A vehicle-mounted intelligent massage method, device, equipment and storage medium

Abstract

The application discloses a vehicle-mounted intelligent massage method and device, equipment and a storage medium. The method comprises the following steps: obtaining historical motion data and real-time physical sign monitoring data of a target user; inputting the historical motion data and the real-time physical sign monitoring data into a fatigue grade prediction model which has been trained, to obtain a predicted fatigue position of the target user and a predicted fatigue grade corresponding to the predicted fatigue position; determining target massage parameters of a vehicle seat where the target user is located based on the predicted fatigue position and the predicted fatigue grade; and controlling the vehicle seat to massage the target user according to the target massage parameters. Through the above technical solution, the vehicle-mounted massage service is upgraded from general massage service to personalized massage service for users, and the massage experience of the user is improved.

Description

Technical Field

[0001] This application relates to the field of smart cockpit technology, specifically to an in-vehicle smart massage method, device, equipment, and storage medium. Background Technology

[0002] As an important component of the vehicle interior, vehicle seats have evolved from simple seating components into complex systems integrating various high-tech functions and ergonomic designs, reflecting consumers' increasing demands for driving and riding comfort.

[0003] Currently, existing in-car massage technologies are mainly designed with fixed modes, supporting only basic massage parameter adjustments. Existing in-car massage technologies are mainly divided into two categories: one is to preset multiple massage modes (such as back rolling and full-body relaxation), which users need to manually select and switch; the other is to simply detect pressure distribution through seat sensors and provide simple area massage.

[0004] Therefore, there is an urgent need to improve in-vehicle massage technology to enhance user comfort. Summary of the Invention

[0005] This application provides an in-vehicle intelligent massage method, device, equipment, and storage medium to provide personalized massage services to users and improve their riding comfort.

[0006] According to one aspect of this application, an in-vehicle intelligent massage method is provided, the method comprising:

[0007] Based on standardized interfaces, historical motion data and real-time vital sign monitoring data of target users are obtained;

[0008] The historical motion data and the real-time vital sign monitoring data are input into the trained fatigue level prediction model to obtain the predicted fatigue location of the target user and the predicted fatigue level corresponding to the predicted fatigue location; wherein, the fatigue level prediction model includes a decision tree sub-model and at least one sub-fatigue prediction model, and different sub-fatigue prediction models are used to predict the fatigue level of different massage object parts.

[0009] Based on the predicted fatigue location and the predicted fatigue level, the target massage parameters for the vehicle seat where the target user is located are determined.

[0010] The vehicle seat is controlled to massage the target user according to the target massage parameters.

[0011] According to another aspect of this application, an in-vehicle smart massage device is provided, the device comprising:

[0012] The data acquisition module is used to acquire the target user's historical motion data and real-time vital sign monitoring data based on a standardized interface;

[0013] The fatigue prediction module is used to input the historical motion data and the real-time vital sign monitoring data into a trained fatigue level prediction model to obtain the predicted fatigue location of the target user and the predicted fatigue level corresponding to the predicted fatigue location; wherein, the fatigue level prediction model includes a decision tree sub-model and at least one sub-fatigue prediction model, and different sub-fatigue prediction models are used to predict the fatigue level of different massage object parts.

[0014] The massage parameter module is used to determine the target massage parameters of the vehicle seat where the target user is located based on the predicted fatigue location and the predicted fatigue level.

[0015] The massage module is used to control the vehicle seat to massage the target user according to the target massage parameters.

[0016] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0017] One or more processors;

[0018] Memory, used to store one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the in-vehicle intelligent massage methods provided in the embodiments of this application.

[0020] According to another aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements any of the in-vehicle intelligent massage methods provided in the embodiments of this application.

[0021] According to another aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the in-vehicle intelligent massage methods provided in the embodiments of this application.

[0022] This application employs a fusion prediction model that includes a decision tree sub-model and at least one sub-fatigue prediction model. It extracts multi-dimensional feature variables from the target user's historical motion data and real-time vital sign monitoring data, and comprehensively predicts the fatigue level from both historical motion and real-time vital sign dimensions. This improves the accuracy of fatigue prediction and upgrades in-vehicle massage services from general massage services to personalized massage services for users, thereby enhancing the user's massage experience. Attached Figure Description

[0023] Figure 1 This is a flowchart of an in-vehicle intelligent massage method provided according to Embodiment 1 of this application.

[0024] Figure 2 This is a flowchart of an in-vehicle intelligent massage method provided according to Embodiment 2 of this application.

[0025] Figure 3 This is a structural schematic diagram of an in-vehicle intelligent massage device provided according to Embodiment 3 of this application.

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the in-vehicle intelligent massage method of Embodiment 4 of this application. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 the embodiments of this application 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 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.

[0029] Example 1

[0030] Figure 1 This is a flowchart of an in-vehicle intelligent massage method according to Embodiment 1 of this application. This embodiment is applicable to situations where a user is massaging a vehicle seat. The massage can be performed by an in-vehicle intelligent massage device, which can be implemented in hardware and / or software. This in-vehicle intelligent massage device can be configured in a computer device, such as an in-vehicle terminal. Figure 1 As shown, the method includes:

[0031] S110: Based on standardized interfaces, acquire historical motion data and real-time vital sign monitoring data of the target user.

[0032] Real-time vital sign monitoring data can characterize a user's physiological state, including real-time heart rate and respiratory rate. Target users can refer to passengers or drivers in vehicle seats.

[0033] Optionally, before acquiring the target user's historical motion data and real-time vital sign monitoring data, the method further includes: determining whether a user is sitting in the vehicle seat based on pressure sensors deployed in the vehicle seat; and acquiring the target user's historical motion data and real-time vital sign monitoring data after determining whether a user is sitting in the vehicle seat.

[0034] Optionally, based on a standardized interface, historical exercise data and real-time vital sign monitoring data of the target user can be obtained, including: acquiring historical exercise data and real-time vital sign monitoring data from the target user's mobile device based on a pre-set standardized interface. It should be noted that mobile devices can refer to wearable devices and / or mobile phones worn by the user, such as sports watches / wristbands.

[0035] The standardized interface can support communication with mobile devices of at least two device types and process mobile device data of at least two device types in a standardized format.

[0036] Specifically, after a user enters the vehicle wearing a wearable device and after exercising or working out, the vehicle's infotainment system can communicate with the wearable device via a pre-set standardized interface through a wireless connection method (such as Bluetooth) and obtain the user's historical exercise data and real-time vital sign monitoring data recorded in the wearable device.

[0037] Optionally, considering that wearable devices worn by users may involve different manufacturers, this embodiment of the invention sets up a unified data interface with a standardized interface in the vehicle system. This standardized interface includes a four-layer interface system, such as a core base layer, a plug-in layer, a data conversion layer, and a plug-in monitoring layer.

[0038] The core foundation layer can be a collection of interfaces conforming to the RESTful architecture specification (a lightweight web service architecture specification that performs CRUD operations on uniquely identified resources through standard HTTP methods, adopts stateless communication, and supports caching), and can define a unified communication connection standard with external devices; the plugin layer can configure device plugins corresponding to different types of wearable devices, and each device plugin is responsible for the conversion of communication protocols and data parsing for the corresponding type of wearable device; the data conversion layer defines standardized data format conversion rules, which can convert device data from different wearable devices into a unified data format; the plugin monitoring layer can monitor connection status, data transmission status, plugin status, and system status. For example, connection status can include average connection success rate and average connection time; data transmission status can include data latency, packet loss rate, and data integrity; plugin status can include plugin response time and error rate; and system status can include interface throughput and CPU / memory utilization.

[0039] For example, in one specific optional implementation, the connection and data transmission process between the vehicle terminal and the wearable device is as follows: Connection process: After discovering a connectable wearable device, the vehicle terminal initiates a connection request to the wearable device, carrying the brand type or device type of the wearable device, through a standardized protocol format defined by the core base layer. The core base layer authenticates the connection request to ensure that the connection request comes from the vehicle terminal and verifies whether the request parameters conform to the standardized protocol format defined by the core base layer. Connection requests that pass the request parameter verification are routed and forwarded to the plugin layer. After receiving the connection request, the plugin layer matches the target device plugin that is compatible with the brand type or device type corresponding to the connection request from the plugin library. The target device plugin converts the request parameters into the private protocol format of the wearable device. The target device plugin establishes a connection with the wearable device through a preset communication protocol and sends an authentication request. The wearable device returns a connection success response information to the target device plugin, and the target device plugin converts the received private protocol format response information into a standardized protocol format response information. The core base layer returns the standardized response information to the vehicle terminal.

[0040] Data transmission process: The in-vehicle terminal and the wearable device have established a session ID. The in-vehicle terminal requests device data from the wearable device in a standardized format. The core base layer verifies the validity and ownership of the session ID, confirming that the in-vehicle terminal has the right to access the device data of the wearable device. Based on the brand type or device type associated with the session ID, the data acquisition request is sent to the target device plugin. The target device plugin converts the request protocol format of the data acquisition request to conform to the private protocol format of the wearable device and sends it to the wearable device. The target device plugin receives the device data returned by the wearable device, calls the standardized data format conversion rules preset by the data conversion layer, performs standardized data format conversion on the device data, and returns the standardized data format converted device data to the in-vehicle terminal.

[0041] By setting up a standardized interface system with a four-layer interface architecture in the vehicle terminal, only one standardized data interface needs to be deployed in the vehicle terminal. All communication requests from wearable devices will pass through the core base layer for identity authentication and permission verification, which improves the security of communication connections. At the same time, the vehicle terminal does not need to deploy corresponding private protocol interfaces for different brands of wearable devices, reducing development costs. Furthermore, when a new brand of wearable device is available, only the corresponding device plugin for that brand needs to be developed, without modifying the code of the vehicle terminal, thus improving device scenario compatibility.

[0042] S120. Input historical motion data and real-time vital sign monitoring data into the trained fatigue level prediction model to obtain the predicted fatigue location of the target user and the predicted fatigue level corresponding to the predicted fatigue location.

[0043] The fatigue level prediction model can include a decision tree sub-model and at least one sub-fatigue prediction model. Different sub-fatigue prediction models can be used to predict the fatigue level of different massage target areas. Optionally, each branch structure in the decision tree sub-model can be used to represent the motion scene corresponding to a massage target area to be massaged. The branch structure can refer to the node path between the root node and the leaf node.

[0044] S130. Based on the predicted fatigue location and predicted fatigue level, determine the target massage parameters for the vehicle seat where the target user is located.

[0045] Optionally, based on the predicted fatigue location and predicted fatigue level, the massage parameters of the vehicle seat where the target user is located are determined, including: matching keywords in a pre-established massage knowledge base according to the fatigue scenario keywords corresponding to the predicted fatigue location and the fatigue level keywords of the predicted fatigue level to determine the target massage parameters.

[0046] The fatigue keywords can include keywords related to the exercise scenario and keywords related to the fatigued body part. It should be noted that the massage knowledge base can be constructed based on professional massage theory, standardized massage operating procedures, and historical massage data from different massage scenarios.

[0047] For example, the massage knowledge base can include different massage scenarios such as "deep kneading of the lower limbs after running", "shoulder and back massage after fitness", and "rolling of the lower back after sitting for a long time". The massage mode, massage intensity and massage area can be dynamically matched in the massage knowledge base according to keywords of exercise scenario, fatigue area and fatigue level.

[0048] By dynamically matching massage parameters based on a massage knowledge base, the adaptability to massage scenarios and the accuracy of massage parameters are improved.

[0049] S140: Control the vehicle seat to massage the target user according to the target massage parameters.

[0050] Optionally, in this embodiment of the invention, the real-time ambient temperature collected by vehicle sensors deployed in the vehicle, such as an ambient temperature sensor, and the user's vital signs data can be further linked with functions such as seat heating and seat ventilation. While the vehicle seat is massaging, the seat heating and / or seat ventilation functions can be automatically turned on to further improve the user's riding experience.

[0051] It should be noted that, in this embodiment of the invention, a hierarchical data access permission strategy can be set for the target user's historical motion data and real-time vital sign monitoring data. During the processing of the target user's historical motion data and real-time vital sign monitoring data, different data processing nodes have different data access permissions. For example, during the data acquisition stage, the standardized interface can only identify "the device has been connected and the device data transmission is normal", but the standardized interface does not have permission to view historical motion data and real-time vital sign monitoring data.

[0052] By setting tiered data access permissions, the security and privacy of data usage are improved.

[0053] This application embodiment employs a fusion prediction model that includes a decision tree sub-model and at least one sub-fatigue prediction model. It extracts multi-dimensional feature variables from the target user's historical motion data and real-time vital sign monitoring data, and comprehensively predicts the fatigue level from both historical motion and real-time vital sign dimensions. This improves the accuracy of fatigue prediction and upgrades the in-vehicle massage service from a general massage service to a personalized massage service for users, thereby enhancing the user's massage experience.

[0054] Example 2

[0055] Figure 2 This is a flowchart of an in-vehicle intelligent massage method according to Embodiment 2 of this application. Based on the technical solutions of the above embodiments, this embodiment further refines the step of "inputting historical motion data and real-time vital sign monitoring data into a trained fatigue level prediction model to obtain the predicted fatigue location of the target user and the corresponding predicted fatigue level." It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. Figure 2 As shown, the method includes:

[0056] S210: Based on standardized interfaces, acquire historical motion data and real-time vital sign monitoring data of the target user.

[0057] S220. Input historical motion data and real-time vital sign monitoring data into the trained fatigue level prediction model, perform feature preprocessing, and generate target feature vectors.

[0058] Specifically, in this embodiment of the invention, preliminary feature extraction can be performed on historical exercise data and real-time vital sign monitoring data to obtain multidimensional feature variables, including exercise intensity system, long decay coefficient, heart rate fluctuation amplitude, pressure distribution density, and exercise type weight, etc. The extracted feature variables are then standardized to the [0,1] interval, and abnormal feature variable values ​​are removed to construct a multidimensional target feature vector.

[0059] S230. Based on the target feature vector and the feature classification rules corresponding to each tree node in the decision tree sub-model, traverse the branch structure in the decision tree sub-model to determine the target leaf node.

[0060] Among them, the target leaf node is used to characterize the predicted fatigue location corresponding to the target feature vector.

[0061] In this embodiment of the invention, the target feature vector can be classified layer by layer by deploying feature classification rules in each tree node of the decision tree sub-model until the target leaf node to which the target feature vector belongs is determined. It should be noted that each branch structure in the decision tree sub-model can be used to represent the motion scene corresponding to a massage object part to be massaged. The branch structure can refer to the node path between the root node and the leaf node, and the number of branch structures in the decision tree sub-model is the same as the number of leaf nodes.

[0062] Optionally, based on the target feature vector and the feature classification rules corresponding to each tree node in the decision tree sub-model, the branch structure in the decision tree sub-model is traversed to determine the target leaf node, including: taking the root node of the decision tree sub-model as the current traversal node, determining the next traversal node of the current traversal node according to the feature classification rules corresponding to the current traversal node, and updating the next traversal node as the current traversal node; when the node type of the current traversal node is a leaf node, the current traversal node is determined as the target leaf node.

[0063] It should be noted that different tree nodes in the decision tree sub-model represent different feature classification rules. That is, different tree nodes classify different feature variables in the target feature vector. For example, the root node of the decision tree sub-model can classify the target feature variable based on the motion intensity coefficient. If the motion intensity coefficient is greater than or equal to a first intensity threshold, the target feature vector enters the first branch under the root node; if the motion intensity coefficient is greater than or equal to a second intensity threshold but less than the first intensity threshold, the target feature vector enters the second branch under the root node; if the motion intensity coefficient is less than the second intensity threshold, the target feature vector enters the third branch under the root node. It should be noted that the first and second intensity thresholds can be adaptively set by those skilled in the art.

[0064] Optionally, after determining the target leaf node, the motion scene classification result corresponding to the target leaf node can be used as a scene weight factor and input together with the target feature vector into the sub-fatigue prediction model corresponding to the target leaf node to achieve differentiated fatigue analysis for different motion scenes and improve the prediction accuracy of the sub-fatigue prediction model.

[0065] S240. Based on the sub-fatigue prediction model deployed in the target leaf node, predict the fatigue level of the target feature vector and determine the predicted fatigue level of the corresponding massage object part by the sub-fatigue prediction model.

[0066] Specifically, in this embodiment of the invention, different sub-fatigue prediction models corresponding to different motion scenarios can be deployed in different target leaf nodes. Optionally, the neural network models of the sub-fatigue prediction models corresponding to different target leaf nodes can have the same or different model structures, which can be adapted according to those skilled in the art, and are not specifically limited here.

[0067] Optionally, in this embodiment of the invention, the sub-fatigue prediction models deployed in different target leaf nodes are trained on the pre-set neural network model using training sample data from different motion scenarios during the model training process. The loss function of the sub-fatigue prediction model during the model training process can be a weighted joint loss function, such as the multi-class cross-entropy loss function corresponding to the decision tree sub-model, and the mean squared error loss between the predicted value and the label value. Those skilled in the art can adapt the weighted loss weights of the loss function.

[0068] It should be noted that the output of the sub-fatigue prediction model's output layer can be represented as an output vector. This output vector can include the prediction probability result for each fatigue level, and the sum of the prediction probabilities for each fatigue level is 1. The fatigue level with the highest prediction probability is taken as the final fatigue level prediction result. Optionally, the output result of the sub-fatigue prediction model can be represented by the following formula:

[0069] ;

[0070] ;

[0071] ;

[0072] Where C represents the number of fatigue levels. This represents the score corresponding to the k-th fatigue level in the hidden layer output. To represent the probability that a sample belongs to the k-th fatigue level given input data x, denoted as the predicted fatigue level output by the model, W represents the output layer weights, h represents the hidden layer features, and b represents the bias vector.

[0073] S250: Based on the predicted fatigue location and predicted fatigue level, determine the target massage parameters for the vehicle seat where the target user is located.

[0074] S260. Control the vehicle seat to massage the target user according to the target massage parameters.

[0075] Optionally, in this embodiment of the invention, massage feedback data from the target user after a massage can be collected, and a reinforcement learning method can be used to dynamically adjust the model parameters of the fatigue level prediction model, using the massage feedback data as a reward. It should be noted that the massage feedback data may include the matching degree of the massage area and the satisfaction level with the massage parameters.

[0076] This application embodiment uses a decision tree as a feature filter to classify the input data according to feature rules and then feeds it into different sub-neural network models for fatigue prediction. This reduces the amount of data in the sub-neural network models, lowers the model complexity, and retains the rule interpretability of the decision tree.

[0077] Example 3

[0078] Figure 3 This is a structural schematic diagram of an in-vehicle intelligent massage device according to Embodiment 3 of this application. It is applicable to situations where a user is massaging a vehicle seat. This in-vehicle intelligent massage device can be implemented in hardware and / or software, and can be configured in a computer device, such as an in-vehicle terminal. Figure 3 As shown, the device includes:

[0079] The data acquisition module 310 is used to acquire the target user's historical motion data and real-time vital sign monitoring data based on a standardized interface;

[0080] The fatigue prediction module 320 is used to input the historical motion data and the real-time vital sign monitoring data into a trained fatigue level prediction model to obtain the predicted fatigue location of the target user and the predicted fatigue level corresponding to the predicted fatigue location; wherein, the fatigue level prediction model includes a decision tree sub-model and at least one sub-fatigue prediction model, and different sub-fatigue prediction models are used to predict the fatigue level of different massage object parts.

[0081] Massage parameter module 330 is used to determine the target massage parameters of the vehicle seat where the target user is located based on the predicted fatigue location and the predicted fatigue level.

[0082] The massage module 340 is used to control the vehicle seat to massage the target user according to the target massage parameters.

[0083] This application embodiment employs a fusion prediction model that includes a decision tree sub-model and at least one sub-fatigue prediction model. It extracts multi-dimensional feature variables from the target user's historical motion data and real-time vital sign monitoring data, and comprehensively predicts the fatigue level from both historical motion and real-time vital sign dimensions. This improves the accuracy of fatigue prediction and upgrades the in-vehicle massage service from a general massage service to a personalized massage service for users, thereby enhancing the user's massage experience.

[0084] Optionally, the fatigue prediction module includes:

[0085] The feature vector generation unit is used to input the historical motion data and the real-time vital sign monitoring data into the trained fatigue level prediction model, perform feature preprocessing, and generate target feature vectors.

[0086] The target node determination unit is used to traverse the branch structure in the decision tree sub-model based on the target feature vector and the feature classification rule corresponding to each tree node in the decision tree sub-model to determine the target leaf node; wherein, the target leaf node is used to characterize the predicted fatigue part corresponding to the target feature vector;

[0087] The fatigue prediction unit is used to predict the fatigue level of the target feature vector based on the sub-fatigue prediction model deployed in the target leaf node, and to determine the predicted fatigue level of the corresponding massage object part by the sub-fatigue prediction model.

[0088] Optionally, the target node determination unit can be specifically used for:

[0089] Using the root node of the decision tree sub-model as the current traversal node, the next traversal node of the current traversal node is determined according to the feature classification rule corresponding to the current traversal node, and the next traversal node is updated to the current traversal node.

[0090] When the node type of the currently traversed node is a leaf node, then the currently traversed node is determined to be the target leaf node.

[0091] Optionally, each branch structure in the decision tree sub-model is used to characterize the motion scene corresponding to a massage object part to be massaged, and the branch structure refers to the node path between the root node and the leaf node.

[0092] Optionally, the data acquisition module 310 can be specifically used for:

[0093] Based on a pre-set standardized interface, historical motion data and real-time vital sign monitoring data are obtained from the target user's mobile device; wherein, the standardized interface supports communication connection with at least two types of mobile devices and performs standardized format processing on the data of at least two types of mobile devices.

[0094] Optionally, the massage parameter module 330 can be specifically used for:

[0095] Based on the fatigue scenario keywords corresponding to the predicted fatigue location and the fatigue level keywords for the predicted fatigue level, keyword matching is performed in a pre-established massage knowledge base to determine the target massage parameters; wherein, the fatigue keywords include exercise scenario keywords and fatigue location keywords.

[0096] The in-vehicle intelligent massage device provided in this application embodiment can execute the in-vehicle intelligent massage method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing each in-vehicle intelligent massage method.

[0097] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0098] Example 4

[0099] Figure 4 This is a schematic diagram of the structure of an electronic device 410 implementing the in-vehicle intelligent massage method according to embodiments of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0100] like Figure 4 As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory 412 or a random access memory 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 412 or loaded from storage unit 418 into the random access memory 413. The random access memory 413 can also store various programs and data required for the operation of the electronic device 410. The processor 411, read-only memory 412, and random access memory 413 are interconnected via a bus 414. An input / output interface 415 is also connected to the bus 414.

[0101] Multiple components in electronic device 410 are connected to input / output interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of monitors, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0102] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as in-vehicle intelligent massage methods.

[0103] In some embodiments, the in-vehicle intelligent massage method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via read-only memory 412 and / or communication unit 419. When the computer program is loaded into random access memory 413 and executed by processor 411, one or more steps of the in-vehicle intelligent massage method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured as the in-vehicle intelligent massage method by any other suitable means (e.g., by means of firmware).

[0104] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), payload programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0105] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable in-vehicle intelligent massage device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0106] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0107] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube or liquid crystal display monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0108] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0109] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual private servers, such as high management difficulty and weak business scalability.

[0110] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0111] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A vehicle-mounted intelligent massage method, characterized in that, include: Based on standardized interfaces, historical motion data and real-time vital sign monitoring data of target users are obtained; The historical motion data and the real-time vital sign monitoring data are input into the trained fatigue level prediction model to obtain the predicted fatigue location of the target user and the predicted fatigue level corresponding to the predicted fatigue location; wherein, the fatigue level prediction model includes a decision tree sub-model and at least one sub-fatigue prediction model, and different sub-fatigue prediction models are used to predict the fatigue level of different massage object parts. Based on the predicted fatigue location and the predicted fatigue level, the target massage parameters for the vehicle seat where the target user is located are determined. The vehicle seat is controlled to massage the target user according to the target massage parameters.

2. The method according to claim 1, characterized in that, The step of inputting the historical motion data and the real-time vital sign monitoring data into the trained fatigue level prediction model to obtain the predicted fatigue location of the target user and the predicted fatigue level corresponding to the predicted fatigue location includes: The historical motion data and the real-time vital sign monitoring data are input into the trained fatigue level prediction model for feature preprocessing to generate a target feature vector. Based on the target feature vector and the feature classification rules corresponding to each tree node in the decision tree sub-model, the branch structure in the decision tree sub-model is traversed to determine the target leaf node; wherein, the target leaf node is used to characterize the predicted fatigue location corresponding to the target feature vector; Based on the sub-fatigue prediction model deployed in the target leaf node, the fatigue level of the target feature vector is predicted, and the predicted fatigue level of the sub-fatigue prediction model for the corresponding massage object part is determined.

3. The method according to claim 2, characterized in that, The step of traversing the branch structure of the decision tree model based on the target feature vector and the feature classification rules corresponding to each tree node in the decision tree sub-model to determine the target leaf node includes: Using the root node of the decision tree sub-model as the current traversal node, the next traversal node of the current traversal node is determined according to the feature classification rule corresponding to the current traversal node, and the next traversal node is updated to the current traversal node. When the node type of the currently traversed node is a leaf node, then the currently traversed node is determined to be the target leaf node.

4. The method according to claim 1, characterized in that, Each branch structure in the decision tree sub-model is used to represent the motion scene corresponding to a massage object part to be massaged. The branch structure refers to the node path between the root node and the leaf node.

5. The method according to claim 1, characterized in that, The process of acquiring historical motion data and real-time vital sign monitoring data of the target user based on a standardized interface includes: Based on a pre-set standardized interface, historical motion data and real-time vital sign monitoring data are obtained from the target user's mobile device; wherein, the standardized interface supports communication connection with at least two types of mobile devices and performs standardized format processing on the data of at least two types of mobile devices.

6. The method according to claim 1, characterized in that, The step of determining the massage parameters of the vehicle seat where the target user is located based on the predicted fatigue location and the predicted fatigue level includes: Based on the fatigue scenario keywords corresponding to the predicted fatigue location and the fatigue level keywords for the predicted fatigue level, keyword matching is performed in a pre-established massage knowledge base to determine the target massage parameters; wherein, the fatigue keywords include exercise scenario keywords and fatigue location keywords.

7. A vehicle-mounted intelligent massage device, characterized in that, include: The data acquisition module is used to acquire the target user's historical motion data and real-time vital sign monitoring data based on a standardized interface; The fatigue prediction module is used to input the historical motion data and the real-time vital sign monitoring data into a trained fatigue level prediction model to obtain the predicted fatigue location of the target user and the predicted fatigue level corresponding to the predicted fatigue location; wherein, the fatigue level prediction model includes a decision tree sub-model and at least one sub-fatigue prediction model, and different sub-fatigue prediction models are used to predict the fatigue level of different massage object parts. The massage parameter module is used to determine the target massage parameters of the vehicle seat where the target user is located based on the predicted fatigue location and the predicted fatigue level. The massage module is used to control the vehicle seat to massage the target user according to the target massage parameters.

8. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the in-vehicle intelligent massage method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the in-vehicle intelligent massage method as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the in-vehicle intelligent massage method according to any one of claims 1-6.

Images