An intelligent cockpit visual intention judgment method, device and electronic equipment

Abstract

This application discloses a method, device, and electronic device for determining visual intent in a smart cockpit, relating to the field of cockpit vision. The method includes: Step S1, cockpit context awareness and user identification: acquiring the user's cockpit role and the vehicle's real-time dynamic status through an onboard sensor system, while simultaneously identifying the user's identity information; Step S2, dynamic judgment parameter loading: loading a set of dynamic judgment parameters matching the current context from a preset strategy library; Step S3, multimodal information acquisition and feature extraction: continuously acquiring multimodal data from the wearable device to determine whether stable gaze events and other confirmation signals exist; Step S4, weighted fusion and dynamic decision-making: based on the determination of whether stable gaze events and other confirmation signals exist, performing weighted fusion calculation on the acquired multimodal information to obtain an intent score; when the intent score exceeds a trigger threshold in the dynamic judgment parameter set, it is determined that the user has generated a valid intent.

Description

Technical Field

[0001] This application relates to the field of cockpit vision, and in particular to intelligent cockpit visual intent judgment methods, intelligent cockpit visual intent judgment devices, intelligent cockpit personalized visual intent judgment implementation methods, electronic devices, storage media, and vehicle platforms. Background Technology

[0002] Existing visual intent recognition algorithms used in AR glasses or general-purpose devices are typically "environmentally unknown." They don't know who the user is, where they are, or what they are doing, so they can only rely on "one-size-fits-all" judgment rules (such as fixed gaze duration). When this kind of general algorithm is ported to the complex environment of a smart cockpit—a multi-user, safety-critical, and dynamically changing environment—its shortcomings become glaringly apparent:

[0003] Lack of safety: It cannot distinguish between the driver and passengers, and may trigger functions due to misjudging the driver's line of sight, interfering with driving safety.

[0004] Lack of accuracy: It cannot adjust the sensitivity of the judgment according to the vehicle status (such as high speed vs. parked), resulting in a high false trigger rate in some scenarios and insensitivity in others.

[0005] Lack of personalization: Unable to provide interactive experiences that match the individual habits of different users. Summary of the Invention

[0006] The purpose of this invention is to provide a method for determining visual intent in an intelligent cockpit, a device for determining visual intent in an intelligent cockpit, a method for realizing personalized visual intent determination in an intelligent cockpit, an electronic device, a storage medium, and a vehicle platform, thereby solving at least one of a number of technical problems.

[0007] The system fails to distinguish between drivers and passengers, potentially triggering functions due to misjudging the driver's line of sight, thus interfering with driving safety. It also fails to adjust the sensitivity of its judgment based on vehicle status (e.g., high-speed driving vs. stationary), resulting in a high rate of accidental activation in some scenarios and insensitivity in others. Finally, it cannot provide an interactive experience tailored to the individual habits of different users.

[0008] This invention provides the following solution:

[0009] According to a first aspect of the present invention, a method for determining visual intent in an intelligent cockpit is provided, comprising:

[0010] Step S1, Cockpit Context Awareness and User Identification:

[0011] The vehicle sensor system acquires the cockpit role of the user wearing the wearable device and the real-time dynamic status of the vehicle, while also identifying the user's identity information.

[0012] Step S2, dynamically determine parameter loading:

[0013] Based on the cockpit role, real-time vehicle dynamic status and user identity information obtained in step S1, load the dynamic judgment parameter set that matches the current situation from the preset strategy library;

[0014] Step S3, Multimodal Information Acquisition and Feature Extraction:

[0015] Continuously collect multimodal data from wearable devices to determine whether stable gaze events and other confirmation signals exist;

[0016] Step S4, Weighted Fusion and Dynamic Decision-Making:

[0017] Using the dynamic judgment parameters loaded in step S2, and based on the determination of whether there is a stable gaze event and other confirmation signals, the collected multimodal information is weighted and fused to obtain the intent score;

[0018] When the intent score exceeds the trigger threshold in the dynamic judgment parameter set, the user is deemed to have generated a valid intent.

[0019] Furthermore, step S1 includes:

[0020] Cockpit roles include driver, co-pilot, or rear passenger;

[0021] The vehicle's real-time dynamic status, including vehicle speed, driving mode, or ADAS system status;

[0022] The vehicle sensor system includes in-vehicle cameras, seat sensors, microphone arrays, and sensing or reference data acquired on the CAN bus;

[0023] Among them, user identity information is obtained through facial recognition or seat sensor recognition, and the user identity information is associated with the vehicle user ID system.

[0024] Furthermore, step S2 includes:

[0025] The dynamic judgment parameter set includes gaze duration threshold, the enabled / disabled status of the confirmation signal and its weight, and the intent score trigger threshold.

[0026] Furthermore, step S3 includes:

[0027] Multimodal data includes eye-tracking data, head pose data, and audio data;

[0028] Confirmation signals include voice signals, gesture signals, or steering wheel button signals.

[0029] According to a second aspect of the present invention, a smart cockpit visual intent determination device is provided, comprising:

[0030] Context acquisition module: used to acquire the cockpit role, identity information of the user wearing the wearable device, and the real-time dynamic status of the vehicle through the vehicle sensor system;

[0031] The strategy library module is used to store the dynamic judgment parameter sets and judgment rules corresponding to different scenarios.

[0032] Dynamic Decision Module: Based on the information obtained by the context acquisition module, it calls the matching dynamic judgment parameter set and judgment rules from the strategy library module, performs weighted fusion calculation on the collected multimodal information, and determines whether the user has generated a valid intent.

[0033] Furthermore, including:

[0034] The context acquisition module is adapted to the vehicle sensor system, including in-vehicle cameras, seat sensors, microphone arrays, and CAN bus;

[0035] The vehicle's real-time dynamic status, including vehicle speed, driving mode, or ADAS system status.

[0036] Furthermore, including:

[0037] The strategy library module stores a set of dynamic judgment parameters, including gaze duration threshold, the enabled / disabled status of the confirmation signal and its weight, and the intent score trigger threshold.

[0038] Furthermore, including:

[0039] The dynamic decision-making module receives multimodal information, including eye-tracking data, head posture data, and audio data from wearable devices;

[0040] Confirmation signals include voice signals, gesture signals, or steering wheel button signals.

[0041] According to a third aspect of the present invention, a method for determining personalized visual intent in an intelligent cockpit is provided. Based on this method, the method for determining personalized visual intent in an intelligent cockpit includes:

[0042] Link the in-vehicle user ID system with the visual intent judgment of wearable devices;

[0043] By identifying the user's corresponding vehicle user ID, a set of personalized dynamic judgment parameters preset for that ID is loaded;

[0044] Visual intent is determined based on a personalized dynamic judgment parameter set.

[0045] in,

[0046] The set of personalized dynamic judgment parameters includes personalized gaze duration threshold, personalized confirmation signal enable / disable status and its weight, and personalized intent score trigger threshold.

[0047] According to a fourth aspect of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0048] The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the intelligent cockpit visual intent determination method.

[0049] According to a fifth aspect of the present invention, a computer-readable storage medium is provided storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a smart cockpit visual intent determination method.

[0050] According to a sixth aspect of the present invention, a vehicle platform is provided, comprising:

[0051] Electronic devices, steps for implementing a visual intent judgment method for intelligent cockpits;

[0052] The processor runs a program, and when the program runs, it executes the steps of the intelligent cockpit visual intent determination method based on data output from electronic devices.

[0053] Storage medium for storing programs that, when running, execute steps of a smart cockpit visual intent determination method based on data output from electronic devices.

[0054] The above solution achieves the following beneficial technical effects:

[0055] This application ensures driving safety by identifying the user's cockpit role (driver / front passenger / rear passenger) and loading high-safety strategies for the driver (such as a longer gaze threshold and limiting the confirmation signal type to steering wheel buttons): clearly distinguishing the driver from other passengers, imposing strict restrictions on the driver's visual interaction, and avoiding interference with core driving tasks (in the case, driver Zhang San needs 3.0 seconds of gaze + button confirmation to trigger, and short gaze will not result in a response).

[0056] This application obtains the real-time dynamic status of the vehicle (vehicle speed, driving mode, ADAS system status) and dynamically adjusts the judgment parameters (gaze duration threshold, confirmation signal weight, trigger threshold) based on the role and vehicle status. It is context-adaptive and makes more accurate judgments: by integrating multi-dimensional information such as "who is looking, where is looking, and what is the vehicle doing", the model is dynamically adjusted, which greatly improves the accuracy and intelligence of the judgment.

[0057] This application identifies the user's identity (UserID) by binding to the vehicle's user ID system, loads the user's preset personalized dynamic judgment parameter set, and realizes personalized and role-based services: providing customized interaction habit settings for different users, and assigning differentiated interaction permissions and feedback according to the in-vehicle role (in the case, the co-driver Li Si loads the standard strategy, and information sharing can be triggered by 1.8 seconds of gaze + voice confirmation). Attached Figure Description

[0058] Figure 1 This is a flowchart of a method for determining visual intent in an intelligent cockpit, provided by one or more embodiments of the present invention.

[0059] Figure 2 This is a flowchart of a method for determining personalized visual intent in an intelligent cockpit, provided by one or more embodiments of the present invention.

[0060] Figure 3 This is a structural diagram of an intelligent cockpit visual intent determination device provided in one or more embodiments of the present invention.

[0061] Figure 4 This is a block diagram of an electronic device for a method of determining visual intent in an intelligent cockpit, provided in one or more embodiments of the present invention. Detailed Implementation

[0062] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0063] Figure 1 This is a flowchart of a method for determining visual intent in an intelligent cockpit, provided by one or more embodiments of the present invention.

[0064] like Figure 1 The intelligent cockpit visual intent determination method shown includes:

[0065] Step S1, Cockpit Context Awareness and User Identification:

[0066] The vehicle sensor system acquires the cockpit role of the user wearing the wearable device and the real-time dynamic status of the vehicle, while also identifying the user's identity information.

[0067] Step S2, dynamically determine parameter loading:

[0068] Based on the cockpit role, real-time vehicle dynamic status and user identity information obtained in step S1, load the dynamic judgment parameter set that matches the current situation from the preset strategy library;

[0069] Step S3, Multimodal Information Acquisition and Feature Extraction:

[0070] Continuously collect multimodal data from wearable devices to determine whether stable gaze events and other confirmation signals exist;

[0071] Step S4, Weighted Fusion and Dynamic Decision-Making:

[0072] Using the dynamic judgment parameters loaded in step S2, and based on the determination of whether there is a stable gaze event and other confirmation signals, the collected multimodal information is weighted and fused to obtain the intent score;

[0073] When the intent score exceeds the trigger threshold in the dynamic judgment parameter set, the user is deemed to have generated a valid intent.

[0074] In this embodiment, step S1 includes:

[0075] Cockpit roles include driver, co-pilot, or rear passenger;

[0076] The vehicle's real-time dynamic status, including vehicle speed, driving mode, or ADAS system status;

[0077] The vehicle sensor system includes in-vehicle cameras, seat sensors, microphone arrays, and sensing or reference data acquired on the CAN bus;

[0078] Among them, user identity information is obtained through facial recognition or seat sensor recognition, and the user identity information is associated with the vehicle user ID system.

[0079] In this embodiment, step S2 includes:

[0080] The dynamic judgment parameter set includes gaze duration threshold, the enabled / disabled status of the confirmation signal and its weight, and the intent score trigger threshold.

[0081] In this embodiment, step S3 includes:

[0082] Multimodal data includes eye-tracking data, head pose data, and audio data;

[0083] Confirmation signals include voice signals, gesture signals, or steering wheel button signals.

[0084] Figure 2 This is a flowchart of a method for determining personalized visual intent in an intelligent cockpit, provided by one or more embodiments of the present invention.

[0085] like Figure 2 The method for determining personalized visual intent in an intelligent cockpit, as shown, includes the following:

[0086] Step S5: Associate the vehicle user ID system with the visual intent judgment of the wearable device;

[0087] Step S6: By identifying the vehicle user ID corresponding to the user, load the preset personalized dynamic judgment parameter set of the ID;

[0088] Step S7: Complete visual intent judgment based on personalized dynamic judgment parameter set;

[0089] in,

[0090] Step S8: Personalize the dynamic judgment parameter set, including personalized gaze duration threshold, personalized confirmation signal enable / disable status and its weight, and personalized intent score trigger threshold.

[0091] Figure 3 This is a structural diagram of an intelligent cockpit visual intent determination device provided in one or more embodiments of the present invention.

[0092] like Figure 3 The intelligent cockpit visual intent determination device shown includes:

[0093] Context acquisition module: used to acquire the cockpit role, identity information of the user wearing the wearable device, and the real-time dynamic status of the vehicle through the vehicle sensor system;

[0094] The strategy library module is used to store the dynamic judgment parameter sets and judgment rules corresponding to different scenarios.

[0095] Dynamic Decision Module: Based on the information obtained by the context acquisition module, it calls the matching dynamic judgment parameter set and judgment rules from the strategy library module, performs weighted fusion calculation on the collected multimodal information, and determines whether the user has generated a valid intent.

[0096] In this embodiment, it includes:

[0097] The context acquisition module is adapted to the vehicle sensor system, including in-vehicle cameras, seat sensors, microphone arrays, and CAN bus;

[0098] The vehicle's real-time dynamic status, including vehicle speed, driving mode, or ADAS system status.

[0099] In this embodiment, it includes:

[0100] The strategy library module stores a set of dynamic judgment parameters, including gaze duration threshold, the enabled / disabled status of the confirmation signal and its weight, and the intent score trigger threshold.

[0101] In this embodiment, it includes:

[0102] The dynamic decision-making module receives multimodal information, including eye-tracking data, head posture data, and audio data from wearable devices;

[0103] Confirmation signals include voice signals, gesture signals, or steering wheel button signals.

[0104] It is worth noting that although this system / device only discloses the above-mentioned modules / units, it does not mean that this system / device is limited to the above-mentioned basic functional modules. On the contrary, what this invention intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. It cannot be assumed that the scope of protection of the claims of this invention is limited to the above-disclosed basic functional modules just because this embodiment only discloses a few basic functional modules.

[0105] In one specific embodiment, a visual intent determination method is disclosed, which runs in a software-based device (intent determination engine), and its core lies in a "context-based dynamic parameter adjustment mechanism".

[0106] The method includes the following steps:

[0107] Step 1: Cockpit Context Awareness and User Identification. Before determining intent, the system first uses the vehicle's sensor system (such as in-vehicle cameras, seat sensors, and microphone arrays) to identify the identity (User ID) and cockpit role (such as driver or front passenger) of the user currently wearing the wearable device, and obtains the vehicle's dynamic status in real time (such as vehicle speed, driving mode, and ADAS system status).

[0108] Step 2: Dynamic Parameter Loading. Based on the context information obtained in the previous step, the system loads a set of dynamic judgment parameters that match the current context from a preset strategy library. This parameter set includes at least: gaze duration threshold, the enabled / disabled status of various confirmation signals (such as voice and gestures) and their weights, and the final intent score trigger threshold.

[0109] Step 3: Multimodal information acquisition and feature extraction. The system continuously acquires eye-tracking data, head posture data, and audio data from the wearable device, and determines whether there are "stable gaze events" and other "confirmation signals".

[0110] Step 4: Weighted Fusion and Dynamic Decision-Making. The system uses the dynamic parameters loaded in Step 2 to perform weighted fusion calculations on the collected multimodal information, resulting in a final intent score. This score is compared to a dynamic trigger threshold; only if the score exceeds the current threshold is the user deemed to have generated a valid intent.

[0111] Based on the above embodiments, an implementation case is disclosed.

[0112] A car equipped with this system is traveling at 40 km / h on an urban road. Both the driver (Zhang San) and the passenger (Li Si) are wearing smart glasses.

[0113] Context awareness: The system uses facial recognition to confirm that the driver is "Zhang San" and the passenger is "Li Si". It also uses the CAN bus to determine that the vehicle speed is 40 km / h and the driving mode is "manual".

[0114] Parameter loading:

[0115] A high-safety strategy was implemented for "Zhang San (driver)": gaze threshold of 3.0 seconds, and only accepting steering wheel buttons as confirmation signals.

[0116] A standard strategy was loaded for "Li Si (co-pilot)": a gaze threshold of 1.8 seconds, and acceptance of voice and gestures as confirmation signals.

[0117] Intent Judgment: Li Si sees a restaurant by the roadside, stares at it for 2 seconds, and says, "Look at this restaurant." The system detects "stable gaze" and "voice confirmation," and its weighted score exceeds Li Si's dynamic threshold, thus successfully triggering information sharing. However, even if Zhang San makes a brief gaze exceeding 2 seconds while driving, because it does not reach his 3.0-second threshold and he does not press a button to confirm, the system will not react, ensuring driving safety.

[0118] Figure 4 This is a block diagram of an electronic device for a method of determining visual intent in an intelligent cockpit, provided in one or more embodiments of the present invention.

[0119] like Figure 4 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0120] The memory stores a computer program that, when executed by a processor, causes the processor to perform steps of a smart cockpit visual intent determination method.

[0121] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the intelligent cockpit visual intent determination method.

[0122] This application also provides a vehicle platform, including:

[0123] Electronic devices, steps for implementing a visual intent judgment method for intelligent cockpits;

[0124] The processor runs a program, and when the program runs, it executes the steps of the intelligent cockpit visual intent determination method based on data output from electronic devices.

[0125] Storage medium for storing programs that, when running, execute steps of a smart cockpit visual intent determination method based on data output from electronic devices.

[0126] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0127] The electronic device comprises a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control the electronic device through processes, such as Linux, Unix, Android, iOS, or Windows. Furthermore, in this embodiment of the invention, the electronic device can be a smartphone, tablet computer, or other handheld device, or a desktop computer, portable computer, or other electronic device; there is no particular limitation in this embodiment.

[0128] In this embodiment of the invention, the executing entity for electronic device control can be an electronic device itself, or a functional module within an electronic device capable of calling and executing a program. The electronic device can obtain the firmware corresponding to the storage medium. This firmware is provided by the supplier, and different storage media may have the same or different firmware; no limitation is made here. After obtaining the firmware corresponding to the storage medium, the electronic device can write this firmware into the storage medium; specifically, it burns the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology, and will not be elaborated upon in this embodiment of the invention.

[0129] Electronic devices can also obtain reset commands corresponding to the storage media. The reset commands corresponding to the storage media are provided by the supplier. The reset commands corresponding to different storage media can be the same or different, and no restrictions are imposed here.

[0130] At this time, the storage medium of the electronic device is a storage medium on which the corresponding firmware has been written. The electronic device can respond to the reset command corresponding to the storage medium on which the corresponding firmware has been written, thereby resetting the storage medium on which the corresponding firmware has been written according to the reset command. The process of resetting the storage medium according to the reset command can be implemented by existing technology and will not be described in detail in this embodiment of the invention.

[0131] For ease of description, the above devices are described separately by function as various units and modules. Of course, in implementing this application, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0132] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined.

[0133] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0134] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining visual intent in an intelligent cockpit, characterized in that, include: Step S1, Cockpit Context Awareness and User Identification: The vehicle sensor system acquires the cockpit role of the user wearing the wearable device and the real-time dynamic status of the vehicle, while also identifying the user's identity information. Step S2, dynamically determine parameter loading: Based on the cockpit role, real-time vehicle dynamic status and user identity information obtained in step S1, load the dynamic judgment parameter set that matches the current situation from the preset strategy library; Step S3, Multimodal Information Acquisition and Feature Extraction: Continuously collect multimodal data from the wearable device to determine whether there are stable gaze events and other confirmation signals; Step S4, Weighted Fusion and Dynamic Decision-Making: Using the dynamic judgment parameters loaded in step S2, and based on the determination of whether there is a stable gaze event and other confirmation signals, the collected multimodal information is weighted and fused to obtain the intent score; When the intent score exceeds the trigger threshold in the set of dynamic judgment parameters, it is determined that the user has generated a valid intent.

2. The intelligent cockpit visual intent judgment method according to claim 1, characterized in that, Step S1 includes: The cockpit roles include driver, co-pilot, or rear passenger; The real-time dynamic status of the vehicle includes vehicle speed, driving mode, or ADAS system status. The vehicle sensor system includes in-vehicle cameras, seat sensors, microphone arrays, and sensing or reference data acquired on the CAN bus; User identity information is obtained through facial recognition or seat sensor recognition, and the user identity information is associated with the vehicle user ID system.

3. The intelligent cockpit visual intent judgment method according to claim 1, characterized in that, Step S2 includes: The dynamic judgment parameter set includes a gaze duration threshold, the enabled / disabled status of the confirmation signal and its weight, and the intent score trigger threshold.

4. The intelligent cockpit visual intent judgment method according to claim 1, characterized in that, Step S3 includes: The multimodal data includes eye-tracking data, head posture data, and audio data; The confirmation signal includes a voice signal, a gesture signal, or a steering wheel button signal.

5. A smart cockpit visual intent determination device, characterized in that, include: Context acquisition module: used to acquire the cockpit role, identity information of the user wearing the wearable device, and the real-time dynamic status of the vehicle through the vehicle sensor system; The strategy library module is used to store the dynamic judgment parameter sets and judgment rules corresponding to different scenarios. Dynamic decision module: Based on the information obtained by the context acquisition module, it calls the matching dynamic judgment parameter set and judgment rules from the strategy library module to perform weighted fusion calculation on the collected multimodal information and determine whether the user has generated a valid intent.

6. The intelligent cockpit visual intent determination device according to claim 5, characterized in that, include: The context acquisition module is adapted to the vehicle sensor system, including in-vehicle camera, seat sensor, microphone array and CAN bus; The real-time dynamic status of the vehicle includes vehicle speed, driving mode, or ADAS system status.

7. The intelligent cockpit visual intent determination device according to claim 6, characterized in that, include: The strategy library module stores a set of dynamic judgment parameters, including gaze duration threshold, the enabled / disabled status of the confirmation signal and its weight, and the intent score trigger threshold.

8. The intelligent cockpit visual intent determination device according to claim 7, characterized in that, include: The dynamic decision-making module receives multimodal information, including eye-tracking data, head posture data, and audio data from wearable devices; The confirmation signal includes a voice signal, a gesture signal, or a steering wheel button signal.

9. A method for determining personalized visual intent in an intelligent cockpit, characterized in that, Based on the intelligent cockpit visual intent judgment method according to any one of claims 1 to 4, the intelligent cockpit personalized visual intent judgment implementation method includes: Link the in-vehicle user ID system with the visual intent judgment of wearable devices; By identifying the user's corresponding vehicle user ID, a set of personalized dynamic judgment parameters preset for that ID is loaded; Visual intent determination is completed based on the personalized dynamic judgment parameter set; in, The personalized dynamic judgment parameter set includes a personalized gaze duration threshold, a personalized confirmation signal enable / disable status and its weight, and a personalized intent score trigger threshold.

10. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program that, when executed by a processor, causes the processor to perform the steps of the intelligent cockpit visual intent determination method as described in any one of claims 1 to 4.

Images