Intelligent cabin interaction priority dynamic allocation system and method and electronic equipment

Abstract

The invention discloses an intelligent cabin interaction priority dynamic allocation system and method and electronic equipment, and relates to the field of cabin interaction, and the system comprises a multi-mode signal input layer which is used for continuously receiving original interaction instruction signals of a voice recognition module, a gesture recognition module, an eye movement tracking module and a touch screen module; the context sensing layer is used for collecting vehicle state data, driver state data and environment state data in parallel; the dynamic priority arrangement engine comprises a multi-factor fusion and weight calculation module and an arbitration and scheduling module; the multi-factor fusion and weight calculation module is used for normalizing the context data into a weight influence factor and calculating a real-time dynamic priority score of each interaction mode; the arbitration and scheduling module is used for comparing priority scores and selecting an optimal execution mode, and sending suppression signals to other modes at the same time; and the instruction execution layer is used for receiving the final instruction of the arbitration and scheduling module and issuing the final instruction to a vehicle-mounted application for execution.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of cockpit interaction, in particular to an intelligent cockpit interaction priority dynamic allocation system, an intelligent cockpit interaction priority dynamic allocation method, an electronic device, a storage medium and a vehicle cockpit. BACKGROUND

[0002] With the development of automobile intelligence, intelligent cockpit has become a core component to improve user experience. Modern intelligent cockpit integrates multiple interaction modalities such as voice recognition, gesture recognition, eye tracking, touch, etc., aiming to provide drivers with a more natural and convenient operation experience.

[0003] The closest prior art: simultaneously receiving multiple input signals such as voice, gesture, etc., and selecting which interaction instruction to execute through a simple priority list (e.g., default voice priority). Its system framework usually includes a signal receiving module, a processing module and an execution module.

[0004] Problems and reasons of the prior art:

[0005] 1. Static priority, lack of situational adaptability: Existing solutions mostly use pre-set, fixed priority strategies (such as always voice priority). However, driving situations are dynamic. For example, in high-load driving states such as high-speed driving, the risk of the driver's line of sight leaving the road for gesture operation is extremely high, at which time voice priority should be forced; while in the parking stationary state, gesture and touch operation are more direct and efficient. Static rules cannot adapt to such changes, resulting in fragmented experience or safety hazards.

[0006] 2. Modal conflict and false triggering: When multiple modal signals are generated at the same time or close in time (such as the driver speaking accompanied by an unconscious gesture), the system lacks intelligent decision-making ability and is prone to false responses to low-priority or non-intended instructions, leading to false operations and affecting driving safety and user experience.

[0007] 3. Single decision factor: Existing technologies often only base their decisions on the effectiveness of the signal itself (such as voice confidence, gesture matching degree), while ignoring key contextual information such as driver state (attention distribution, fatigue), environmental state (vehicle noise level) and task attributes (adjusting air conditioning vs. emergency call), resulting in less intelligent and accurate decision-making results.

[0008] Therefore, the difficulty of realizing true dynamic priority allocation lies in how to quantitatively, comprehensively quantify the impact of multiple heterogeneous information (driving state, user state, environmental state) on interaction safety and efficiency in real time, and map these impacts into a calculable, unified priority weight value, and then realize reliable scheduling at the millisecond level. SUMMARY

[0009] The application aims to provide an intelligent cockpit interaction priority dynamic allocation system, an intelligent cockpit interaction priority dynamic allocation method, an electronic device, a storage medium and a vehicle cockpit, and at least solve one of the technical problems.

[0010] The application solves the problem of poor situational adaptability of the existing intelligent cockpit multi-modal interaction system caused by static priority rules, solves the problem of high false triggering rate and low interaction reliability caused by modal conflicts, and solves the problem of un-intelligent interaction strategy and non-compliance with actual driving requirements caused by single decision factor.

[0011] The application provides the following solutions:

[0012] According to a first aspect of the application, an intelligent cockpit interaction priority dynamic allocation system is provided, comprising:

[0013] A multi-modal signal input layer is configured to continuously receive original interaction instruction signals of a voice recognition module, a gesture recognition module, an eye tracking module and a touch screen module.

[0014] A context perception layer is configured to collect vehicle state data, driver state data and environmental state data in parallel.

[0015] A dynamic priority arrangement engine comprises a multi-factor fusion and weight calculation module and an arbitration and scheduling module.

[0016] The multi-factor fusion and weight calculation module is configured to normalize the context data into weight influence factors and calculate real-time dynamic priority scores of each interaction mode.

[0017] The arbitration and scheduling module is configured to compare the priority scores and select the optimal execution mode, and send an inhibition signal to other modes.

[0018] An instruction execution layer is configured to receive the final instruction of the arbitration and scheduling module and issue it to the vehicle-mounted application for execution.

[0019] Further, the context perception layer is configured to collect vehicle state data, driver state data and environmental state data in parallel.

[0020] The vehicle state data includes data of vehicle speed, gear, turn signal and ACC start-stop state.

[0021] The driver state data includes data of line of sight direction, head posture and fatigue state.

[0022] The environmental state data includes data of in-vehicle noise decibel value.

[0023] Further, the weight influence factor includes:

[0024] A driving load factor F_drive, an attention distraction factor F_distract, an environmental noise factor F_noise, and a task urgency factor F_urgent;

[0025] The quantification range of each factor is 0-1;

[0026] The driving load factor is positively correlated with the vehicle speed;

[0027] The attention distraction factor is positively correlated with the length of time during which the driver's line of sight deviates from the front of the road;

[0028] The environmental noise factor is positively correlated with the noise level;

[0029] The task urgency factor is positively correlated with the urgency of the intention of the personnel interaction.

[0030] Further, the multi-factor fusion and weight calculation module comprises:

[0031] A voice modality priority score S_voice=(W1*(1-F_noise)+W2F_drive+W3F_urgent);

[0032] A gesture modality priority score S_gesture=(W4*(1-F_drive)+W5*(1-F_distract));

[0033] Wherein, W1, W2, W3, W4, and W5 are pre-trained weight coefficients;

[0034] F_noise is the environmental noise factor, F_drive is the driving load factor, F_urgent is the task urgency factor, and F_distract is the attention distraction factor;

[0035] Further, the arbitration and scheduling module compares the priority scores of all available modalities in real time;

[0036] The modality with the highest score is selected as the final execution channel for this interaction, and an inhibition signal is sent to other modalities to avoid conflicts.

[0037] Further, the dynamic priority arrangement engine further comprises generating an active service instruction and calculating its priority score based on multi-dimensional context information association analysis.

[0038] Further, it comprises: when the single modality input is incomplete or the confidence level is reduced to a preset threshold, the priority score of the active service instruction is determined based on the environmental danger degree evaluation.

[0039] According to a second aspect of the present application, a method for dynamically deploying intelligent cockpit interaction priority is provided, comprising:

[0040] Step S1, signal and data collection, including receiving original interactive instruction signals through a multi-modal signal input layer, collecting context data of the vehicle, the driver and the environment through a context perception layer;

[0041] Step S2, dynamic priority calculation, including quantifying the context data into a unified weight influence factor, and calculating real-time dynamic priority scores of each interactive mode based on a preset priority synthesis formula;

[0042] Step S3, arbitration and scheduling, including comparing the priority scores of each mode, selecting the mode with the highest score as the execution channel, and suppressing other conflicting modes;

[0043] Step S4, instruction execution, including issuing the final instruction to the vehicle-mounted application to complete the interactive closed loop.

[0044] Further, step S2 further includes dynamic priority factor tuning.

[0045] The dynamic priority factor tuning includes adjusting the weight coefficient by using an algorithm model based on actual performance and user feedback.

[0046] Further, step S3 further includes:

[0047] Suppressing other conflicting modes is used to avoid mis-triggering caused by multiple modes responding at the same time.

[0048] According to a third aspect of the present application, 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 through the communication bus;

[0049] The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the intelligent cabin interactive priority dynamic allocation method.

[0050] According to a fourth aspect of the present application, a computer readable storage medium is provided, which stores a computer program executable by an electronic device, and when the computer program runs on the electronic device, the electronic device executes the steps of the intelligent cabin interactive priority dynamic allocation method.

[0051] According to a fifth aspect of the present application, a vehicle cabin is provided, comprising:

[0052] An electronic device is used to implement the steps of the intelligent cabin interactive priority dynamic allocation method;

[0053] A processor runs a program, and when the program runs, the data output from the electronic device executes the steps of the intelligent cabin interactive priority dynamic allocation method;

[0054] A storage medium for storing a program, the program performing steps of the method for dynamically adjusting intelligent cockpit interaction priority when data output from an electronic device is running.

[0055] Through the above scheme, the following beneficial technical effects are obtained:

[0056] The present application greatly reduces the probability of false triggering by making decisions based on multi-dimensional context information, enables the system to more accurately understand the driver's intention, improves the success rate of one interaction, brings a smooth and natural experience, and realizes the improvement of interaction fluency and accuracy.

[0057] The present application dynamically adjusts to automatically suppress interaction modes that require visual attention (such as gestures, touch) in high-risk driving situations, and forces the use of voice and other "hands-on" modes, thereby fundamentally reducing the distraction caused by interaction operations and significantly improving driving safety.

[0058] The present application makes the interaction system no longer a tool for mechanically executing commands, but an intelligent agent that can perceive the environment, understand the user, predict risks and make the best decisions, laying the foundation for future higher-level intelligent cockpit applications, and realizing the enhancement of system intelligence and adaptive ability. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 is a flowchart of an intelligent cockpit interaction priority dynamic adjustment method provided by one or more embodiments of the present application.

[0060] Figure 2 is a structural diagram of an intelligent cockpit interaction priority dynamic adjustment system provided by one or more embodiments of the present application.

[0061] Figure 3 is a structural diagram of a system principle framework of an intelligent cockpit interaction priority dynamic adjustment based on multi-modal information fusion according to one specific embodiment of the present application.

[0062] Figure 4 is a structural block diagram of an electronic device for an intelligent cockpit interaction priority dynamic adjustment method provided by one or more embodiments of the present application. DETAILED DESCRIPTION

[0063] The technical solutions of the present application will be described below in conjunction with the drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0064] Figure 1is a flow chart of an intelligent cockpit interaction priority dynamic allocation method provided by one or more embodiments of the present application.

[0065] As shown in the intelligent cockpit interaction priority dynamic allocation method, Figure 1 comprises the following steps.

[0066] Step S1, signal and data collection, comprising receiving original interaction instruction signals through a multi-modal signal input layer, and collecting context data of the vehicle, the driver and the environment through a context perception layer;

[0067] Step S2, dynamic priority calculation, comprising quantifying the context data into a unified weight influence factor, and calculating real-time dynamic priority scores of each interaction mode based on a preset priority synthesis formula;

[0068] Step S3, arbitration and scheduling, comprising comparing the priority scores of each mode, selecting the mode with the highest score as the execution channel, and suppressing other conflicting modes;

[0069] Step S4, instruction execution, comprising issuing the final instruction to the vehicle-mounted application to complete the interaction closed loop.

[0070] In this embodiment, step S2 further comprises dynamic priority factor tuning.

[0071] The dynamic priority factor tuning comprises adjusting the weight coefficient by using an algorithm model based on actual performance and user feedback.

[0072] In this embodiment, step S3 further comprises:

[0073] suppressing other conflicting modes, for avoiding mis-triggering caused by multiple modes responding at the same time.

[0074] Figure 2 is a structural diagram of an intelligent cockpit interaction priority dynamic allocation system provided by one or more embodiments of the present application.

[0075] As shown in the intelligent cockpit interaction priority dynamic allocation system, Figure 2 comprises the following components.

[0076] The multi-modal signal input layer is configured to continuously receive original interaction instruction signals of a voice recognition module, a gesture recognition module, an eye tracking module and a touch screen module.

[0077] The context perception layer is configured to collect vehicle state data, driver state data and environment state data in parallel.

[0078] The dynamic priority arrangement engine comprises a multi-factor fusion and weight calculation module and an arbitration and scheduling module.

[0079] A multi-factor fusion and weight calculation module is configured to normalize the context data into weight influence factors and calculate real-time dynamic priority scores of each interaction modality.

[0080] An arbitration and scheduling module is configured to compare the priority scores and select an optimal execution modality, while sending an inhibition signal to other modalities.

[0081] An instruction execution layer is configured to receive the final instruction of the arbitration and scheduling module and issue it to a vehicle-mounted application for execution.

[0082] In this embodiment, the context perception layer is configured to collect vehicle state data, driver state data and environmental state data in parallel, including:

[0083] The vehicle state data includes data of vehicle speed, gear, turn signal and ACC start-stop state.

[0084] The driver state data includes data of line-of-sight direction, head posture and fatigue state.

[0085] The environmental state data includes data of in-vehicle noise decibel value.

[0086] In this embodiment, the weight influence factors include:

[0087] A driving load factor F_drive, an attention distraction factor F_distract, an environmental noise factor F_noise and a task urgency factor F_urgent.

[0088] The quantization range of each factor is 0-1.

[0089] The driving load factor is positively correlated with vehicle speed.

[0090] The attention distraction factor is positively correlated with the length of time during which the driver's line of sight is away from the front of the road.

[0091] The environmental noise factor is positively correlated with noise level.

[0092] The task urgency factor is positively correlated with the demand urgency of the personnel interaction intention.

[0093] In this embodiment, the multi-factor fusion and weight calculation module includes:

[0094] A voice modality priority score S_voice=(W1*(1-F_noise)+W2F_drive+W3F_urgent);

[0095] A gesture modality priority score S_gesture=(W4*(1-F_drive)+W5*(1-F_distract));

[0096] Wherein, W1, W2, W3, W4, W5 are pre-trained weight coefficients;

[0097] F_noise is an environmental noise factor, F_drive is a driving load factor, F_urgent is a task urgency factor, and F_distract is an attention distraction factor;

[0098] Further comprising, the arbitration and scheduling module compares the priority scores of all available modalities in real time;

[0099] The modality with the highest score is selected as the final execution channel for this interaction, and a suppression signal is sent to other modalities to avoid conflicts.

[0100] In this embodiment, the dynamic priority arrangement engine further comprises generating active service instructions based on multi-dimensional context information association analysis and calculating their priority scores.

[0101] In this embodiment, when the single modality input is incomplete or the confidence level is reduced to a preset threshold, the priority score of the active service instruction is determined based on the environmental danger level assessment.

[0102] It is worth noting that although the system / device only discloses the above-mentioned module / unit module, it does not mean that the system / device is limited to the above-mentioned basic function modules. On the contrary, the meaning expressed by the present application is that on the basis of the above-mentioned basic function modules, those skilled in the art can add one or more function modules in combination with the prior art to form infinite embodiments or technical solutions. That is to say, the system is open rather than closed, and it cannot be considered that the protection scope of the present application is limited to the above-mentioned basic function modules just because the present embodiment only discloses individual basic function modules.

[0103] In one specific embodiment, as shown in Figure 3 a system principle framework for intelligent cockpit interaction priority dynamic allocation based on multi-modal information fusion is disclosed. Under this framework:

[0104] Step 1: Signal and data acquisition

[0105] Multi-modal signal input layer: continuously receives raw interaction instruction signals input from voice recognition module, gesture recognition module, eye tracking module, touch screen, etc.

[0106] Context awareness layer: simultaneously obtains vehicle state data (such as vehicle speed, gear position, turn signal state, ACC start-stop state) from vehicle CAN bus; obtains driver state data (such as line of sight direction, head posture, fatigue score) from in-vehicle camera, steering wheel holding sensor, etc.; obtains environmental state data (such as in-vehicle noise decibel value) from microphone array.

[0107] Step two: Dynamic priority calculation (core)

[0108] The multi-factor fusion and weight calculation module in the dynamic priority arrangement engine works as follows:

[0109] Factor quantization: normalize various types of collected context data into a unified, comparable weight influencing factor (such as a scalar value between 0 and 1).

[0110] Driving load factor (F_drive): positively correlated with vehicle speed. When the vehicle speed is greater than 80 km / h, the factor approaches 1; when the vehicle speed is 0, the factor approaches 0.

[0111] Distraction factor (F_distract): positively correlated with the proportion of time the driver's line of sight is away from the road directly in front.

[0112] Environmental noise factor (F_noise): positively correlated with noise level, the higher the noise, the lower the availability of the voice modality.

[0113] Task urgency factor (F_urgent): determined according to the interaction intent itself (e.g. "open airbag" is of extremely high urgency, "next song" is of low urgency).

[0114] Application priority synthesis formula: calculate a real-time dynamic priority score S_i for each interaction modality i (such as voice, gesture).

[0115] Example formula: S_voice=(W1*(1-F_noise)+W2*F_drive+W3*F_urgent);

[0116] S_gesture=(W4*(1-F_drive)+W5*(1-F_distract));

[0117] Where W1, W2, W3, W4, W5 are pre-trained weight coefficients, which can be optimized through machine learning.

[0118] Beneficial effects include: this formula converts abstract context information into specific, calculable mathematical quantities, enabling the system to quantitatively compare the suitability of different modalities at the current instant.

[0119] Step three: Arbitration and execution

[0120] The arbitration and scheduling module compares the priority scores S_i of all available modalities in real time.

[0121] Select the modality with the highest score as the final execution channel for this interaction.

[0122] Meanwhile, the suppression signal can be sent to other modalities to avoid conflicts.

[0123] The beneficial effects include that this module is the executor of decision-making, ensuring that the calculated optimal strategy can be applied in real time, directly solving the problems of modal conflict and false triggering.

[0124] Step four: instruction execution

[0125] The instruction execution layer receives the final instruction from the arbitration module, issues it to the corresponding vehicle application for execution, and completes an interactive closed loop.

[0126] Step five: dynamic priority factor optimization

[0127] The quantification in step two is therefore manually preset before going online, and through online actual performance and user feedback, the algorithm model is adjusted to achieve better experience effect.

[0128] In another specific embodiment, different scenarios of modal conflict resolution cases are disclosed:

[0129] Embodiment 1: Modal conflict resolution in the same scene (high-speed driving to adjust air conditioner)

[0130] Scenario: The vehicle is driving at 100km / h on the highway (high driving load factor). The sun is strong, and the driver feels hot and sweaty.

[0131] Interaction conflict:

[0132] The driver gives a voice command: "Adjust the temperature down." (Voice modality activated)

[0133] At the same time, he subconsciously raises his right elbow to wipe the sweat on his forehead. The vehicle-mounted camera captures the rapid upward movement of the arm, and the gesture recognition module mistakenly identifies it as a "wave hand up" command (the function of this gesture is preset to adjust the air conditioner temperature up). (Gesture modality activated, conflict)

[0134] The driver's gaze (confirmed by eye tracking module) is always focused on the road ahead (high distraction factor).

[0135] System decision-making process:

[0136] Context awareness layer: Real-time collection of vehicle speed = 100km / h (F_drive≈1.0), gaze time away from the road <5% (F_distract≈0), normal environmental noise.

[0137] Dynamic priority arrangement engine calculation:

[0138] The voice instruction intent is clear ("lower the temperature"), and voice is the recommended modality when driving at high speed. Its priority score S_voice gets a significant boost due to high F_drive.

[0139] The gesture instruction confidence is low (the action does not match the preset library well), and in the context of high F_drive and high F_distract, gesture operation is considered high-risk. Its priority score S_gesture is greatly suppressed.

[0140] Arbitration and scheduling: the system determines S_voice > S_gesture. Therefore, the voice instruction is executed, and the air conditioner temperature is lowered by 2°C, and the gesture instruction triggered by mistake is completely ignored. At the same time, in order to avoid the driver being distracted by operating the screen, the system gives a voice feedback "temperature has been lowered for you", instead of calling up a complex air conditioner setting interface.

[0141] Beneficial effect: this embodiment shows how the system intelligently solves the modality conflict, suppresses the mis-triggering, and selects the safest and most efficient interaction channel, effectively avoiding the driver's confusion and secondary operation distraction due to system misresponse.

[0142] Embodiment 2: Multi-modal fusion enhancement in extreme scenarios (heavy rain weather safety assistance)

[0143] Scenario: extreme heavy rain weather, vehicle driving at 60km / h. The sound of rain, thunder and wiper is huge (environmental noise factor is extremely high). The front windshield is slightly foggy, and the visibility is obstructed.

[0144] Interaction and state:

[0145] The driver leans forward, frowns, and tries to see through the rain curtain to focus on the front (the driver state sensor detects tension and concentration posture, and may not see the road ahead clearly).

[0146] Voice instruction is issued, but due to high noise, voice recognition only captures incomplete: "... except... " (voice modality input is incomplete, confidence is extremely low).

[0147] The vehicle state sensor detects an increase in windshield humidity and a sharp decrease in external visibility.

[0148] System decision process:

[0149] Context awareness layer: a variety of information is collected, including high noise (F_noise ≈ 1.0), high driving load (F_drive = 0.8), driver tension state, high window humidity, and low visibility.

[0150] Dynamic priority arrangement engine calculation:

[0151] The single, incomplete voice command cannot be reliably executed, and its priority score S_voice drops to a very low level due to high F_noise.

[0152] The system does not do nothing in the face of voice failure. Based on multi-factor fusion, the engine correlates "high humidity", "driver leaning forward in a tense posture", "low visibility", and the fragmented voice "except...", and infers that the user's potential intent is most likely "requesting defogging" and "needing navigation assistance".

[0153] At this time, the system generates a high-priority proactive service instruction S_proactive, whose score jumps based on the degree of environmental danger.

[0154] Arbitration and scheduling: the system determines that S_proactive is the highest score. Therefore, two instructions are automatically executed: ① automatically start the strongest windshield defogging function; ② highlight the navigation information of the next exit on the instrument panel in the simplest and clearest way, and use calm voice broadcast: "Defogging has been strengthened for you, the next exit is 2 kilometers away, please maintain a safe following distance."

[0155] Beneficial effect embodiment: this embodiment shows how the invention understands the user's potential intent by fusing multi-dimensional context information in the face of single modality failure in extreme environments, and initiates the most suitable interaction and service for the current safety needs, upgrading the traditional "passive response" to "active guardianship", greatly improving the driving safety in extreme working conditions.

[0156] The core key points of the present application include:

[0157] The overall system architecture of the dynamic priority arrangement engine (including the division and cooperation of the context perception layer, the fusion calculation layer, and the arbitration and scheduling layer).

[0158] Multi-factor fusion model and synthesis formula for calculating real-time priority of modalities (its mathematical model and input-output relationship).

[0159] The specific types of factors and their quantification methods (i.e. how to convert raw data such as vehicle speed and noise into factor values between 0 and 1).

[0160] The specific control logic for arbitration based on real-time priority score and suppression of conflicting modalities.

[0161] In another specific embodiment, alternatives are also provided for comparison with the scheme of the present application:

[0162] 1. Rule engine-based alternative: Instead of using a continuous computation formula, a "fuzzy logic" or "decision tree" model can be used. For example, define a set of rules: IF (vehicle speed > 80) AND (noise < 60) THEN voice priority = high. This method can also achieve dynamic allocation, but is less flexible and less precise than the continuous computation formula.

[0163] 2. Machine learning-based alternative: The multi-modal signals and context data can be directly input into a deep learning model (such as a neural network), and the instructions to be executed can be output end-to-end. This solution omits the step of manually designing a formula, but requires a large amount of data for training and has poor interpretability.

[0164] Figure 4 is a structural block diagram of an electronic device provided by one or more embodiments of the application.

[0165] As shown in Figure 4 The present application provides an electronic device, 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 through the communication bus.

[0166] The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the intelligent cockpit interaction priority dynamic allocation method.

[0167] The present application also provides a computer readable storage medium storing a computer program executable by an electronic device, and when the computer program runs on the electronic device, the electronic device executes the steps of the intelligent cockpit interaction priority dynamic allocation method.

[0168] The present application also provides a vehicle cabin, comprising:

[0169] An electronic device for implementing the steps of the intelligent cockpit interaction priority dynamic allocation method.

[0170] A processor, the processor runs a program, and when the program runs, the data output from the electronic device executes the steps of the intelligent cockpit interaction priority dynamic allocation method.

[0171] A storage medium for storing a program, and when the program runs, the data output from the electronic device executes the steps of the intelligent cockpit interaction priority dynamic allocation method.

[0172] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus can be divided into an address bus, a data bus, a control bus, and the like. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0173] The electronic device includes a hardware layer, an operating system layer running above 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 a memory. The operating system can be any one or more computer operating systems that implement control of the electronic device through a process, such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a windows operating system. In embodiments of the present application, the electronic device can be a handheld device such as a smartphone or a tablet computer, or an electronic device such as a desktop computer or a portable computer, and is not particularly limited in embodiments of the present application.

[0174] The execution subject of the electronic device control in embodiments of the present application can be the electronic device, or a functional module capable of calling and executing a program in the electronic device. The electronic device can obtain a firmware corresponding to the storage medium, and the firmware corresponding to the storage medium is provided by a supplier. The firmware corresponding to different storage media can be the same or different, and is not limited herein. After the electronic device obtains the firmware corresponding to the storage medium, the electronic device can write the firmware corresponding to the storage medium into the storage medium, specifically, burn the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented by using existing technology, and is not described in detail in embodiments of the present application.

[0175] The electronic device can also obtain a reset command corresponding to the storage medium, and the reset command corresponding to the storage medium is provided by a supplier. The reset command corresponding to different storage media can be the same or different, and is not limited herein.

[0176] At this time, the storage medium of the electronic device is a storage medium in which the corresponding firmware is written, and the electronic device can respond to the reset command corresponding to the storage medium in the storage medium in which the corresponding firmware is written, so that the electronic device resets the storage medium in which the corresponding firmware is written according to the reset command corresponding to the storage medium. The process of resetting the storage medium according to the reset command can be implemented by using existing technology, and is not described in detail in embodiments of the present application.

[0177] For the convenience of description, the above apparatus is described in various units, modules, and the like in terms of functions. Of course, the functions of the units and modules can be implemented in one or more software and / or hardware in implementing the present application.

[0178] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless specifically so defined.

[0179] For the convenience of description, the above apparatus is described in various units, modules, and the like in terms of functions. Of course, the functions of the units and modules can be implemented in one or more software and / or hardware in implementing the present application.

[0180] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments of the present application.

[0181] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent cockpit interaction priority dynamic allocation system, characterized in that, The intelligent cockpit interaction priority dynamic allocation system comprises: A multi-modal signal input layer for continuously receiving original interaction instruction signals of a voice recognition module, a gesture recognition module, an eye tracking module and a touch screen module; A context awareness layer for collecting vehicle state data, driver state data and environment state data in parallel; A dynamic priority arrangement engine comprising a multi-factor fusion and weight calculation module and an arbitration and scheduling module; The multi-factor fusion and weight calculation module is configured to normalize the context data into weight influence factors and calculate real-time dynamic priority scores of each interaction mode; The arbitration and scheduling module is configured to compare the priority scores and select the optimal execution mode, while sending inhibition signals to other modes; An instruction execution layer for receiving the final instruction of the arbitration and scheduling module and issuing it to the vehicle-mounted application for execution. 2.The intelligent cabin interaction priority dynamic allocation system of claim 1, wherein, The context awareness layer is configured to collect vehicle state data, driver state data and environment state data in parallel, comprising: The vehicle state data includes data of vehicle speed, gear, turn signal and ACC start-stop state; The driver state data includes data of line of sight direction, head posture and fatigue state; The environment state data includes data of in-vehicle noise decibel value. 3.The intelligent cabin interaction priority dynamic allocation system of claim 2, wherein, The weight influence factors include: Driving load factor F_drive, attention distraction factor F_distract, environmental noise factor F_noise, task urgency factor F_urgent; The quantization range of each factor is 0-1; The driving load factor is positively correlated with the vehicle speed; The attention distraction factor is positively correlated with the length of time when the driver's line of sight deviates from the front of the road; The environmental noise factor is positively correlated with the noise level; The task urgency factor is positively correlated with the demand urgency of the personnel interaction intention. 4.The intelligent cabin interaction priority dynamic allocation system of claim 3, wherein, The multi-factor fusion and weight calculation module comprises: Voice mode priority score: S_voice=(W1*(1-F_noise)+W2F_drive+W3F_urgent); Gesture mode priority score: S_gesture=(W4*(1-F_drive)+W5*(1-F_distract)); Wherein, W1, W2, W3, W4, W5 are pre-trained weight coefficients; F_noise is the environmental noise factor, F_drive is the driving load factor, F_urgent is the task urgency factor, and F_distract is the attention distraction factor; The arbitration and scheduling module also compares the priority scores of all available modes in real time; Select the mode with the highest score as the final execution channel for this interaction, and send inhibition signals to other modes to avoid conflicts.

5. The intelligent cabin interaction priority dynamic allocation system of claim 4, wherein, The dynamic priority arrangement engine also comprises generating active service instructions based on multi-dimensional context information association analysis and calculating their priority scores. 6.The intelligent cabin interaction priority dynamic allocation system of claim 5, wherein, Including: When the single mode input is incomplete or the confidence level is reduced to a preset threshold, the priority score of the active service instruction is determined based on the environmental danger level assessment. 7.A method for dynamically adjusting an intelligent cockpit interaction priority, characterized in that, The intelligent cockpit interaction priority dynamic allocation method comprises: Step S1, signal and data collection, including receiving original interactive instruction signals through a multi-modal signal input layer, and collecting context data of the vehicle, driver and environment through a context perception layer; Step S2, dynamic priority calculation, including quantifying the context data into a unified weight influence factor, and calculating real-time dynamic priority scores of each interactive mode based on a preset priority synthesis formula; Step S3, arbitration and scheduling, including comparing the priority scores of each mode, selecting the mode with the highest score as the execution channel, and suppressing other conflicting modes; Step S4, instruction execution, including issuing the final instruction to the vehicle-mounted application to complete the interactive closed loop. 8.The method of claim 7, wherein, Step S2 further includes dynamic priority factor tuning. The dynamic priority factor tuning includes adjusting the weight coefficient using an algorithm model through online actual performance and user feedback. 9.The intelligent cabin interaction priority dynamic allocation method of claim 7, wherein, Step S3 further includes: suppressing other conflicting modes to avoid mis-triggering caused by multiple modal instructions responding at the same time.

10. An electronic device, comprising: It includes: 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; The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the intelligent cockpit interactive priority dynamic allocation method according to any one of claims 7 to 9.

Images