A multi-scene perception-based online homestay equipment linkage control method and system

Abstract

The application discloses a kind of based on multi-scene perception's online homestay equipment linkage method, method includes the following steps: obtaining and integrating multi-source sensor data, generates fused perception features;Fused perception features and equipment initial operating state input scene adaptation controller, generate equipment linkage control vector and scene adaptation control vector and corresponding time series information;Control vector, time series information, perception features and time information are input equipment linkage decision maker and feedback optimizer, output optimized feature vector;According to the optimized feature vector, update equipment operating state, and output equipment linkage result.The application not only improves the comfort of user, but also significantly improves energy utilization efficiency, has higher application value.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and specifically discloses a method and system for the linkage control of online homestay equipment based on multi-scene perception. Background Technology

[0002] With the rapid development of smart home and IoT technologies, device linkage methods based on multi-scenario perception have demonstrated significant importance in enhancing user experience and optimizing resource utilization. This is particularly true in online homestay scenarios, where users increasingly demand intelligent living environments, such as intelligent linkage between devices through sensing environmental conditions, user behavior, or usage habits to provide more comfortable and convenient services. However, existing device linkage technologies still have significant shortcomings in terms of multi-scenario adaptability, level of intelligence, and user experience optimization.

[0003] A search revealed that patent CN113467261B proposes a linkage control method based on the runtime of the main device. This method monitors the runtime of the main device to determine the control information of the linked devices and adjusts their operating modes accordingly. This technical solution simplifies device control to some extent and improves the user experience in specific scenarios. However, this method relies primarily on single-dimensional runtime data and lacks the ability to comprehensively analyze complex perceptual data from multiple scenarios (such as ambient temperature, light intensity, and user behavior), making it difficult to meet the diverse needs of online homestays. Furthermore, the system's response speed to scene switching is slow, potentially failing to adapt to dynamically changing user needs in real time.

[0004] Another patent, CN106372412B, proposes a method for analyzing the energy efficiency of interconnected devices. By collecting energy consumption-related parameters of the interconnected devices and combining data preprocessing, frame segmentation, and correlation coefficient calculation, it enables the investigation and energy efficiency optimization of device interconnection anomalies. This technical solution has certain advantages in improving the overall operational stability and energy-saving effect of the system. However, this method mainly focuses on the energy efficiency optimization of the devices and lacks the ability to deeply perceive user behavior and environmental conditions, making it unable to dynamically adjust the device interconnection strategy according to specific scenario requirements. Furthermore, this solution does not involve intelligent design for multi-device collaborative work, and may not be able to meet the complex needs of multi-device interconnection in online homestays in practical applications.

[0005] The aforementioned issues indicate that existing device linkage technologies still have significant shortcomings in terms of multi-scenario perception capabilities, intelligence level, and dynamic adaptability. Particularly in the context of online homestays, users have high demands for flexibility, real-time performance, and personalization in device linkage, which current technologies struggle to fully meet. Therefore, there is an urgent need for a device linkage method and system that can integrate multi-dimensional perception data and optimize scenario adaptation algorithms to achieve intelligent linkage between devices, thereby improving user experience, reducing operating costs, and meeting the intelligent management needs of modern online homestays. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a method and system for linking online homestay equipment based on multi-scene perception, so as to improve the above-mentioned problems.

[0007] A method for linking online homestay equipment based on multi-scene perception, characterized by the following steps:

[0008] Acquire and integrate multi-source sensor data to generate fused sensing features;

[0009] The fused sensing features and the initial operating state of the device are input into the scene adaptation controller to generate device linkage control vectors and scene adaptation control vectors, as well as corresponding time series information.

[0010] The control vector, time series information, sensing features, and time information are input into the device, which is linked to the decision-maker and feedback optimizer to output the optimized feature vector.

[0011] The device operating status is updated based on the optimized feature vector, and the device linkage results are output.

[0012] Preferably, the acquisition and integration of multi-source sensor data includes the following steps:

[0013] Denoising and normalization are performed on multi-source sensing data;

[0014] Generate a dynamic weight matrix of the same dimension as the importance distribution information of the data;

[0015] The dynamic weight matrix and the preprocessed data are input into the adaptive feature extraction network to obtain the fused perceptual features.

[0016] Preferably, the scene adaptation controller includes the following sub-steps:

[0017] Based on the initial operating status of the equipment, the characteristics of the equipment operating area and the environmental background are obtained and merged into the regional characteristics of the equipment-environment pair;

[0018] Use convolutional layers and multilayer perceptrons to predict device start-up and shutdown points, operating intensity points, and scene switching points;

[0019] Operational features are obtained by sampling three types of key points, and the temporal relationship of the three types of points is constructed to generate temporal features;

[0020] By aggregating operational and temporal characteristics, the final device, environmental, and scenario characteristics are obtained.

[0021] The three features are combined and a device linkage control vector and a scene adaptation control vector are generated through a multilayer perceptron.

[0022] The time series information of the device control vector and the scene control vector is obtained by applying the cosine embedding function to the device linkage control vector and the scene adaptation control vector respectively.

[0023] Preferably, the device start / stop point, operating intensity point, and scene switching point are normalized to between zero and one using the Sigmoid activation function.

[0024] Preferably, the device linkage decision-maker and feedback optimizer are composed of stacked multi-layer dynamic programming networks, with each layer using the feature vector output by the previous layer to update the control vector of the current layer.

[0025] Preferably, the device linkage results include device operating status, environmental adaptation status, scene switching time, and user satisfaction.

[0026] This invention also provides a multi-scene perception-based online homestay equipment linkage system, which includes a perception data fusion unit, a scene adaptation controller, an equipment linkage decision-maker, and a feedback optimizer, wherein:

[0027] A perception data fusion unit is used to acquire and integrate multi-source sensor data to generate fused perception features.

[0028] The scene adaptation controller is used to input the fused perception features and the initial operating state of the device into the scene adaptation controller to generate device linkage control vectors and scene adaptation control vectors, as well as corresponding time series information;

[0029] The device linkage decision-maker is used to input control vectors, time series information, sensing features and time information into the device linkage decision-maker and feedback optimizer, and output the optimized feature vector.

[0030] The feedback optimizer is used to update the device operating status based on the optimized feature vector and output the device linkage results.

[0031] Preferably, the sensing data fusion unit is specifically used for: denoising and normalizing multi-source sensing data;

[0032] Generate a dynamic weight matrix of the same dimension as the importance distribution information of the data;

[0033] The dynamic weight matrix and the preprocessed data are input into the adaptive feature extraction network to obtain the fused perceptual features.

[0034] Preferably, the scene adaptation controller is specifically used for:

[0035] Based on the initial operating status of the equipment, the characteristics of the equipment operating area and the environmental background are obtained and merged into the regional characteristics of the equipment-environment pair;

[0036] Convolutional layers and multilayer perceptrons are used to predict three key points: device start-up and shutdown points, operating intensity points, and scene switching points.

[0037] Operational features are obtained by sampling three types of key points, and the temporal relationship of the three types of points is constructed to generate temporal features;

[0038] By aggregating operational and temporal characteristics, we obtain device characteristics, environmental characteristics, and scene characteristics.

[0039] The system merges device features, environmental features, and scene features, and generates device linkage control vectors and scene adaptation control vectors through a multilayer perceptron.

[0040] The time series information of the device control vector and the scene control vector is obtained by applying the cosine embedding function to the device linkage control vector and the scene adaptation control vector respectively.

[0041] Preferably, the device linkage decision-maker and feedback optimizer are implemented through a stacked multi-layer dynamic programming network, and output the results of device operating status, environmental adaptation status, scene switching time and user satisfaction, respectively.

[0042] In summary, this invention achieves multi-scenario perception-based linkage of homestay equipment through the collaborative operation of a perception data fusion unit, a scene adaptation controller, a device linkage decision-maker, and a feedback optimizer. In practical applications, for example, when a user enters a homestay room, the system can automatically adjust the air conditioning temperature, turn on background music, and adjust the lighting brightness based on real-time perception data, thereby providing a personalized living experience. This intelligent device linkage not only enhances user comfort but also significantly improves energy efficiency, demonstrating high application value. Attached Figure Description

[0043] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1This is a schematic diagram of the structure of the online homestay equipment linkage system based on multi-scene perception provided in the first embodiment of the present invention.

[0045] Figure 2 This is a flowchart illustrating the online homestay equipment linkage method based on multi-scene perception provided in the second embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention.

[0047] This invention proposes a method and system for the linkage of online homestay equipment based on multi-scene perception in several embodiments. Its core lies in achieving intelligent collaborative linkage between devices through multimodal data fusion and dynamic scene adaptation algorithms. The following, in conjunction with the appendix... Figure 1 To be continued Figure 2 The specific structure and process of the present invention will be described in detail, and the specific implementation of the present invention will be described in detail.

[0048] First, such as Figure 1 As shown, the online homestay equipment linkage method and system based on multi-scene perception of the present invention consists of four main modules: a perception data fusion unit 1, a scene adaptation controller 2, an equipment linkage decision-maker 3, and a feedback optimizer 4. The data flow and linkage process between these modules constitute the operating mechanism of the entire system. In practical applications, taking an online homestay environment as an example, it is assumed that the environment is equipped with multi-source perception devices such as temperature sensors, humidity sensors, light sensors, and sound sensors, as well as controllable devices such as air conditioners, humidifiers, lights, and background music players. After acquiring and integrating multi-source sensor data through the perception data fusion unit, the initial operating state of a group of devices is initialized, and the fused perception data and the initial state of the devices are input into the scene adaptation controller. The scene adaptation controller 2 generates two sets of control vectors and time series information of the control vectors according to the input, which are then processed by the equipment linkage decision-maker and the feedback optimizer, and finally output the optimized linkage control command set to realize intelligent collaborative linkage between devices.

[0049] Next, each part will be explained in detail:

[0050] The first part is the perceptual data fusion unit 1.

[0051] In this embodiment, the sensor data fusion unit 1 consists of a multimodal data preprocessing module and an adaptive feature extraction network. In actual operation, multi-source sensor data includes data from multiple dimensions such as temperature, humidity, light intensity, and sound. This data is first processed by the preprocessing module for noise reduction and normalization to ensure data quality and consistency. For example, the raw data collected by the temperature sensor may contain noise or outliers; the preprocessing module removes these interferences using filtering algorithms and normalizes the data to the range of 0 to 1 for subsequent processing. The preprocessed data is used to generate a dynamic weight matrix of the same dimension, serving as the importance distribution information of the data. The generation of the dynamic weight matrix is ​​achieved by calculating the relative importance of each type of sensor data in the current scene. For example, in a nighttime scene, the importance of light intensity data may be low, while the importance of sound data may be high. The generated dynamic weight matrix, along with the preprocessed data, is input into the adaptive feature extraction network. After processing by a multi-layer neural network, the fused sensor features are finally obtained. This process not only integrates multi-source data but also provides high-quality feature input for subsequent scene adaptation.

[0052] Part Two, Learnable Scene Adaptive Controller 2.

[0053] The main function of the scene adaptation controller 2 is to generate two sets of control vectors: device linkage control vectors and scene adaptation control vectors. To achieve this, the controller needs to input the fused perception features and the initial operating state of the device. Taking an air conditioner as an example, assuming the initial state is that the air conditioner is off and the temperature is set to 25℃, the controller first obtains the corresponding device operating area features F based on the initial state. device and environmental background characteristics F env These two features are then combined along the time dimension to obtain the regional features F of the device-environment pair. device-env The formula is defined as:

[0054] F device-env =Concat(F device F env )

[0055] Subsequently, these three features are used to predict three types of keypoints, namely the device start / stop points P, through a convolutional layer (Conv) and a multilayer perceptron (MLP). start Operating intensity point P intensity and scene transition point P switch Since these key points need to be normalized to between 0 and 1 during sampling, the predicted key points also need to be normalized using the Sigmoid activation function. The prediction results of these key points can accurately reflect the operational requirements of the device in different scenarios.

[0056] After obtaining the key points, the scene adaptation controller 2 further performs feature sampling and aggregation operations. To obtain richer information, the scene adaptation controller 2 samples the three types of key points to obtain operational features, and also constructs the temporal features of these three types of points. For operational features, the scene adaptation controller 2 uses the device start and stop points P respectively. start Operating intensity point P intensity and scene transition point P switch Equipment-environment relationship with regional characteristics F device-env Perform bilinear interpolation sampling to generate the device operating characteristics F. run Environmental adaptation characteristics F adapt Scene switching feature F switch The specific calculation steps are as follows:

[0057] F run =Bilinear(P) star ,F device -env)

[0058] F adapt =Bilinear(P instensity ,F device -env)

[0059] F switch =Bilinear(P) switch ,F device -env)

[0060] Wherein, Bilinear represents the bilinear interpolation sampling operation.

[0061] For time characteristics, the scene adaptation controller 2 constructs the time relationship of three types of key points, regards the scene switching point as the origin between the device start / stop point and the running intensity point, and then connects the device start / stop point and the running intensity point to the origin to form two corresponding vectors V. start and V instensity The formula is defined as:

[0062] V start =P star -P switch

[0063] V instensity =P instensity -P switch

[0064] Next, the time difference between these two vectors is calculated, and a time matrix is ​​generated to represent the temporal relationship between the three types of keypoints. Finally, the time matrix is ​​flattened from two dimensions to one dimension and passed through a fully connected layer (FC) to obtain the temporal feature T.feature The formula is defined as:

[0065] T relation =Flatten(V start ×V instensity )

[0066] T feature =FC(T) relation )

[0067] Based on the above operations, the scenario adaptation controller 2 further aggregates the running features F. run and time features T feature To obtain the final device characteristics F final-device Environmental characteristics F final-env and scene features F final-switch The formula is defined as:

[0068] F final-device =F run ⊙T feature

[0069] F final-env =F adapt ⊙T feature

[0070] F final-switch =F switch ⊙T feature

[0071] Where ⊙ represents element-wise multiplication.

[0072] After feature sampling and aggregation are completed, the scene adaptation controller 2 merges the final device features, environmental features, and scene features, and obtains the mixed feature F through a multilayer perceptron (MLP). mixed Finally, regarding the mixed feature F mixed After segmentation, the device linkage control vector C generated by scene adaptation controller 2 is obtained. device Scene-adaptive control vector C scene The specific calculation steps are as follows:

[0073] F mixed =MLP(Concat(F final-device ,F final-device F final-env ,F final-switch ))

[0074] The formula for calculating the segmented control vector is:

[0075] [C device C scene ] = Split(F mixed )

[0076] Concat is a merge operation, and Split is a split operation.

[0077] In addition, the scene adaptation controller 2 also controls the device linkage control vector C respectively. device Scene-adaptive control vector C scene The cosine embedding function is used to obtain the time-series information T of the device control vector and scene control vector. device and T scene The formula is defined as:

[0078] T device =CosineEmbed(C device )

[0079] T scene =CosineEmbed(C scene )

[0080] CosineEmbed is a cosine embedding function that transforms temporal information into a feature vector.

[0081] Next, we will proceed with the implementation of the device linkage decision-maker 3 and the feedback optimizer 4. Both modules consist of stacked multi-layer dynamic programming networks and require the device linkage control vector C generated by the scenario adaptation controller 2. device Scene-adaptive control vector C scene The process involves multiplying the generated control vector (excluding the first layer) by the optimized feature vector output by the previous layer's decision maker to obtain a control vector that retains previously valid information. Then, the control vector, time series information, perceptual features, and corresponding time information are input into the respective decision makers, which output the optimized feature vector. The specific calculation steps are as follows:

[0082]

[0083] in This is the output of the device linkage decision-maker at the current layer. The output of the feedback optimizer for the current layer. and These are the features output from the previous layer.

[0084] After each layer outputs a feature vector, the feature vector linked to the device is used to update the device's operating state S. device and S scene The formula is defined as:

[0085] S device =φ(Update(D device ))

[0086] S scene=φ(Update(D scene ))

[0087] Where Update is the feedforward network that updates the device's operating state, and φ is an activation function that normalizes the values ​​to between 0 and 1.

[0088] Finally, the feature vector output by the last decision layer is passed through a head feedforward network used for optimization to obtain the device operating state R. device Environmental adaptation status R env Scene switching time R time The results of device linkage with user satisfaction. The formula for calculating device operating status is:

[0089] R device =φ(Output(D device ))

[0090] R env =φ(Output(D scene ))

[0091] R time =φ(Output(T) scene ))

[0092] R satisfaction =φ(Output(S) device ,S scene ))

[0093] Where Output is the final predicted feedforward network, and φ is the activation function.

[0094] In summary, this embodiment of the invention achieves multi-scene perception-based linkage of online homestay equipment through the collaborative operation of the perception data fusion unit 1, the scene adaptation controller 2, the device linkage decision-maker 3, and the feedback optimizer 4. In practical application scenarios, for example, when a user enters a homestay room, the system can automatically adjust the air conditioning temperature, turn on background music, and adjust the lighting brightness based on real-time perception data, thereby providing a personalized living experience. This intelligent device linkage not only improves user comfort but also significantly improves energy efficiency, fully demonstrating the technical advantages and application value of this invention.

[0095] Please see Figure 2 The second embodiment of the present invention provides a method for linking online homestay equipment based on multi-scene perception, which includes the following steps:

[0096] S201, Acquire and integrate multi-source sensor data to generate fused perception features;

[0097] S202, input the fused perception features and the initial operating state of the device into the scene adaptation controller to generate device linkage control vector and scene adaptation control vector and corresponding time series information;

[0098] S203 inputs control vectors, time series information, sensing features and time information into the device, links the decision-maker and feedback optimizer, and outputs the optimized feature vector;

[0099] S204 updates the device operating status based on the optimized feature vector and outputs the device linkage result.

[0100] The third embodiment of the present invention also provides a computer-readable storage medium storing a computer program that can be executed by the processor of the device where the computer-readable storage medium is located, so as to realize the above-described method for linking online homestay devices based on multi-scene perception.

[0101] Exemplarily, the computer program described in the third embodiment of the present invention can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the error correction device. For example, the apparatus described in the second embodiment of the present invention.

[0102] The processor referred to can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the error correction method, connecting the various parts of the implementation of the processing method through various interfaces and lines.

[0103] The memory can be used to store the computer program and / or modules. The processor implements various functions of an error correction method by running or executing the computer program and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, text conversion function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, text message data, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0104] If the implemented module is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0105] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0106] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions that fall within the scope of the present invention are within the scope of protection of the present invention.

Claims

1. A method for linking online homestay equipment based on multi-scene perception, characterized in that, Includes the following steps: Acquire and integrate multi-source sensor data to generate fused sensing features; The fused sensing features and the initial operating state of the device are input into the scene adaptation controller to generate device linkage control vectors, scene adaptation control vectors, and corresponding time series information; wherein, the scene adaptation controller is used for: Based on the initial operating status of the equipment, the characteristics of the equipment operating area and the environmental background are obtained and merged into the regional characteristics of the equipment-environment pair; Convolutional layers and multilayer perceptrons are used to predict three key points: device start-up and shutdown points, operating intensity points, and scene switching points. Operational features are obtained by sampling three types of key points, and the temporal relationship of the three types of key points is constructed to generate temporal features; By aggregating operational and temporal characteristics, the final device, environmental, and scenario characteristics are obtained. The final device features, environmental features, and scene features are merged, and device linkage control vectors and scene adaptation control vectors are generated through a multilayer perceptron. The time series information of the device control vector and the scene control vector is obtained by applying the cosine embedding function to the device linkage control vector and the scene adaptation control vector respectively. The control vector, time series information, sensing features, and time information are input into the device, which is linked to the decision-maker and feedback optimizer to output the optimized feature vector. The device operating status is updated based on the optimized feature vector, and the device linkage results are output.

2. The method according to claim 1, characterized in that, The acquisition and integration of multi-source sensor data includes the following steps: Denoising and normalization are performed on multi-source sensing data; Generate a dynamic weight matrix of the same dimension as the importance distribution information of the data; The dynamic weight matrix and the preprocessed data are input into the adaptive feature extraction network to obtain the fused perceptual features.

3. The method according to claim 2, characterized in that, The device start / stop points, operating intensity points, and scene switching points are normalized to between zero and one using the Sigmoid activation function.

4. The method according to claim 1, characterized in that, The device linkage decision-maker and feedback optimizer consist of stacked multi-layer dynamic programming networks, with each layer updating its control vector using the feature vector output from the previous layer.

5. The method according to claim 1, characterized in that, The device linkage results include device operating status, environmental adaptation status, scene switching time, and user satisfaction.

6. A multi-scene perception-based online homestay equipment linkage system, characterized in that, It includes a perception data fusion unit, a scene adaptation controller, a device linkage decision-maker, and a feedback optimizer, among which: A perception data fusion unit is used to acquire and integrate multi-source sensor data to generate fused perception features. A scene adaptation controller is used to input the fused sensing features and the initial operating state of the device into the scene adaptation controller, generating device linkage control vectors and scene adaptation control vectors, as well as corresponding time series information; the scene adaptation controller is used for: Based on the initial operating status of the equipment, the characteristics of the equipment operating area and the environmental background are obtained and merged into the regional characteristics of the equipment-environment pair; Convolutional layers and multilayer perceptrons are used to predict three key points: device start-up and shutdown points, operating intensity points, and scene switching points. Operational features are obtained by sampling three types of key points, and the temporal relationship of the three types of key points is constructed to generate temporal features; By aggregating operational and temporal characteristics, the final device, environmental, and scenario characteristics are obtained. The final device features, environmental features, and scene features are merged, and device linkage control vectors and scene adaptation control vectors are generated through a multilayer perceptron. The time series information of the device control vector and the scene control vector is obtained by applying the cosine embedding function to the device linkage control vector and the scene adaptation control vector respectively. The device linkage decision-maker is used to input control vectors, time series information, sensing features and time information into the device linkage decision-maker and feedback optimizer, and output the optimized feature vector. The feedback optimizer is used to update the device operating status based on the optimized feature vector and output the device linkage results.

7. The system according to claim 6, characterized in that, The sensor data fusion unit is specifically used for: denoising and normalizing multi-source sensor data; Generate a dynamic weight matrix of the same dimension as the importance distribution information of the data; The dynamic weight matrix and the preprocessed data are input into the adaptive feature extraction network to obtain the fused perceptual features.

8. The system according to claim 6, characterized in that, The device linkage decision-maker and feedback optimizer are implemented through a stacked multi-layer dynamic programming network, and output the results of device operating status, environmental adaptation status, scene switching time and user satisfaction, respectively.

Images