Internet of Things device linkage control method, system and storage medium based on cloud computing

Abstract

The present invention discloses a method, system and storage medium for linkage control of Internet of Things devices based on cloud computing, and relates to the field of intelligent control technology. The method includes: building a home coverage network; performing network partition aggregation, establishing network partition aggregation results, and configuring a distributed computing center; synchronizing the monitoring data of the sensor group to the distributed computing center; using the distributed computing center to call and locate home devices, and reading the device status of the corresponding home devices, performing linkage control optimization of devices in the region, and establishing a first linkage control result; if the probability evaluation result of the partition linkage meets the preset threshold, the first linkage control result and the monitoring data are synchronized to the centralized computing center; and the second linkage control result is used to perform linkage control of home devices. The technical problems of slow response and low efficiency of linkage control of Internet of Things devices in the prior art are solved, and the technical effect of improving the real-time and efficiency of linkage control of Internet of Things devices is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a cloud computing-based Internet of Things device linkage control method, system and storage medium. Background Art

[0002] With the rapid development of Internet of Things technology, the application of smart home devices is becoming more and more extensive, from basic environmental monitoring to multi-device collaborative control, gradually covering all aspects of people's daily life. However, with the increase in the types and number of smart devices, the control of devices in home scenes has become more complex, and the coordination and linkage requirements between devices have also increased. At the same time, users have higher requirements for the response speed, control accuracy and overall home experience of smart devices. In this context, existing solutions seem to be unable to cope with the diverse home needs and it is difficult to fully meet users' needs for intelligence, convenience and efficiency. How to further optimize the linkage control of smart home devices and improve the overall user experience has become an important issue that needs to be paid attention to and solved in this field. Summary of the invention

[0003] The present application provides a method, system and storage medium for the linkage control of IoT devices based on cloud computing, which solves the technical problems of slow response and low efficiency of the linkage control of IoT devices in the prior art.

[0004] In view of the above problems, the present application provides a cloud computing-based IoT device linkage control method, system and storage medium.

[0005] The first aspect of the present application provides a method for controlling linkage of IoT devices based on cloud computing, the method comprising:

[0006] A home coverage network is constructed by communicating with smart modules of home devices, wherein the home coverage network is provided with a centralized computing center; network partition aggregation of the home coverage network is performed, a network partition aggregation result is established, and a distributed computing center is configured based on the network partition aggregation result; after a sensor group is connected to the home coverage network, the monitoring data of the sensor group is synchronized to the distributed computing center; the distributed computing center is used to call and locate home devices, and the device status of the corresponding home devices is read, and the distributed computing center performs regional device linkage control optimization based on the device status and the monitoring data, and establishes a first linkage control result; a probability evaluation of partition linkage is performed according to the monitoring data, and if the probability evaluation result of the partition linkage meets a preset threshold, the first linkage control result and the monitoring data are synchronized to the centralized computing center; a second linkage control result is output according to the centralized computing center, and the linkage control of home devices is performed using the second linkage control result.

[0007] The second aspect of the present application provides an Internet of Things device linkage control system based on cloud computing, the system comprising:

[0008] Device networking unit: communicates and networks through the intelligent modules of home devices to build a home coverage network, and the home coverage network is provided with a centralized computing center; network partition aggregation unit: performs network partition aggregation of the home coverage network, establishes network partition aggregation results, and configures a distributed computing center based on the network partition aggregation results; data synchronization unit: after the sensor group is connected to the home coverage network, the monitoring data of the sensor group is synchronized to the distributed computing center; control optimization unit: uses the distributed computing center to call and locate home devices, and reads the device status of the corresponding home devices. The distributed computing center performs regional device linkage control optimization based on the device status and the monitoring data, and establishes a first linkage control result; probability evaluation unit: performs probability evaluation of partition linkage according to the monitoring data. If the probability evaluation result of partition linkage meets the preset threshold, the first linkage control result and the monitoring data are synchronized to the centralized computing center; linkage control unit: outputs a second linkage control result according to the centralized computing center, and uses the second linkage control result to perform linkage control of home devices.

[0009] The third aspect of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the cloud computing-based Internet of Things device linkage control method provided in the present application.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] First, a communication network is formed through the intelligent module of the home device to build a home coverage network, and the home coverage network is provided with a centralized computing center. Then, the network partition aggregation of the home coverage network is performed, the network partition aggregation result is established, and the distributed computing center is configured based on the network partition aggregation result. Next, after the sensor group is connected to the home coverage network, the monitoring data of the sensor group is synchronized to the distributed computing center. Then, the distributed computing center is used to call and locate the home device, and the device status of the corresponding home device is read. The distributed computing center performs the optimization of the linkage control of the devices in the region based on the device status and monitoring data, and establishes the first linkage control result. Further, the probability evaluation of the partition linkage is performed according to the monitoring data. If the probability evaluation result of the partition linkage meets the preset threshold, the first linkage control result and the monitoring data are synchronized to the centralized computing center. Finally, the second linkage control result is output according to the centralized computing center, and the linkage control of the home device is performed using the second linkage control result. The technical problem of slow response and low efficiency of the linkage control of the Internet of Things devices in the prior art is solved, and the technical effect of improving the real-time and efficiency of the linkage control of the Internet of Things devices is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of a method for controlling the linkage of IoT devices based on cloud computing provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a cloud computing-based Internet of Things device linkage control system provided in an embodiment of the present application.

[0015] Explanation of the accompanying drawings: device networking unit 11, network partition aggregation unit 12, data synchronization unit 13, control optimization unit 14, probability evaluation unit 15, linkage control unit 16. DETAILED DESCRIPTION

[0016] The present application solves the technical problems of slow response and low efficiency of linkage control of IoT devices in the prior art by providing a cloud computing-based linkage control method, system and storage medium for IoT devices.

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0018] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0019] Embodiment 1, as Figure 1 As shown, the present application provides a method for controlling linkage of IoT devices based on cloud computing, wherein the method includes:

[0020] The intelligent modules of the home devices are used for communication networking to build a home coverage network, which is provided with a centralized computing center.

[0021] Through the smart modules (such as built-in wireless communication modules, including Wi-Fi modules, Bluetooth modules or Zigbee modules) of home devices (such as smart TVs, smart refrigerators, smart door locks, etc.), communication connections between devices are established to form a communication network covering the entire home environment, namely the home coverage network. The home coverage network covers the entire home environment, including all rooms and areas, ensuring that each device can join the network and communicate. A centralized computing center is set up in the home coverage network, which is equivalent to a central control unit, responsible for collecting data in the entire network and uniformly scheduling and managing all the devices in the home.

[0022] Perform network partition aggregation of the home coverage network, establish network partition aggregation results, and configure a distributed computing center based on the network partition aggregation results.

[0023] There may be a large number of devices in the home coverage network and they may be distributed in different areas (such as the living room, bedroom, and kitchen). In order to optimize network management and improve efficiency, the home coverage network will be subjected to network partition aggregation operations, that is, the network will be divided into multiple logical areas, each of which contains a certain number of devices and resources for more effective management and control. According to the results of network partition aggregation, a distributed computing center is deployed in each partition. The distributed computing center is used to process the device data in the partition, perform localized computing tasks and control operations, and reduce the burden on the centralized computing center. For example, the distributed computing center in the living room partition can be responsible for collecting data from sensors in the living room (such as temperature and humidity) and controlling smart lighting, air conditioning and other equipment in the living room. This distributed structure can significantly improve the response speed of device control, reduce network latency, and improve the reliability and scalability of the system.

[0024] Furthermore, the performing of the network partition aggregation of the home coverage network and establishing the network partition aggregation result includes:

[0025] Obtaining a location distribution of a home coverage network, and establishing a first partition feature according to the location distribution;

[0026] Acquire device functions corresponding to the home coverage network, and establish second partition characteristics according to the device functions;

[0027] Perform device linkage history analysis on the home coverage network and establish third-zone features based on device linkage frequency;

[0028] Obtaining a device communication protocol of the home coverage network, and establishing a fourth partition feature according to the device communication protocol;

[0029] Network partition aggregation optimization is performed according to the first partition feature, the second partition feature, the third partition feature, and the fourth partition feature to establish a network partition aggregation result.

[0030] The network devices are partitioned through multiple feature dimensions, and the partitioning results are optimized to form the best partition aggregation solution.

[0031] Specifically, through GPS positioning, the location distribution of each device in the home coverage network is collected, that is, the geographical location of the device, such as the room where the device is located (living room, bedroom, kitchen, etc.); based on the location distribution information, physically adjacent devices are grouped into one partition, for example, devices in the same room (such as lamps, air conditioners, sensors) will be divided into the same partition. Device function refers to the functional attributes of each device in the home coverage network, such as lighting equipment, temperature control equipment, security equipment, etc.; based on the similarity of device functions, devices with the same or similar functions are grouped into one partition, for example, all lighting devices (such as chandeliers, wall lamps, and atmosphere lights) can be grouped into one partition, while temperature control devices (such as air conditioners and humidifiers) can be grouped into another partition. Collect the linkage history data between devices, including linkage events, time, trigger conditions, etc., and analyze the past collaborative control behaviors between devices, such as lamps and curtains are often turned on / off together, and air conditioners and humidifiers often adjust temperature and humidity together; according to the frequency of device linkage, devices that often operate in collaboration are grouped into one partition, for example, if a lamp and a sensor have a high linkage frequency, they may belong to the same area. The device communication protocol refers to the communication standard or protocol used by the device, such as Wi-Fi, Bluetooth, Zigbee, LoRa, etc. According to the communication protocol supported by the device, the devices using the same protocol are grouped into one partition. For example, all devices using the Wi-Fi protocol can be grouped into one group, and all devices using Bluetooth can be grouped into another group. Based on the first partition feature, the second partition feature, the third partition feature, and the fourth partition feature, a partition aggregation algorithm, such as K-means and hierarchical clustering, is applied to perform cluster analysis to obtain the network partition aggregation results.

[0032] Further, performing network partition aggregation optimization according to the first partition feature, the second partition feature, the third partition feature, and the fourth partition feature to establish a network partition aggregation result includes:

[0033] Configure the partition aggregation fitness function, perform aggregation optimization through the partition aggregation fitness function, and establish the network partition aggregation result. The partition aggregation fitness function is as follows:

[0034] ; Where Q is the partition aggregation fitness value, k represents the number of partitions, i represents any partition, and W i Characterize the weight of partition i, C i represents the internal communication strength of partition i, j represents any partition different from partition i, L ij Characterizes the cross-partition communication strength.

[0035] Specifically, the partition aggregation fitness function is used to quantitatively evaluate the partition scheme, and the fitness value Q is used to measure the quality of the partition. The higher the fitness value, the more reasonable the partition scheme and the higher the communication efficiency. i It is used to measure the importance of partition i, which can be determined based on the number of devices in the partition, the type of device (critical device or common device), the priority of the device, etc.; C i Indicates the closeness of communication between devices in a partition. The communication intensity can be calculated based on indicators such as the communication frequency and data volume between devices. ij Indicates the communication intensity between partition i and partition j. The higher the cross-partition communication intensity, the stronger the dependence between partitions. λ is used to balance the communication efficiency within the partition and the communication cost across partitions. Use optimization algorithms (such as genetic algorithms, particle swarm optimization algorithms, etc.) to search for possible partitioning schemes. In each iteration, the fitness function value Q is calculated according to the current partitioning scheme. According to the size of the fitness function value, the optimal partitioning scheme (that is, the scheme with the largest fitness value) is selected as the result of the current iteration. Repeat the iterative process until the stop condition is met (such as reaching the maximum number of iterations, the fitness value no longer changes significantly, etc.). After the aggregation optimization process is completed, the network partition aggregation result is established based on the final partitioning scheme.

[0036] After the sensor group is connected to the home coverage network, the monitoring data of the sensor group is synchronized to the distributed computing center.

[0037] After the sensor group is connected to the home coverage network, various sensors in the sensor group (such as temperature sensors, humidity sensors, light sensors, air quality sensors, motion sensors, etc.) establish communication connections with the home coverage network through built-in communication modules (such as Wi-Fi, Zigbee, Bluetooth, etc.) and become part of the network. These sensors run continuously and collect monitoring data in the home environment in real time, such as room temperature, humidity, light intensity, air quality index, and personnel activities. The collected monitoring data will be synchronously transmitted to the corresponding distributed computing center in an efficient manner through the home coverage network. The distributed computing center will classify, store, analyze and process these monitoring data, and trigger the corresponding device linkage control operation in combination with the device status, linkage rules or preset scenarios. For example, when the temperature sensor detects that the room temperature is too high, the distributed computing center will analyze the current data and the set temperature threshold, determine that the indoor temperature needs to be lowered, and then send a cooling instruction to the air conditioning equipment; or when the motion sensor detects an abnormal activity signal, the distributed computing center will link the security equipment to start the alarm function and push relevant notifications to the user, and can automatically start the camera for real-time monitoring and recording. By distributing the processing and linkage control tasks of monitoring data to the local distributed computing center, not only the response speed of equipment linkage is significantly improved and the data transmission delay is reduced, but also the burden on the centralized computing center is effectively reduced, while enhancing the system's operating efficiency and intelligence level in complex home environments.

[0038] The distributed computing center is used to call and locate home devices and read the device status of the corresponding home devices. The distributed computing center performs optimization of regional device linkage control based on the device status and the monitoring data to establish a first linkage control result.

[0039] After using the distributed computing center to call and locate the home devices, the target device that needs to be operated is accurately located according to the device's geographical location and functional attributes, and the real-time status information of the device is read, such as whether it is currently in an open or closed state, working mode, operating parameters, etc. At the same time, the distributed computing center combines the device status with the monitoring data provided by the sensor group (such as temperature, humidity, light intensity, etc.) to conduct a comprehensive analysis and linkage control optimization of the devices in the current area, that is, under the premise of meeting the functional requirements, the algorithm calculates the optimal linkage control strategy. For example, in an area, when the temperature sensor detects that the indoor temperature is too high, the distributed computing center will calculate the optimal device linkage control plan based on the status of the air-conditioning equipment (such as the current temperature setting value and operating mode), combined with the status and linkage logic of curtains, fans and other equipment, such as appropriately adjusting the temperature setting value of the air conditioner, closing the curtains to reduce direct sunlight, and turning on the fan to improve the cold air circulation efficiency. Through this optimization process, the distributed computing center generates the first linkage control result, which defines the devices that need to be linked, the specific control instructions and the execution order, providing a reliable basis for the efficient collaboration and precise control of subsequent devices.

[0040] Furthermore, the distributed computing center performs regional equipment linkage control optimization based on the equipment status and the monitoring data to establish a first linkage control result, including:

[0041] Establish a response real-time constraint based on the monitoring data; obtain the current working mode of the equipment based on the equipment status, and generate an energy-saving constraint based on the current working mode of the equipment; configure a balancing network based on the real-time constraint and the energy-saving constraint; use the balancing network to optimize the linkage control of equipment in the area, and establish the first linkage control result.

[0042] When the distributed computing center is optimizing the linkage control of devices in the region, it first establishes response real-time constraints based on the monitoring data (such as temperature, humidity, light intensity, etc.) collected by the sensor group to determine the time requirements for the linkage of devices. For example, a longer response time can be allowed in the temperature adjustment scenario, while in the fire alarm or security event, the device is required to complete the linkage operation in a very short time. At the same time, the distributed computing center will read the current status of the devices in the region, obtain the operation mode and related parameters of each device, such as the air conditioner may be in "cooling mode" or "energy-saving mode", and the lighting equipment may be in "dimming mode", and generate energy-saving constraints based on the device operation mode to ensure that the energy consumption of the device is reduced as much as possible while meeting the linkage requirements, such as giving priority to reducing power or selecting low-power devices to participate in the linkage. On the basis of comprehensive real-time constraints and energy-saving constraints, the distributed computing center further configures a balancing network, takes the above constraints as the input of the optimization model, and assigns weights to dynamically balance the contradiction between real-time and energy-saving. For example, in the ordinary environment control scenario, energy-saving is given priority, while in emergency situations, more attention is paid to response speed. After completing the configuration of the balancing network, the optimization algorithm (such as dynamic programming or genetic algorithm) is used to perform optimal calculations on the linkage control of devices in the area, and finally the first linkage control result is generated. The first linkage control result includes a specific list of linkage devices, control instructions for each device (such as adjusting the air conditioner to 26°C, dimming some lights, starting the fan, etc.), operation priority, and execution time sequence. Through this optimization process, the distributed computing center ensures that the device linkage is completed efficiently within the set time. At the same time, the overall energy consumption of the system is significantly reduced through energy-saving constraints, achieving a dynamic balance between real-time and energy efficiency, and improving the operating efficiency and intelligence level of the entire smart home environment.

[0043] Furthermore, the using the balancing network to perform linkage control optimization of devices in the region and establish the first linkage control result includes:

[0044] Perform monitoring trend prediction based on the monitoring data to establish a trend prediction result; input the device status, the trend prediction result, and the monitoring data as input data into the balancing network to generate the first linkage control result.

[0045] When the distributed computing center uses the balancing network to optimize the linkage control of equipment in the region and establish the first linkage control result, it further combines the trend prediction analysis of the monitoring data to improve the foresight and accuracy of the control. Specifically, the distributed computing center uses data analysis algorithms or prediction models (such as time series analysis, ARIMA models or machine learning prediction models, etc.) to perform trend prediction on the monitoring data based on the real-time monitoring data (such as temperature, humidity, light intensity, etc.) to generate trend prediction results. For example, when the monitoring data indicates that the temperature is rising rapidly, the prediction model can infer that the room temperature may exceed the set comfort threshold in the next few minutes; or, when the air quality sensor detects a continuous increase in particulate matter concentration, the prediction result may show a trend of air quality deterioration in a short period of time. After completing the trend prediction, the distributed computing center inputs the current status of the equipment (such as the operation mode of the air conditioner, the dimming status of the light, the start and stop status of the fan), the prediction results, and the real-time monitoring data as input data into the configured balancing network. The balancing network performs comprehensive calculations based on these input data, combined with the set response real-time constraints and energy-saving constraints, through optimization algorithms (such as genetic algorithms or dynamic programming), and finally generates the first linkage control result. The first linkage control result includes a list of devices that need to be linked, specific control instructions (such as air conditioning to lower the temperature, fan start-up to assist in cooling, turning off some lights to reduce heat, etc.) and the execution order and time schedule of the operation. By introducing the trend prediction results into the control optimization process, the distributed computing center can perceive potential problems in advance and take preventive measures, which not only improves the response speed and accuracy of the equipment linkage, but also enhances the system's intelligent operation capabilities in complex home environments, thereby realizing efficient and intelligent equipment linkage management.

[0046] Furthermore, the method further comprises:

[0047] After the emotion perception sensor is connected to the home coverage network, the emotion perception sensor is used to collect multimodal data of the user to establish an emotion perception data set; perception constraints are established based on the emotion perception data set, and the perception constraints are fed back to the distributed computing center to execute the first linkage control result compensation.

[0048] When the emotion perception sensor (such as a device with functions such as speech recognition, facial expression analysis, and heart rate detection) is connected to the home coverage network, the sensor is used to collect the user's multimodal data, including voice pitch, speech speed, facial expression, eye movement trajectory, body surface temperature, heart rate changes, etc., to establish a comprehensive emotion perception data set. By analyzing and processing the emotion perception data set, the user's emotional state, such as relaxation, pleasure, tension, anxiety and other emotional characteristics, is identified, and the perception constraints reflecting the user's emotional needs are dynamically generated by combining environmental data (such as the lighting and temperature of the current scene) and the user's historical behavior pattern. The distributed computing center uses this perception constraint as a supplementary input and feeds it back to the original balanced network model to compensate and optimize the first linkage control result. The specific process of compensation includes emotional adjustment of the current control scheme. For example, when the user is emotionally nervous, the linkage strategy of the device is appropriately adjusted: lowering the light brightness, enabling soft background music, adjusting the air conditioner to a more comfortable temperature, or turning off devices that may generate noise. This compensation optimization mechanism based on emotion perception can better meet the user's personalized needs and enhance the comfort and user experience of the home environment while maintaining the original response real-time constraints and energy-saving constraints. By introducing emotion-aware sensors and perception-constraint feedback, the system is not only endowed with the ability to proactively identify the user's emotional state, but can also dynamically adjust device linkage plans based on the user's emotional changes, making the intelligent management of home devices more in line with the user's real needs, while further improving the system's personalized service capabilities and user satisfaction.

[0049] A probability evaluation of partition linkage is performed according to the monitoring data. If a probability evaluation result of partition linkage meets a preset threshold, the first linkage control result and the monitoring data are synchronized to a centralized computing center.

[0050] After the distributed computing center completes the optimization of the linkage control of the equipment in the region and generates the first linkage control result, it is also necessary to conduct a probability evaluation of the possibility and rationality of the linkage of the partitions based on the monitoring data. Specifically, by analyzing the monitoring data, combining the linkage history records of the equipment, the current equipment status and the collaborative relationship between the equipment in the region, the probability evaluation value of the linkage of the partition is calculated. The probability evaluation value is used to measure whether the linkage scheme of the equipment in the current partition is efficient and necessary for execution, such as whether the linkage between the equipment can achieve the expected effect, whether it meets the current environmental requirements, and whether it can effectively respond to the changes reflected by the monitoring data. After completing the probability evaluation, the probability evaluation result is compared with the preset threshold; if the probability evaluation result meets or exceeds the preset threshold (for example, the success probability or efficiency of the linkage reaches a certain standard), it indicates that the first linkage control result of the current partition is executable and has an optimization effect. At this time, the system will synchronize the first linkage control result together with the relevant monitoring data to the centralized computing center. After receiving these data, the centralized computing center can further combine the linkage control results of other partitions and global data (such as the overall monitoring information and linkage requirements of the entire home environment) to optimize the global linkage control of the equipment in the entire home environment. This mechanism ensures that relevant data is uploaded to the centralized computing center only when partition linkage has high execution efficiency and necessity, thereby avoiding redundant transmission of invalid data, reducing the computing burden of the centralized computing center, and further improving the efficiency and effectiveness of global optimization.

[0051] The distributed computing center comprehensively calculates the probability evaluation value of partition linkage by analyzing monitoring data, equipment linkage history records, current equipment status, and the collaborative relationship between equipment in the region. First, the linkage success rate between equipment is extracted from the historical records to measure whether the equipment has reliability in past collaboration, such as the ratio of the number of successful linkages of lights and curtains to the total number of attempts in the history, which is used to evaluate the basic credibility of linkage. Second, the current status of the equipment is read, including whether the equipment is operating normally, the operating mode, and the current working parameters, such as whether the air conditioner is turned on, the brightness level of the light, etc., and the current availability of the equipment is reflected through the status score. At the same time, the system analyzes the collaboration intensity between equipment in the region, and evaluates their synergy in achieving the current linkage goal based on the frequency and dependence of equipment linkage. For example, the linkage weight between lights and curtains is higher, while the collaborative relationship between lights and air purifiers is weaker. Finally, combined with real-time monitoring data, it is evaluated whether the current linkage scheme matches the environmental requirements. For example, when the temperature is too high and the air conditioner is in cooling mode, the adaptability is higher, while when the light is too strong but the light is not dimmed, the adaptability is lower. By integrating the above information, the distributed computing center uses a weighted computing model to proportionally combine the historical success rate of linkage, equipment status score, collaboration intensity and environmental adaptability to calculate the probability evaluation value of partition linkage. This value is used to quantify the success possibility and execution effect of the current linkage plan, thereby providing an accurate basis for subsequent linkage control decisions.

[0052] Furthermore, the probability evaluation of zone linkage based on the monitoring data includes:

[0053] If the probability evaluation result of the partition linkage cannot meet the preset threshold, a lightweight rule calling instruction is generated; according to the lightweight rule calling instruction, a linkage control analysis based on the first linkage control result and the monitoring data is performed to generate a third linkage control result; according to the third linkage control result, linkage control of home appliances is performed.

[0054] When the distributed computing center conducts probability evaluation of partition linkage on the monitoring data, if the probability evaluation result fails to meet the preset threshold, it means that the current linkage scheme may be less effective or have a lower probability of success in actual execution. At this time, the system will generate a lightweight rule call instruction to optimize the control scheme. The role of the lightweight rule call instruction is to quickly adjust and optimize the linkage strategy by simplifying the linkage control logic and reducing complexity. The system re-analyzes the first linkage control result and the current monitoring data according to the lightweight rule call instruction, and preferentially selects devices with lower execution cost, faster response speed or less environmental impact for linkage operation through lightweight rules. For example, when the temperature is too high, only the air conditioner is enabled without starting the fan and curtain linkage at the same time to reduce unnecessary equipment linkage burden. Through this optimization analysis, the system generates a third linkage control result, which contains a list of optimized linkage devices, specific control instructions, and execution order and priority. Subsequently, the distributed computing center executes the linkage operation of home devices based on the third linkage control result to ensure that while reducing the control complexity, it can still meet the basic home environment needs and improve the linkage execution efficiency. Through this lightweight rule-based adjustment, the system can quickly generate optimization solutions when faced with complex scenarios or a low probability of successful linkage, avoiding response delays or execution failures caused by complex control logic, and further improving the flexibility and adaptability of smart home systems.

[0055] The centralized computing center outputs a second linkage control result, and utilizes the second linkage control result to perform linkage control of home appliances.

[0056] After receiving the first linkage control results and related monitoring data from each distributed computing center, the centralized computing center generates the second linkage control results through a global optimization algorithm in combination with the global home environment information (such as the device status, monitoring data and linkage requirements of each partition). Unlike the local optimization of the distributed computing center, the global optimization of the centralized computing center focuses more on the coordination and resource allocation across partitions. For example, in the scenario of whole-house temperature control, it will not only optimize the linkage of devices within a single partition, but also consider the temperature gradient changes between partitions and the load balancing between devices. Based on the global optimization goals, such as minimizing energy consumption, maximizing response speed or improving user comfort, the centralized computing center comprehensively analyzes all input data, determines the global device list that needs to be linked, the specific control instructions of the device (such as air conditioning temperature adjustment, curtain opening and closing angle, light brightness adjustment, etc.), and clarifies the operation priority and time sequence of each device. After generating the second linkage control result, the system synchronizes the result to each distributed computing center, and the distributed computing center is responsible for transmitting the instructions to the specific device and executing them. Through the implementation of the second linkage control results, home devices can achieve cross-zone intelligent linkage, thereby improving device collaboration efficiency, optimizing energy utilization, and providing users with a more comfortable and efficient smart home experience. For example, in the whole house night mode, the centralized computing center can turn off unnecessary lighting equipment, adjust the air conditioners of all zones to low-power operation mode, and dynamically adjust the equipment according to real-time monitoring data to maintain the best environmental state, thereby achieving comprehensive intelligent linkage control.

[0057] Furthermore, the method further comprises:

[0058] A verification node is established according to the second linkage control result; control effect verification is performed at the verification node to generate verification feedback; and control self-optimization is performed on the second linkage control result according to the verification feedback.

[0059] After the second linkage control result is generated, a verification mechanism is introduced to evaluate and feedback the control effect in real time by establishing a verification node to achieve self-optimization of linkage control. Specifically, according to the second linkage control result generated by the centralized computing center, the system synchronously establishes a verification node when executing the linkage operation. The verification node is responsible for real-time collection of data related to the control effect, such as changes in environmental status (such as whether the temperature drops to the target range, whether the light brightness meets the set value), equipment operation status (such as whether the air conditioner adjusts the temperature according to the command, whether the curtains are opened and closed correctly), and energy consumption. These data are compared and analyzed with the expected control effect to generate verification feedback. The content of the verification feedback includes whether the current control effect has achieved the expected goal, whether there are deviations or anomalies in the execution process (for example, a device does not respond to the control command or the environmental parameters do not change as expected), and whether the linkage control strategy has room for further optimization. Based on the verification feedback, the system self-optimizes the second linkage control result. For example, when the verification feedback shows that the temperature has not dropped to the target value within the expected time, the system can optimize the strategy by extending the air conditioner operation time or linking other devices (such as turning on the fan) to assist in cooling; if the verification feedback indicates that a device has failed to execute or has not met expectations, the system will reallocate the control task or skip the faulty device. Through the introduction of verification nodes, the system can not only dynamically monitor the effect of linkage control, but also realize self-learning and self-optimization mechanisms based on feedback. This self-optimization process can continuously improve the accuracy and reliability of linkage control, further optimize resource scheduling, reduce energy consumption, and enhance the system's adaptability to complex and dynamic environments. For example, in the whole-house intelligent environment control, after the verification node finds the temperature and humidity control deviation in a certain area, the system can quickly adjust the operation strategy of the equipment in other areas to compensate, thereby achieving stable optimization of the global environment.

[0060] In summary, the embodiments of the present application have at least the following technical effects:

[0061] First, a communication network is formed through the intelligent module of the home device to build a home coverage network, and the home coverage network is provided with a centralized computing center. Then, the network partition aggregation of the home coverage network is performed, the network partition aggregation result is established, and the distributed computing center is configured based on the network partition aggregation result. Next, after the sensor group is connected to the home coverage network, the monitoring data of the sensor group is synchronized to the distributed computing center. Then, the distributed computing center is used to call and locate the home device, and the device status of the corresponding home device is read. The distributed computing center performs the optimization of the linkage control of the devices in the region based on the device status and monitoring data, and establishes the first linkage control result. Further, the probability evaluation of the partition linkage is performed according to the monitoring data. If the probability evaluation result of the partition linkage meets the preset threshold, the first linkage control result and the monitoring data are synchronized to the centralized computing center. Finally, the second linkage control result is output according to the centralized computing center, and the linkage control of the home device is performed using the second linkage control result. The technical problem of slow response and low efficiency of the linkage control of the Internet of Things devices in the prior art is solved, and the technical effect of improving the real-time and efficiency of the linkage control of the Internet of Things devices is achieved.

[0062] Embodiment 2 is based on the same inventive concept as the method for controlling the linkage of IoT devices based on cloud computing in the above embodiment. Figure 2 As shown, the present application provides an IoT device linkage control system based on cloud computing, wherein the system includes:

[0063] The device networking unit 11 is used to communicate and network through the intelligent modules of the home devices to build a home coverage network, and the home coverage network is provided with a centralized computing center; the network partition aggregation unit 12 is used to perform network partition aggregation of the home coverage network, establish a network partition aggregation result, and configure a distributed computing center based on the network partition aggregation result; the data synchronization unit 13 is used to synchronize the monitoring data of the sensor group to the distributed computing center after the sensor group is connected to the home coverage network; the control optimization unit 14 is used to call and locate the home devices by using the distributed computing center, and read the device status of the corresponding home devices, and the distributed computing center performs regional device linkage control optimization based on the device status and the monitoring data, and establishes a first linkage control result; the probability evaluation unit 15 is used to perform probability evaluation of partition linkage according to the monitoring data, and if the probability evaluation result of the partition linkage meets the preset threshold, the first linkage control result and the monitoring data are synchronized to the centralized computing center; the linkage control unit 16 is used to output the second linkage control result according to the centralized computing center, and the linkage control of the home devices is performed by using the second linkage control result.

[0064] Furthermore, the network partition aggregation unit 12 is used to perform the following method:

[0065] Obtain the location distribution of the home coverage network, and establish a first partition feature according to the location distribution; obtain the device function corresponding to the home coverage network, and establish a second partition feature according to the device function; perform device linkage history analysis of the home coverage network, and establish a third partition feature according to the device linkage frequency; obtain the device communication protocol of the home coverage network, and establish a fourth partition feature according to the device communication protocol; perform network partition aggregation and optimization according to the first partition feature, the second partition feature, the third partition feature, and the fourth partition feature, and establish a network partition aggregation result.

[0066] Furthermore, the network partition aggregation unit 12 is used to perform the following method:

[0067] Configure the partition aggregation fitness function, perform aggregation optimization through the partition aggregation fitness function, and establish the network partition aggregation result. The partition aggregation fitness function is as follows:

[0068] ; Where Q is the partition aggregation fitness value, k represents the number of partitions, i represents any partition, and W i Characterize the weight of partition i, C i represents the internal communication strength of partition i, j represents any partition different from partition i, L ij Characterizes the cross-partition communication strength.

[0069] Furthermore, the probability evaluation unit 15 is used to perform the following method:

[0070] If the probability evaluation result of the partition linkage cannot meet the preset threshold, a lightweight rule calling instruction is generated; according to the lightweight rule calling instruction, a linkage control analysis based on the first linkage control result and the monitoring data is performed to generate a third linkage control result; according to the third linkage control result, linkage control of home appliances is performed.

[0071] Furthermore, the control optimization unit 14 is used to execute the following method:

[0072] Establish a response real-time constraint based on the monitoring data; obtain the current working mode of the equipment based on the equipment status, and generate an energy-saving constraint based on the current working mode of the equipment; configure a balancing network based on the real-time constraint and the energy-saving constraint; use the balancing network to optimize the linkage control of equipment in the area, and establish the first linkage control result.

[0073] Furthermore, the control optimization unit 14 is used to execute the following method:

[0074] Perform monitoring trend prediction based on the monitoring data to establish a trend prediction result; input the device status, the trend prediction result, and the monitoring data as input data into the balancing network to generate the first linkage control result.

[0075] Furthermore, the control optimization unit 14 is used to execute the following method:

[0076] After the emotion perception sensor is connected to the home coverage network, the emotion perception sensor is used to collect multimodal data of the user to establish an emotion perception data set; perception constraints are established based on the emotion perception data set, and the perception constraints are fed back to the distributed computing center to execute the first linkage control result compensation.

[0077] Furthermore, the linkage control unit 16 is used to execute the following method:

[0078] A verification node is established according to the second linkage control result; control effect verification is performed at the verification node to generate verification feedback; and control self-optimization is performed on the second linkage control result according to the verification feedback.

[0079] Embodiment 3, based on the same inventive concept as the method for controlling the linkage of IoT devices based on cloud computing in the above-mentioned embodiment, this embodiment provides a computer-readable storage medium, which can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the method for controlling the linkage of IoT devices based on cloud computing in the embodiment of the present application. The processor executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory, that is, realizing the above-mentioned method for controlling the linkage of IoT devices based on cloud computing.

[0080] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0081] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0082] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for controlling the linkage of IoT devices based on cloud computing, characterized in that: The method comprises: The intelligent modules of home devices are used to communicate and network, and a home coverage network is constructed, wherein the home coverage network is provided with a centralized computing center; Execute network partition aggregation of the home coverage network, establish network partition aggregation results, and configure a distributed computing center based on the network partition aggregation results; After the sensor group is connected to the home coverage network, the monitoring data of the sensor group is synchronized to the distributed computing center; The distributed computing center is used to call and locate the home device, and the device status of the corresponding home device is read. The distributed computing center performs regional device linkage control optimization based on the device status and the monitoring data, and establishes a first linkage control result; Performing a probability evaluation of partition linkage according to the monitoring data, and if a probability evaluation result of partition linkage meets a preset threshold, synchronizing the first linkage control result and the monitoring data to a centralized computing center; According to the output of the second linkage control result by the centralized computing center, linkage control of the home equipment is performed using the second linkage control result; The performing of the network partition aggregation of the home coverage network and establishing the network partition aggregation result includes: Obtaining a location distribution of a home coverage network, and establishing a first partition feature according to the location distribution; Acquire device functions corresponding to the home coverage network, and establish second partition characteristics according to the device functions; Perform device linkage history analysis on the home coverage network and establish third-zone features based on device linkage frequency; Obtaining a device communication protocol of the home coverage network, and establishing a fourth partition feature according to the device communication protocol; Perform network partition aggregation optimization according to the first partition feature, the second partition feature, the third partition feature, and the fourth partition feature, and establish a network partition aggregation result; The performing network partition aggregation optimization according to the first partition feature, the second partition feature, the third partition feature, and the fourth partition feature to establish a network partition aggregation result includes: Configure the partition aggregation fitness function, perform aggregation optimization through the partition aggregation fitness function, and establish the network partition aggregation result. The partition aggregation fitness function is as follows: ； Among them, Q is the partition aggregation fitness value, k represents the number of partitions, i represents any partition, and W i Characterize the weight of partition i, C i represents the internal communication strength of partition i, j represents any partition different from partition i, L ij Characterizes the cross-partition communication strength.

2. The method for controlling the Internet of Things devices based on cloud computing according to claim 1, characterized in that: The probability evaluation of zone linkage according to the monitoring data includes: If the probability evaluation result of partition linkage cannot meet the preset threshold, a lightweight rule call instruction is generated; Perform linkage control analysis based on the first linkage control result and the monitoring data according to the lightweight rule calling instruction to generate a third linkage control result; The home appliances are controlled in linkage according to the third linkage control result.

3. The method for controlling the Internet of Things devices based on cloud computing according to claim 1, characterized in that: The distributed computing center performs regional equipment linkage control optimization based on the equipment status and the monitoring data, and establishes a first linkage control result, including: Establishing response real-time constraints based on the monitoring data; Acquire a current working mode of the device according to the device state, and generate an energy-saving constraint according to the current working mode of the device; Configuring a balancing network according to the real-time constraint and the energy-saving constraint; The balancing network is used to optimize the linkage control of devices in the area and establish the first linkage control result.

4. The method for controlling the Internet of Things devices based on cloud computing according to claim 3, characterized in that: The using the balancing network to perform the optimization of the linkage control of the devices in the area and establish the first linkage control result includes: Perform monitoring trend forecasting based on the monitoring data and establish trend forecasting results; The device status, the trend prediction result, and the monitoring data are input into the balancing network as input data to generate the first linkage control result.

5. The method for controlling the linkage of IoT devices based on cloud computing according to claim 1, characterized in that: The method further comprises: After connecting the emotion perception sensor to the home coverage network, using the emotion perception sensor to collect multimodal data of the user to establish an emotion perception data set; A perception constraint is established according to the emotion perception data set, the perception constraint is fed back to the distributed computing center, and the first linkage control result compensation is performed.

6. The method for controlling the Internet of Things devices based on cloud computing according to claim 1, characterized in that: The method further comprises: Establishing a verification node according to the second linkage control result; Performing control effect verification at the verification node and generating verification feedback; The second linkage control result is controlled and self-optimized according to the verification feedback.

7. The IoT device linkage control system based on cloud computing is characterized by: The system for implementing the cloud computing-based IoT device linkage control method according to any one of claims 1 to 6 comprises: Device networking unit: communicates and networks through the intelligent modules of home devices to build a home coverage network, which is equipped with a centralized computing center; A network partition aggregation unit: performs network partition aggregation of the home coverage network, establishes a network partition aggregation result, and configures a distributed computing center based on the network partition aggregation result; Data synchronization unit: after connecting the sensor group to the home coverage network, synchronizing the monitoring data of the sensor group to the distributed computing center; Control optimization unit: using the distributed computing center to call and locate the home device, and reading the device status of the corresponding home device, the distributed computing center performs regional device linkage control optimization based on the device status and the monitoring data, and establishes a first linkage control result; Probability evaluation unit: performing probability evaluation of partition linkage according to the monitoring data, and synchronizing the first linkage control result and the monitoring data to a centralized computing center if the probability evaluation result of the partition linkage meets a preset threshold; Linkage control unit: according to the second linkage control result output by the centralized computing center, linkage control of home appliances is performed using the second linkage control result.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the cloud computing-based Internet of Things device linkage control method as described in any one of claims 1 to 6 is implemented.

Images