Vehicle cabin scene automatic construction method, device and equipment and storage medium

Abstract

The invention discloses a vehicle cabin scene automatic construction method, device and equipment and a storage medium, and relates to the technical field of vehicle control, the method comprises the steps that instruction data input by a current user and associated data corresponding to a current vehicle are collected, and the associated data comprise in-vehicle state data and out-vehicle environment data of the current vehicle; determining a demand service and an experience dimension corresponding to the current user according to the instruction data and the associated data; and constructing a target cabin scene matched with the current user in the current vehicle based on the demand service and the experience dimension. The demand service and the experience dimension corresponding to the current user are determined according to the instruction data input by the current user and the in-vehicle state data and the out-vehicle environment data corresponding to the current vehicle, and then the target cabin scene matched with the current user is constructed in the current vehicle based on the demand service and the experience dimension. The technical problem that in the prior art, complex or abstract requirements cannot be recognized to automatically construct a vehicle cabin scene is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a method, device, equipment and storage medium for automatically constructing a vehicle cockpit scene. Background Art

[0002] Service-oriented architecture (SOA) is a key technology for software-defined smart cars. Under the SOA architecture, software and hardware are decoupled, and diversified and iterative functional combinations are achieved through mutual calls. These functional modules are connected to form a "travel scenario", which effectively improves the personalized car experience. Mainstream car manufacturers in the market have successively launched their own SOA architectures. Users can edit the combination of trigger conditions, execution actions, etc. in the form of drag and drop to create personalized vehicle cockpit scenes, or directly import official preset scenes and user co-created scenes. The current cockpit scenes of smart cars have problems such as limited number of preset scenes, complex autonomous programming capabilities, and high learning costs, which make the SOA architecture unable to be fully utilized.

[0003] At present, in order to solve these problems, the existing technology combines a large language model, that is, after receiving the user's scenario requirements, the large model converts the user's requirements into a computer language for creating scenarios, automatically creates scenarios or directly calls the corresponding SOA atomic capabilities of the car to meet the user's current needs. However, the existing technology only targets simple instructions or clear requirements, and cannot cope with complex or abstract requirements. Summary of the invention

[0004] The main purpose of this application is to provide a method, device, equipment and storage medium for automatically constructing a vehicle cockpit scene, aiming to solve the technical problem that the prior art is unable to identify complex or abstract requirements to automatically construct a vehicle cockpit scene.

[0005] To achieve the above objectives, the present application provides a method for automatically constructing a vehicle cockpit scene, the method comprising the following steps:

[0006] Collecting the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle state data and the out-vehicle environment data of the current vehicle;

[0007] Determine the required service and experience dimension corresponding to the current user according to the instruction data and the associated data;

[0008] A target cockpit scene adapted to the current user is constructed in the current vehicle based on the demand service and the experience dimension.

[0009] In one embodiment, the step of determining the required service and experience dimension corresponding to the current user according to the instruction data and the associated data includes:

[0010] Inputting the instruction data and the associated data into a vertical large model of a travel scenario to obtain the user travel intention of the current user;

[0011] In the vertical large model of the travel scenario, the required services and experience dimensions corresponding to the current user are determined according to the user's travel intention.

[0012] In one embodiment, the step of determining the required service and experience dimension corresponding to the current user according to the user's travel intention in the vertical large model of the travel scenario includes:

[0013] Parsing the user's travel intention in the travel scenario vertical model to obtain a service architecture corresponding to the user's travel intention;

[0014] Determine the demand service corresponding to the current user according to the service architecture, and split the user's travel intention into dimensions based on the demand service to obtain the experience dimension corresponding to the current user.

[0015] In one embodiment, the vertical large model of the travel scene is constructed based on the thought chain, and the training steps of the vertical large model of the travel scene include:

[0016] After cleaning and preprocessing the historical data set, a training data set is obtained, and a feature label is assigned to each data in the training data set;

[0017] The initial model is trained and optimized based on the training data set and the feature labels to obtain a vertical large model of the travel scene, and the initial model is a general large model for performing text classification tasks.

[0018] In one embodiment, the step of constructing a target cockpit scene adapted to the current user in the current vehicle based on the required service and the experience dimension includes:

[0019] Acquire a correlation coefficient between the demand service and the experience dimension, where the correlation coefficient is used to represent a quantitative value of the degree of association between the demand service and the experience dimension;

[0020] The optimal gear value corresponding to the demand service is determined by the correlation coefficient, and a target cockpit scene adapted to the current user is constructed in the current vehicle according to the optimal gear value.

[0021] In one embodiment, the step of determining the optimal gear value corresponding to the demand service by using the correlation coefficient includes:

[0022] If there is no mutually exclusive relationship between the demand services, determining the optimal gear value corresponding to the demand service according to a mapping table between the correlation coefficient and the demand service;

[0023] If there is a mutually exclusive relationship between the demand services, a weight is assigned to the correlation coefficient according to the mutually exclusive relationship, and then the optimal gear value corresponding to the demand service is determined according to the correlation coefficient after the weight is assigned.

[0024] In addition, to achieve the above purpose, the present application also proposes a vehicle cockpit scene automatic construction device, the vehicle cockpit scene automatic construction device comprising:

[0025] A data collection module, used to collect the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle state data and the out-vehicle environment data of the current vehicle;

[0026] A data analysis module, used to determine the required service and experience dimension corresponding to the current user according to the instruction data and the associated data;

[0027] A scene construction module is used to construct a target cockpit scene adapted to the current user in the current vehicle based on the required service and the experience dimension.

[0028] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle cockpit scene automatic construction device, which includes: a memory, a processor, and a vehicle cockpit scene automatic construction program stored on the memory and executable on the processor, and the vehicle cockpit scene automatic construction program is configured to implement the steps of the vehicle cockpit scene automatic construction method as described above.

[0029] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and on which is stored a vehicle cockpit scene automatic construction program, and when the vehicle cockpit scene automatic construction program is executed by a processor, the steps of the vehicle cockpit scene automatic construction method as described above are implemented.

[0030] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer program product, which includes a vehicle cockpit scene automatic construction program, and when the vehicle cockpit scene automatic construction program is executed by a processor, it implements the steps of the vehicle cockpit scene automatic construction method as described above.

[0031] The present application collects the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle status data and the external environment data of the current vehicle; determines the required services and experience dimensions corresponding to the current user according to the command data and the associated data; and constructs a target cockpit scene adapted to the current user in the current vehicle based on the required services and the experience dimensions. Compared with the traditional vehicle cockpit scene construction method, the above method of the present application determines the required services and experience dimensions corresponding to the current user according to the command data input by the current user and the in-vehicle status data and the external environment data corresponding to the current vehicle, and then constructs a target cockpit scene adapted to the current user in the current vehicle based on the required services and experience dimensions, thereby solving the technical problem that the prior art cannot identify complex or abstract requirements to automatically construct vehicle cockpit scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the structure of a vehicle cockpit scene automatic construction device in the hardware operating environment involved in the embodiment of the present application;

[0033] Figure 2 This is a flow chart of the first embodiment of the method for automatically constructing a vehicle cockpit scene of the present application;

[0034] Figure 3 This is a flow chart of the second embodiment of the method for automatically constructing a vehicle cockpit scene of the present application;

[0035] Figure 4 This is a flow chart of the third embodiment of the method for automatically constructing a vehicle cockpit scene of the present application;

[0036] Figure 5 This is a structural block diagram of the first embodiment of the vehicle cockpit scene automatic construction device of the present application.

[0037] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0038] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0039] Reference Figure 1 , Figure 1 A schematic diagram of the device structure is automatically constructed for a vehicle cockpit scenario in the hardware operating environment involved in the embodiment of the present application.

[0040] like Figure 1As shown, the vehicle cockpit scene automatic construction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0041] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the vehicle cockpit scene automatic construction device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0042] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a vehicle cockpit scene automatic construction program.

[0043] exist Figure 1 In the vehicle cockpit scene automatic construction device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the vehicle cockpit scene automatic construction device of the present application can be set in the vehicle cockpit scene automatic construction device, and the vehicle cockpit scene automatic construction device calls the vehicle cockpit scene automatic construction program stored in the memory 1005 through the processor 1001, and executes the vehicle cockpit scene automatic construction method provided in the embodiment of the present application.

[0044] The present application embodiment provides a method for automatically constructing a vehicle cockpit scene, referring to Figure 2 , Figure 2 This is a flow chart of the first embodiment of the method for automatically constructing a vehicle cockpit scene of the present application.

[0045] In this embodiment, the vehicle cockpit scene automatic construction method includes the following steps:

[0046] Step S10: collecting the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle state data and the out-of-vehicle environment data of the current vehicle.

[0047] It should be noted that the execution subject of the method of this embodiment can be a terminal device with data analysis, data processing and program running functions, such as an intelligent vehicle machine, a computer, etc., or an electronic device with the same or similar functions, such as the above-mentioned vehicle cockpit scene automatic construction device. The following takes the vehicle cockpit scene automatic construction device as an example to illustrate this embodiment and the following embodiments.

[0048] It is understandable that the above instruction data can be generated according to text instructions manually input by the user, or according to voice instructions issued by the user.

[0049] It should be understood that the above-mentioned in-vehicle status data may include but is not limited to cruising range, vehicle speed, lighting status, handbrake status, door status, window status, steering angle, fuel percentage, battery percentage, engine and brake status, etc., and the above-mentioned external vehicle environment data may include but is not limited to traffic, pedestrians, road conditions, weather conditions, traffic signs, signal lights, etc.

[0050] In a specific implementation, the above command data input by the current user and the associated data corresponding to the current vehicle can be collected through a vehicle-mounted data collection terminal (such as T-BOX). The vehicle-mounted data collection terminal is usually built into the vehicle and is responsible for collecting and transmitting vehicle data. These terminals can obtain the command data input by the user and the associated data corresponding to the vehicle through communication with the vehicle ECU (electronic control unit).

[0051] Step S20: Determine the required service and experience dimension corresponding to the current user according to the instruction data and the associated data.

[0052] It should be noted that the above-mentioned demand services represent services published by SOA (Service-Oriented Architecture) to meet user needs, and the above-mentioned experience dimensions represent the dimensions for describing and evaluating the current user's perception and feelings of the demand services and the depth and breadth of the user experience. For example, taking driving and control as an example, the corresponding demand services may include but are not limited to automatic driving mode switching, steering wheel force adjustment, braking force, steering assistance, path planning and navigation services, parking assistance (automatic parking), etc., and the corresponding experience dimensions may include the degree of automation, operation portability, safety, riding experience, environmental quality, etc.

[0053] Step S30: constructing a target cockpit scene adapted to the current user in the current vehicle based on the required service and the experience dimension.

[0054] In a specific implementation, the scene parameters of the vehicle can be determined based on the above-mentioned demand services and experience dimensions, and then a target cockpit scene adapted to the current user can be constructed in the current vehicle according to the scene parameters.

[0055] This embodiment collects the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle status data and the external environment data of the current vehicle; determines the required services and experience dimensions corresponding to the current user according to the command data and the associated data; and constructs a target cockpit scene adapted to the current user in the current vehicle based on the required services and the experience dimensions. Compared with the traditional vehicle cockpit scene construction method, the above method of this embodiment determines the required services and experience dimensions corresponding to the current user according to the command data input by the current user and the in-vehicle status data and the external environment data corresponding to the current vehicle, and then constructs a target cockpit scene adapted to the current user in the current vehicle based on the required services and experience dimensions, thereby solving the technical problem that the prior art cannot identify complex or abstract requirements to automatically construct vehicle cockpit scenes.

[0056] refer to Figure 3 , Figure 3 This is a flow chart of the second embodiment of the method for automatically constructing a vehicle cockpit scene of the present application.

[0057] In a feasible implementation manner, the step S20 may include:

[0058] Step S201: input the instruction data and the associated data into a vertical large model of a travel scenario to obtain the travel intention of the current user.

[0059] Step S202: Determine the required services and experience dimensions corresponding to the current user according to the user's travel intention in the vertical large model of the travel scenario.

[0060] It should be noted that the above-mentioned vertical model of travel scenarios can be constructed based on the thought chain. The thought chain refers to breaking down a logically complex problem and forming a complete thinking process through a series of logically related thinking. These steps or ideas are connected to each other to form a coherent thinking thread.

[0061] It should be understood that the training steps of the above-mentioned vertical large model of travel scenarios may include: cleaning and preprocessing the historical data set to obtain a training data set, and assigning feature labels to each data in the training data set; training and optimizing the initial model based on the training data set and the feature labels to obtain a vertical large model of travel scenarios, and the initial model is a general large model for performing text classification tasks. Specifically, the above-mentioned initial model may include but is not limited to a llama model, a glm model, a baichuan model, etc.

[0062] In the specific implementation, the above-mentioned travel scenario vertical big model has undergone fine-tuning from the general big model to the automobile industry vertical big model, and then to the vertical big model fine-tuned only for travel scenarios. Among them, the automobile industry big model collects a large amount of automobile-related official documents / guidelines, automobile forums and social media, automobile industry reports, automobile customer service evaluations, automobile-related literature and patent databases, and automobile software data as the first step of the data set through crawlers and manual downloads, while the company's cloud SOA metadata, user travel feedback data, automobile blogger evaluation corpus data, and user real behavior buried data are used as the data set of the travel scenario vertical big model.

[0063] In another feasible implementation, the specific training steps of the vertical large model of the travel scene can also be referred to as follows: clean and preprocess the data set, standardize the text content, and encode the classification label; select open source and suitable pre-trained models for text classification tasks, such as llama, glm, and baichuan as training models, use the lora partial parameter adjustment method to introduce low-order matrices to simulate full fine-turning to achieve parameter adjustment, and configure the rank and alpha value to achieve the best effect; automotive industry experts participate in the scoring of the answers related to the car scene output by the annotation model, and train the corresponding reward model so that it can automatically perform supervised training to guide the output of professional smart car content; select a suitable loss function such as the cross entropy loss function for model training, the learning rate is 1e-5 or 2e-5, the batch size is set to 8 or 16 according to the GPU memory size, the number of training rounds is 2 to 4 rounds, and the weight decay is about 0.01. The process includes forward propagation, loss calculation, back propagation and weight update, and finally updates the weights of some model parameters.

[0064] In a feasible implementation manner, the step S202 may include:

[0065] Step S2021: Analyze the user's travel intention in the vertical large model of the travel scenario to obtain a service architecture corresponding to the user's travel intention.

[0066] Step S2022: Determine the demand service corresponding to the current user according to the service architecture, and split the user's travel intention into dimensions based on the demand service to obtain the experience dimension corresponding to the current user.

[0067] In specific implementation, the above user travel intentions can be split into various experience dimensions in the vertical big model of travel scenarios, such as seat comfort, climate control, acoustic comfort, handling and driving performance, infotainment and connectivity, safety and other experience dimensions. Based on the powerful natural language understanding ability and extensive knowledge base of the big model, combined with the thought chain examples provided to the big model, we can directly input instructions to help us generate dimension scores and write out the derivation process. For example, when a user expresses in the car, "I am about to have a meeting in the car", the big model splits the user's intention into various experience dimensions. The following is the split result: (1) Seat and space: Sitting comfort and spaciousness are key to ensure that participants can maintain a good body posture and reduce fatigue when sitting for a long time; (2) Acoustic comfort: Noise level is crucial to ensure that the meeting is not disturbed by external noise, and the voice communication in the car (whether face-to-face or through the car microphone) is clear and accurate; (3) Climate control: The temperature suitability and humidity index need to be carefully adjusted to create a user's favorite temperature and a comfortable air circulation environment to help concentrate for a long time. In this way, we can obtain the user’s specific demands in these three dimensions of vehicle experience through the user’s abstract instructions.

[0068] In this embodiment, the user travel intention of the current user is obtained by inputting the instruction data and the associated data into the vertical big model of the travel scene; the vertical big model of the travel scene is constructed based on the thinking chain, and the training step of the vertical big model of the travel scene includes cleaning and preprocessing the historical data set to obtain the training data set, and assigning feature labels to each data in the training data set; the initial model is trained and optimized based on the training data set and the feature labels to obtain the vertical big model of the travel scene, and the initial model is a general big model for performing text classification tasks; the user travel intention is parsed in the vertical big model of the travel scene to obtain the service architecture corresponding to the user travel intention; the demand service corresponding to the current user is determined according to the service architecture, and the user travel intention is dimensionally split based on the demand service to obtain the experience dimension corresponding to the current user. Compared with the traditional vehicle cabin scene construction method, the above method of this embodiment constructs a vertical big model of the travel scene based on the thinking chain, and the user travel intention is parsed through the vertical big model of the travel scene, so as to accurately split the user travel intention into various experience dimensions, thereby improving the accuracy of the analysis of user needs in this embodiment.

[0069] refer to Figure 4 , Figure 4 This is a flow chart of the third embodiment of the method for automatically constructing a vehicle cockpit scene of the present application.

[0070] In a feasible implementation manner, the step S30 may include:

[0071] Step S301: obtaining a correlation coefficient between the demand service and the experience dimension, wherein the correlation coefficient is used to represent a quantitative value of a correlation degree between the demand service and the experience dimension.

[0072] Step S302: determining the optimal gear value corresponding to the demand service through the correlation coefficient, and constructing a target cockpit scene adapted to the current user in the current vehicle according to the optimal gear value.

[0073] In a specific implementation, a correlation coefficient table can be constructed to represent the quantitative value of the correlation between the demand service and the experience dimension. The quantitative value of the correlation can be used to describe and evaluate the functional characteristics of each demand service and the value of the user experience dimension.

[0074] In a feasible implementation manner, the step S302 may include:

[0075] Step S3021: If there is no mutually exclusive relationship between the demand services, then determining the optimal gear value corresponding to the demand service according to a mapping table between the correlation coefficient and the demand service.

[0076] Step S3022: If there is a mutually exclusive relationship between the demand services, a weight is assigned to the correlation coefficient according to the mutually exclusive relationship, and then the optimal gear value corresponding to the demand service is determined by the correlation coefficient after the weight is assigned.

[0077] In the specific implementation, with the correlation coefficient table, each experience dimension can be directly mapped to the corresponding service through the coefficient. When there is no mutually exclusive relationship, the services with a correlation coefficient ≥ 60 (correlation threshold) are screened out, and the scene adjustment can be completed by adjusting the service corresponding to the experience dimension to the best gear. For example, if you need to adjust the safest driving mode, you can directly find the relevant service and adjust it to the maximum value. When there is a mutually exclusive relationship, for example, a "driving mode suitable for experienced drivers and safe" is currently needed, the model analysis involves the experience dimensions of automation and safety. The services involved in the two have a negative relationship (that is, the higher the automation, the lower the safety). Users need to meet low automation and high safety. Therefore, the model needs to analyze the weights first, and then determine the optimal gear value corresponding to the required service by assigning the weighted correlation coefficient.

[0078] This embodiment obtains the correlation coefficient between the demand service and the experience dimension, and the correlation coefficient is used to represent the quantitative value of the degree of association between the demand service and the experience dimension; if there is no mutually exclusive relationship between the demand services, the optimal gear value corresponding to the demand service is determined according to the mapping table between the correlation coefficient and the demand service; if there is a mutually exclusive relationship between the demand services, a weight is assigned to the correlation coefficient according to the mutually exclusive relationship, and then the optimal gear value corresponding to the demand service is determined according to the weighted correlation coefficient; and a target cockpit scene adapted to the current user is constructed in the current vehicle according to the optimal gear value. Compared with the traditional vehicle cockpit scene construction method, the above method of this embodiment determines the optimal gear value according to the correlation coefficient between the demand service and the experience dimension, so that a target cockpit scene that is more adapted to the current user can be constructed in the current vehicle according to the optimal gear value, thereby improving the current user's vehicle experience.

[0079] In addition, an embodiment of the present application further proposes a storage medium, on which a vehicle cockpit scene automatic construction program is stored. When the vehicle cockpit scene automatic construction program is executed by a processor, the steps of the vehicle cockpit scene automatic construction method described above are implemented.

[0080] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the vehicle cockpit scene automatic construction device of the present application.

[0081] like Figure 5 As shown, the vehicle cockpit scene automatic construction device proposed in the embodiment of the present application includes:

[0082] The data collection module 501 is used to collect the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle state data and the external environment data of the current vehicle;

[0083] A data analysis module 502, configured to determine the required service and experience dimension corresponding to the current user according to the instruction data and the associated data;

[0084] The scene construction module 503 is used to construct a target cockpit scene adapted to the current user in the current vehicle based on the required service and the experience dimension.

[0085] This embodiment collects the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle status data and the external environment data of the current vehicle; determines the required services and experience dimensions corresponding to the current user according to the command data and the associated data; and constructs a target cockpit scene adapted to the current user in the current vehicle based on the required services and the experience dimensions. Compared with the traditional vehicle cockpit scene construction method, the above method of this embodiment determines the required services and experience dimensions corresponding to the current user according to the command data input by the current user and the in-vehicle status data and the external environment data corresponding to the current vehicle, and then constructs a target cockpit scene adapted to the current user in the current vehicle based on the required services and experience dimensions, thereby solving the technical problem that the prior art cannot identify complex or abstract requirements to automatically construct vehicle cockpit scenes.

[0086] Based on the first embodiment of the automatic vehicle cockpit scene construction device of the present application, a second embodiment of the automatic vehicle cockpit scene construction device of the present application is proposed.

[0087] In this embodiment, the data analysis module 502 is also used to input the instruction data and the associated data into the vertical big model of the travel scene to obtain the user travel intention of the current user; in the vertical big model of the travel scene, determine the demand service and experience dimension corresponding to the current user according to the user travel intention.

[0088] Furthermore, the data analysis module 502 is also used to analyze the user's travel intention in the travel scene vertical big model to obtain a service architecture corresponding to the user's travel intention; determine the demand service corresponding to the current user according to the service architecture, and divide the user's travel intention into dimensions based on the demand service to obtain the experience dimension corresponding to the current user. The travel scene vertical big model is constructed based on the thought chain, and the training steps of the travel scene vertical big model include: cleaning and preprocessing the historical data set to obtain a training data set, and assigning feature labels to each data in the training data set; training and optimizing the initial model based on the training data set and the feature labels to obtain a travel scene vertical big model, and the initial model is a general big model for performing text classification tasks.

[0089] Furthermore, the scenario construction module 503 is also used to obtain a correlation coefficient between the demand service and the experience dimension, wherein the correlation coefficient is used to represent a quantitative value of the degree of association between the demand service and the experience dimension; the optimal gear value corresponding to the demand service is determined by the correlation coefficient, and a target cockpit scene adapted to the current user is constructed in the current vehicle according to the optimal gear value.

[0090] Furthermore, the scenario construction module 503 is also used to determine the optimal gear value corresponding to the demand service based on a mapping table between the correlation coefficient and the demand service if there is no mutually exclusive relationship between the demand services; if there is a mutually exclusive relationship between the demand services, assign weights to the correlation coefficients based on the mutually exclusive relationship, and then determine the optimal gear value corresponding to the demand service through the correlation coefficients after the weighted assignment.

[0091] Other embodiments or specific implementation methods of the vehicle cockpit scene automatic construction device of the present application can refer to the above-mentioned method embodiments and will not be repeated here.

[0092] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0093] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0094] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0095] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for automatically constructing a vehicle cockpit scene, characterized in that: The method comprises the following steps: Collecting the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle state data and the out-vehicle environment data of the current vehicle; Determine the required service and experience dimension corresponding to the current user according to the instruction data and the associated data; A target cockpit scene adapted to the current user is constructed in the current vehicle based on the demand service and the experience dimension.

2. The method for automatically constructing a vehicle cockpit scene according to claim 1, characterized in that: The step of determining the required service and experience dimension corresponding to the current user according to the instruction data and the associated data includes: Inputting the instruction data and the associated data into a vertical large model of a travel scenario to obtain the user travel intention of the current user; In the vertical large model of the travel scenario, the required services and experience dimensions corresponding to the current user are determined according to the user's travel intention.

3. The method for automatically constructing a vehicle cockpit scene according to claim 2, characterized in that: The step of determining the required service and experience dimension corresponding to the current user according to the user's travel intention in the vertical large model of the travel scenario includes: Parsing the user's travel intention in the travel scenario vertical model to obtain a service architecture corresponding to the user's travel intention; Determine the demand service corresponding to the current user according to the service architecture, and split the user's travel intention into dimensions based on the demand service to obtain the experience dimension corresponding to the current user.

4. The method for automatically constructing a vehicle cockpit scene according to claim 3, characterized in that: The vertical large model of the travel scenario is constructed based on the thought chain, and the training steps of the vertical large model of the travel scenario include: After cleaning and preprocessing the historical data set, a training data set is obtained, and a feature label is assigned to each data in the training data set; The initial model is trained and optimized based on the training data set and the feature labels to obtain a vertical large model of the travel scene, and the initial model is a general large model for performing text classification tasks.

5. The method for automatically constructing a vehicle cockpit scene according to claim 1, characterized in that: The step of constructing a target cockpit scene adapted to the current user in the current vehicle based on the required service and the experience dimension includes: Acquire a correlation coefficient between the demand service and the experience dimension, where the correlation coefficient is used to represent a quantitative value of the degree of association between the demand service and the experience dimension; The optimal gear value corresponding to the demand service is determined by the correlation coefficient, and a target cockpit scene adapted to the current user is constructed in the current vehicle according to the optimal gear value.

6. The method for automatically constructing a vehicle cockpit scene according to claim 5, characterized in that: The step of determining the optimal gear value corresponding to the demand service by using the correlation coefficient includes: If there is no mutually exclusive relationship between the demand services, determining the optimal gear value corresponding to the demand service according to a mapping table between the correlation coefficient and the demand service; If there is a mutually exclusive relationship between the demand services, a weight is assigned to the correlation coefficient according to the mutually exclusive relationship, and then the optimal gear value corresponding to the demand service is determined according to the correlation coefficient after the weight is assigned.

7. A vehicle cockpit scene automatic construction device, characterized in that: The vehicle cockpit scene automatic construction device comprises: A data collection module, used to collect the command data input by the current user and the associated data corresponding to the current vehicle, wherein the associated data includes the in-vehicle state data and the out-vehicle environment data of the current vehicle; A data analysis module, used to determine the required service and experience dimension corresponding to the current user according to the instruction data and the associated data; A scene construction module is used to construct a target cockpit scene adapted to the current user in the current vehicle based on the required service and the experience dimension.

8. A vehicle cockpit scene automatic construction device, characterized in that: The device comprises: a memory, a processor, and a vehicle cockpit scene automatic construction program stored in the memory and executable on the processor, wherein the vehicle cockpit scene automatic construction program is configured to implement the steps of the vehicle cockpit scene automatic construction method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which is stored a vehicle cockpit scene automatic construction program, which, when executed by a processor, implements the steps of the vehicle cockpit scene automatic construction method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises a vehicle cockpit scene automatic construction program, and when the vehicle cockpit scene automatic construction program is executed by a processor, the steps of the vehicle cockpit scene automatic construction method according to any one of claims 1 to 6 are implemented.

Images