Smart home equipment control method, system equipment and medium

Abstract

The invention discloses a smart home equipment control method, system equipment and a medium. The method comprises the following steps: acquiring state data of a target area and control parameters of smart home equipment; according to the state data and the control parameters, constructing a state influence graph of the smart home equipment; calculating a target deviation item of the smart home equipment according to the state data and the control parameters; according to the target deviation item and the control parameter, constructing a local cost function of the smart home device, and generating a first control strategy of the at least two smart home devices; based on the local cost function, constructing a global cost function of the target area according to the state influence graph; the first control strategy is iteratively optimized according to the global cost function, the optimal control strategy of the at least two intelligent household devices is generated, multi-device cooperative control and optimization can be achieved through the game among multiple devices, the scene applicability of the scheme is improved, and the personalized requirement of a user can be met.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular, to a control method, system, device and medium for smart home devices. Background Art

[0002] With the intensification of the aging trend of the population in our country, home health management, smart elderly care and digital medicine have become the key directions of current social concern. As an important carrier of medical care and rehabilitation, the smart home system is gradually developing from single-device control to an integrated system that combines perception, decision-making and execution. Especially among special groups such as the elderly and chronic disease patients, higher requirements are put forward for the personalized adjustment of the home environment, the real-time response to health status, and the collaborative optimization of device control.

[0003] Currently, most smart home systems are centered around local controllers or APP applications, and the start and stop operations of single devices are completed through fixed rules or simple sensing logic. As a result, there is a lack of a unified strategy coordination mechanism between devices, making it difficult to achieve efficient collaboration under the dynamic changes of complex environments, lacking a unified coordination strategy for dealing with complex scenarios, and affecting the user experience and energy efficiency level. In addition, the existing technology lacks the ability to fuse and analyze user health status and environmental perception data, and the control strategies are mainly statically set, making it difficult to meet the personalized needs in multi-device and multi-target scenarios, and difficult to generate dynamic strategies based on environmental changes, user preferences and device status. Therefore, the existing technology lacks the ability to unify modeling and optimization in multi-device, multi-target and dynamic environments, and cannot achieve collaborative control between devices and optimal allocation of resources. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail in this article. This overview is not intended to limit the scope of protection of the claims.

[0005] The main purpose of the embodiments of this application is to propose a control method, system, device and storage medium for smart home devices, which can achieve the organic unity of multi-device collaborative control, adaptive optimization and user satisfaction guarantee through the game between multiple devices, and improve the scenario applicability of the solution, and can meet the personalized requirements of users.

[0006] The first aspect of the embodiments of this application provides a control method for smart home devices, which is used for smart home devices. The method includes: Obtain the status data of the target area and the control parameters of the smart home devices; wherein, the target area includes at least two of the smart home devices; the status data includes at least environmental status data; Construct a status influence diagram of the smart home devices according to the status data and the control parameters; Calculate the target deviation term of the smart home device according to the state data and the control parameters; Construct the local cost function of the smart home device according to the target deviation term and the control parameters, and generate the first control strategy for at least two of the smart home devices; Based on the local cost function, construct the global cost function of the target area according to the state influence diagram; Iteratively optimize the first control strategy according to the global cost function to generate the optimal control strategy for at least two of the smart home devices.

[0007] In some embodiments of the present application, constructing the state influence diagram of the smart home device according to the state data and the control parameters includes: Divide the control parameters into a continuous control parameter subset and a discrete control parameter subset; Establish a continuous control mapping set between the continuous control parameter subset and the state data; Establish a discrete control mapping set between the discrete control parameter subset and the state data; Combine the continuous control mapping set and the discrete control mapping set to obtain a mixed parameter structure mapping set; Generate the state influence diagram of the smart home device according to the mixed parameter structure mapping set.

[0008] In some embodiments of the present application, the state data further includes human body sign data. Calculating the target deviation term of the smart home device according to the state data and the control parameters includes: Generate target control parameters according to the environmental state data and the human body sign data; Calculate the target deviation term of each smart home device according to the target control parameters and the control parameters of the smart home device.

[0009] In some embodiments of the present application, before constructing the local cost function of the smart home device according to the target deviation term and the control parameters and generating the first control strategy for at least two of the smart home devices, the method further includes: When the target deviation term of each smart home device is less than a preset threshold, obtain the real-time control parameters of each smart home device; Obtain the optimal control strategy according to the real-time control parameters of each smart home device.

[0010] In some embodiments of the present application, the iterative optimization of the first control strategy according to the global cost function to generate the optimal control strategies for at least two of the smart home devices includes: By using the Lagrangian multiplier relaxation and subgradient response algorithms, iteratively calculate the variational inequality problem of the global cost function according to the target control parameters to generate the Nash equilibrium control strategy; Optimize the first control strategy according to the target control parameters and the Nash equilibrium control strategy to generate the optimal control strategy for the target area.

[0011] In some embodiments of the present application, after the iterative optimization of the first control strategy according to the global cost function to generate the optimal control strategies for at least two of the smart home devices, the method further includes: Combine the state data of the target area, the control parameters of the smart home devices, and the optimal control strategy to obtain a first application scenario; Store the first application scenario in a preset repository; Obtain a second application scenario of the area to be controlled, where the second application scenario is composed of the first state data of the area to be controlled and the first control parameters of the smart home devices in the area to be controlled; Match the second application scenario with the preset repository to obtain a matching result.

[0012] In some embodiments of the present application, the matching of the second application scenario with the stored data in the preset repository to obtain a matching result includes: In the case of a successful match, extract the first application scenario that matches the application scenario of the area to be controlled from the preset repository to obtain the optimal control strategy; the successful match includes the matching of the first state data and the state data, and the matching of the first control parameters and the control parameters.

[0013] To achieve the above object, a second aspect of the embodiments of the present invention provides a smart home device control system, the system includes: A data acquisition module, configured to acquire the state data of a target area and the control parameters of smart home devices; wherein, the target area includes at least two of the smart home devices; the state data includes at least environmental state data; A state construction module, configured to construct a state influence diagram of the smart home devices according to the state data and the control parameters; A deviation calculation module, configured to calculate the target deviation term of the smart home devices according to the state data and the control parameters; A first construction module, configured to construct a local cost function of the smart home device according to the target deviation term and the control parameter, and generate a first control strategy for at least two of the smart home devices; A second construction module, configured to construct a global cost function of the target area according to the state influence diagram based on the local cost function; An update and iteration module, configured to iteratively optimize the first control strategy according to the global cost function to generate an optimal control strategy for at least two of the smart home devices.

[0014] To achieve the above object, a third aspect of the embodiments of the present invention provides an electronic device, including: at least one control processor and a memory communicatively connected to the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the above-mentioned smart home device control method.

[0015] To achieve the above object, a fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, which stores computer-executable instructions for causing a computer to execute the above-mentioned smart home device control method.

[0016] An embodiment of the present application provides a smart home device control method, which includes obtaining state data of a target area and control parameters of a smart home device; constructing a state influence diagram of the smart home device according to the state data and the control parameters; calculating a target deviation term of the smart home device according to the state data and the control parameters; constructing a local cost function of the smart home device according to the target deviation term and the control parameters, and generating a first control strategy for at least two of the smart home devices; constructing a global cost function of the target area according to the state influence diagram based on the local cost function; iteratively optimizing the first control strategy according to the global cost function to generate an optimal control strategy for at least two of the smart home devices, which can realize multi-device collaborative control and optimization through the game between multiple devices, and improve the scenario applicability of the solution, and can meet the personalized requirements of users.

[0017] It can be understood that the beneficial effects of the above second aspect to the fourth aspect compared with the related art are the same as those of the above first aspect compared with the related art. For the relevant descriptions, reference can be made to the relevant descriptions in the above first aspect, and details will not be described herein again. Description of the Drawings

[0018] The above and / or additional aspects and advantages of the present application will become apparent and easier to understand from the following description of the embodiments in conjunction with the accompanying drawings, where: Figure 1It is a schematic flowchart of a method for controlling a smart home device provided by an embodiment of the present application; Figure 2 It is a schematic structural diagram of a training system for controlling a smart home device provided by an embodiment of the present application; Figure 3 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0019] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary only for explaining the present application and should not be construed as a limitation to the present application.

[0020] In the description of the present application, if the first, second, etc. are described, it is only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0021] In the description of the present application, it should be understood that the orientation or positional relationship indicated by terms such as up and down, etc., is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application.

[0022] In the description of the present application, it should be noted that unless otherwise clearly defined, terms such as setting, installation, connection, etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present application in combination with the specific content of the technical solution.

[0023] With the intensification of the aging trend of the population in our country, home health management, smart elderly care, and digital medicine have become the key directions of current social concern. As an important carrier of medical care and rehabilitation, the smart home system is gradually developing from single-device control to an integrated system that integrates perception, decision-making, and execution. Especially among special groups such as the elderly and chronic disease patients, higher requirements are put forward for the personalized adjustment of the home environment, the real-time response to health status, and the collaborative optimization of device control.

[0024] Currently, most smart home systems are centered around local controllers or APP applications, and they complete the start / stop operations of single devices through fixed rules or simple sensing logic. Such systems lack the ability to deeply model the user's health status and are difficult to generate dynamic strategies based on environmental changes, user preferences, and device status. In addition, the control behaviors among multiple devices are often independent of each other, lacking a unified policy coordination mechanism, which easily leads to problems such as resource conflicts, control mutual exclusion, or inconsistent execution logic, further affecting the user experience and energy efficiency level.

[0025] Although some studies have introduced functional modules such as scene recognition, voice interaction, or remote control, their core control logic still mainly relies on preset solutions, lacking the scheduling ability for multi-objective optimization, and even more, they have not achieved policy coordination and game evolution control among devices. In the face of dynamic smart home scenarios with coexistence of multiple users, multiple devices, and multiple tasks, the existing technologies still have significant deficiencies in information integration, policy coordination, and personalized response, and it is difficult to meet the actual needs of complex scenarios such as intelligent health care and intelligent nursing.

[0026] Based on this, the embodiments of this application provide a smart home device control method, system, electronic device, and medium, aiming to achieve the organic unity of multi-device collaborative control, adaptive optimization, and user satisfaction guarantee through the game among multiple devices, and moreover, improve the scenario applicability of the solution and be able to meet the personalized requirements of users.

[0027] The smart home device control method, system, electronic device, and medium provided by the embodiments of this application are specifically described through the following embodiments. First, the smart home device control method in the embodiments of this application is described.

[0028] The embodiments of this application can obtain and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0029] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0030] The smart home device control method provided by the embodiments of the present application relates to the field of artificial intelligence technology. The smart home device control method provided by the embodiments of the present application can be applied to a terminal, or to a server side, or can also be software running on a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application for implementing the smart home device control method, etc., but is not limited to the above forms.

[0031] The present application can be used in many general or specific computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0032] It should be noted that in each specific embodiment of the present application, when it comes to relevant processing that needs to be carried out according to data related to the user's identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or jumping to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for enabling the embodiments of the present application to operate normally will be obtained.

[0033] For this reason, with reference to Figure 1, an embodiment of the present application provides a method for controlling smart home devices. This method is applied to a central controller, which can be a server, an electronic device, a mobile terminal, etc., and no specific limitation is made here. The method includes the following steps S110 to S160: Step S110, obtain the status data of the target area and the control parameters of the smart home devices; wherein, the target area includes at least two smart home devices; the status data includes at least environmental status data; Step S120, construct a status influence diagram of the smart home devices according to the status data and the control parameters; Step S130, calculate the target deviation term of the smart home devices according to the status data and the control parameters; Step S140, construct a local cost function of the smart home devices according to the target deviation term and the control parameters, and generate a first control strategy for at least two smart home devices; Step S150, based on the local cost function, construct a global cost function of the target area according to the status influence diagram; Step S160, iteratively optimize the first control strategy according to the global cost function to generate an optimal control strategy for at least two smart home devices.

[0034] In this step, first, obtain the status data of the target area and the control parameters of the smart home devices. Among them, the target area includes at least two smart home devices, and the status data includes environmental status data and human vital signs data. Then, according to the obtained status data and control parameters, construct a status influence diagram of the smart home devices, which is used to represent the mutual influence relationship between the devices.

[0035] Specifically, the status data of the target area refers to environmental parameters and human physiological indicators obtained through sensors or user input. It can be collected by temperature sensors, humidity sensors, infrared human sensors, wearable devices or any smart home device, and is used to comprehensively sense the environmental status and user health information in the target area, providing a data basis for constructing the collaborative relationship between devices. For example, the environmental status data is collected by temperature sensors, humidity sensors, light sensors, etc., and the human vital signs data is collected by wearable devices, including physiological indicators such as body temperature, heart rate, and blood pressure.

[0036] Among them, the status influence diagram is a topological model that describes the mutual influence of the status of smart home devices. It can be constructed by using a mixed parameter structure mapping set. By quantifying the correlation degree of device control parameters on environmental status and human vital signs, the problem of lack of unified modeling in multi-device collaborative control is solved.

[0037] Further, based on the state data and control parameters, calculate the target deviation term of the smart home device, which reflects the difference between the current state and the target state, so as to construct the local cost function of the smart home device according to the target deviation term and control parameters, and generate the first control strategy for at least two smart home devices.

[0038] Among them, the target deviation term refers to the difference metric between the actual state and the desired state of the smart home device, which can be calculated by the difference between the target control parameter and the actual control parameter, and is used to evaluate the control effect of a single device, providing an optimization basis for constructing the local cost function.

[0039] Further, based on the local cost function and the state influence diagram, construct the global cost function of the target area to achieve overall optimization. Finally, iteratively optimize the first control strategy according to the global cost function to generate the optimal control strategy for at least two smart home devices, so as to quantify the dynamic association relationship between devices by constructing the state influence diagram, combine the hierarchical cost function with the iterative optimization algorithm, realize the cooperative control and resource optimal allocation of multiple smart home devices in complex scenarios, improve the system response speed and energy efficiency level, and achieve the cooperative control and global optimization of multiple smart home devices.

[0040] Among them, the local cost function and the global cost function refer to the control effect evaluation models for single-device and multi-device systems respectively, which can be constructed by combining weighted target deviation terms and constraint conditions, and solve the problem of device resource allocation conflicts in multi-objective scenarios through a hierarchical optimization structure; iterative optimization refers to the process of dynamically adjusting the control strategy based on the global cost function, which can be specifically implemented by combining the Lagrangian multiplier relaxation algorithm with subgradient response calculation, and ensure the convergence and stability of the multi-device control strategy in a dynamic environment through distributed cooperative solution.

[0041] In some embodiments, in step S120 of constructing the state influence diagram of the smart home device according to the state data and control parameters, the following steps S210 to S250 are included: Step S210: Divide the control parameters into a continuous control parameter subset and a discrete control parameter subset; Step S220: Establish a continuous control mapping set of the continuous control parameter subset and the state data; Step S230: Establish a discrete control mapping set of the discrete control parameter subset and the state data; Step S240: Combine the continuous control mapping set and the discrete control mapping set to obtain a mixed parameter structure mapping set; Step S250: Generate the state influence diagram of the smart home device according to the mixed parameter structure mapping set.

[0042] In this step, the control parameters are divided into a continuous control parameter subset and a discrete control parameter subset. For example, continuously adjustable parameters such as temperature, humidity, and brightness are divided into the continuous control parameter subset, and discretely adjustable parameters such as switch states and mode selections are divided into the discrete control parameter subset.

[0043] Among them, the continuous control parameter subset preferably includes the power gradient of the temperature adjustment device in the smart home device or the wind speed gear of the air purifier, and the discrete control parameter subset includes the switch state of the lighting device in the smart home device or the start / stop instruction of the curtain motor.

[0044] Furthermore, a continuous control mapping set of the continuous control parameter subset and the state data is established. Specifically, it is preferably to use the polynomial regression method to establish the mapping relationship between the continuous control parameter and the environmental state data. Exemplarily, the continuous control mapping set establishes the correlation between the environmental temperature and the device power through a regression model.

[0045] Furthermore, a discrete control mapping set of the discrete control parameter subset and the state data is established. Specifically, it is preferably to use the decision tree method to establish the mapping relationship between the discrete control parameter and the environmental state data. Exemplarily, the discrete control mapping set describes the change correlation between the device switch state and the light intensity through a state transition matrix.

[0046] Furthermore, by combining the continuous control mapping set and the discrete control mapping set, a hybrid parameter structure mapping set is obtained. Preferably, the hybrid parameter structure mapping set adopts a hierarchical fusion mechanism, taking the continuous parameter mapping result as the underlying constraint condition and the discrete parameter mapping result as the upper-level decision variable. Thus, a state influence diagram of the smart home device is generated according to the hybrid parameter structure mapping set, representing the influence relationship of each control parameter on the environmental state in the form of a directed graph. This realizes the classification processing of continuous and discrete control parameters, establishes the mapping relationship between different types of parameters and the environmental state, and generates a state influence diagram reflecting the influence of each device control parameter on the environmental state. Furthermore, it can comprehensively capture the characteristics of different types of control parameters, improve the accuracy and integrity of the state influence diagram, and lay a foundation for the subsequent optimization of the control strategy based on the state influence diagram.

[0047] Taking the collaborative scenario of air conditioners and lighting equipment as an example, the temperature set value of the air conditioner is input into the regression model as a continuous parameter to generate a predicted value of the temperature change rate; the lighting switch state is used as a discrete parameter to generate a probability distribution of the light intensity change through the state transition matrix. The hybrid parameter structure mapping set uses the temperature change rate as the boundary condition for lighting adjustment, restricting the lighting brightness adjustment range to avoid local overheating. Through the hierarchical fusion of continuous and discrete parameters, the state influence diagram can accurately reflect the dynamic coupling effect between devices. For example, when the air conditioner cools down, the lighting equipment needs to reduce its brightness to maintain human comfort, thereby improving the accuracy of the strategy generation for multi-device collaborative control.

[0048] In some embodiments, in step S130 of calculating the target deviation term of the smart home device according to the state data and control parameters, the following steps S310 to S320 are included: Step S310: Generate target control parameters according to the environmental state data and human body sign data; Step S320: Calculate the target deviation term of each smart home device according to the target control parameters and the control parameters of the smart home device.

[0049] In this step, target control parameters are generated according to the environmental state data and human body sign data. For example, according to the indoor temperature and the user's body temperature, the target temperature set value of the air conditioner is calculated; according to the indoor light intensity and the user's heart rate, the target brightness value of the light is calculated.

[0050] Furthermore, the target control parameters are compared with the current control parameters of the smart home device to calculate the target deviation term of each smart home device. Among them, the target control parameters are generated by jointly mapping the set physical sign thresholds and environmental parameters. For example, calculate the difference between the target temperature of the air conditioner and the current temperature, and calculate the difference between the target brightness of the light and the current brightness, so as to comprehensively consider the environmental state and the user's physiological state, dynamically generate personalized device control targets, calculate the deviation between the current state and the target state of the device, and thus achieve real-time response to the user's health state and environmental changes, improving the personalized adjustment ability of the smart home system and the user's comfort.

[0051] Specifically, the target deviation term is calculated through the difference matrix between the target control parameters and the current control parameters of the device. The dimension of the difference matrix is the same as the number of devices, and each element corresponds to the parameter deviation of a single device. The weight coefficient of the target deviation term is dynamically adjusted according to the degree of deviation of the physical sign data from the threshold. When the physical signs are abnormal, the weight of the deviation term of the corresponding device is increased to the preset upper limit value.

[0052] In some embodiments, before constructing the local cost function of the smart home device according to the target deviation term and the control parameter in step S140 to generate the first control strategy for at least two smart home devices, the following steps S410 to S420 are included: Step S410: When the target deviation term of each smart home device is less than the preset threshold, obtain the real-time control parameter of each smart home device; Step S420: Obtain the optimal control strategy according to the real-time control parameter of each smart home device.

[0053] In this step, when the target deviation term of each smart home device is less than the preset threshold, it indicates that the device control parameter has met the dynamic requirements of the target area. Furthermore, obtaining the real-time control parameter of each smart home device and directly extracting the real-time parameter as the optimal strategy can avoid redundant optimization.

[0054] Among them, the preset threshold is set according to the allowable fluctuation range of the environmental state data and the human body sign data. For example, the allowable range of temperature deviation is ±0.5 °C, and the allowable range of light intensity deviation is ±50 lux. The real-time control parameter includes the current operation mode of the device, the power value, and the sensor feedback data.

[0055] Exemplarily, for the air conditioner device, the real-time control parameters such as the current set temperature, wind speed, and mode can be obtained; for the lighting device, the real-time control parameters such as the current brightness and color temperature can be obtained; for the humidifier, the real-time control parameters such as the current humidity setting value and the fog volume can be obtained.

[0056] Furthermore, taking the obtained real-time control parameters of each device as the initial value, combining the environmental state data and the user preference, the optimal control parameter combination of each device is calculated through the optimization algorithm to form the optimal control strategy. Thus, when the device operation state is already close to the target state, fine-tuning optimization can be directly performed based on the current real-time parameter. When the device operation state is already relatively ideal, the current control parameter can be quickly obtained and optimized, improving the efficiency of generating the control strategy. At the same time, by directly using the real-time parameter for fine-tuning, unnecessary large adjustments can be avoided, reducing energy consumption and improving user comfort.

[0057] In some embodiments, in step S160 of iteratively optimizing the first control strategy according to the global cost function to generate the optimal control strategy for at least two smart home devices, the following steps S510 to S520 are included: Step S510: Through the Lagrangian multiplier relaxation and subgradient response algorithm, iteratively calculate the variational inequality problem of the global cost function according to the target control parameter to generate the Nash equilibrium control strategy; Step S520: Optimize the first control strategy according to the target control parameters and the Nash equilibrium control strategy to generate the optimal control strategy for the target area.

[0058] In this step, through the Lagrangian multiplier relaxation and the subgradient response algorithm, the variational inequality problem of the global cost function is iteratively calculated according to the target control parameters to generate the Nash equilibrium control strategy.

[0059] Preferably, the Lagrangian multiplier relaxation decomposes the original constrained optimization problem into multiple sub-problems by introducing a relaxation factor. The subgradient response algorithm uses the subgradient projection method in non-smooth optimization to update the policy parameters. The target control parameters include a multi-dimensional vector of temperature set value, light intensity threshold, and user heart rate reference value. During the generation process of the Nash equilibrium control strategy, the error tolerance is set to 0.5% - 1.2%, and the policy update step size is controlled within the range of 0.05 - 0.15. The number of iterative solutions for the variational inequality problem is set to 50 - 200 times. After each iteration, the change amount of the second-order norm of the policy vector is detected, and when the change amount is less than 0.01, the termination condition is triggered.

[0060] Furthermore, optimizing the first control strategy according to the target control parameters and the Nash equilibrium control strategy to generate the optimal control strategy for the target area realizes the global optimization of multi-device collaborative control, avoids the sub-optimal solution caused by the independent decision-making of a single device, improves the overall control effect, and through the two-stage solution of Nash equilibrium and objective function optimization, not only ensures the interest balance of each device but also realizes the global optimum, thus achieving the efficient collaborative control of the smart home system in a complex dynamic environment.

[0061] In some embodiments, after step S160 iteratively optimizes the first control strategy according to the global cost function to generate the optimal control strategies for at least two smart home devices, the following steps S610 to S640 are included: Step S610: Combine the state data of the target area, the control parameters of the smart home devices, and the optimal control strategy to obtain the first application scenario; Step S620: Store the first application scenario in a preset repository; Step S630: Obtain the second application scenario of the area to be controlled, which is composed of the first state data of the area to be controlled and the first control parameters of the smart home devices in the area to be controlled; Step S640: Match the second application scenario with the preset repository to obtain the matching result.

[0062] In this step, the status data of the target area, the control parameters of the smart home devices, and the optimal control strategy are combined to obtain the first application scenario. For example, if the target area is the living room, the status data includes a temperature of 25°C, a humidity of 60%, and a light intensity of 500 lux. The control parameters include an air conditioner set temperature of 24°C, a dehumidifier set humidity of 50%, and a curtain opening of 80%. The optimal control strategy is to lower the temperature of the air conditioner by 1°C, reduce the humidity of the dehumidifier by 10%, and adjust the curtain opening to 60%. By combining the status data of the target area, the control parameters of the smart home devices, and the optimal control strategy, the first application scenario is obtained.

[0063] Further, the first application scenario is stored in a preset repository. The preset repository can be a cloud database or a local memory.

[0064] Further, the second application scenario of the area to be controlled is obtained. The second application scenario is composed of the first status data of the area to be controlled and the first control parameters of the smart home devices in the area to be controlled. Then, the second application scenario is matched with the preset repository to obtain a matching result, thereby quickly identifying similar scenarios and applying the optimized control strategy, improving the control efficiency and accuracy.

[0065] In some embodiments, in step S640, the second application scenario is matched with the stored data in the preset repository to obtain a matching result, including the following step S710.

[0066] Step S710: In the case of a successful match, the first application scenario that matches the application scenario of the area to be controlled is extracted from the preset repository to obtain the optimal control strategy; a successful match includes a match between the first status data and the status data, and a match between the first control parameters and the control parameters.

[0067] In this step, by matching the first status data with the status data and matching the first control parameters with the control parameters, when the match is successful, the first application scenario that matches the application scenario of the area to be controlled is extracted from the preset repository to obtain the optimal control strategy. Through scenario matching and strategy reuse, repeated calculations and optimization processes are reduced, system resource consumption is lowered, and the overall operation efficiency is improved, realizing the scenario-based control and optimization of the smart home system.

[0068] Exemplarily, when the environmental sensors in the target area detect an indoor temperature of 28°C, a humidity of 65%, and a user's body surface temperature of 36.8°C, an optimal strategy including a temperature adjustment curve and a humidity control timing sequence is generated by combining parameters such as the air conditioner set temperature of 26°C and the dehumidifier power of 800W, forming a first application scenario containing a 6-dimensional feature vector and storing it in the repository. When the temperature of 27.5°C, humidity of 63%, and user's body surface temperature of 36.7°C are detected in the area to be controlled, the system extracts the feature vectors in the repository for comparison and finds that the vector distance from the scenario numbered S015 is 0.12, which is lower than the threshold of 0.15. The air conditioner stage cooling and dehumidifier intermittent operation strategies in this scenario are directly called, shortening the response time from the 8.2 seconds required for conventional optimization to 1.5 seconds.

[0069] In some embodiments, with the coordination of devices as the goal, a modeling framework with policy interaction capabilities is constructed to implement the control system of smart home devices.

[0070] 1. Control variable modeling: Let the system be at time Containing control devices, and the control variable vector is: ; Among them, represents the transpose of the current calculation vector. The control variable set can be divided into a continuous control variable index set and a discrete control variable index set , representing temperature setting, wind speed adjustment (continuous) and mode selection, switch control (discrete), etc. respectively; represents the control action of the th device at time , which can be a real value or an enumerated type; represents the vector composed of all device control actions, which is the main decision variable for optimization; represents the variable classification index set, which is predefined and comes from the device function configuration table.

[0071] 2. System state and dynamics: The state data in the system includes data in dimensions such as environment, user, and physiological indicators, and is defined as: ; Specifically, the state evolves with the change of control variables:

[0072] Among them, is the state transition function, represents external disturbances or sensing errors, represents the A state variable, such as temperature, humidity, PM2.5, heart rate, etc., is obtained by sensors or calculated from states; represents the current environment-user joint state, represents the state transition function, which can be a data-driven model or constructed from device response rules, represents the disturbance term, considering noise, uncertainties, and modeling errors.

[0073] 3. Local cost function modeling (including control coupling terms): Each device has a local cost function of the following form: ; where the first term is the system state error used to measure the deviation of the device from the target state (such as temperature, brightness, heart rate, blood pressure, etc.); the second term is the energy consumption term indicating that the greater the control intensity, the higher the energy consumption; the third term is the conflict term. If and are controlled simultaneously and the targets are inconsistent, then this term incurs a loss; represents the conflict severity coefficient between devices; represents the th device's individual objective function, including three types of terms: comfort, energy consumption, and conflict; represents the cost function weighting factor, which comes from user preference settings or device type adjustment parameters; represents the device desired state target, such as "22°C, low noise", etc.; represents all devices that conflict with the current device list; represents the control conflict loss function, such as interference caused by opposite targets of two devices (air conditioner and ventilation); represents the conflict severity penalty factor.

[0074] 4. Nash equilibrium derivation: Due to the interaction of control behaviors between devices, the stable operating state of the system should satisfy the following Nash equilibrium conditions: ; Specifically, when the strategies of other devices are fixed, each device reaches an optimal response by optimizing its own cost function, forming an equilibrium state where no device changes its strategy , represents the optimal control strategy of device , which achieves the minimum cost when the behaviors of other current devices are fixed; represents the feasible control space of device , which is defined by its physical limitations such as control accuracy and operation range.

[0075] 5. Control Constraints and Explanations: To ensure system safety, physical feasibility, and human - machine comfort, control actions need to meet the following constraints: First, the boundary constraints for continuous control variables are: ; Among them, the control output cannot exceed the upper limit of device capabilities or the safety range (such as brightness, wind speed).

[0076] Second, the value constraints for discrete control variables are: ; Among them, for devices such as switches and curtain modes, their control values must come from a predefined discrete set.

[0077] Third, the state - index constraints are: ; Among them, for variables such as temperature, PM2.5, and noise intensity, they must be maintained within a healthy and comfortable range.

[0078] Fourth, the response - delay constraints are: ; Among them, after the input changes, the system needs to complete the action execution within a specified time to ensure the user experience.

[0079] Specifically, , represents the minimum and maximum allowable values of continuous variables, which are derived from the device specification or preset; represents the value - range set of discrete control variables, such as {on, off}, {high, medium, low}; , represents the health or comfort - range limit of state variables, such as the temperature range [20, 26] °C; represents the response delay and the upper limit tolerated by the system, which comes from the performance specification or service design.

[0080] 6. System Solution Objectives: The final control problem of the system is formulated as: finding a set of control - variable combinations such that, under the condition of satisfying all the above - mentioned constraints, each device can achieve its own optimal response, thus realizing the coordinated equilibrium at the system level: ; ; ; ; ; Among them, represents the optimal control solution for the entire system, which is a set of game equilibrium solutions and the control vector finally issued by the system calculation.

[0081] The modeling in this embodiment reflects the strategic dependence and competitiveness among control variables, meets the requirements of multi-objective dynamic regulation and multi-device collaborative optimization, and is the basis for realizing a highly responsive, energy-efficient, and highly stable control mechanism in the smart home scenario.

[0082] Exemplarily, the current smart home system includes three typical devices: an air conditioner (denoted as device A), lights (device B), and an air purifier (device C). Each device has adjustable control parameters, such as the temperature setting of the air conditioner, the brightness level of the lights, and the wind speed or switch state of the purifier. The system organizes the control variables of all devices into a vector.

[0083] First, the system obtains the current working states of devices A, B, and C in real time through environmental perception and device feedback data, denoted as a, b, and c respectively. For example, a represents the current room temperature, b represents the current light brightness, and c represents the current wind speed or purifier switch state. The system integrates these states into the overall state vector of the system for subsequent analysis and control calculations.

[0084] Second, the system generates corresponding control objectives according to the user's current behavior scenario (such as "sleeping"). At this time, the system determines that device A needs to adjust the temperature to the target value X to improve the user's sleep quality; the current brightness of device B already meets the requirements and no further control is needed; device C needs to increase the wind speed to a medium speed suitable for night operation, corresponding to the target value Y. Therefore, each device has a clear target state in this scenario: a needs to approach X, b remains in the original state, and c needs to be adjusted to Y.

[0085] Then, the system constructs a comprehensive utility function based on the difference between the current state and the target state, the energy consumption characteristics of each device, and the control coupling relationship between devices (such as there may be air flow interference between the air conditioner and the purifier), and sets reasonable control strategies according to the device type and response ability. The system evaluates the control cost of each device through this utility function and determines a set of control instructions that optimize the coordination of the overall system through multiple rounds of strategy iteration calculations.

[0086] Finally, the system converts this set of optimal control strategies into control commands recognizable by actual devices, such as "set the air conditioner temperature to 25°C" and "turn on the purifier in medium speed mode", and synchronously issues them to all relevant devices to achieve the optimal regulation and closed-loop control of the entire environmental state.

[0087] In some embodiments, by constructing a structural mapping system of continuous + discrete control variables, designing a coupled modeling mechanism that combines multiple cost functions, and introducing a variational inequality-driven response solver, a policy equilibrium can be efficiently and stably generated. And through the action mapping and feedback closed-loop mechanism, an end-to-end adaptive control process is realized, which has the advantages of strong generalization, high adaptability, low communication volume, etc., as follows: Step 1: Modeling and variable structure design, where the inputs are: a set of control devices and their control types (continuous variables and discrete variables), the current system time step , multi-modal perception data: environmental state (temperature, humidity, light, PM2.5, etc.) and user state (heart rate, body temperature, activities, etc.), state transition knowledge, prior coupling structure (such as influence diagram); the outputs are: a control variable vector , and index partitioning , , a state variable vector a set of coupling mapping functions used to describe the current perception state of the system, control variables, and state variables , local cost functions corresponding to each device .

[0088] 1. Decomposition and structural mapping of control variables: In the multi-device smart home control scenario, device control variables usually include different dimensions and types, including continuous variables (such as temperature setting, wind speed adjustment) and discrete variables (such as mode switch, gear selection). To achieve unified modeling of heterogeneous control variables, this paper adopts a structured hybrid variable modeling mechanism (MIP-Structure Mapping) to construct all device control variables into a hybrid control vector : ; where here represents the transpose of the current calculation vector, and the variable set is divided into two subsets: a set of continuous control variables , where , and the control quantity satisfies ; a set of discrete control variables , where , and the control quantity satisfies , is a finite set.

[0089] Example: If represents the set temperature of the air conditioner, it is a continuous variable ; if represents the opening and closing state of the curtain, it is a discrete variable .

[0090] This modeling structure not only maintains the integrity of control variables, but also provides a distinguishable variable structure mapping for subsequent optimal response algorithms, which is beneficial to the feasibility detection and grouped optimization of the design algorithm.

[0091] 2. State Influence Modeling and Representation of Coupling between Devices: The system state is composed of environmental and user states in multiple dimensions, denoted as: ; where, can represent state variables such as temperature, humidity, air quality, illuminance, and user comfort.

[0092] Considering the heterogeneity and non-linearity of the influence of control variables on state variables, in this embodiment, a linear-nonlinear cross-state influence graph (Hybrid Coupling Influence Graph, HCIG) is constructed to establish the action path from control variables to state variables in the form of a directed weighted graph. Formally, it is assumed that the state evolution satisfies the following relationship:

[0093] where, is a non-linear state transition function, represents the disturbance term.

[0094] Example: Indoor PM2.5 State affected by the air purifier wind speed can be modeled as: ; The state coupling between devices occurs indirectly through shared state variables. For example, both the air conditioner and the curtain affect temperature and light intensity, and conflict regulation is required to prevent target conflicts.

[0095] 3. Construction of Local Objective Function and Design of Coordination Cost: A cost function is constructed for each control device to measure its operation effect. In this paper, a partially separable convex cost model is adopted, and the structure is as follows: ; where: the first term represents the adjustment error of the device to the target state; the second term reflects the energy consumption corresponding to the control intensity of the device; the third term represents the control coupling cost with other devices (such as when heating and cooling devices operate simultaneously).

[0096] Example: The goal of the air conditioner is to maintain the room temperature , and avoid running simultaneously with the heater. The cost function can be written as: ; In addition, to achieve time-varying adaptability of the conflict cost between devices, a dynamic conflict factor is introduced to adjust the intensity of device conflicts and enable the model to have higher scenario adaptability.

[0097] Step 2: Response strategy generation and equilibrium solution, specifically: Modeling control conflicts as a strategy coupling problem of multiple parties through a game framework, and designing an optimal response equilibrium solution process with low communication and fast convergence. Specifically, the LS-BRD mechanism (Lagrangian Subgradient Best-Response Dynamics) is adopted to transform the game problem into a generalized convex game problem with coupling constraints, and the Nash equilibrium control strategy is generated through Lagrangian relaxation and subgradient response algorithms to ensure strategy coordination, solution efficiency, and convergence stability.

[0098] Among them, the inputs are: the control variable structure and type index , , ; the set of local objective functions ; the conflict penalty coefficient ; the parameters of the optimization algorithm: the step size , the tolerance , the relaxation coefficient ; the definition of the feasible solution space and response constraints. The outputs are: the optimal response strategy combination ; the set of candidate feasible strategies ; the utility evaluation values corresponding to each strategy ; Optionally: the evolution trajectory, variational residual, and convergence index.

[0099] 1. Modeling the control game as a convex game problem: In the above-mentioned modeling, each device has a local control objective function , which depends on its own control behavior and the control strategies of other devices. To express the mutual influence relationship between devices, this embodiment models the entire system as a generalized convex game problem.

[0100] The game model is formalized as: ; Among them, is the feasible domain of the control variable, which may be a continuous interval or a discrete set.

[0101] There are coupling terms in the strategy space of this problem (i.e., explicitly depends on , ), so it is transformed into a multi-objective optimization problem with joint constraints, and the equilibrium condition is further characterized by variational inequality theory.

[0102] 2. Optimal response iterative solution mechanism: To solve the equilibrium solution of the above game problem, this embodiment adopts the Best Response Dynamics mechanism. When other strategies are fixed, each device updates itself to minimize the cost function.

[0103] The specific update rules are as follows: ; Considering that has a good convexity structure, this paper introduces the Lagrange multiplier relaxation mechanism to eliminate the coupling effect of conflict terms, and uses the subgradient descent method for optimal response update to avoid non-convergence caused by direct decoupling failure.

[0104] 3. Variational inequality equilibrium point solution mechanism: To theoretically ensure the existence and uniqueness of the Nash equilibrium point, the above multi-objective coupled game problem is further transformed into a variational inequality (VI) problem. Let the joint strategy space be , and define the mapping operator: ; Then the VI problem is expressed as: ; Using the projection algorithm to solve the VI problem can converge to the game equilibrium point. This method has theoretical convergence guarantee and is applicable to the mixed structure of the strategy space (i.e., mixed type).

[0105] Example: In a smart home system that includes continuous adjustment and discrete switches, the optimal control combination of all devices in the current environment can be obtained uniformly through the VI solution method.

[0106] Step three: Control strategy execution and mapping, specifically: through the device-level state translator (DLST) mechanism for heterogeneous devices, construct the mapping relationship from the control vector to the device instruction set; at the same time, to reduce the overhead caused by frequent solving, introduce the policy table approximation (PTA) mechanism based on state fluctuations to improve the response speed and robustness of the control system.

[0107] Among them, the input: the current control strategy combination , the control mapping function , the device control interface protocol and mapping template, the current system state , state change threshold , policy cache table . Output: actual execution command set , used to drive physical devices and control the system state after execution ; sliding state window , used for trend estimation and policy cache update results.

[0108] 1. Policy mapping and physical action conversion mechanism: Specifically, the control variable and the device control instruction are related through the mapping function : ; For different device types, it can be a quantization function, look-up table mapping or coding conversion. Specifically, for continuous control: map real-valued variables to protocol parameters through linear or piecewise functions; for discrete control: map to a finite set of control actions, such as {on, off} or {low, medium, high}.

[0109] Exemplarily, when the optimal control variable is (indicating the brightness percentage), it is converted to the device protocol command \setBrightness(75) and sent to the intelligent lighting system.

[0110] The mapping mechanism supports the rapid generation of control instructions and is compatible with devices of different brands, with good portability and scalability.

[0111] 2. State feedback acquisition and incremental update mechanism: After the control strategy is executed, the system needs to continuously monitor the environment and user status in real time and feedback to the decision-making module to update the system state , forming a closed-loop control.

[0112] To avoid unstable feedback caused by fluctuations in a short period of time, a sliding window feedback mechanism is introduced. For each state dimension , the system maintains the state sequence of the most recent cycles:

[0113] and estimates the current state change trend through the trend function : ; If the trend of state change significantly deviates from the model prediction result, the error correction module is triggered to correct the state estimation model, thereby enhancing the stable operation ability of the system under real-world disturbances and effectively avoiding the control oscillation problem caused by feedback distortion.

[0114] Exemplarily, if the PM2.5 reading fluctuates more than a preset threshold within = 5 consecutive time instants, the system automatically retraces the pollution source intervention mechanism and adjusts the influence parameters in the state transition function.

[0115] When the state change is within the acceptable fluctuation range, the strategy combination obtained in the previous round is directly reused .

[0116] The following trigger conditions are specifically set: ; where is the state change threshold, which can be dynamically set according to the application scenario.

[0117] On this basis, the system maintains a policy cache table of finite size , records the optimal policy combinations in common states, and allows fast look-up table-based policy invocation: ; where represents the known policies stored in the cache table.

[0118] Example: In the summer night sleep scenario, the temperature, light, and noise states are highly stable. The policy cache can be reused for a long time, such as the combined policy of "air conditioner at medium speed + curtains fully closed + purifier at low speed", avoiding repeated game reasoning, and thus significantly improving the system execution efficiency while ensuring the rationality of policy response, especially suitable for deployment on resource-constrained edge control devices.

[0119] Step 4: End-to-end control feedback closed-loop design, specifically a window-based consistency assessment (WCA) mechanism for closed-loop state consistency assessment driven by state, which is used to dynamically detect the effectiveness of feedback signals and the consistency of system behavior, and design a stability trigger and sliding prediction mechanism to improve the long-term operation robustness of the control system.

[0120] Among them, the inputs are: the current system state and the historical state sequence , the previous control policy ; the stability discrimination threshold ; the sliding prediction window length Output: Stability judgment result (whether to trigger recalculation), predicted value of the next moment state ; Trend estimation of each state variable , Prediction error ; Updated closed-loop input state .

[0121] To implement the end-to-end closed-loop control logic, in this embodiment, the control strategy generation module, the actuator action interface, and the state perception subsystem are integrated into an integrated structure for unified scheduling and communication.

[0122] This structure includes the following four core modules: Control strategy generator : Calculate the optimal strategy based on the current state ; ; Device action mapper : Convert the strategy into device instructions ; Behavior executor : Actually drive the physical device to complete the control action; State perception and corrector : Collect and correct the state vector at the moment .

[0123] This structure has interface encapsulation, and all modules realize the closed-loop control process through the data flow .

[0124] In continuous control cycles, if the environmental state changes little or the device state is stable, frequent recalculation of the strategy will lead to an increase in system load and an increase in response delay. Therefore, this embodiment introduces a "strategy stability trigger mechanism". When the system state is in the "low change interval", the strategy generation stage is automatically skipped and the previous moment's strategy is used.

[0125] Let the state change judgment function be: ; Set the threshold , when , it is judged as a stable section: ; This mechanism can avoid frequent recalculation caused by small perturbations and ensure the stable operation of the control process.

[0126] Example: If the bedroom temperature fluctuates less than within 3 minutes, the system does not recalculate the air conditioner strategy and maintains the current set value.

[0127] Considering that the control system has a certain lag in response to state changes, in this embodiment, a short-term prediction mechanism based on a sliding window is further designed to proactively judge possible state offsets in the next cycle, so as to make preparations in advance for policy calculation.

[0128] Let the state prediction window be , and a linear extrapolation model is used to estimate each dimension of the state: ; where , when the deviation between the prediction result and the current state is large (i.e., ), the policy updater can be activated in advance or the device warm-up time can be adjusted.

[0129] Example: It is predicted that the air humidity will exceed the threshold within the next 2 minutes due to the user taking a bath. The system turns on the dehumidification device in advance to improve the user's comfort experience and enhance the reaction speed and overall intelligence level of the control chain.

[0130] As Figure 2 shown, some embodiments of the present application provide a control system for smart home devices. The system includes a data acquisition module 210, a state construction module 220, a deviation calculation module 230, a first construction module 240, a second construction module 250, and an update iteration module 260. Specifically: The data acquisition module 210 is used to acquire the state data of the target area and the control parameters of the smart home devices; among them, the target area includes at least two smart home devices; the state data includes at least environmental state data.

[0131] The state construction module 220 is used to construct a state influence diagram of the smart home devices according to the state data and the control parameters.

[0132] The deviation calculation module 230 is used to calculate the target deviation term of the smart home devices according to the state data and the control parameters.

[0133] The first construction module 240 is used to construct a local cost function of the smart home devices according to the target deviation term and the control parameters, and generate a first control strategy for at least two smart home devices.

[0134] The second construction module 250 is used to construct a global cost function of the target area based on the local cost function according to the state influence diagram.

[0135] The update iteration module 260 is used to iteratively optimize the first control strategy according to the global cost function to generate an optimal control strategy for at least two smart home devices.

[0136] In some embodiments, the state construction module 220 may include: dividing the control parameters into a continuous control parameter subset and a discrete control parameter subset.

[0137] In some embodiments, the state construction module 220 may include: establishing a continuous control mapping set between the continuous control parameter subset and the state data.

[0138] In some embodiments, the state construction module 220 may include: establishing a discrete control mapping set between the discrete control parameter subset and the state data.

[0139] In some embodiments, the state construction module 220 may include: combining the continuous control mapping set and the discrete control mapping set to obtain a hybrid parameter structure mapping set.

[0140] In some embodiments, the state construction module 220 may include: generating a state influence diagram of the smart home device according to the hybrid parameter structure mapping set.

[0141] In some embodiments, the deviation calculation module 230 may include: generating target control parameters according to the environmental state data and the human body sign data.

[0142] In some embodiments, the deviation calculation module 230 may include: calculating a target deviation term for each smart home device according to the target control parameters and the control parameters of the smart home device.

[0143] In some embodiments, the first construction module 240 may include: obtaining the real-time control parameters of each smart home device when the target deviation term of each smart home device is less than a preset threshold.

[0144] In some embodiments, the first construction module 240 may include: obtaining an optimal control strategy according to the real-time control parameters of each smart home device.

[0145] In some embodiments, the update iteration module 260 may include: iteratively calculating the variational inequality problem of the global cost function according to the target control parameters by the Lagrange multiplier relaxation and subgradient response algorithms, and generating a Nash equilibrium control strategy.

[0146] In some embodiments, the update iteration module 260 may include: optimizing the first control strategy according to the target control parameters and the Nash equilibrium control strategy to generate an optimal control strategy for the target area.

[0147] In some embodiments, the update iteration module 260 may include: combining the state data of the target area, the control parameters of the smart home device, and the optimal control strategy to obtain a first application scenario.

[0148] In some embodiments, the update and iteration module 260 may include: storing the first application scenario in a preset repository.

[0149] In some embodiments, the update and iteration module 260 may include: obtaining a second application scenario of the area to be controlled, where the second application scenario is composed of first state data of the area to be controlled and first control parameters of smart home devices in the area to be controlled.

[0150] In some embodiments, the update and iteration module 260 may include: matching the second application scenario with the preset repository to obtain a matching result.

[0151] In some embodiments, the update and iteration module 260 may include: in the case of successful matching, extracting a first application scenario that matches the application scenario of the area to be controlled from the preset repository to obtain an optimal control strategy; successful matching includes matching of the first state data and the state data, and matching of the first control parameter and the control parameter.

[0152] It should be noted that the smart home device control system provided in this embodiment and the above-mentioned smart home device control method are based on the same inventive concept. Therefore, the relevant content of the above-mentioned smart home device control method also applies to the content of the smart home device control system. Therefore, it will not be elaborated here.

[0153] For this purpose, the system obtains the state data of the target area and the control parameters of the smart home devices; constructs a state influence diagram of the smart home devices according to the state data and the control parameters; calculates the target deviation term of the smart home devices according to the state data and the control parameters; constructs a local cost function of the smart home devices according to the target deviation term and the control parameters, and generates a first control strategy for at least two smart home devices; constructs a global cost function of the target area according to the state influence diagram based on the local cost function; and iteratively optimizes the first control strategy according to the global cost function to generate an optimal control strategy for at least two smart home devices. In this way, through the game between multiple devices, multi-device collaborative control and optimization can be realized, and the scenario applicability of the solution is improved, and the personalized requirements of users can be met.

[0154] An embodiment of the present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the above-mentioned smart home device control method is implemented.

[0155] Such as Figure 3 , Figure 3 is a schematic hardware structure diagram of the electronic device provided in an embodiment of the present application. The electronic device includes: At least one battery; At least one memory; At least one processor; At least one program; The program is stored in the memory, and the processor executes at least one program to implement the smart home device control method described above in the present application.

[0156] The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), an in-vehicle computer, etc.

[0157] The electronic device of the embodiments of the present application will be introduced in detail below.

[0158] The processor 1600 can be implemented by using a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application; The memory 1700 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 1700 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1700, and the processor 1600 is called to execute a smart home device control method of the embodiments of the present application.

[0159] The input / output interface 1800 is used to implement information input and output; The communication interface 1900 is used to implement communication interaction between this device and other devices, and can implement communication through a wired method (such as USB, network cable, etc.) or through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.); The bus 2000 transmits information between various components of the device (such as the processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900); Among them, the processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900 are communicatively connected to each other inside the device through the bus 2000.

[0160] The embodiments of the present application also provide a storage medium, which is a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the above-mentioned smart home device control method.

[0161] As a non-transitory computer-readable storage medium, a memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely provided relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0162] The embodiments described in the embodiments of the present application are for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0163] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figures, or combine certain steps, or different steps.

[0164] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof.

[0166] In the description of this application and the above-mentioned accompanying drawings, terms such as "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0167] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or its similar expression refers to any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0168] In several embodiments provided by this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0169] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0171] If the integrated unit is implemented in the form of 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, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present application. The foregoing storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0172] The above is a specific description of the preferred embodiments of the present application, but the embodiments of the present application are not limited to the above-mentioned implementation manners. Those skilled in the art can make various equivalent deformations or substitutions without departing from the spirit of the embodiments of the present application, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the embodiments of the present application.

[0173] The above has described the embodiments of the present application in detail with reference to the drawings, but the present application is not limited to the above embodiments. Various changes can be made without departing from the gist of the present application within the knowledge scope of those of ordinary skill in the art.

Claims

1. A method for controlling a smart home device, characterized in that, The method includes: Obtaining the status data of the target area and the control parameters of the smart home devices; wherein, the target area includes at least two of the smart home devices; the status data at least includes environmental status data; Constructing a status influence graph of the smart home devices according to the status data and the control parameters; Calculating the target deviation term of the smart home devices according to the status data and the control parameters; Constructing a local cost function of the smart home devices according to the target deviation term and the control parameters, and generating a first control strategy for at least two of the smart home devices; Based on the local cost function, constructing a global cost function of the target area according to the status influence graph; Iteratively optimizing the first control strategy according to the global cost function to generate an optimal control strategy for at least two of the smart home devices.

2. The smart home device control method according to claim 1, characterized in that, The constructing a status influence graph of the smart home devices according to the status data and the control parameters includes: Dividing the control parameters into a continuous control parameter subset and a discrete control parameter subset; Establishing a continuous control mapping set between the continuous control parameter subset and the status data; Establishing a discrete control mapping set between the discrete control parameter subset and the status data; Combining the continuous control mapping set and the discrete control mapping set to obtain a mixed parameter structure mapping set; Generating a status influence graph of the smart home devices according to the mixed parameter structure mapping set.

3. The smart home device control method according to claim 1, characterized in that, The status data further includes human body sign data, and the calculating the target deviation term of the smart home devices according to the status data and the control parameters includes: Generating target control parameters according to the environmental status data and the human body sign data; Calculating the target deviation term of each of the smart home devices according to the target control parameters and the control parameters of the smart home devices.

4. The smart home device control method according to claim 3, wherein, Before the constructing a local cost function of the smart home devices according to the target deviation term and the control parameters and generating a first control strategy for at least two of the smart home devices, the method further includes: When the target deviation term of each of the smart home devices is less than a preset threshold, obtaining the real-time control parameters of each of the smart home devices; Obtaining the optimal control strategy according to the real-time control parameters of each of the smart home devices.

5. The smart home device control method according to claim 3, wherein, The iteratively optimizing the first control strategy according to the global cost function to generate an optimal control strategy for at least two of the smart home devices includes: Iteratively calculating the variational inequality problem of the global cost function according to the target control parameters by using the Lagrange multiplier relaxation and subgradient response algorithm to generate a Nash equilibrium control strategy; Optimizing the first control strategy according to the target control parameters and the Nash equilibrium control strategy to generate an optimal control strategy of the target area.

6. The smart home device control method according to claim 1, characterized in that After the iteratively optimizing the first control strategy according to the global cost function to generate an optimal control strategy for at least two of the smart home devices, the method further includes: Combine the status data of the target area, the control parameters of the smart home device, and the optimal control strategy to obtain a first application scenario; Store the first application scenario in a preset repository; Obtain a second application scenario of the area to be controlled, where the second application scenario consists of the first status data of the area to be controlled and the first control parameters of the smart home devices in the area to be controlled; Match the second application scenario with the preset repository to obtain a matching result.

7. The smart home device control method according to claim 6, characterized in that, The matching the second application scenario with the stored data in the preset repository to obtain a matching result includes: In the case of successful matching, extract the first application scenario that matches the application scenario of the area to be controlled from the preset repository to obtain the optimal control strategy; the successful matching includes the matching of the first status data and the status data, and the matching of the first control parameter and the control parameter.

8. A smart home device control system, characterized in that, The system includes: A data acquisition module for acquiring the status data of the target area and the control parameters of the smart home device; wherein, the target area includes at least two of the smart home devices; the status data at least includes environmental status data; A status construction module for constructing a status influence diagram of the smart home device according to the status data and the control parameters; A deviation calculation module for calculating the target deviation term of the smart home device according to the status data and the control parameters; A first construction module for constructing a local cost function of the smart home device according to the target deviation term and the control parameters, and generating a first control strategy for at least two of the smart home devices; A second construction module for constructing a global cost function of the target area according to the status influence diagram based on the local cost function; An update and iteration module for iteratively optimizing the first control strategy according to the global cost function to generate an optimal control strategy for at least two of the smart home devices.

9. An electronic device, characterized in that, Comprising at least one control processor and a memory for communicatively connecting with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute a smart home device control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to execute a smart home device control method according to any one of claims 1 to 7.

Images