A smart home device control method, system device and medium

Abstract

The application discloses a smart home device control method and system, and a medium. The method comprises the following steps: acquiring state data of a target area and control parameters of a smart home device; constructing a state influence graph 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 of at least two smart home devices; constructing a global cost function of the target area according to the state influence graph based on the local cost function; and iteratively optimizing the first control strategy according to the global cost function, and generating an optimal control strategy of the at least two smart home devices. The method can realize multi-device collaborative control and optimization through a game among the multiple devices, improve the scene applicability of the scheme, and meet the individual requirements of users.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a smart home device control method and system, and a medium. BACKGROUND

[0002] With the intensification of the aging trend of the population in China, home health management, smart aging and digital medicine have become the focus of current social attention. As an important carrier of medical and health care, smart home systems are gradually developing from single device control to integrated systems that integrate sensing, decision-making and execution. Especially in special groups such as the elderly and chronic patients, higher requirements are put forward for personalized adjustment of the home environment, real-time response to health status, and collaborative optimization of device control.

[0003] At present, the smart home system mostly takes the local controller or APP application as the core, and completes the start-stop operation of single device through fixed rules or simple sensing logic, resulting in a lack of unified strategy coordination mechanism among devices, making it difficult to achieve efficient collaboration under complex environmental dynamic changes, lacking unified coordination strategy to cope with complex scenarios, affecting user experience and energy efficiency. In addition, the existing technology lacks the ability to analyze the fusion of user health status and environmental sensing data, and the control strategy is mostly based on static setting, which is difficult to meet the personalized needs in multi-device and multi-target scenarios, and is difficult to generate dynamic strategies based on environmental changes, user preferences and device status. Therefore, the existing technology lacks unified modeling and optimization capabilities in multi-device, multi-target and dynamic environment, and cannot realize collaborative control and resource optimization allocation among devices. SUMMARY

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The main purpose of the embodiments of the present application is to provide a smart home device control method, system, device and storage medium, which can realize the organic unity of multi-device collaborative control, adaptive optimization and user satisfaction guarantee through the game among multiple devices, and improve the scene applicability of the scheme, and meet the personalized requirements of users.

[0006] The first aspect of the embodiments of the present application provides a smart home device control method for a smart home device, the method comprising:

[0007] obtaining state data of a target area and control parameters of a smart home device; wherein the target area includes at least two smart home devices; and the state data includes at least environmental state data;

[0008] constructing a state influence graph of the smart home device according to the state data and the control parameters;

[0009] According to the state data and the control parameters, a target bias term of the smart home device is calculated;

[0010] According to the target bias term and the control parameters, a local cost function of the smart home device is constructed, and a first control strategy of at least two smart home devices is generated;

[0011] Based on the local cost function, a global cost function of the target area is constructed according to the state influence graph;

[0012] According to the global cost function, the first control strategy is iteratively optimized to generate an optimal control strategy of at least two smart home devices.

[0013] In some embodiments of the present application, the state influence graph of the smart home device is constructed according to the state data and the control parameters, comprising:

[0014] The control parameters are divided into a continuous control parameter subset and a discrete control parameter subset;

[0015] A continuous control mapping set of the continuous control parameter subset and the state data is established;

[0016] A discrete control mapping set of the discrete control parameter subset and the state data is established;

[0017] The continuous control mapping set and the discrete control mapping set are combined to obtain a hybrid parameter structure mapping set;

[0018] The state influence graph of the smart home device is generated according to the hybrid parameter structure mapping set.

[0019] In some embodiments of the present application, the state data further includes human body sign data, and the target bias term of the smart home device is calculated according to the state data and the control parameters, comprising:

[0020] The target control parameters are generated according to the environmental state data and the human body sign data;

[0021] The target bias term of each smart home device is calculated according to the target control parameters and the control parameters of the smart home device.

[0022] In some embodiments of the present application, before the local cost function of the smart home device is constructed according to the target bias term and the control parameters, and the first control strategy of at least two smart home devices is generated, the method further comprises:

[0023] In a case where the target deviation term of each of the smart home devices is less than a preset threshold, a real-time control parameter of each of the smart home devices is acquired;

[0024] An optimal control strategy is obtained according to the real-time control parameter of each of the smart home devices.

[0025] 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 strategy of at least two of the smart home devices comprises:

[0026] The variational inequality problem of the global cost function is iteratively calculated according to the target control parameter by using a Lagrange multiplier relaxation and a sub-gradient response algorithm to generate a Nash equilibrium control strategy;

[0027] The first control strategy is optimized according to the target control parameter and the Nash equilibrium control strategy to generate the optimal control strategy of the target area.

[0028] 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 strategy of at least two of the smart home devices, the method further comprises:

[0029] The state data of the target area, the control parameter of the smart home device, and the optimal control strategy are combined to obtain a first application scenario.

[0030] The first application scenario is stored in a preset repository.

[0031] A second application scenario of a to-be-controlled area is acquired, and the second application scenario is composed of first state data of the to-be-controlled area and first control parameters of smart home devices in the to-be-controlled area.

[0032] The second application scenario is matched with the preset repository to obtain a matching result.

[0033] 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 comprises:

[0034] In a case where the matching is successful, a first application scenario matched with the application scenario of the to-be-controlled area is extracted from the preset repository to obtain the optimal control strategy; the successful matching includes the matching of the first state data and the state data, and the matching of the first control parameter and the control parameter.

[0035] To achieve the above object, a second aspect of an embodiment of the present application provides a smart home device control system, which comprises:

[0036] a data acquisition module configured to acquire state data of a target area and control parameters of smart home devices; wherein the target area comprises at least two smart home devices; and the state data comprises at least environmental state data;

[0037] a state construction module configured to construct a state influence graph of the smart home devices according to the state data and the control parameters;

[0038] a bias calculation module configured to calculate a target bias term of the smart home devices according to the state data and the control parameters;

[0039] a first construction module configured to construct a local cost function of the smart home devices according to the target bias term and the control parameters, and generate a first control strategy of the at least two smart home devices;

[0040] a second construction module configured to construct a global cost function of the target area according to the state influence graph based on the local cost function;

[0041] an update iteration module configured to iteratively optimize the first control strategy according to the global cost function, and generate an optimal control strategy of the at least two smart home devices.

[0042] To achieve the above object, a third aspect of the embodiment of the present application provides an electronic device, comprising: at least one control processor and a memory connected in communication 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 to enable the at least one control processor to execute the above-mentioned smart home device control method.

[0043] To achieve the above object, a fourth aspect of the embodiment of the present application 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.

[0044] The embodiment of the present application provides a smart home device control method, state data of a target area and control parameters of a smart home device are acquired; a state influence graph of the smart home device is constructed according to the state data and the control parameters; a target deviation term of the smart home device is calculated according to the state data and the control parameters; a local cost function of the smart home device is constructed according to the target deviation term and the control parameters, and a first control strategy of at least two smart home devices is generated; a global cost function of the target area is constructed according to the state influence graph based on the local cost function; and the first control strategy is iteratively optimized according to the global cost function, so that an optimal control strategy of the at least two smart home devices is generated, the game among the multiple devices is realized, the collaborative control and optimization of the multiple devices are realized, the scene applicability of the scheme is improved, and the individualized requirements of a user can be met.

[0045] It can be understood that the beneficial effects of the second aspect to the fourth aspect and the related technologies compared with the first aspect and the related technologies are the same, and the related description in the first aspect can be referred to, and details are not repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0046] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the description of the embodiments, taken in conjunction with the following drawings in which:

[0047] Figure 1 FIG. 1 is a flow diagram of a smart home device control method provided by an embodiment of the present application;

[0048] Figure 2 FIG. 2 is a structural diagram of a smart home device control training system provided by an embodiment of the present application;

[0049] Figure 3 FIG. 3 is a hardware structure diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the drawings, in which the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0051] In the description of the present application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or the sequence of indicated technical features.

[0052] In the description of the present application, it should be understood that the orientation description, such as the orientation or position relationship indicated by up, down and the like, is based on the orientation or position relationship shown in the drawings, only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0053] In the description of the present application, it should be noted that, unless otherwise explicitly limited, the words such as setting, installation, connection and the like should be understood in a broad sense, and the person skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0054] With the aggravation of the population aging trend in China, home health management, smart aging and digital medical care have become the focus of current social attention. As an important carrier of medical care, the smart home system is gradually developing from single device control to a comprehensive system integrating perception, decision-making and execution. Especially in special groups such as the elderly and chronic disease patients, higher requirements are put forward for personalized adjustment of the home environment, real-time response of the health status, and collaborative optimization of device control.

[0055] At present, the smart home system mostly takes a local controller or an APP application as the core, and completes the start-stop operation of a single device through fixed rules or simple sensing logic. Such a system lacks the ability to deeply model the user's health status, and it is 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 strategy coordination mechanism, which is prone to problems such as resource conflicts, control exclusion or inconsistent execution logic, further affecting user experience and energy efficiency.

[0056] Although some researches introduce scene recognition, voice interaction or remote control function modules, the core control logic is still mainly based on preset schemes, lacking scheduling ability for multi-objective optimization, and not realizing strategy coordination and game evolution control among devices. In the face of dynamic smart home scenes with multiple users, multiple devices and multiple tasks coexisting, the existing technology still has significant deficiencies in information integration, strategy coordination and personalized response, and it is difficult to meet the actual needs of smart health care, intelligent nursing and other complex scenes.

[0057] Based on this, the embodiments of the present application provide a smart home device control method and system, an electronic device and a medium, aiming to realize the organic unity of multi-device collaborative control, adaptive optimization and user satisfaction guarantee through the game among multiple devices, and improve the scene applicability of the scheme, which can meet the personalized requirements of users.

[0058] The smart home device control method and system provided by the embodiments of the present application, the electronic device and the medium are specifically described through the following embodiments. First, the smart home device control method in the embodiments of the present application is described.

[0059] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. The artificial intelligence (AI) is a theory, method, technology and application system for using a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.

[0060] The artificial intelligence basic technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0061] 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 in a terminal, can be applied in a server end, and can also be software running in a terminal or a server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server end can be configured as an independent physical server, can be configured as a server cluster or a distributed system composed of multiple physical servers, can also be configured as a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform, etc.; and the software can be an application for implementing the smart home device control method, etc., but is not limited to the above forms.

[0062] The application is operable in a multitude of generic or specific computer system environments or configurations. Examples of well known computing systems, environments, and / or configurations that can be suitable for use with the application include personal computers, server computers, handheld or laptop devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like, that perform particular tasks or implement particular abstract data types. The application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.

[0063] It should be noted that in each specific embodiment of the present application, when it is necessary to process relevant data related to the identity or characteristics of the user according to user information, user behavior data, user history data, and user location information, etc., the user's permission or consent will be obtained first, and 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 sensitive personal information of the user, the separate permission or separate consent of the user will be obtained through a pop-up window or a jump to a confirmation page, and after obtaining the separate permission or separate consent of the user, the necessary user-related data for enabling the embodiments of the present application to normally operate will be obtained.

[0064] To this end, with reference to Figure 1 The embodiments of the present application provide a smart home device control method, the method is applied to a central controller, the controller can be a server, can be an electronic device, can also be a mobile terminal, etc., which is not specifically limited here, and the method comprises the following steps S110 to S160:

[0065] Step S110, obtaining state data of a target area and control parameters of smart home devices; wherein the target area comprises at least two smart home devices; and the state data at least comprises environmental state data;

[0066] Step S120, constructing a state influence graph of the smart home devices according to the state data and the control parameters;

[0067] Step S130, calculating a target bias term of the smart home devices according to the state data and the control parameters;

[0068] Step S140, constructing a local cost function of the smart home devices according to the target bias term and the control parameters, and generating a first control strategy of the at least two smart home devices.

[0069] Step S150, constructing a global cost function of the target area according to the state influence graph based on the local cost function;

[0070] Step S160, iteratively optimizing the first control strategy according to the global cost function to generate an optimal control strategy of the at least two smart home devices.

[0071] In this step, first, the state data of the target area and the control parameters of the smart home devices are obtained, wherein the target area includes at least two smart home devices, and the state data includes environmental state data and human body sign data. Then, according to the obtained state data and control parameters, a state influence graph of the smart home devices is constructed to represent the mutual influence relationship between the devices.

[0072] Specifically, the state data of the target area refers to the environmental parameters and human physiological indicators obtained through sensors or user input, which can be collected by temperature sensors, humidity sensors, infrared human sensors, wearable devices or any smart home devices, for comprehensively sensing the environmental state and user health information in the target area, and providing a data basis for constructing the collaborative relationship between the devices. For example, the environmental state data is collected by temperature sensors, humidity sensors, light sensors, etc., and the human body sign data is collected by wearable devices, including physiological indicators such as body temperature, heart rate, blood pressure, etc.

[0073] The state influence graph refers to a topological model describing the mutual interaction between smart home devices, which can be constructed by a hybrid parameter structure mapping set. By quantifying the correlation between device control parameters and environmental state and human body signs, the problem of lack of unified modeling in multi-device collaborative control is solved.

[0074] Further, based on the state data and control parameters, a target bias term of the smart home device is calculated to reflect the difference between the current state and the target state. According to the target bias term and the control parameters, a local cost function of the smart home device is constructed, and a first control strategy of the at least two smart home devices is generated.

[0075] The target bias term refers to the difference between the actual state and the expected state of the smart home device, which can be calculated by the difference between the target control parameters and the actual control parameters, and is used to evaluate the control effect of a single device and provide optimization basis for the construction of the local cost function.

[0076] Further, based on the local cost function and the state influence graph, a global cost function of the target region is constructed to realize overall optimization. Finally, the first control strategy is iteratively optimized according to the global cost function to generate an optimal control strategy of at least two smart home devices, so as to quantify the dynamic correlation between devices by constructing the state influence graph, and realize collaborative control and resource optimization allocation of multiple smart home devices in a complex scene by combining the hierarchical cost function and the iterative optimization algorithm, thereby improving the system response speed and energy efficiency, and realizing collaborative control and global optimization of multiple smart home devices.

[0077] The local cost function and the global cost function refer to 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 to solve the device resource allocation conflict in a multi-objective scene through a hierarchical optimization structure; the iterative optimization refers to the process of dynamically adjusting the control strategy based on the global cost function, which can be realized by combining the Lagrange multiplier relaxation algorithm with the sub-gradient response calculation to ensure the convergence and stability of the multi-device control strategy in a dynamic environment through distributed collaborative solution.

[0078] In some embodiments, in the step S120 of constructing the state influence graph of the smart home device according to the state data and the control parameters, the following steps S210 to S250 are included:

[0079] Step S210, dividing the control parameters into a continuous control parameter subset and a discrete control parameter subset;

[0080] Step S220, establishing a continuous control mapping set of the continuous control parameter subset and the state data;

[0081] Step S230, establishing a discrete control mapping set of the discrete control parameter subset and the state data;

[0082] Step S240, combining the continuous control mapping set and the discrete control mapping set to obtain a hybrid parameter structure mapping set;

[0083] Step S250, generating the state influence graph of the smart home device according to the hybrid parameter structure mapping set.

[0084] In this step, the control parameters are divided into a continuous control parameter subset and a discrete control parameter subset. For example, parameters such as temperature, humidity, brightness, etc. that can be continuously adjusted are divided into the continuous control parameter subset, and parameters such as switch state, mode selection, etc. that are discretely adjusted are divided into the discrete control parameter subset.

[0085] The continuous control parameter subset preferably includes a power gradient of a temperature regulating device or a wind speed gear of an air purifier in the smart home device, and the discrete control parameter subset includes a switch state of a lighting device or a start-stop instruction of a curtain motor in the smart home device.

[0086] Further, a continuous control mapping set of the continuous control parameter subset and the state data is established, and a mapping relationship between the continuous control parameter and the environmental state data is preferably established by a polynomial regression method. For example, the continuous control mapping set establishes an association between the environmental temperature and the device power through a regression model.

[0087] Further, a discrete control mapping set of the discrete control parameter subset and the state data is established, and a mapping relationship between the discrete control parameter and the environmental state data is preferably established by a decision tree method. For example, the discrete control mapping set describes the change association between the device switch state and the illumination intensity through a state transition matrix.

[0088] Further, the continuous control mapping set and the discrete control mapping set are combined to obtain a hybrid parameter structure mapping set. Preferably, the hybrid parameter structure mapping set adopts a hierarchical fusion mechanism, and the continuous parameter mapping result is used as a bottom constraint condition, and the discrete parameter mapping result is used as an upper decision variable, so that a state influence graph of the smart home device is generated according to the hybrid parameter structure mapping set, the influence relationship of each control parameter on the environmental state is represented in the form of a directed graph, the classification processing of the continuous and discrete control parameters is realized, the mapping relationship between different types of parameters and the environmental state is established, and the state influence graph reflecting the influence of each device control parameter on the environmental state is generated. Further, the characteristics of different types of control parameters can be comprehensively captured, the accuracy and integrity of the state influence graph are improved, and a foundation is laid for subsequent control strategy optimization based on the state influence graph.

[0089] Taking an air conditioner and lighting device collaborative scene as an example, the temperature set value of the air conditioner is input into a regression model as a continuous parameter to generate a temperature change rate prediction value, and the lighting switch state is input into a state transition matrix as a discrete parameter to generate an illumination intensity change probability distribution. The hybrid parameter structure mapping set uses the temperature change rate as a boundary condition for illumination adjustment to limit the lighting brightness adjustment range to avoid local overheating. Through hierarchical fusion of the continuous and discrete parameters, the state influence graph can accurately reflect the dynamic coupling effect between devices, for example, the air conditioner cooling causes the lighting device to reduce the brightness to maintain human comfort, thereby improving the strategy generation precision of multi-device collaborative control.

[0090] In some embodiments, in step S130, a target bias term of the smart home device is calculated according to the state data and the control parameter, including steps S310 to S320:

[0091] Step S310, generating a target control parameter according to the environmental state data and the human body sign data;

[0092] Step S320, calculating a target deviation term of each smart home device according to the target control parameter and the control parameter of the smart home device.

[0093] In this step, the target control parameter is generated according to the environmental state data and the human body sign data. For example, the target temperature setting value of the air conditioner is calculated according to the indoor temperature and the user body temperature; the target brightness value of the light is calculated according to the indoor light intensity and the user heart rate.

[0094] Further, the target control parameter is compared with the current control parameter of the smart home device, and the target deviation term of each smart home device is calculated. The target control parameter is generated by setting a sign threshold interval and jointly mapping with the environmental parameter. For example, the difference between the target temperature of the air conditioner and the current temperature is calculated, and the difference between the target brightness of the light and the current brightness is calculated, so as to comprehensively consider the environmental state and the user physiological state, dynamically generate the individualized device control target, and calculate the deviation between the current state and the target state of the device, thereby realizing the real-time response to the user health state and the environmental change, and improving the individualized adjustment ability of the smart home system and the user comfort.

[0095] Specifically, the target deviation term is calculated by a difference matrix of the target control parameter and the current control parameter of the device. The dimension of the difference matrix is consistent with 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 sign data from the threshold value. When the sign is abnormal, the weight of the deviation term of the corresponding device is increased to a preset upper limit value.

[0096] In some embodiments, before step S140 of constructing a local cost function of the smart home device according to the target deviation term and the control parameter, and generating a first control strategy of at least two smart home devices, the following steps S410 to S420 are included:

[0097] Step S410, acquiring a real-time control parameter of each smart home device when the target deviation term of each smart home device is less than a preset threshold value;

[0098] Step S420, obtaining an optimal control strategy according to the real-time control parameter of each smart home device.

[0099] In this step, when the target deviation term of each smart home device is less than a preset threshold value, it indicates that the device control parameter has met the dynamic demand of the target area, and then the real-time control parameter of each smart home device is acquired, so as to avoid redundant optimization by directly extracting the real-time parameter as the optimal strategy.

[0100] wherein the preset threshold is set according to an allowable fluctuation range of the environmental state data and the human body sign data, for example, the temperature deviation allowable range is ±0.5℃, and the illumination intensity deviation allowable range is ±50 lux. The real-time control parameters include the current running mode of the device, the power value, and the sensor feedback data.

[0101] For example, for an air conditioning device, the current set temperature, air speed, mode, and the like can be acquired as real-time control parameters; for a lighting device, the current brightness, color temperature, and the like can be acquired as real-time control parameters; and for a humidifier, the current humidity set value, fog amount, and the like can be acquired as real-time control parameters.

[0102] Further, the acquired real-time control parameters of each device are taken as initial values, and the optimal control parameter combination of each device is calculated by an optimization algorithm in combination with the environmental state data and the user preference to form an optimal control strategy. Thus, in the case where the running state of the device has approached the target state, fine tuning and optimization can be directly performed based on the current real-time parameters, the current control parameters can be quickly acquired and optimized in the case where the running state of the device is already relatively ideal, and the efficiency of the control strategy generation is improved. Meanwhile, unnecessary large-scale adjustment can be avoided by directly using the real-time parameters for fine tuning, energy consumption is reduced, and user comfort is improved.

[0103] In some embodiments, in the step S160 of iteratively optimizing the first control strategy according to the global cost function to generate the optimal control strategy of the at least two smart home devices, the following steps S510 to S520 are included:

[0104] The step S510 comprises: iteratively calculating a variational inequality problem of the global cost function according to the target control parameters by using a Lagrange multiplier relaxation and a subgradient response algorithm to generate a Nash equilibrium control strategy.

[0105] The step S520 comprises: optimizing the first control strategy according to the target control parameters and the Nash equilibrium control strategy to generate the optimal control strategy of the target region.

[0106] In this step, the variational inequality problem of the global cost function is iteratively calculated according to the target control parameters by using a Lagrange multiplier relaxation and a subgradient response algorithm to generate a Nash equilibrium control strategy.

[0107] Preferably, the Lagrange multiplier relaxation decomposes the original constrained optimization problem into multiple sub-problems by introducing a relaxation factor, and the sub-gradient response algorithm adopts a sub-gradient projection method in non-smooth optimization to update the strategy parameters. The target control parameters include a multi-dimensional vector of temperature set value, light intensity threshold and user heart rate benchmark value, and the error tolerance is set to 0.5%-1.2% during the generation of the Nash equilibrium control strategy, and the strategy update step is controlled within the range of 0.05-0.15. The iteration solving number of the variational inequality problem is set to 50-200 times, and the second order norm change of the strategy vector is detected after each iteration, and the termination condition is triggered when the change is less than 0.01.

[0108] Further, the first control strategy is optimized according to the target control parameters and the Nash equilibrium control strategy to generate an optimal control strategy for the target area, realizing global optimization of multi-device collaborative control, avoiding sub-optimal solution caused by single-device independent decision, improving overall control effect, and through two-stage solving of Nash equilibrium and target function optimization, the interests of each device are balanced and global optimization is realized, thereby realizing efficient collaborative control of the smart home system in a complex dynamic environment.

[0109] In some embodiments, after the optimal control strategy of at least two smart home devices is generated by iteratively optimizing the first control strategy according to the global cost function in step S160, the following steps S610-S640 are included:

[0110] Step S610, combining 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;

[0111] Step S620, storing the first application scenario to a preset repository;

[0112] Step S630, obtaining a second application scenario of a to-be-controlled area, the second application scenario being composed of first state data of the to-be-controlled area and first control parameters of smart home devices in the to-be-controlled area;

[0113] Step S640, matching the second application scenario with the preset repository to obtain a matching result.

[0114] In this step, the state 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, the target area is the living room, the state 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 air conditioner temperature by 1°C, reduce the dehumidifier humidity by 10%, and adjust the curtain opening to 60%. By combining the state data of the target area, the control parameters of the smart home devices, and the optimal control strategy, the first application scenario is obtained.

[0115] Furthermore, the first application scenario is stored in a preset storage repository, wherein the preset storage repository may be a cloud database or a local memory.

[0116] Furthermore, a second application scenario of the area to be controlled is obtained, and 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 device in the area to be controlled. The second application scenario is then matched with the preset storage library to obtain a matching result, thereby quickly identifying similar scenarios and applying the optimized control strategy, thereby improving control efficiency and accuracy.

[0117] In some embodiments, in step S640 , matching the second application scenario with the data stored in the preset storage repository to obtain a matching result includes the following step S710 .

[0118] Step S710: If the match is successful, extract the first application scenario that matches the application scenario of the area to be controlled from the preset storage library to obtain the optimal control strategy; the successful match includes matching the first state data with the state data, and matching the first control parameter with the control parameter.

[0119] In this step, by matching the first state data with the state data and matching the first control parameter with the control parameter, 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 storage library to obtain the optimal control strategy, thereby achieving scene matching and strategy reuse, reducing repeated calculations and optimization processes, reducing system resource consumption, and thereby improving the overall operating efficiency to achieve scenario-based control and optimization of the smart home system.

[0120] For example, when the environmental sensors of the target area detect indoor temperature of 28℃, humidity of 65%, and user body surface temperature of 36.8℃, combined with the air conditioner set temperature of 26℃, dehumidifier power of 800W and other parameters, an optimal strategy containing temperature adjustment curve and humidity control timing is generated, a first application scenario containing a 6-dimensional feature vector is formed and stored in the storage library. When the area to be controlled detects temperature of 27.5℃, humidity of 63%, and user body surface temperature of 36.7℃, the system extracts the feature vector in the storage library for comparison, finds that the distance with the vector of scenario No. S015 is 0.12, which is lower than the threshold value of 0.15, directly calls the air conditioner stage cooling and dehumidifier intermittent operation strategy under the scenario, and shortens the response time from 8.2 seconds required by conventional optimization to 1.5 seconds.

[0121] In some embodiments, a modeling framework with strategy interaction capability is constructed with the goal of coordination between devices, realizing the control system of smart home devices.

[0122] 1. Control variable modeling:

[0123] Let the system be at time The control variable vector is:

[0124] ;

[0125] Wherein, represents the transpose of the current calculation vector, and the control variable set can be divided into a continuous control variable index set and a discrete control variable index set , which respectively represent temperature setting, wind speed adjustment (continuous) and mode selection, switch control (discrete) and the like; represents the control action of the th device at time , which can be a real value or an enumeration type; represents the vector composed of all device control actions, which is the main decision variable of optimization; represents the variable classification index set, which is predefined and derived from the device function configuration table.

[0126] 2. System state and dynamics:

[0127] The state data in the system includes environmental, user, physiological index and other dimensional data, which are defined as:

[0128] ;

[0129] Specifically, the state evolves with the change of the control variable:

[0130]

[0131] ​where, is the state transition function, represents external disturbance or perception error, represents the th state variable, such as temperature, humidity, PM2.5, heart rate, etc., obtained by sensors or state calculation; represents the current time environment-user joint state, represents the state transition function, which can be a data-driven model or constructed by device response rules, represents the disturbance term, considering noise, uncertainty factors and modeling errors.

[0132] 3. Local cost function modeling (including control coupling terms):

[0133] Each device has a local cost function of the following form:

[0134] ;

[0135] where the first term is the system state error used to measure the degree of 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 reflects that the greater the control intensity, the higher the energy consumption; the third term is the conflict term, which produces a loss if and are controlled at the same time and the targets are inconsistent; represents the conflict severity coefficient between devices; represents the th device individual objective function, including comfort, energy consumption and conflict terms; represents the cost function weighting factor, which comes from user preference settings or device type adjustment parameters; represents the state target that the device is expected to achieve, such as "22℃, low noise", etc.; represents all devices that conflict with the current device table; represents the control conflict loss function, such as two devices with opposite targets (air conditioner and ventilation) causing interference; represents the conflict severity penalty factor.

[0136] 4. Nash equilibrium derivation:

[0137] Due to the interaction of control behavior between devices, the stable running state of the system should satisfy the following Nash equilibrium conditions:

[0138] ;

[0139] Specifically, each device optimizes its own cost function to achieve the optimal response given the fixed strategies of other devices, forming an equilibrium state where no device changes its strategy , represents the optimal control strategy of device , which achieves the minimum cost given the fixed behaviors of other devices; represents the feasible control space of device , which is defined by its control precision, operating range, and other physical limitations.

[0140] 5. Control constraints and interpretations:

[0141] To ensure system safety, physical feasibility, and human comfort, the control behavior needs to satisfy the following constraints:

[0142] First, the boundary constraints for continuous control variables are:

[0143] ;

[0144] where the control output cannot exceed the device's upper limit or safety interval (e.g., brightness, wind speed).

[0145] Second, the value constraints for discrete control variables are:

[0146] ;

[0147] where, for example, switch devices, curtain modes, etc., their control values must come from a predefined discrete set.

[0148] Third, the state index constraints are:

[0149] ;

[0150] where, for example, temperature, PM2.5, noise intensity, etc., must be kept within the healthy and comfortable interval.

[0151] Fourth, the response time delay constraints are:

[0152] ;

[0153] where the system needs to complete action execution within a specified time after input changes to ensure user experience.

[0154] Specifically, , represent the minimum and maximum allowed values of continuous variables, derived from device specifications or presets; represent the value range set of discrete control variables, such as {on, off}, {high, medium, low}; , represent the health or comfort interval limits of state variables, such as temperature interval [20, 26]℃. denotes the response delay and the upper limit of system tolerance, from performance specification or service design.

[0155] 6. The solution of the system objective:

[0156] The final control problem of the system is formulated as: finding a combination of control variables that meets all the above constraints, so that each device reaches its own optimal response, thus achieving a coordinated balance at the system level:

[0157] ;

[0158] ;

[0159] ;

[0160] ;

[0161] ;

[0162] wherein, denotes the optimal control solution of the whole system, which is the set of game equilibrium solutions, and the control vector calculated by the system.

[0163] The modeling of this embodiment reflects the strategic dependence and competition between control variables, meeting the needs of multi-objective dynamic adjustment and multi-device collaborative optimization, and is the basis for realizing the control mechanism of high responsiveness, high energy efficiency and high stability in the smart home scenario.

[0164] For example, the current smart home system includes three typical devices: air conditioner (denoted as device A), light (device B) and air purifier (device C). Each device has adjustable control parameters, such as temperature setting of air conditioner, brightness level of light, and wind speed or on-off state of purifier, and the system organizes all the control variables of the devices into a vector.

[0165] First, the system obtains the current working states of devices A, B and C, denoted as a, b and c, through environmental perception and device feedback data. For example, a represents the current room temperature, b represents the current light brightness, and c represents the current wind speed or purifier on-off state. The system integrates these states into the overall state vector of the system for subsequent analysis and control calculation.

[0166] Secondly, the system generates corresponding control targets according to the current behavior scenario of the user (such as "sleeping"). At this time, the system determines that device A needs to adjust the temperature to the target value X to promote the user's sleep quality; the current brightness of device B has met the requirements and does not need further control; device C needs to increase the wind speed to a medium speed state 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 adjust to Y.

[0167] Then, the system constructs a comprehensive utility function according to 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 the air flow interference between the air conditioner and the purifier), and sets a reasonable control strategy according to the device type and response ability. The system evaluates the control cost of each device through the utility function, and determines a set of optimal control instructions that make the overall system coordination optimal through multiple rounds of strategy iteration calculation.

[0168] Finally, the system converts this set of optimal control strategies into actual device recognizable control commands, such as "set the air conditioner temperature to 25°C" and "purifier starts medium speed mode", and synchronously issues them to all related devices, achieving optimal adjustment and closed-loop control of the entire environment state.

[0169] In some embodiments, by constructing a continuous + discrete control variable structure mapping system, designing a coupling modeling mechanism of multiple cost function combinations, and introducing a response solver driven by variational inequality to efficiently and stably generate strategy equilibrium, and through action mapping and feedback loop mechanism, an end-to-end adaptive control process is realized, with advantages such as strong generalization, high adaptability, and low communication volume, as follows:

[0170] Step 1: Modeling and variable structure design, input: control device set and its control type (continuous variable and discrete variable), current system time step , multi-modal perception data: environmental state (temperature, humidity, light, PM2.5, etc.) and user state (heart rate, body temperature, activity, etc.), state transition knowledge, prior coupling structure (such as influence graph); output: control variable vector , and index division 、 , state variable vector used to describe the coupling mapping function set of the current perception state, control variable and state variable of the system , and the local cost function of each device .

[0171] 1. Control variable decomposition and structure mapping:

[0172] In the multi-device smart home control scenario, the device control variables usually contain different dimensions and types, including continuous variables (e.g., temperature setting, wind speed adjustment) and discrete variables (e.g., mode switch, gear selection). To achieve the unified modeling of heterogeneous control variables, this paper adopts the structured mixed variable modeling mechanism (MIP-Structure Mapping) to construct all device control variables as a mixed control vector :

[0173] ;

[0174] where, here represents the transpose of the current calculation vector, and the variable set is divided into two subsets:

[0175] The set of continuous control variables , where , the control variable satisfies ;

[0176] The set of discrete control variables , where , the control variable satisfies , is a finite set.

[0177] Example: if represents the air conditioner set temperature, it is a continuous variable ; if represents the curtain opening and closing state, it is a discrete variable .

[0178] This modeling structure not only maintains the integrity of the control variables, but also provides distinguishable variable structure mapping for subsequent optimal response algorithms, which is beneficial to the design of algorithm feasibility detection and group optimization.

[0179] 2. State influence modeling and device coupling representation:

[0180] The system state is composed of multiple dimensions of environmental and user states, denoted as:

[0181] ;

[0182] where, may represent temperature, humidity, air quality, illumination, user comfort, etc.

[0183] Considering the heterogeneity and nonlinearity of the influence of control variables on state variables, this embodiment constructs a linear-nonlinear hybrid coupling influence graph (HCIG) to establish the action path of 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:

[0184]

[0185] wherein, is a nonlinear state transition function, represents a disturbance term.

[0186] Example: Indoor PM2.5 state Affected by air purifier wind speed , which can be modeled as:

[0187] ;

[0188] The state coupling between devices occurs indirectly through shared state variables. For example, air conditioners and curtains both affect temperature and light intensity, and conflict regulation is needed to prevent target conflicts.

[0189] 3. Local objective function construction and coordination cost design:

[0190] A cost function is constructed for each control device to measure its operation effect. This paper adopts a partially separable convex cost model, which has the following structure:

[0191] ;

[0192] Wherein: 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 strength of the device; and the third term represents the control coupling cost with other devices (such as simultaneous operation of cooling and heating devices).

[0193] Example: The air conditioner aims to maintain the room temperature , and avoid simultaneous operation with the heater, and the cost function can be written as:

[0194] ;

[0195] In addition, to achieve time-varying self-adaptation of the conflict cost between devices, a dynamic conflict factor is introduced to adjust the conflict strength of the device, so that the model has higher scene adaptability.

[0196] Step two: response strategy generation and equilibrium solving, specifically: through the game framework, the control conflict is modeled as a multi-participant strategy coupling problem, and a low-communication, fast-converging optimal response equilibrium solving process is designed, specifically using the LS-BRD mechanism (Lagrangian Subgradient Best-Response Dynamics), the game problem is converted into a generalized convex game problem with coupling constraints, and through the Lagrangian relaxation and subgradient response algorithm, the Nash equilibrium control strategy is generated, ensuring strategy coordination, solving efficiency and convergence stability.

[0197] wherein, input: control variable structure and type index , , ; local objective function set ; conflict penalty coefficient ; optimization algorithm parameters: step size , tolerance , relaxation coefficient ; feasible solution space definition and response constraints. Output: optimal response strategy combination ; feasible strategy candidate set ; the utility evaluation value corresponding to each strategy ; optional: evolution trajectory, variation residual, convergence index.

[0198] 1. Control game modeling as a convex game problem:

[0199] In the foregoing 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, the entire system is modeled as a generalized convex game (Generalized Convex Game) problem.

[0200] The game model is formalized as:

[0201] ;

[0202] wherein, is the feasible region of the control variable, which can be a continuous interval or a discrete set.

[0203] The strategy space of this problem has coupling terms (i.e. explicitly depends , ), so it is converted into a multi-objective optimization problem with joint constraints, and further described by the variational inequality theory.

[0204] 2. Optimal response iterative solving mechanism:

[0205] To solve the equilibrium of the above game, the embodiment adopts the best response dynamics, and each device updates itself to minimize the cost function when other strategies are fixed.

[0206] The specific update rule is as follows:

[0207] ;

[0208] Considering With good convex structure, this paper introduces the Lagrange multiplier relaxation mechanism to eliminate the coupling effect of the conflict term, and uses the sub-gradient descent method for optimal response update to avoid non-convergence caused by direct decoupling failure.

[0209] 3. Variational inequality equilibrium point solving mechanism:

[0210] To theoretically guarantee 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:

[0211] ;

[0212] The VI problem is expressed as:

[0213] ;

[0214] The projection algorithm is used to solve the VI problem, which can converge to the game equilibrium point. This method has theoretical convergence guarantee and is suitable for mixed strategy space structure (i.e. mixed type).

[0215] Example: In a smart home system containing continuous adjustment and discrete switching, the optimal control combination of all devices under the current environment can be obtained by the VI solution.

[0216] Step three: control policy execution and mapping, specifically: through the device-level state translator (DLST: Device-Level State Translator) oriented to heterogeneous devices, the mapping relationship from the control vector to the device instruction set is constructed; at the same time, in order to reduce the overhead brought by frequent solving, the policy table approximation (PTA: Policy Table Approximation) based on state fluctuation is introduced, to improve the response speed and robustness of the control system.

[0217] Wherein, input: current control policy combination , control mapping function Device control interface protocol and mapping template, current system state State change threshold Policy cache table Output: actual execution command set System state after execution Sliding state window Trend estimation, policy cache update result

[0218] 1. Policy mapping and physical action conversion mechanism:

[0219] Specifically, the control variable and the device control instruction establish a relationship through a mapping function :

[0220] ;

[0221] For different device types, it can be a quantitative function, a lookup table mapping, or an encoding conversion. Specifically, for continuous control: Map the real-valued variable to a protocol parameter through a linear or piecewise function; for discrete control: Map to a finite set of control actions, such as {on, off} or {low, medium, high}.

[0222] For example, when the optimal control variable is (indicating the percentage of brightness), it is converted to the device protocol command \setBrightness(75) and issued to the intelligent lighting system.

[0223] The mapping mechanism supports rapid generation of control instructions and compatibility with different brands of devices, with good portability and scalability.

[0224] 2. State feedback collection and incremental update mechanism:

[0225] After the control policy is executed, the system needs to monitor the environment and user state in real time and feed back to the decision module to update the system state , forming a closed-loop control.

[0226] 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 last period:

[0227]

[0228] and estimates the current state change trend through a trend function :

[0229] ;

[0230] If the state change trend deviates significantly from the model prediction result, the error correction module is triggered to correct the state estimation model, thereby enhancing the system's ability to operate stably under real disturbances and effectively avoiding control oscillation problems caused by feedback distortion.

[0231] For example, if the PM2.5 readings are continuously = If the fluctuation is greater than the preset threshold within 5 moments, the system will automatically backtrack to the pollution source intervention mechanism and adjust the state transfer function The influencing parameters in .

[0232] When the state change is within the acceptable fluctuation range, directly reuse the strategy combination obtained in the previous round .

[0233] The specific trigger conditions are as follows:

[0234] ;

[0235] in, It is the state change threshold, which can be set dynamically according to the application scenario.

[0236] On this basis, the system maintains a limited size policy cache table , records the optimal strategy combination under common conditions, allowing fast table lookup strategy calls:

[0237] ;

[0238] in, Represents a known policy stored in the cache table.

[0239] For example, in summer nighttime sleep scenarios, temperature, lighting, and noise levels are highly stable. Policy caching can reuse long-term strategies such as "mid-range air conditioning, closed curtains, and low-speed air purifiers," avoiding repeated game reasoning. This significantly improves system execution efficiency while ensuring the rationality of policy responses. This is particularly suitable for deployment on resource-constrained edge control devices.

[0240] Step 4: Design an end-to-end control feedback closed-loop. Specifically, this involves a closed-loop state consistency assessment mechanism (WCA) for state-driven updates. This mechanism dynamically detects the effectiveness of feedback signals and the consistency of system behavior. It also designs stability triggering and slip prediction mechanisms to improve the long-term robustness of the control system.

[0241] Among them, input: current system status and historical state sequence , the previous round of control strategy ; Stability judgment threshold ; Sliding prediction window length Output: stability judgment result (whether to trigger recalculation), next moment state prediction value ; Trend estimation of each state variable , prediction error ;Updated closed-loop input status .

[0242] In order to realize end-to-end closed-loop control logic, this embodiment integrates the control strategy generation module, actuator action interface and state perception subsystem into an integrated structure to unify scheduling and communication.

[0243] The structure includes the following four core modules:

[0244] Control Strategy Generator : Based on the current state Calculate the optimal strategy ;

[0245] Device Action Mapper :Strategy Convert to device instructions ;

[0246] Behavior Executor : Actually drives the physical device to complete the control action;

[0247] State Awareness and Correction : Collect and correct The state vector at time .

[0248] The structure has interface encapsulation, and all modules are connected through data flow Achieve a closed loop control process.

[0249] During continuous control cycles, if environmental conditions change little or device status is stable, frequent policy recalculation can increase system load and response latency. Therefore, this embodiment introduces a "policy stability trigger mechanism" that automatically skips policy generation when the system status is in the "low volatility range" and retains the previous policy.

[0250] Assume that the state change judgment function is:

[0251] ;

[0252] Setting thresholds ,when When , it is determined to be a stable section:

[0253] ;

[0254] This mechanism can avoid frequent recalculation caused by small disturbances and ensure stable operation of the control process.

[0255] Example: If the bedroom temperature fluctuates less than 0.5°C within 3 minutes , the system does not recalculate the air conditioning strategy, maintaining the current set value.

[0256] Considering that the control system has a certain hysteresis to state changes, this embodiment further designs a short-term prediction mechanism based on a sliding window to anticipate the possible state deviation in the next period, thereby providing advance preparation for strategy calculation.

[0257] Let the state prediction window be , a linear extrapolation model is used to estimate each dimension of the state:

[0258] ;

[0259] Where, , when the prediction result deviates greatly from the current state (i.e. ), the strategy updater or device preheating time can be activated in advance.

[0260] Example: Predicting that the air humidity will rise above the threshold within the next 2 minutes due to user showering behavior, the system activates the dehumidification device in advance to improve user comfort experience and improve the reaction speed and overall intelligence of the control chain.

[0261] As shown in Figure 2 , some embodiments of the present application provide an intelligent home device control system, which 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:

[0262] The data acquisition module 210 is used to acquire state data of a target area and control parameters of intelligent home devices; wherein the target area includes at least two intelligent home devices; and the state data at least includes environmental state data.

[0263] The state construction module 220 is used to construct a state influence graph of the intelligent home devices according to the state data and the control parameters.

[0264] The deviation calculation module 230 is used to calculate a target deviation term of the intelligent home devices according to the state data and the control parameters.

[0265] The first construction module 240 is used to construct a local cost function of the intelligent home devices according to the target deviation term and the control parameters, and generate a first control strategy of at least two intelligent home devices.

[0266] The second construction module 250 is configured to construct a global cost function of the target area according to the state influence graph based on a local cost function.

[0267] The update iteration module 260 is configured to iteratively optimize the first control strategy according to the global cost function to generate an optimal control strategy of the at least two smart home devices.

[0268] In some embodiments, the state construction module 220 can include dividing the control parameters into a continuous control parameter subset and a discrete control parameter subset.

[0269] In some embodiments, the state construction module 220 can include establishing a continuous control mapping set of the continuous control parameter subset and the state data.

[0270] In some embodiments, the state construction module 220 can include establishing a discrete control mapping set of the discrete control parameter subset and the state data.

[0271] In some embodiments, the state construction module 220 can include combining the continuous control mapping set and the discrete control mapping set to obtain a hybrid parameter structure mapping set.

[0272] In some embodiments, the state construction module 220 can include generating the state influence graph of the smart home devices according to the hybrid parameter structure mapping set.

[0273] In some embodiments, the deviation calculation module 230 can include generating the target control parameter according to the environmental state data and the human body sign data.

[0274] In some embodiments, the deviation calculation module 230 can include calculating the target deviation term of each smart home device according to the target control parameter and the control parameter of the smart home device.

[0275] In some embodiments, the first construction module 240 can include obtaining the real-time control parameter of each smart home device in a case that the target deviation term of each smart home device is less than a preset threshold.

[0276] In some embodiments, the first construction module 240 can include obtaining the optimal control strategy according to the real-time control parameter of each smart home device.

[0277] In some embodiments, the update iteration module 260 can include iteratively calculating a variational inequality problem of the global cost function according to the target control parameter by a Lagrange multiplier relaxation and a subgradient response algorithm to generate a Nash equilibrium control strategy.

[0278] In some embodiments, the updating iteration module 260 can comprise: optimizing the first control strategy according to the target control parameter and the Nash equilibrium control strategy, to generate an optimal control strategy of the target area.

[0279] In some embodiments, the updating iteration module 260 can comprise: combining the state data of the target area, the control parameter of the smart home device, and the optimal control strategy to obtain the first application scenario.

[0280] In some embodiments, the updating iteration module 260 can comprise: storing the first application scenario to a preset repository.

[0281] In some embodiments, the updating iteration module 260 can comprise: obtaining a second application scenario of the to-be-controlled area, the second application scenario being composed of first state data of the to-be-controlled area and first control parameter of the smart home device in the to-be-controlled area.

[0282] In some embodiments, the updating iteration module 260 can comprise: matching the second application scenario with the preset repository to obtain a matching result.

[0283] In some embodiments, the updating iteration module 260 can comprise: in the case of successful matching, extracting the first application scenario matched with the application scenario of the to-be-controlled area from the preset repository to obtain an optimal control strategy; the successful matching comprises matching of the first state data and the state data, and matching of the first control parameter and the control parameter.

[0284] It should be noted that the smart home device control system provided in the embodiment and the smart home device control method described above are based on the same inventive concept, and therefore the related content of the smart home device control method described above is also applicable to the content of the smart home device control system, and therefore, the details are not repeated here.

[0285] In order to, the system obtains state data of a target area and control parameters of smart home devices; constructs a state influence graph of the smart home devices according to the state data and the control parameters; calculates a target bias 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 bias term and the control parameters, to generate a first control strategy of at least two smart home devices; constructs a global cost function of the target area according to the state influence graph based on the local cost function; iteratively optimizes the first control strategy according to the global cost function, to generate an optimal control strategy of the at least two smart home devices. In this way, multi-device collaborative control and optimization can be achieved through the game among multiple devices, and the scene applicability of the scheme is improved, which can meet the individualized requirements of users.

[0286] The embodiment of the present application further provides an electronic device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the smart home device control method when executing the computer program.

[0287] As Figure 3 , Figure 3 The hardware structure schematic diagram of the electronic device provided by the embodiment of the present application is shown in the figure, and the electronic device comprises:

[0288] at least one battery;

[0289] at least one memory;

[0290] at least one processor;

[0291] at least one program;

[0292] The program is stored in the memory, and the processor executes the at least one program to implement the smart home device control method provided by the embodiment of the present application.

[0293] The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a vehicle-mounted computer, etc.

[0294] The electronic device of the embodiment of the present application will be described in detail below.

[0295] The processor 1600 can be implemented in the form of a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided by the embodiment of the present application.

[0296] 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, and when the technical solutions provided by the embodiment of the present application are implemented by software or firmware, the related program codes are saved in the memory 1700 and are called and executed by the processor 1600 to implement the smart home device control method.

[0297] The input / output interface 1800 is used to realize information input and output.

[0298] The communication interface 1900 is configured to realize the communication interaction between the device and other devices, and can realize the communication through a wired manner (for example, a USB, a network cable, or the like) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, or the like).

[0299] The bus 2000 is configured to transmit information between various components (for example, the processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900) of the device.

[0300] The processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900 are connected to each other through the bus 2000 to realize the communication connection between the device.

[0301] The storage medium is a computer readable storage medium, and the computer readable storage medium stores computer executable instructions. The computer executable instructions are used to make the computer execute the intelligent home device control method.

[0302] The memory is a non-transitory computer readable storage medium, and can be used to store a non-transitory software program and a non-transitory computer executable program. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, for example, at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory that is remotely arranged relative to the processor, and the remote memory can be connected to the processor through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0303] The embodiments described in the embodiments of the present application are used to more clearly illustrate 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 can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0304] Those skilled in the art can understand that the technical solutions shown in the drawings do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than the drawings, or combine certain steps or different steps.

[0305] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to realize the purpose of the embodiments of the present application.

[0306] Those skilled in the art can understand that all or some of the steps in the method disclosed above, the function modules / units in the system and the device can be implemented as software, firmware, hardware or appropriate combination thereof.

[0307] The terms "first", "second", "third", "fourth" and the like in the description of the application and in the claims, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of these terms herein is to be construed to cover a general order and / or structure unless otherwise indicated. Furthermore, the terms "comprise", "comprising", "has", "having", "includes", "including", "contain", "containing" or any other similar forms are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises, has, includes, contains items or components does not include items or components not explicitly recited. The terms "a" or "an", as used herein in the detailed description and in the claims, mean "one or more" or "at least one", unless otherwise indicated.

[0308] It should be understood that, in the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that there are three cases: only A, only B, and A and B at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least 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 singular or plural.

[0309] In several embodiments provided in the present 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 schematic, and the division of units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0310] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0311] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0312] If the integrated unit is realized 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 solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The 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 embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0313] The above is a specific description of the preferred implementation of the embodiments of the present application, but the embodiments of the present application are not limited to the above implementation. Those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the embodiments of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the embodiments of the present application.

[0314] The embodiments of the present application have been described in detail above in combination with the drawings, but the present application is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the purpose of the present application.

Claims

1. A smart home device control method, characterized by, The method comprises: acquiring state data of a target area and control parameters of smart home devices; wherein the target area comprises at least two smart home devices; and the state data comprises at least environmental state data; constructing a state influence graph of the smart home devices according to the state data and the control parameters; calculating target bias terms of the smart home devices according to the state data and the control parameters; constructing a local cost function of the smart home devices according to the target bias terms and the control parameters, to generate a first control strategy of at least two smart home devices; constructing a global cost function of the target area according to the state influence graph based on the local cost function; iteratively optimizing the first control strategy according to the global cost function to generate an optimal control strategy of at least two smart home devices; the constructing a state influence graph of the smart home devices according to the state data and the control parameters comprises: dividing the control parameters into a continuous control parameter subset and a discrete control parameter subset; establishing a continuous control mapping set of the continuous control parameter subset and the state data; establishing a discrete control mapping set of the discrete control parameter subset and the state data; combining the continuous control mapping set and the discrete control mapping set to obtain a hybrid parameter structure mapping set; generating a state influence graph of the smart home devices according to the hybrid parameter structure mapping set; the state data further comprises human body sign data, and the calculating target bias terms of the smart home devices according to the state data and the control parameters comprises: generating target control parameters according to the environmental state data and the human body sign data; calculating target bias terms of each smart home device according to the target control parameters and the control parameters of the smart home devices; the process of constructing the local cost function of the smart home devices is further based on an energy consumption term and a conflict term of the smart home devices, wherein the energy consumption term is the energy consumption of the smart home devices, and the conflict term is a loss generated when the smart home devices are simultaneously controlled; the process of constructing the local cost function of the smart home devices is further based on a device type adjustment parameter and a control conflict loss function of each smart home device, wherein the control conflict loss function is based on other devices that conflict with the current smart home device; the state influence graph is in the form of a directed graph; the iteratively optimizing the first control strategy according to the global cost function to generate an optimal control strategy of at least two smart home devices comprises: iteratively calculating a variational inequality problem of the global cost function according to the target control parameters by a Lagrange multiplier relaxation and a 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. 2.The smart home device control method of claim 1, wherein, Before the constructing the local cost function of the smart home device according to the target bias term and the control parameter, and generating the first control strategy of at least two smart home devices, the method further comprises: In the case that the target bias term of each smart home device is less than a preset threshold, obtaining the real-time control parameter of each smart home device; According to the real-time control parameter of each smart home device, obtaining the optimal control strategy. 3.The smart home device control method of claim 1, wherein, After the iteratively optimizing the first control strategy according to the global cost function, and generating the optimal control strategy of at least two smart home devices, the method further comprises: Combining the state data of the target area, the control parameter of the smart home device, and the optimal control strategy, obtaining a first application scenario; Storing the first application scenario to a preset repository; Obtaining a second application scenario of a to-be-controlled area, the second application scenario being composed of first state data of the to-be-controlled area and first control parameter of a smart home device in the to-be-controlled area; Matching the second application scenario with the preset repository, and obtaining a matching result. 4.The smart home device control method of claim 3, wherein, The matching the second application scenario with the stored data in the preset repository, and obtaining a matching result, comprises: In the case of successful matching, extracting the first application scenario matched with the application scenario of the to-be-controlled area from the preset repository, and obtaining the optimal control strategy; the successful matching comprises matching the first state data with the state data, and matching the first control parameter with the control parameter.

5. A smart home device control system, characterized by, The system comprises: A data acquisition module, configured to acquire state data of a target area and control parameter of a smart home device; wherein the target area comprises at least two smart home devices; and the state data at least comprises environmental state data; A state construction module, configured to construct a state influence graph of the smart home device according to the state data and the control parameter; A bias calculation module, configured to calculate a target bias term of the smart home device according to the state data and the control parameter; A first construction module, configured to construct a local cost function of the smart home device according to the target bias term and the control parameter, and generate a first control strategy of at least two smart home devices; A second construction module, configured to construct a global cost function of the target area according to the state influence graph based on the local cost function; An update iteration module, configured to iteratively optimize the first control strategy according to the global cost function, and generate an optimal control strategy of at least two smart home devices; The constructing the state influence graph of the smart home device according to the state data and the control parameter, comprises: Dividing the control parameter into a continuous control parameter subset and a discrete control parameter subset; Establishing a continuous control mapping set of the continuous control parameter subset and the state data; Establishing a discrete control mapping set of the discrete control parameter subset and the state data; Combine the continuous control mapping set and the discrete control mapping set to obtain a hybrid parameter structure mapping set; Generate a state influence graph of the smart home device according to the hybrid parameter structure mapping set; The state data further includes human body sign data, and the target bias term of the smart home device is calculated according to the state data and the control parameter, including: Generate a target control parameter according to the environmental state data and the human body sign data; Calculate a target bias term of each smart home device according to the target control parameter and the control parameter of the smart home device; The process of constructing the local cost function of the smart home device is further based on an energy consumption term and a conflict term of the smart home device, wherein the energy consumption term is the energy consumption of the smart home device, and the conflict term is the loss generated when the smart home devices are simultaneously controlled; The process of constructing the local cost function of the smart home device is further based on a device type adjustment parameter and a control conflict loss function of each smart home device, wherein the control conflict loss function is based on other devices that conflict with the current smart home device; The state influence graph is in the form of a directed graph; The first control strategy is iteratively optimized according to the global cost function to generate an optimal control strategy of at least two smart home devices, including: According to the target control parameter, the variational inequality problem of the global cost function is iteratively calculated by using a Lagrange multiplier relaxation and a sub-gradient response algorithm to generate a Nash equilibrium control strategy; According to the target control parameter and the Nash equilibrium control strategy, the first control strategy is optimized to generate an optimal control strategy of the target area.

6. An electronic device, comprising: The memory is connected in communication with the at least one control processor, and the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to perform the smart home device control method of any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions for causing a computer to perform the smart home device control method of any one of claims 1 to 4.

Images