Intelligent cabin child safety state monitoring method, device, equipment and program product

Abstract

This invention discloses a method, device, equipment, and program product for monitoring the safety status of children in intelligent cockpits. The method includes: acquiring cabin environmental data of a target vehicle and acquiring image data, vital sign data, and interaction data of child occupants; inputting the cabin environmental data, image data, vital sign data, and interaction data into a pre-trained child safety risk identification model to obtain the target safety risk type and corresponding target risk level of the child occupants; matching the target safety risk type and target risk level with corresponding target intervention measures from a pre-set emergency plan database, and implementing emergency control of the target vehicle based on the target intervention measures. This invention achieves real-time, accurate monitoring and precise intervention of the safety status of children in the cockpit, improving the safety of child occupants, and can be widely applied in the field of intelligent cockpit technology.

Description

Technical Field

[0001] This invention relates to the field of smart cockpit technology, and in particular to a method, device, equipment, and program product for monitoring the safety status of children in a smart cockpit. Background Technology

[0002] Currently, smart cockpit child safety monitoring technologies can be mainly divided into three categories: The first category is a single visual monitoring solution, such as the "CabinCamera" system in Tesla Model Y, which identifies the state of a child left behind through an in-car camera, but has a high false alarm rate in situations where the child is covered by a blanket or in backlit conditions; the second category is a visual + environmental fusion solution, such as the BYD DiLink 5.0 system, which triggers warnings by combining in-car temperature and camera data, but does not involve the core indicators of a child's vital signs; the third category is the latest publicly available technology, such as the "Child Protection System" in NIO ET9, which introduces millimeter-wave radar to monitor breathing, but uses a traditional CNN model to fuse data, resulting in weak feature correlation capabilities and high latency in identifying abnormal behavior.

[0003] In summary, the existing technology has the following drawbacks: 1) One-sided monitoring dimensions: Most systems ignore the connection between children's emotions and vital signs, and cannot distinguish between "crying for help" and "normal play", resulting in excessive warnings or missed warnings; 2) Poor robustness in occluded scenarios: Visual-dependent systems have a high false negative rate when occluded by clothing or toys, and a single radar system cannot identify postural abnormalities such as seizures; 3) Lack of personalized intervention strategies: The intensity of intervention was not dynamically adjusted based on the child's age and the parents' location, and intervention was not timely in high-temperature and high-risk scenarios.

[0004] The above problems urgently need to be addressed. Summary of the Invention

[0005] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0006] Therefore, one objective of this invention is to provide a smart cockpit child safety status monitoring method, which enables real-time and accurate monitoring and precise intervention of the child's safety status in the cockpit, thereby improving the safety of child occupants.

[0007] Another objective of this invention is to provide a smart cockpit child safety status monitoring device.

[0008] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include: On one hand, embodiments of the present invention provide a method for monitoring the safety status of children in a smart cockpit, comprising the following steps: Acquire cabin environment data of the target vehicle, and acquire image data, vital sign data, and interaction data of child occupants; The cabin environment data, image data, vital sign data, and interaction data are input into a pre-trained child safety risk identification model to obtain the target safety risk type and corresponding target risk level of the child occupant. Based on the target safety risk type and the target risk level, a corresponding target intervention measure is matched in the preset emergency plan database, and the target vehicle is subjected to emergency control according to the target intervention measure.

[0009] Furthermore, in one embodiment of the present invention, the cabin environment data includes cabin temperature and humidity, carbon dioxide concentration, and window status; the image data includes thermal infrared images and visible light images of the child occupant; the vital signs data includes the child occupant's heart rate signal and respiratory wave signal; and the interaction data includes the child occupant's voice signal and tapping / pressing signals of the safety seat touch panel.

[0010] Furthermore, in one embodiment of the present invention, the child safety risk identification model is trained through the following steps: We acquire cabin environment samples, children's image samples, children's vital signs samples, and children's interaction samples from historical driving scenarios, and determine the corresponding safety risk labels through manual annotation; The cockpit environment sample, the child image sample, the child vital signs sample, and the child interaction sample are input into a pre-built multi-branch Transformer model to obtain the predicted safety risk type and the corresponding predicted risk level. The loss value is determined based on the predicted security risk type, the predicted risk level, and the security risk label; The parameters of the multi-branch Transformer model are updated using the backpropagation algorithm based on the loss value to obtain the trained child safety risk identification model; The multi-branch Transformer model includes a Min-Max encoding layer, an EfficientViT-Lite layer, an LSTM layer, an MLP encoding layer, a feature fusion layer, and an output layer. The security risk label includes a primary label for security risk type and a secondary label for risk level.

[0011] Furthermore, in one embodiment of the present invention, the step of inputting the cabin environment sample, the child image sample, the child vital sign sample, and the child interaction sample into a pre-built multi-branch Transformer model to obtain the predicted safety risk type and the corresponding predicted risk level specifically includes: The cockpit environment sample is input into the Min-Max encoding layer for feature extraction to obtain the cockpit environment features; The child image samples are input into the EfficientViT-Lite layer for feature extraction to obtain the child image features; The child's vital signs samples are input into the LSTM layer for feature extraction to obtain the child's vital signs features; The child interaction samples are input into the MLP encoding layer for feature extraction to obtain the child interaction features; The feature fusion layer uses a self-attention mechanism to fuse the cabin environment features, the child image features, the child vital signs features, and the child interaction features to obtain a fused feature vector. The output layer maps the fused feature vector to the predicted security risk type and the predicted risk level.

[0012] Furthermore, in one embodiment of the present invention, the step of matching the corresponding target intervention measures in a preset emergency plan database based on the target safety risk type and the target risk level specifically includes: Based on the target safety risk type, a first-level match is performed in the emergency plan database to obtain the corresponding emergency intervention strategy table; The target intervention measures are obtained by performing a secondary match on the emergency intervention strategy table based on the target risk level.

[0013] Furthermore, in one embodiment of the present invention, after the emergency control of the target vehicle according to the target intervention measures, the method further includes the following steps: Acquire the updated cockpit environment data, image data, vital sign data, and interaction data; The updated cabin environment data, image data, vital sign data, and interaction data are input into the child safety risk identification model to obtain the current safety risk type and corresponding current risk level of the child occupant. The current security risk type and the current risk level are compared with the target security risk type and the target risk level, and the emergency response plan database is optimized based on the comparison results.

[0014] Furthermore, in one embodiment of the present invention, after the emergency control of the target vehicle according to the target intervention measures, the method further includes the following steps: Obtain driver feedback data for the target vehicle; The actual safety risk type and corresponding actual risk level of the child occupant are determined based on the driving feedback data. The child safety risk identification model is incrementally learned based on the cabin environment data, the image data, the vital signs data, the interaction data, the actual safety risk type, and the actual risk level to obtain an updated child safety risk identification model.

[0015] On the other hand, embodiments of the present invention provide a smart cockpit child safety status monitoring device, comprising: The data acquisition module is used to acquire cabin environment data of the target vehicle, as well as image data, vital sign data, and interaction data of child occupants; The safety risk identification module is used to input the cabin environment data, the image data, the vital signs data, and the interaction data into a pre-trained child safety risk identification model to obtain the target safety risk type and corresponding target risk level of the child occupant. The risk intervention module is used to match the corresponding target intervention measures in a preset emergency plan library according to the target safety risk type and the target risk level, and to perform emergency control on the target vehicle according to the target intervention measures.

[0016] On the other hand, embodiments of the present invention provide an electronic device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described method for monitoring the safety status of children in a smart cockpit.

[0017] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described method for monitoring the safety status of children in a smart cockpit.

[0018] On the other hand, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described intelligent cockpit child safety status monitoring method.

[0019] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention: This invention acquires cabin environment data of a target vehicle, as well as image data, vital sign data, and interaction data of a child occupant. This data is then input into a pre-trained child safety risk identification model to obtain the target safety risk type and corresponding risk level of the child occupant. Based on the target safety risk type and risk level, a corresponding intervention measure is matched against a pre-set emergency plan database, and emergency control is implemented on the target vehicle according to the intervention measure. This invention identifies the target safety risk type and corresponding risk level of a child occupant based on cabin environment data and the child occupant's image data, vital sign data, and interaction data. On the one hand, it improves the accuracy of child safety status monitoring by utilizing multi-dimensional sensing data; on the other hand, the target safety risk type and risk level output by the child safety risk identification model can more accurately match target intervention measures. This overcomes the shortcomings of existing technologies that provide overly general safety risk warnings and interventions for child occupants, achieving real-time, accurate monitoring and precise intervention of the child's safety status in the cabin, thus improving the safety of child occupants. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the steps of a smart cockpit child safety status monitoring method provided in this embodiment of the invention; Figure 2 A structural block diagram of a smart cockpit child safety status monitoring device provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0024] The intelligent cockpit child safety status monitoring method provided in this invention can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the intelligent cockpit child safety status monitoring method, but is not limited to the above forms.

[0025] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0026] It should be noted that in various specific embodiments of the present invention, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of the present invention require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the user's separate permission or consent is the necessary user-related data for the normal operation of the embodiments of the present invention acquired.

[0027] Reference Figure 1 This invention provides a method for monitoring the safety status of children in a smart cockpit, which specifically includes the following steps: S101. Obtain cabin environment data of the target vehicle, and obtain image data, vital sign data and interaction data of the child occupants; S102. Input the cabin environment data, image data, vital sign data and interaction data into the pre-trained child safety risk identification model to obtain the target safety risk type and corresponding target risk level of the child occupant; S103. Match the corresponding target intervention measures in the preset emergency plan database according to the target safety risk type and target risk level, and carry out emergency control of the target vehicle according to the target intervention measures.

[0028] This invention identifies the target safety risk type and corresponding target risk level of a child occupant based on cabin environment data, image data, vital sign data, and interactive data. On the one hand, it improves the accuracy of child safety status monitoring by utilizing multi-dimensional perception data; on the other hand, the target safety risk type and target risk level output by the child safety risk identification model can more accurately match target intervention measures. This overcomes the shortcomings of existing technologies that provide overly general safety risk warnings and interventions for child occupants, achieving real-time, accurate monitoring and precise intervention of the child's safety status in the cabin, and improving the safety of child occupants.

[0029] As an optional implementation, the cabin environment data includes cabin temperature and humidity, carbon dioxide concentration, and window status; the image data includes thermal infrared images and visible light images of the child occupant; the vital signs data includes the child occupant's heart rate signal and respiratory wave signal; and the interaction data includes the child occupant's voice signal and the tapping / pressing signal of the safety seat touch panel.

[0030] Specifically, the embodiments of the present invention perform four-dimensional data acquisition and synchronization, including: 1) Environment module: Acquire cabin temperature and humidity, carbon dioxide concentration, and window status through in-vehicle temperature and humidity sensors, carbon dioxide sensors, and window status sensors; 2) Vision module: The infrared camera on the A-pillar acquires thermal infrared images of the child occupants to extract body temperature and posture contours. The visible light camera on the center console acquires visible light images of the child occupants to track facial expressions such as crying and seizures based on key facial points. 3) Vital signs module: The millimeter-wave radar built into the seat penetrates clothing to output the heart rate and respiratory wave signals of the child occupant; 4) Child interaction module: Collects voice signals from child occupants through a roof microphone array and captures intentional actions such as patting and pressing through the safety seat touch panel.

[0031] As an optional implementation, the child safety risk identification model is trained through the following steps: S201. Obtain cabin environment samples, child image samples, child vital sign samples, and child interaction samples from historical driving scenarios, and determine the corresponding safety risk labels through manual annotation; S202. Input the cabin environment samples, children's image samples, children's vital signs samples, and children's interaction samples into the pre-built multi-branch Transformer model to obtain the predicted safety risk type and the corresponding predicted risk level. S203. Determine the loss value based on the predicted safety risk type, predicted risk level, and safety risk label; S204. Update the parameters of the multi-branch Transformer model based on the loss value using the backpropagation algorithm to obtain the trained child safety risk identification model. The multi-branch Transformer model includes a Min-Max encoding layer, an EfficientViT-Lite layer, an LSTM layer, an MLP encoding layer, a feature fusion layer, and an output layer. The security risk labels include a primary label for security risk type and a secondary label for risk level.

[0032] Specifically, the system acquires cabin environment samples, child image samples, child vital sign samples, and child interaction samples from historical driving scenarios. These samples are then manually labeled to determine the corresponding primary safety risk type and secondary risk level labels. The cabin environment samples, child image samples, child vital sign samples, and child interaction samples are input into a pre-built multi-branch Transformer model to obtain the predicted safety risk type and corresponding predicted risk level. A loss value is determined based on the predicted safety risk type, predicted risk level, primary safety risk type label, and secondary risk level label. The parameters of the multi-branch Transformer model are updated using the backpropagation algorithm based on the loss value, completing one iteration of training. Training stops when the number of iterations reaches a preset threshold or the loss value falls below a preset threshold, resulting in a well-trained child safety risk identification model.

[0033] As a further optional implementation, cockpit environment samples, child image samples, child vital sign samples, and child interaction samples are input into a pre-built multi-branch Transformer model to obtain the predicted safety risk type and the corresponding predicted risk level, which specifically includes: S2021. Input the cockpit environment samples into the Min-Max coding layer for feature extraction to obtain cockpit environment features; S2022. Input the children's image samples into the EfficientViT-Lite layer for feature extraction to obtain the children's image features; S2023. Input the child's vital signs sample into the LSTM layer for feature extraction to obtain the child's vital signs features; S2024. Input the children's interaction samples into the MLP coding layer for feature extraction to obtain the children's interaction features; S2025. The feature fusion layer performs feature fusion on cockpit environment features, children's image features, children's vital signs features and children's interaction features based on the self-attention mechanism to obtain a fused feature vector. S2026. The fused feature vectors are mapped to the predicted security risk type and the predicted risk level through the output layer.

[0034] Specifically, cockpit environment samples are input into the Min-Max encoding layer for feature encoding, resulting in a 32-dimensional cockpit environment feature vector. Child image samples are input into the EfficientViT-Lite layer to extract 256-dimensional child image features. Child vital sign samples are denoised using wavelet transform and then input into the LSTM layer for feature extraction, resulting in 128-dimensional child vital sign features. Child interaction samples are input into the MLP encoding layer for feature encoding, resulting in 64-dimensional child interaction features. The feature fusion layer fuses cockpit environment features, child image features, child vital sign features, and child interaction features based on a self-attention mechanism. It uses attention gating units to dynamically allocate weights. For example, the weight of environmental features is increased to 0.5 in high-temperature scenarios and the weight of child vital sign features is increased to 0.6 in occlusion scenarios, solving the problem of fixed weights in traditional models.

[0035] Finally, the fused feature vector is mapped to the predicted safety risk type and the predicted risk level through the output layer. For example, the predicted safety risk type can be a child being alone, a child having physical abnormalities, a child having emotional abnormalities, etc., while the predicted risk level is a further subdivision of the risk level under different safety risk types. For example, it can be divided into levels 1 to 5. The higher the risk level, the higher the degree of danger of the corresponding safety risk type for the occupant.

[0036] After acquiring cabin environment data of the target vehicle, as well as image data, vital sign data, and interaction data of the child occupants, these data are input into the child safety risk identification model trained through the above steps to obtain the target safety risk type and corresponding target risk level of the child occupants.

[0037] As an optional implementation method, corresponding target intervention measures are matched from a pre-set emergency plan database based on the target safety risk type and target risk level, specifically including: S1031. Based on the type of target safety risk, perform a first-level match in the emergency plan database to obtain the corresponding emergency intervention strategy table; S1032. Based on the target risk level, perform secondary matching in the emergency intervention strategy table to obtain the target intervention measures.

[0038] Specifically, in this embodiment of the invention, corresponding emergency intervention measures are pre-configured for different risk levels of specific security risk types, forming an emergency intervention strategy table for each security risk type. Then, all emergency intervention strategy tables for all security risk types are summarized to obtain an emergency plan library. After identifying the target security risk type and target risk level, a primary matching is performed in the emergency plan library based on the target security risk type to obtain the corresponding emergency intervention strategy table. Then, a secondary matching is performed in the emergency intervention strategy table based on the target risk level to obtain the target intervention measures.

[0039] Taking the scenario of a child being alone as an example, under Level 1 risk, only a soft sound and light reminder is activated inside the vehicle (to avoid startling the child), while a "child is in the car" notification is pushed to the driver's terminal. Under Level 3 risk, the cabin temperature is adaptively adjusted, preset nursery rhymes are played to soothe the child, and a "child is in the car" notification is pushed to the driver's terminal. If there is no response within 1 minute, a voice call is made. Under Level 5 risk, emergency intervention is triggered, and within 1 second, a warning containing location and real-time video (data has been anonymized) is pushed to the driver's terminal. Within 3 seconds, the car window is automatically lowered by 10cm (to balance the temperature and prevent falls). Within 5 seconds, a distress signal is pushed to roadside units (RSUs) and surrounding vehicles within 500 meters via V2X. Within 10 seconds, the rescue platform is activated and the child's vital signs data are synchronized.

[0040] As a further optional implementation, after emergency control of the target vehicle based on the target intervention measures, the following steps are also included: S301. Obtain updated cockpit environment data, image data, vital signs data, and interaction data; S302. Input the updated cabin environment data, image data, vital signs data, and interaction data into the child safety risk identification model to obtain the current safety risk type and corresponding current risk level of the child occupant; S303. Compare the current safety risk type and current risk level with the target safety risk type and target risk level, and optimize the emergency response plan database based on the comparison results.

[0041] Specifically, after implementing the target intervention measures, updated cabin environment data, image data, vital sign data, and interaction data can be obtained to identify the current safety risk type and corresponding current risk level of the child occupant. Then, the current safety risk type and current risk level are compared with the target safety risk type and target risk level to determine whether the target intervention measures can alleviate the child's safety risk, thereby optimizing the emergency plan database.

[0042] As a further optional implementation, after emergency control of the target vehicle based on the target intervention measures, the following steps are also included: S401. Obtain driver feedback data for the target vehicle; S402. Determine the actual safety risk type and corresponding actual risk level of child occupants based on driving feedback data; S403. Based on cabin environment data, image data, vital sign data, interaction data, real safety risk types, and real risk levels, incremental learning is performed on the child safety risk identification model to obtain an updated child safety risk identification model.

[0043] Specifically, after implementing the target intervention measures, driver feedback data can be obtained (either while the driver is in the vehicle or after the incident). Then, based on the driver feedback data, the actual safety risk type and corresponding actual risk level of the child occupant can be determined. This allows for the formation of incremental learning samples by combining cabin environment data, image data, vital sign data, and interaction data. Based on these incremental learning samples, the child safety risk identification model can be incrementally learned, thereby achieving incremental updates to the child safety risk identification model and further improving the accuracy of child safety status monitoring.

[0044] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention identify the target safety risk type and corresponding target risk level of the child occupant based on cabin environment data and the child occupant's image data, vital sign data, and interaction data. On the one hand, this utilizes multi-dimensional perception data to improve the accuracy of child safety status monitoring; on the other hand, the target safety risk type and target risk level output by the child safety risk identification model can more accurately match target intervention measures. This overcomes the shortcomings of the prior art, which provides overly general safety risk warnings and interventions for child occupants, achieving real-time, accurate monitoring and precise intervention of the child's safety status in the cabin, thus improving the safety of child occupants.

[0045] Reference Figure 2 This invention provides an intelligent cockpit child safety status monitoring device, comprising: The data acquisition module is used to acquire cabin environment data of the target vehicle, as well as image data, vital sign data, and interaction data of child occupants; The safety risk identification module is used to input cabin environment data, image data, vital sign data and interaction data into a pre-trained child safety risk identification model to obtain the target safety risk type and corresponding target risk level of the child occupant. The risk intervention module is used to match the corresponding target intervention measures in the preset emergency plan library according to the target safety risk type and target risk level, and to carry out emergency control of the target vehicle according to the target intervention measures.

[0046] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0047] Reference Figure 3 This invention provides an electronic device, comprising: At least one processor; At least one memory for storing at least one program; When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned intelligent cockpit child safety status monitoring method.

[0048] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0049] This invention also provides a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described method for monitoring the safety status of children in a smart cockpit.

[0050] This invention provides a computer-readable storage medium that can execute a smart cockpit child safety status monitoring method provided in the method embodiments of this invention. It can execute any combination of the implementation steps of the method embodiments and has the corresponding functions and beneficial effects of the method.

[0051] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for monitoring the safety status of children in a smart cockpit.

[0052] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0053] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0054] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0055] The terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0056] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0057] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0058] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0059] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0060] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0061] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0062] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0063] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0064] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for monitoring the safety status of children in an intelligent cockpit, characterized in that, Includes the following steps: Acquire cabin environment data of the target vehicle, and acquire image data, vital sign data, and interaction data of child occupants; The cabin environment data, image data, vital sign data, and interaction data are input into a pre-trained child safety risk identification model to obtain the target safety risk type and corresponding target risk level of the child occupant. Based on the target safety risk type and the target risk level, a corresponding target intervention measure is matched in the preset emergency plan database, and the target vehicle is subjected to emergency control according to the target intervention measure.

2. The method for monitoring the safety status of children in an intelligent cockpit according to claim 1, characterized in that, The cabin environment data includes cabin temperature and humidity, carbon dioxide concentration, and window status; the image data includes thermal infrared and visible light images of the child occupant; the vital signs data includes the child occupant's heart rate and respiratory wave signals; and the interaction data includes the child occupant's voice signals and tapping / pressing signals from the safety seat touch panel.

3. The method for monitoring the safety status of children in an intelligent cockpit according to claim 1, characterized in that, The child safety risk identification model is trained through the following steps: We acquire cabin environment samples, children's image samples, children's vital signs samples, and children's interaction samples from historical driving scenarios, and determine the corresponding safety risk labels through manual annotation; The cockpit environment sample, the child image sample, the child vital signs sample, and the child interaction sample are input into a pre-built multi-branch Transformer model to obtain the predicted safety risk type and the corresponding predicted risk level. The loss value is determined based on the predicted security risk type, the predicted risk level, and the security risk label; The parameters of the multi-branch Transformer model are updated using the backpropagation algorithm based on the loss value to obtain the trained child safety risk identification model; The multi-branch Transformer model includes a Min-Max encoding layer, an EfficientViT-Lite layer, an LSTM layer, an MLP encoding layer, a feature fusion layer, and an output layer. The security risk label includes a primary label for security risk type and a secondary label for risk level.

4. The method for monitoring the safety status of children in an intelligent cockpit according to claim 3, characterized in that, The process of inputting the cabin environment samples, the child image samples, the child vital sign samples, and the child interaction samples into a pre-built multi-branch Transformer model to obtain the predicted safety risk type and the corresponding predicted risk level specifically includes: The cockpit environment sample is input into the Min-Max encoding layer for feature extraction to obtain the cockpit environment features; The child image samples are input into the EfficientViT-Lite layer for feature extraction to obtain the child image features; The child's vital signs samples are input into the LSTM layer for feature extraction to obtain the child's vital signs features; The child interaction samples are input into the MLP encoding layer for feature extraction to obtain the child interaction features; The feature fusion layer uses a self-attention mechanism to fuse the cabin environment features, the child image features, the child vital signs features, and the child interaction features to obtain a fused feature vector. The output layer maps the fused feature vector to the predicted security risk type and the predicted risk level.

5. The method for monitoring the safety status of children in an intelligent cockpit according to claim 1, characterized in that, The step of matching the corresponding target intervention measures from a pre-set emergency plan database based on the target safety risk type and the target risk level specifically includes: Based on the target safety risk type, a first-level match is performed in the emergency plan database to obtain the corresponding emergency intervention strategy table; The target intervention measures are obtained by performing a secondary match on the emergency intervention strategy table based on the target risk level.

6. A method for monitoring the safety status of children in an intelligent cockpit according to any one of claims 1 to 5, characterized in that, After implementing emergency control of the target vehicle according to the target intervention measures, the method further includes the following steps: Acquire the updated cockpit environment data, image data, vital sign data, and interaction data; The updated cabin environment data, image data, vital sign data, and interaction data are input into the child safety risk identification model to obtain the current safety risk type and corresponding current risk level of the child occupant. The current security risk type and the current risk level are compared with the target security risk type and the target risk level, and the emergency response plan database is optimized based on the comparison results.

7. A method for monitoring the safety status of children in an intelligent cockpit according to any one of claims 1 to 5, characterized in that, After implementing emergency control of the target vehicle according to the target intervention measures, the method further includes the following steps: Obtain driver feedback data for the target vehicle; The actual safety risk type and corresponding actual risk level of the child occupant are determined based on the driving feedback data. The child safety risk identification model is incrementally learned based on the cabin environment data, the image data, the vital signs data, the interaction data, the actual safety risk type, and the actual risk level to obtain an updated child safety risk identification model.

8. A smart cockpit child safety status monitoring device, characterized in that, include: The data acquisition module is used to acquire cabin environment data of the target vehicle, as well as image data, vital sign data, and interaction data of child occupants; The safety risk identification module is used to input the cabin environment data, the image data, the vital signs data, and the interaction data into a pre-trained child safety risk identification model to obtain the target safety risk type and corresponding target risk level of the child occupant. The risk intervention module is used to match the corresponding target intervention measures in a preset emergency plan library according to the target safety risk type and the target risk level, and to perform emergency control on the target vehicle according to the target intervention measures.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a smart cockpit child safety status monitoring method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements a smart cockpit child safety status monitoring method as described in any one of claims 1 to 7.

Images