, etc. A computer-readable storage medium may include: any entity or device capable of carrying a computer program code, recording media, USB flash drives, mobile hard disks, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0104] In certain embodiments of the present invention, the device may include a controller, which is a single-chip microcomputer chip that integrates a processor, a memory, a communication module, etc. The processor may refer to a processor included in the controller. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.

[0105] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0106] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processing module or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing driving experience data, used to provide a development basis for developers, characterized in that: include: Obtaining user portraits and user experience data during driving a vehicle, wherein the experience data includes human-computer interaction data and driving scenario data; Acquire emotional data corresponding to a driving scene during the user's driving process based on the human-computer interaction data, and analyze the emotional data, the driving scene data, the vehicle model configuration data, and the user portrait, where the user portrait is used to characterize the user's personal information characteristics; Predicting user demand behavior based on the analysis results, and producing corresponding performance configuration optimization results according to the predicted user demand behavior, wherein the performance configuration optimization results include selecting different performance optimization configurations according to different vehicle models, or increasing existing configurations, or developing new functions; Among them, based on the driving scene data and the vehicle model configuration data, the correlation degree between the emotion type represented by the emotion data during driving and the driving scene is counted to determine whether the emotion data is related to the vehicle model configuration data; if so, a user emotion curve is established, and the emotion curve is combined with the driving scene data, the vehicle model configuration data and the user portrait for correlation analysis, including classifying the user emotion curve according to the user type according to the user portrait, counting the corresponding driving scene data and vehicle model configuration data for different categories of user emotion curves, and classifying and analyzing the driving scene data and vehicle model configuration data with large emotion fluctuations in the user emotion curve to form correlation data between function points and emotions, In addition, story symbols including vehicle functional points, vehicle configuration, and advantages and disadvantages labels are combined into storyboard data, and the performance configuration optimization results are presented in the form of a storyboard.

2. The method for processing driving experience data according to claim 1, characterized in that: The acquiring of emotion data corresponding to the driving scene during the user's driving process based on the human-computer interaction data includes: Obtain voice, user expression images, user sitting posture data, and health data from human-computer interaction data; The emotional data of the user during driving the vehicle is calculated based on the voice, user expression image, user sitting posture data, and health data, and the emotional data is classified according to driving scene tags.

3. The method for processing driving experience data according to claim 1, characterized in that: The obtaining of the user portrait and the user's experience data during driving the vehicle includes: Obtain or collect data about the user based on user input or associated account information to form the user portrait; Human-computer interaction data and driving scene data are obtained based on the human-computer interaction operations, driving environment, driving purpose, driving path, and user's driving status during driving, and the frequency of the human-computer interaction data and driving scene data is counted.

4. The method for processing driving experience data according to claim 1, characterized in that: The predicting of user demand behavior based on the analysis result includes: The user's acceptance of the function point is analyzed according to the association data between the function point and the emotion, and the user's demand behavior is predicted based on the acceptance degree.

5. A device for processing driving experience data, used to provide a development basis for developers, characterized in that: include: An acquisition module is used to acquire a user portrait and user experience data during driving a vehicle, wherein the experience data includes human-computer interaction data and driving scenario data; An analysis module, used to obtain emotional data corresponding to a driving scene during the user's driving process based on the human-computer interaction data, and analyze the emotional data with the driving scene data, vehicle configuration data and the user portrait, where the user portrait is used to characterize the user's personal information characteristics; A prediction module, used to predict the user's demand behavior based on the analysis results, and produce corresponding performance configuration optimization results according to the predicted user's demand behavior, wherein the performance configuration optimization results include selecting different performance optimization configurations according to different vehicle models, or adding existing configurations, or developing new functions; Wherein, the analysis module includes a first analysis subunit, which is used to count the correlation between the emotion type represented by the emotion data and the driving scene during driving based on the driving scene data and the vehicle model configuration data, and determine whether the emotion data is related to the vehicle model configuration data; if so, establish a user emotion curve, and perform correlation analysis on the emotion curve, the driving scene data, the vehicle model configuration data and the user portrait; wherein the first analysis subunit includes a second analysis subunit, which is used to classify the user emotion curve according to the user portrait according to the user type, count the corresponding driving scene data and vehicle model configuration data for different categories of user emotion curves, classify and analyze the driving scene data and vehicle model configuration data with large emotion fluctuations in the user emotion curve, and form correlation data between function points and emotions; The output module is used to form storyboard data from story symbols including vehicle functional points, vehicle configuration, and advantages and disadvantages labels, and to present the performance configuration optimization results in the form of a storyboard.

6. The device for processing driving experience data according to claim 5, characterized in that: The analysis module comprises: The analysis subunit is used to obtain voice, user expression images, user sitting posture data, and health data in the human-computer interaction data; and calculate the user's emotional data during driving the vehicle based on the voice, user expression images, user sitting posture data, and health data, and the emotional data is classified according to the driving scene tags.

7. The device for processing driving experience data according to claim 5, characterized in that: The acquisition module comprises: The acquisition subunit is used to acquire or collect data about the user based on the user input or associated account information to form the user portrait; and to acquire human-computer interaction data and driving scene data based on the human-computer interaction operation, driving environment, driving purpose, driving path, and user's driving status during driving, and to perform frequency statistics on the human-computer interaction data and driving scene data.

8. The device for processing driving experience data according to claim 5, characterized in that: The prediction module comprises: The prediction submodule is used to analyze the user's acceptance of the function point according to the association data between the function point and the emotion, and predict the user's demand behavior based on the acceptance degree.

9. A vehicle, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the method for processing driving experience data according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for processing driving experience data according to any one of claims 1 to 4 are implemented.

Images