Equipment control method and device, storage medium and electronic device

Abstract

The invention discloses an equipment control method, a storage medium and an electronic device, and relates to the field of smart home, and the method comprises the steps: calling a pre-trained natural language model to construct a corresponding natural language expression based on a voice instruction under the condition that the voice instruction of a target object is received; determining identification information of the target object and a control intention of the target object according to the natural language expression; the identification information is correspondingly associated with a plurality of controllable devices; generating a control instruction according to the environment information of the area where the target object is located, the control intention and historical control conditions of the multiple pieces of controllable equipment; the control instruction comprises to-be-controlled equipment and control parameters of the to-be-controlled equipment; and sending a control instruction to the to-be-controlled equipment so as to control the to-be-controlled equipment to act. The control instruction can be intelligently generated in combination with the voice instruction, the environment information and the historical control condition, the actual requirement of the target object is better met, and the intelligent degree of voice control is improved.

Description

TECHNICAL FIELD

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

[0002] With the rapid development of smart home technology, voice control has become an indispensable part of smart home control due to its convenience, efficiency and humanized experience. Users can control various smart devices in the home, such as smart TVs, smart speakers, smart air conditioners, etc., through simple voice commands.

[0003] In related technologies, the execution of voice control by smart home is to determine the specified device from the voice command, and then control the specified device to act.

[0004] However, the related technology needs the user to specify the device name and specific operation to be controlled, such as "turn on the air conditioner in the living room and set the temperature to 25 degrees", and can only control the device action specified by the user, so there is a limitation in the execution of voice commands. SUMMARY

[0005] The embodiments of the present application provide a device control method and device, storage medium and electronic device to at least solve the problem of limitation of the execution of voice commands by household appliances in related technologies.

[0006] According to one embodiment of the embodiments of the present application, a device control method is provided, comprising: in the case of receiving a voice command of a target object, calling a pre-trained natural language model to construct a corresponding natural language expression based on the voice command, wherein the natural language model is pre-trained using a training set including voice commands and control strategies to match the corresponding control strategy according to the input voice command and convert the control strategy into a natural language expression; determining the identification information of the target object and the control intention of the target object according to the natural language expression; the identification information corresponds to a plurality of controllable devices; generating a control command according to the environmental information of the area where the target object is located, the control intention, and the historical control situation of the plurality of controllable devices; the control command includes the device to be controlled and the control parameter of the device to be controlled; sending the control command to the device to be controlled to control the device to act.

[0007] In one exemplary embodiment, the device to be controlled is determined according to the control intention and the historical control situation of the plurality of controllable devices; the environmental information of the area where the target object is located is obtained; the environmental information includes temperature information and illumination information; the control parameter of the device to be controlled is determined according to the temperature information and the illumination information to generate the control command.

[0008] In an example embodiment, according to the control intention, a plurality of candidate devices related to the control intention are determined; according to historical control conditions of the plurality of controllable devices, a first device is determined from the plurality of candidate devices; according to the first device and a preset device linkage relationship table, a second device having a linkage relationship with the first device is determined; the device linkage relationship table includes linkage relationships between a plurality of devices, and the devices to be controlled include the first device and the second device.

[0009] In an example embodiment, according to the historical control conditions of the plurality of controllable devices and a preset home appliance linkage sequence table, a first control sequence of the devices to be controlled is determined; according to the environmental information, the first control sequence is adjusted to determine a second control sequence of the devices to be controlled; and according to the second control sequence, a control instruction is sent to the devices to be controlled to control the devices to be controlled to act.

[0010] In an example embodiment, the method further includes: generating a plurality of scenes corresponding to different environmental information according to historical data; each scene includes control instructions of a plurality of devices, and the historical data includes historical voice instructions issued by a target object under different environmental information and action conditions of corresponding devices to be controlled; in response to a scene selection instruction of the target object, a target scene is determined; and the plurality of devices are controlled to execute the control instructions indicated by the target scene.

[0011] In an example embodiment, after the plurality of devices are controlled to execute the control instructions indicated by the target scene, the method further includes: in a case where the target scene has been executed, if a new voice instruction issued by the target object is received, a control instruction corresponding to the new voice instruction is determined; and according to the control instruction, the target scene is updated.

[0012] In an example embodiment, the method further includes: according to the historical data, a trigger environmental condition corresponding to each scene is determined; and in a case where the environmental information of the area where the target object is located meets the trigger environmental condition corresponding to the target scene, the plurality of devices are controlled to execute the control instructions indicated by the target scene.

[0013] In an example embodiment, according to the natural language expression, the identification information of the target object and the control intention of the target object are determined, including: the natural language expression is parsed to determine the feature information of the target object and the control intention contained in the voice instruction; according to the feature information of the target object, the identification information of the target object is determined; and according to the identification information, a preset device list is queried to determine a plurality of controllable devices associated with the identification information.

[0014] According to another embodiment of the embodiment of the present application, a control device of an apparatus is further provided, comprising: an instruction obtaining module, configured to, in a case where a voice instruction of a target object is received, invoke a pre-trained natural language model to construct a corresponding natural language expression based on the voice instruction, wherein the natural language model is pre-trained by using a training set comprising the voice instruction and a control strategy, so as to match the corresponding control strategy according to the input voice instruction and convert the control strategy into the natural language expression; an instruction analyzing module, configured to determine identification information of the target object and a control intention of the target object according to the natural language expression; the identification information corresponds to a plurality of controllable apparatuses in association; a control instruction generating module, configured to generate a control instruction according to environmental information of a region where the target object is located, the control intention, and historical control conditions of the plurality of controllable apparatuses; the control instruction comprises an apparatus to be controlled and a control parameter of the apparatus to be controlled; and a control module, configured to send the control instruction to the apparatus to be controlled, so as to control the apparatus to be controlled to act.

[0015] According to still another aspect of the embodiment of the present application, a computer readable storage medium is further provided, and the computer readable storage medium stores a computer program, wherein the computer program is set to execute the above-mentioned control method of the apparatus when running.

[0016] According to still another aspect of the embodiment of the present application, an electronic device is further provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned control method of the apparatus by the computer program.

[0017] The control method of the device first acquires the voice instruction of the target object, so that the system can quickly respond to the instant needs of the target object by accurately capturing and understanding the voice instruction, and enhance the voice interaction experience, then call the pre-trained natural language model to construct the corresponding natural language expression based on the voice instruction. According to the natural language expression, the identification information of the target object and the control intention of the target object are determined, so that the identification information of the target object can determine the multiple controllable devices associated with the target object, and the control intention of the target object can determine the device and the control mode expected to be controlled by the target object. Then, according to the environmental information of the area where the target object is located, the control intention, and the historical control situation of the multiple controllable devices, a control instruction is generated. Through the control intention and the historical control situation of the multiple controllable devices, the control preference of the target object can be intelligently analyzed and determined, and at the same time, combined with the current environmental condition, a control instruction more suitable for the needs of the target object can be generated. Then, the control instruction is sent to the device to be controlled to control the action of the device to be controlled. In summary, the present application can intelligently generate a control instruction by combining the voice instruction of the target object, the environmental information and the historical control situation. By analyzing the characteristic information and the historical behavior of the target object, the preference of the target object can be learned and predicted, and the generated control instruction is not limited to the device indicated by the voice instruction, but is more suitable for the actual needs of the target object, and the intelligent degree of voice control is improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate an embodiment consistent with the present application and, together with the description, serve to explain the principles of the application.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0020] Figure 1 is a hardware environment schematic diagram of a device control method according to an embodiment of the present application;

[0021] Figure 2 is a flowchart of a device control method according to an embodiment of the present application;

[0022] Figure 3 is a flowchart of a device control method according to an embodiment of the present application;

[0023] Figure 4 is a flowchart of a device control method according to an embodiment of the present application;

[0024] Figure 5Figure 4 is a flowchart of a control method of a device according to an embodiment of the present application;

[0025] Figure 6 Figure 5 is a flowchart of a control method of a device according to an embodiment of the present application;

[0026] Figure 7 Figure 6 is a flowchart of a control method of a device according to an embodiment of the present application;

[0027] Figure 8 Figure 7 is a flowchart of a control method of a device according to an embodiment of the present application;

[0028] Figure 9 Figure 8 is a flowchart of a control method of a device according to an embodiment of the present application;

[0029] Figure 10 Figure 9 is a structural block diagram of a control device of a device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to the process, method, product, or device.

[0032] According to an aspect of an embodiment of the present application, a control method of a device is provided. The control method of the device is widely applied to smart home, smart home, smart home device ecology, intelligence house ecology, and other whole-house intelligent digital control application scenarios. Optionally, in the present embodiment, the above-mentioned interaction method of the smart home device can be applied to, for example, Figure 1The hardware environment shown by the terminal device 102 and the server 104. As shown in Figure 1 The server 104 is connected with the terminal device 102 through the network, which can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal, and a database can be set on the server or independently of the server, which is used to provide data storage services for the server 104, and cloud computing and / or edge computing services can be configured on the server or independently of the server, which is used to provide data operation services for the server 104.

[0033] The above network can include but is not limited to at least one of the following: wired network, wireless network. The above wired network can include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the above wireless network can include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 can not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart oven, smart refrigerator, smart oven, smart oven, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projection equipment, smart television, smart clothesline, smart curtain, smart audio and video, smart socket, smart sound, smart sound box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart window cleaning robot, smart mopping robot, smart air purification equipment, smart steamer, smart microwave oven, smart kitchen treasure, smart purifier, smart water dispenser, smart door lock, etc.

[0034] In this embodiment, a device control method is provided, which is applied to the terminal device, Figure 2 The flow chart of the device control method according to the embodiment of the present application, which includes the following steps S200-S230:

[0035] Step S200, in the case of receiving the voice instruction of the target object, calling the pre-trained natural language model to construct the corresponding natural language expression based on the voice instruction.

[0036] The natural language model is pre-trained using a training set including voice instructions and control strategies to match the corresponding control strategy according to the voice instruction and convert the control strategy into a natural language expression. The natural language model can be a generative pre-trained transformer (GPT) model that is trained using a large training data set containing user voice instructions and their corresponding control strategies. The model generates a natural language expression describing the user's intent and desired situation based on the received voice instruction text and the user's historical behavior, preferences, and home environment information in the user profile. For example, if the voice instruction is "I'm coming home", the generated natural language expression can be "The user wants to turn on the air conditioner to a comfortable mode and adjust the living room light to a reading-friendly level after coming home, and play the user's favorite light music." Converting simple instructions into natural language expressions with rich context enables the model to understand a wider range of information and generate control strategies that better fit the user's habits and preferences, improving the personalized service level and user satisfaction of the smart home system. The model can be pre-trained based on the user's operation habits, such as physical environment information, which can be described using natural language, for example, today is August 1, 2024, the current indoor temperature is 30 degrees, the air humidity is 40, and the PM2.5 is 120. In this case, the user's usual operation habit is to turn on the air conditioner, set the temperature to 25 degrees, and use the dehumidification mode. Or the user has used the air conditioner 40 times in the past 30 days, and the user's favorite temperature setting is 25 degrees. The user likes to turn on the air conditioner and set the temperature to 25 degrees when unlocking the door. The user's operation control habits are input into the natural language model as training data, and then when the user inputs a voice instruction, the control strategy that matches the user's operation habits can be directly invoked.

[0037] Specifically, the target object interacts directly with the smart home system, and the smart home system obtains the voice instruction of the target object. The voice instruction can include, for example, "I'm coming home", "It's too hot", etc. The smart home system needs to have high sensitivity and accuracy of voice recognition function, which can quickly capture and understand the voice instruction of the target object.

[0038] For example, advanced speech recognition technology such as the ASR (Automatic Speech Recognition) system can be used, combined with microphone array technology to enhance the capture ability of voice signals and reduce noise interference, ensuring that the target object's voice can still be clearly and accurately recognized in a complex home environment. The system also needs to be configured with natural language understanding algorithms to analyze the specific meaning of the target object's voice instruction and identify entities and actions therein, providing a clear control target for subsequent steps.

[0039] Exemplarily, the pre-trained natural language model can automatically convert the voice instruction input by the user into a required natural language expression according to the user's home device list, the physical environment information, and the user's preference information for using the household appliance. For example, the voice instruction of the user is "I am coming home", and the natural language model can generate the natural language expression for the user as: turn on the hallway light, turn on the air conditioner in the living room, set the temperature to 25 degrees, and play music.

[0040] In step S210, the identification information of the target object and the control intention of the target object are determined according to the natural language expression.

[0041] The identification information corresponds to a plurality of controllable devices. The identification information of each target object is associated with a corresponding device list, which includes the devices that can be controlled by the target object, and the state, type, and function of the devices.

[0042] Specifically, after receiving the voice instruction, the system needs to identify the identification information of the target object, such as the identity, and understand which devices the target object expects to control and what specific operation to perform. The identification information of the target object, such as the ID of the target object, can help the system locate the historical data and device list of the target object, so as to more accurately predict and perform the linkage control.

[0043] Exemplarily, the identity of the target object is identified by using the personalized features (such as voiceprint) in the voice instruction or other information (such as mobile phone Bluetooth signal) bound to the target object. The target object instruction can be parsed by natural language understanding technology, such as identifying "living room" and "light" in "turn on the living room light", determining the type and specific device that the target object wants to control, and identifying "turn on" to determine the operation that the target object expects.

[0044] In step S220, the control instruction is generated according to the environmental information of the area where the target object is located, the control intention, and the historical control situation of the plurality of controllable devices.

[0045] The control instruction includes the device to be controlled and the control parameter of the device to be controlled.

[0046] Specifically, the environmental information of the area where the target object is located (such as temperature, humidity, and light intensity), the control intention of the target object, and the historical control situation of the target object to each device need to be considered comprehensively to determine the control preference of the target object, and then a series of control instructions can be intelligently generated. These instructions not only include the devices that need to be operated in the voice instruction, but also can include other devices that are not mentioned in the voice instruction, and further include specific control parameters of the devices, such as air conditioner temperature and light brightness.

[0047] Exemplarily, the system collects environmental data through integrated environmental sensors, combines the control intention parsed from the voice instruction of the target object, and the historical control data of the device recorded in the profile of the target object, and applies a machine learning algorithm (such as a decision tree, a neural network) to analyze the optimal parameters of device control. For example, when the system receives the instruction "It's too hot", it will refer to the current indoor temperature, the target object's preference for air conditioner control, and possibly generate the control instruction "Turn on the air conditioner and set the temperature to 26 degrees". In combination with the historical control of the target object on multiple controllable devices, it is determined that the target object will also usually turn on the fresh air device when turning on the air conditioner, so the system will also generate the control instruction "Turn on the fresh air device" in linkage.

[0048] In step S230, a control instruction is sent to the device to be controlled to control the action of the device to be controlled.

[0049] Specifically, after the generation of the control instruction is completed, the system needs to send the instruction to the corresponding device to execute the control intention of the target object.

[0050] Exemplarily, the system sends the control instruction to the target device through wireless communication technologies such as Wi-Fi, Bluetooth, ZigBee, etc. Before sending, the online state of the device needs to be checked to ensure that the instruction can be correctly received. After the device receives the instruction, it parses and executes the instruction through the built-in control unit, such as adjusting the air conditioner temperature, changing the light brightness, etc.

[0051] In this embodiment, the voice instruction of the target object is first acquired, so that the system can quickly respond to the immediate needs of the target object by accurately capturing and understanding the voice instruction, and enhance the voice interaction experience. Then a pre-trained natural language model is called to construct a corresponding natural language expression based on the voice instruction. Then the identification information of the target object and the control intention of the target object are determined based on the natural language expression, so that the multiple controllable devices associated with the target object can be determined through the identification information of the target object, and the device and control method expected to be controlled by the target object can be determined through the control intention of the target object. Then, according to the environmental information of the area where the target object is located, the control intention, and the historical control situation of the multiple controllable devices, a control instruction is generated. Through the analysis of the control intention and the historical control situation of the multiple controllable devices, the control preference of the target object can be intelligently analyzed and determined, and at the same time combined with the current environmental conditions, a control instruction that better meets the needs of the target object can be generated. Then the control instruction is sent to the device to be controlled to control the action of the device to be controlled. In summary, the present application can intelligently generate a control instruction in combination with the voice instruction, environmental information and historical control situation of the target object. By analyzing the characteristic information and historical behavior of the target object, the preference of the target object can be learned and predicted, and the generated control instruction is not limited to the device indicated by the voice instruction, but better meets the actual needs of the target object, and improves the intelligent degree of voice control.

[0052] In one embodiment, as shown in Figure 3 step S220, the control instruction is generated according to the environmental information of the area where the target object is located, the control intention, and the historical control situation of the plurality of controllable devices. It includes steps S300-S320, wherein:

[0053] Step S300 determines the device to be controlled according to the control intention and the historical control situation of the plurality of controllable devices.

[0054] Specifically, based on the control intention of the target object, combined with its historical use habits of home devices, the device most in need of control is intelligently selected. The historical control situation provides information such as device usage frequency, preference settings, etc., which helps the system to predict the device control needs of the target object in a specific situation.

[0055] Illustratively, the system uses the historical control data of the target object and the device usage association knowledge base, combined with the current control intention of the target object (such as obtained by voice instruction analysis), to evaluate and select the device most suitable for the needs of the target object through a data analysis algorithm (such as a machine learning classifier). For example, if the target object says "I'm ready for bed", the system will refer to the target object's past device control behavior before sleep, and prefer to control the lights and curtains in the bedroom, and adjust the air conditioning temperature to the target object's preferred sleep environment temperature.

[0056] Step S310 obtains the environmental information of the area where the target object is located.

[0057] The environmental information includes temperature information, illumination information.

[0058] Specifically, in order to control the device more accurately, the system needs to obtain the environmental information of the area where the target object is located in real time, including but not limited to temperature, humidity, illumination intensity, etc. These information will be an important reference for determining the control parameters of the device.

[0059] Illustratively, the system integrates various environmental sensors (such as temperature sensors, illumination sensors), which continuously monitor the home environment to obtain the environmental information of the target area.

[0060] Step S320 determines the control parameters of the device to be controlled according to the temperature information and the illumination information to generate the control instruction.

[0061] Specifically, after determining the device to be controlled, the system needs to calculate the most appropriate control parameters according to the environmental information of the target area to ensure that the device control can meet the needs of the target object and comply with the principles of energy saving and environmental protection.

[0062] Exemplarily, the system uses a pre-trained smart home large model, combines environmental information and target object preferences, and calculates device control parameters through modular algorithms such as temperature adjustment algorithms and light optimization algorithms. For example, if the current temperature is higher than the target object's preferred sleep temperature, the system will generate a control instruction to require the air conditioner to adjust the temperature to the target object's preferred range; if the light is too strong, the system will generate an instruction to require the light-blocking curtain to close to a certain opening degree.

[0063] In this embodiment, the system can reduce unnecessary operations of the target object, improve the efficiency and intelligent level of home control, and provide a device control experience that is more in line with personal habits and preferences by intelligently analyzing the devices to be controlled. Real-time environmental information data helps the system adjust device control parameters according to actual conditions, improving the comfort of the home environment and the efficiency of device use, while achieving energy saving and environmental protection. Through intelligent analysis of environmental information, the system can dynamically adjust the control parameters of the devices, achieve fine management of the home environment, improve the target object's experience, and also reduce energy consumption, achieving the dual goals of intelligent control and environmental protection and energy saving. In this way, the smart home system can more humanely respond to the needs of the target object, enhancing the intelligence and practicality of home automation control.

[0064] In one embodiment, as shown in Figure 4 Step S300, according to the control intention and the historical control situation of the plurality of controllable devices, determining the device to be controlled. Including steps S400-S420, wherein:

[0065] Step S400, according to the control intention, determining a plurality of candidate devices related to the control intention.

[0066] Specifically, after identifying the target object's control intention, the system needs to select the devices related to the current intention from all controllable devices in the target object's home to form a candidate device list. These devices may be devices directly mentioned by the target object, or devices intelligently inferred according to the target object's control intention and device functions.

[0067] Exemplarily, the system analyzes the target object's voice instructions through natural language understanding technology to identify entities (such as "air conditioner" and "light") and actions (such as "turn on" and "adjust temperature") therein. Subsequently, the system queries the target object's home device list to filter out devices matching the mentioned entities and functions, and uses device function association knowledge, such as the association between "air conditioner" and "temperature adjustment" and the association between "air conditioner" and "fresh air device", to further expand the scope of candidate devices, including those devices that are not directly mentioned but are related to the control intention.

[0068] Step S410, determining the first device from the plurality of candidate devices according to historical control conditions of the plurality of controllable devices.

[0069] Specifically, further screening among the candidate devices, selecting the device most consistent with the target object's historical behavior pattern and current needs as the first device for priority control.

[0070] Illustratively, the system analyzes the historical control data of the target object, including device usage frequency, control parameter preference, device usage time, etc. information, combined with the current control intention, using machine learning algorithms such as clustering analysis or decision tree, to evaluate the matching degree of the candidate device and the target object's historical behavior, and select the device with the highest matching degree as the first device. For example, the target object has used the air conditioner 40 times in the past 30 days, so when the target object issues an instruction to adjust the temperature, the air conditioner is positioned as the first device, and the target object's favorite temperature setting is 25 degrees, so the control parameter is set to 25°. The target object likes to turn on the air conditioner when opening the door lock, and the temperature is set to 25 degrees, so the door lock and the air conditioner are linked devices.

[0071] Step S420, determining the second device having a linkage relationship with the first device according to the first device and the preset device linkage relationship table.

[0072] Among them, the device linkage relationship table includes the linkage relationship between a plurality of devices, and the devices to be controlled include the first device and the second device.

[0073] Specifically, after determining the first device, the system needs to identify other devices that have linkage operation logic with the first device according to the device linkage relationship table, in order to form a more coordinated and practical control sequence, i.e. the list of devices to be controlled.

[0074] Illustratively, the system queries the preset device linkage relationship table, which records the linkage rules between devices in the target object's home, such as "when the air conditioner is turned on, the fresh air system should also be started", "after the door lock is unlocked, the living room lights should be automatically turned on". By matching the first device, the system identifies all second devices having a linkage relationship with the first device, and combines the current environment and the target object's preference to evaluate whether linkage control is needed and the parameter settings when linkage control is performed.

[0075] In this embodiment, by accurately identifying and intelligently expanding the range of alternative devices, the system can more comprehensively understand the target object control intent, lay the foundation for subsequent device selection and linkage control, and achieve more efficient and intelligent home control. Through device selection based on historical data, the system can achieve more personalized and intelligent device control, preferentially meeting the target object's most habitual device operation needs, and improving the target object's satisfaction. Through intelligent application of the device linkage relationship table, the system can generate more coherent and efficient device control instruction sequences, not only meeting the target object's direct expression of needs, but also predicting and executing potential linkage operations, achieving intelligent management and optimization of the home environment, and improving the intelligent level of home automation control and the target object's experience.

[0076] In one embodiment, as shown in Figure 5 step S230, a control instruction is sent to the device to be controlled to control the action of the device to be controlled. This includes steps S500-S520, in which:

[0077] Step S500 determines the first control order of the device to be controlled according to the historical control situation of the plurality of controllable devices and the preset home appliance linkage order table.

[0078] Specifically, the system needs to analyze the target object's historical control data and the preset device linkage rules to determine the initial order of device control. The historical control situation provides information about the target object's preferences and habits, while the linkage order table defines the logical relationship between devices based on function.

[0079] Illustratively, the system first calls the historical control database to analyze the target object's interaction history with the device to be controlled, identifies the device that the target object most frequently or most prefers to control, and the device type that is preferentially controlled under a specific instruction. Subsequently, referring to the preset home appliance linkage order table, which records the linkage logic and priority between devices, the system determines a preliminary control order, i.e., the first control order, based on the current control intent and device state.

[0080] Step S510 adjusts the first control order according to the environmental information to determine the second control order of the device to be controlled.

[0081] Specifically, in order to adapt to the current environmental conditions, the system needs to fine-tune or reorder based on the first control order according to the environmental information to generate a more suitable second control order.

[0082] Exemplarily, the system collects environmental information of the target area in real time, including temperature, humidity, light intensity, etc., and performs associated analysis with the devices in the first control sequence. If the environmental temperature is too high, the system will advance the control sequence of the air conditioner or fan and execute it preferentially; if the light intensity is too low, the sequence of the light or curtain control may be advanced to adapt to the current environmental conditions. The adjustment process can adopt a dynamic programming algorithm to ensure that the control sequence is both efficient and meets the environmental requirements.

[0083] In step S520, a control instruction is sent to the device to be controlled according to the second control sequence, so as to control the device to be controlled to act.

[0084] Specifically, after the optimized device control sequence is generated, the system needs to send control instructions to the related devices according to the sequence to execute the control intention of the target object.

[0085] Exemplarily, the system sends control instructions to the device to be controlled in sequence according to the second control sequence through wireless communication. Before sending the instructions, the system checks the online state and controllability of the device to ensure that the instructions can be correctly received and executed. The instruction content includes the ID of the device, the control action and the related parameters.

[0086] In this embodiment, by combining the historical behavior of the target object and the device linkage rules, the first control sequence can ensure that the device control not only meets the habits of the target object, but also follows the logical relationship between devices, thereby improving the control efficiency and the satisfaction of the target object. Through dynamic adjustment of environmental information, the second control sequence can more accurately respond to actual environmental changes, ensure the comfort and energy-saving effect of the home environment, and also enhance the flexibility and adaptability of the intelligent control of the home. By following the second control sequence to execute device control, not only can the accurate execution of the intention of the target object be ensured, but also the cooperation between devices can be optimized to achieve smoother and more coordinated adjustment of the home environment, thereby improving the overall experience and satisfaction of the target object to the smart home system. At the same time, the orderly control process also helps to avoid conflicts between devices and ensures the stability and safety of the control operation.

[0087] In one embodiment, as shown in Figure 6 the device control method further includes steps S600-S620, wherein:

[0088] In step S600, a plurality of scenes corresponding to different environmental information are generated according to historical data.

[0089] Each scene includes control instructions of a plurality of devices.

[0090] The historical data includes historical voice instructions of the target object and corresponding actions of the device to be controlled under different environmental information.

[0091] Specifically, to provide an intelligent and personalized home control experience, the system needs to learn and generate preset scene patterns based on the historical control behavior of the target object in different environments. These scenes will cover a series of device control instructions that can be linked to adapt to specific environmental conditions.

[0092] Illustratively, the system analyzes the historical data in the target object's profile, including the target object's voice instructions in specific environmental information (such as temperature, humidity, light intensity, etc.), and the specific actions subsequently performed by the device. Using machine learning algorithms (such as clustering analysis or sequence pattern mining algorithms), the system identifies the most common device control combinations performed by the target object under similar environmental conditions, thereby generating a sequence of control instructions for the corresponding scene. For example, the target object often says "I'm back" when returning home in the summer evening, and the subsequent control devices are usually "turn on the hallway light", "turn on the living room air conditioner", "set the temperature to 25 degrees", etc. The system associates these control instruction sequences with their corresponding environmental information to form multiple preset scenes.

[0093] Step S610, in response to the target object's scene selection instruction, determine the target scene.

[0094] Specifically, the system can understand the target object's scene selection instruction and identify the specific preset scene the target object wants to execute to quickly respond and execute the relevant control instructions.

[0095] Illustratively, when the target object issues a scene selection instruction through voice, application or home control interface, such as "execute the sleep scene", the system uses natural language processing technology to analyze the instruction and identify the scene type the target object refers to. Then, the system filters the scenes from the preset scene library that match the target object's instruction and determines the selected scene as the "target scene".

[0096] Step S620, control multiple devices to execute the control instructions indicated by the target scene.

[0097] Specifically, after determining the target scene, the system needs to send control instructions to the relevant devices to execute the device actions defined in the scene.

[0098] Illustratively, the system sends control signals to the corresponding devices according to the device control instructions defined in the target scene through wireless communication technology. Each control instruction contains device ID, action description and parameter settings, such as "device ID: air conditioner, action: turn on, parameter: temperature 25 degrees". The system ensures that the instructions are executed in the order preset by the scene to achieve device linkage control under the scene setting.

[0099] In this embodiment, by generating a scene mode based on historical behavior, the system can provide the target object with a preset control scheme that conforms to its habits and preferences, reducing the target object's operation steps, achieving fast response and personalized service for home control, and improving the target object's experience. The response mechanism of the scene selection instruction enables the target object to call a complex device control sequence through a simple instruction, further simplifying the target object's operation and improving the convenience and intelligent level of smart home control. By automatically executing the control instructions of the target scene, the system can quickly and accurately adjust the home environment to meet the target object's specific needs, such as creating a quiet and comfortable sleep environment. This process not only saves the target object's operation time, but also improves the coherence and intelligence of device control, enhancing the practicality of the smart home system and the target object's satisfaction.

[0100] In one embodiment, as shown in FIG. 6B, after the step S620 of controlling a plurality of devices to execute the control instructions indicated by the target scene, the method further includes steps S700-S710, wherein: Figure 7

[0101] Step S700, in the case where the target scene has been executed, if a new voice instruction issued by the target object is received, the control instruction corresponding to the new voice instruction is determined.

[0102] Specifically, even if the system is executing or has completed a certain preset scene, the target object may still have immediate control needs or adjustment needs, and the system must be able to respond to new voice instructions immediately, identify and execute the corresponding control actions.

[0103] Illustratively, when the system is in a scene execution state, it continuously listens for new voice instructions that the target object may issue. Once a new instruction is received, the system immediately analyzes the instruction content using voice recognition and natural language understanding techniques to determine the control intent and the involved device. For example, the target object issues the instruction "turn down the air conditioner temperature by two degrees", and the system analyzes and identifies that the control intent is to adjust the air conditioner temperature, and the involved device is the air conditioner that has been turned on in the current scene.

[0104] Step S710, updating the target scene according to the control instruction.

[0105] Specifically, the system can intelligently adjust the scene that is currently being executed or has been completed according to the new voice instruction, ensuring that the scene is consistent with the target object's latest control intent.

[0106] ​Exemplarily, the system matches and fuses the new control instruction with the target scene being executed, updates the device control parameters in the scene. If the new instruction conflicts with the device control in the scene (such as the new instruction requires turning off the device that has been turned on), the system needs to provide an intelligent decision mechanism, such as asking the target object for confirmation or automatically adjusting according to the preset priority rules, to determine whether to execute the new instruction. After determining to execute the new instruction, the system sends the updated control instruction to the corresponding device, and updates the definition of the scene in the scene database to reflect the latest linkage control logic.

[0107] In this embodiment, by responding to new voice instructions in real time, the system can quickly adapt to changes in the target object's needs, improve the flexibility and real-time nature of control, and enhance the target object's interactive experience. By updating the scene in real time, the system not only enhances the dynamic adaptability of the scene, but also continuously optimizes the scene content based on the target object's feedback, realizes more intelligent and personalized scene control, and improves the intelligent level of the smart home system and the target object's satisfaction. In addition, the dynamic update of the scene also helps the system to learn the behavior patterns of the target object, continuously improve its prediction and control capabilities, and realize more efficient home device linkage control.

[0108] In one embodiment, as shown in Figure 8 The method further includes steps S800-S810, in which:

[0109] Step S800, according to historical data, determine the trigger environmental condition corresponding to each scene.

[0110] Specifically, the system needs to analyze historical data and identify common environmental conditions when a specific scene is activated, so as to automatically trigger the scene in the future under similar conditions.

[0111] Exemplarily, the system uses data analysis and machine learning algorithms to extract patterns from the target object's historical control behavior. For example, by analyzing the target object's history of selecting to execute the "sleep scene" under different environmental conditions (such as temperature, humidity, time, light intensity, etc.), the system can induce the trigger conditions of the scene, which may be a specific time period at night, the bedroom light is off, and the air conditioner temperature is adjusted to a lower value. These conditions are recorded in the scene database and associated with each scene.

[0112] Step S810, in the case where the environmental information of the area where the target object is located meets the trigger environmental condition corresponding to the target scene, control the plurality of devices to execute the control instruction indicated by the target scene.

[0113] Specifically, when the system detects that the current environmental information matches the trigger condition of a certain scene, it automatically activates and executes the control instruction sequence of the scene.

[0114] Exemplarily, the system continuously monitors the environmental information of the target area, such as collecting data through integrated environmental sensors. When the environmental parameters reach or approach the trigger conditions of the preset scenes, the system performs a condition matching check. If the matching is successful, the system will call the corresponding control instruction sequence from the scene database, send instructions to the relevant devices through wireless communication, and execute the device actions defined in the scene. For example, when it is detected that the lights in the target object's bedroom are turned off at 10 o'clock at night and the air conditioner temperature is set to 20 degrees, the system automatically activates the "sleeping scene" and turns off the lights in the living room, adjusts the curtains to a fully closed state, and so on.

[0115] In this embodiment, by automatically learning the scene trigger conditions, the system can actively predict and respond to the potential needs of the target object, without the target object having to manually select or activate the scene each time, thereby realizing a more intelligent and automated home control experience and improving the satisfaction of the target object and the intelligent level of the system. Through intelligent matching of environmental information and scene trigger conditions, the system can actively create an ideal home environment for the target object, not only improving the automation level of home control, but also reducing the burden of the target object's operation and enhancing the active service capability of the smart home system and the quality of life of the target object. At the same time, this automatic triggering mechanism also helps to achieve energy saving and environmental protection, such as automatically stopping the air conditioner from running when the temperature is suitable, reducing unnecessary energy consumption.

[0116] In one embodiment, as shown in FIG. 9, at step S210, the identification information of the target object and the control intention of the target object are determined according to the natural language expression. This includes steps S900-S920, wherein: Figure 9

[0117] Step S900, the natural language expression is parsed to determine the feature information of the target object and the control intention contained in the voice instruction.

[0118] Specifically, the system needs to deeply understand the natural language expression and identify the control target and environmental preference information contained therein.

[0119] Exemplarily, the system uses voice recognition technology to convert the natural language expression into text, and then uses natural language understanding algorithms to parse the text content, extract keywords and phrases, and perform semantic analysis. Through the natural language understanding algorithm, the system can identify the device name, control action (such as "turn on", "turn off", "adjust temperature") and possible environmental parameters (such as "temperature", "humidity") mentioned in the instruction. In addition, the system also obtains the feature information of the target object by identifying the voice characteristics (such as voiceprint, speech speed, commonly used vocabulary, etc.) of the target object, which helps to perform personalized operations and scene matching.

[0120] Step S910, the identification information of the target object is determined according to the feature information of the target object.​

[0121] Specifically, based on the feature information of the target object, the system needs to identify the identity of the target object in order to call its personalized device control preferences and historical data.

[0122] Illustratively, the system matches the feature information of the target object (such as voiceprint data, usage habits, preference settings, etc.) with the records in the target object database to determine the identity information of the target object. For example, through voiceprint recognition technology, it is confirmed that the target object is a specific individual in the family members, such as "Xiaoming". This process ensures the personalization and security of subsequent device control instructions and scene matching.

[0123] Step S920, according to the identification information, query the preset device list, determine the multiple controllable devices associated with the identification information.

[0124] Specifically, after identifying the target object, the system needs to query the device list that the target object can control to determine the specific device that can execute the control instruction.

[0125] Illustratively, the system looks up the device list associated with the target object in the device permission and association database according to the identification information of the target object. The device list contains information such as the name, type, state, and control permission of the device. For example, if the system identifies the target object as "Xiaoming", it will query the devices that "Xiaoming" can control, such as "Xiaoming's bedroom air conditioner", "Xiaoming's study room lighting", etc. to ensure that the subsequent device control instructions are not only legal but also within the scope of the target object's permissions.

[0126] In this embodiment, by accurately analyzing the voice instruction, the system can accurately understand the intention of the target object, not only improving the accuracy of device control, but also providing basic information for subsequent personalized services and scene matching, enhancing the target object's interactive experience. Through identity confirmation, the system can call the target object's personal device control history and preferences, providing a more considerate and secure home control experience for the target object, while enhancing the personalized service capabilities of the smart home system and the isolation of the target object's operation, protecting privacy and security. By querying the devices associated with the identification information of the target object, the system can ensure that the control instructions not only meet the needs of the target object, but also comply with the permission settings of device control within the family, enhancing the security and control accuracy of the system, while also avoiding the misoperation of irrelevant devices, improving the target object's trust and convenience in using the smart home system.

[0127] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software on a general hardware platform as necessary, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or in the form of a part of the prior art that makes a contribution, and the computer software product is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk), and includes a plurality of instructions for causing an end device (which can be a mobile phone, a computer, a server, or a network device) to execute the method of each embodiment of the present application.

[0128] Figure 10 is a structural block diagram of a control device of an apparatus according to an embodiment of the present application. As shown in Figure 10 , it comprises:

[0129] The instruction obtaining module 1001 is configured to, in a case where a voice instruction of a target object is received, call a pre-trained natural language model to construct a corresponding natural language expression based on the voice instruction, wherein the natural language model is pre-trained using a training set comprising voice instructions and control strategies, to match a corresponding control strategy according to an input voice instruction and convert the control strategy into a natural language expression.

[0130] The instruction analysis module 1002 is configured to determine identification information of the target object and a control intention of the target object according to the natural language expression, wherein the identification information corresponds to a plurality of controllable devices.

[0131] The control instruction generation module 1003 is configured to generate a control instruction according to environmental information of a region where the target object is located, the control intention, and historical control conditions of the plurality of controllable devices, wherein the control instruction comprises a device to be controlled and a control parameter of the device to be controlled.

[0132] The control module 1004 is configured to send the control instruction to the device to be controlled, to control the device to be controlled to act.

[0133] In an example embodiment, the control instruction generation module 1003 is further configured to determine the device to be controlled according to the control intention and the historical control conditions of the plurality of controllable devices, and obtain environmental information of a region where the target object is located, wherein the environmental information comprises temperature information and illumination information, and determine the control parameter of the device to be controlled according to the temperature information and the illumination information, to generate the control instruction.

[0134] In an example embodiment, the control instruction generation module 1003 is further configured to determine, according to the control intention, a plurality of candidate devices related to the control intention. A first device is determined from the plurality of candidate devices according to historical control conditions of the plurality of controllable devices. A second device having a linkage relationship with the first device is determined according to the first device and a preset device linkage relationship table. The device linkage relationship table includes linkage relationships between a plurality of devices, and the devices to be controlled include the first device and the second device.

[0135] In an example embodiment, the control module 1004 is further configured to determine a first control order of the devices to be controlled according to the historical control conditions of the plurality of controllable devices and a preset home appliance linkage order table. A second control order of the devices to be controlled is determined by adjusting the first control order according to the environmental information. The control module 1004 is further configured to send control instructions to the devices to be controlled according to the second control order, so as to control the devices to be controlled to act.

[0136] In an example embodiment, the above apparatus further includes:

[0137] A scene generation module configured to generate a plurality of scenes corresponding to different environmental information according to historical data. Each scene includes control instructions of a plurality of devices, and the historical data includes historical voice instructions issued by a target object under different environmental information and action conditions of corresponding devices to be controlled.

[0138] A scene determination module configured to determine a target scene in response to a scene selection instruction of the target object.

[0139] A scene execution module configured to control a plurality of devices to execute control instructions indicated by the target scene.

[0140] In an example embodiment, the above apparatus further includes:

[0141] An instruction acquisition module configured to, in a case where the target scene has been executed, determine control instructions corresponding to a new voice instruction issued by the target object if the new voice instruction is received.

[0142] A scene update module configured to update the target scene according to the control instructions.

[0143] In an example embodiment, the above apparatus further includes:

[0144] A condition determination module configured to determine a trigger environmental condition corresponding to each scene according to historical data.

[0145] A condition judgment module configured to, in a case where environmental information of a region where the target object is located meets the trigger environmental condition corresponding to the target scene, control a plurality of devices to execute control instructions indicated by the target scene.

[0146] In an example embodiment, the instruction parsing module 1002 is further configured to parse the natural language expression, determine the feature information of the target object and the control intention contained in the voice instruction. According to the feature information of the target object, the identification information of the target object is determined. According to the identification information, a preset device list is queried, and a plurality of controllable devices associated with the identification information are determined.

[0147] Embodiments of the present application also provide a storage medium comprising a stored program, wherein the program performs any of the above methods when executed.

[0148] Optionally, in the present embodiment, the storage medium can be configured to store program code for performing the following steps:

[0149] S1, in the case of receiving a voice instruction of a target object, a pre-trained natural language model is called to construct a corresponding natural language expression based on the voice instruction, wherein the natural language model is pre-trained using a training set comprising voice instructions and control strategies to match the corresponding control strategy according to the input voice instruction and convert the control strategy into a natural language expression.

[0150] S2, according to the natural language expression, the identification information of the target object and the control intention of the target object are determined. Wherein the identification information corresponds to a plurality of controllable devices.

[0151] S3, according to the environmental information of the area where the target object is located, the control intention, and the historical control situation of the plurality of controllable devices, a control instruction is generated. Wherein the control instruction includes the device to be controlled and the control parameter of the device to be controlled.

[0152] S4, the control instruction is sent to the device to be controlled to control the device to be controlled to act.

[0153] Embodiments of the present application also provide an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor being configured to execute the computer program to perform the steps in any of the above method embodiments.

[0154] Optionally, the electronic device can further comprise a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0155] Optionally, in the present embodiment, the processor can be configured to execute the following steps through the computer program:

[0156] S1, in the case of receiving a voice instruction of a target object, calling a pre-trained natural language model to construct a corresponding natural language expression based on the voice instruction, wherein the natural language model is pre-trained by using a training set including the voice instruction and a control strategy, so as to match the corresponding control strategy according to the input voice instruction and convert the control strategy into the natural language expression.

[0157] S2, determining the identification information of the target object and the control intention of the target object according to the natural language expression, wherein the identification information corresponds to a plurality of controllable devices.

[0158] S3, generating a control instruction according to the environmental information of the area where the target object is located, the control intention, and the historical control situation of the plurality of controllable devices, wherein the control instruction includes a device to be controlled and a control parameter of the device to be controlled.

[0159] S4, sending the control instruction to the device to be controlled to control the device to be controlled to act.

[0160] Optionally, in the embodiment, the storage medium can include but is not limited to a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0161] Optionally, specific examples in the embodiment can refer to examples described in the above embodiments and optional implementation manners, and the embodiment will not be described here.

[0162] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the application can be realized by a general computing device, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices, and can be realized by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in different order, or they can be manufactured into individual integrated circuit modules, or multiple modules or steps can be manufactured into a single integrated circuit module. Therefore, the application is not limited to any specific hardware and software combination.

[0163] The above is only the preferred embodiment of the application, and it should be pointed out that for those skilled in the art, without departing from the principle of the application, a number of improvements and refinements can be made, which should be regarded as the protection scope of the application.

Claims

1. A method for controlling a device, characterized in that, include: Upon receiving a voice command from the target object, a pre-trained natural language model is invoked to construct a corresponding natural language expression based on the voice command. The natural language model is pre-trained using a training set that includes voice commands and control strategies to match the corresponding control strategy according to the input voice command and convert the control strategy into a natural language expression. Based on the natural language expression, the identification information of the target object and the control intent of the target object are determined; wherein, the identification information corresponds to multiple controllable devices; Based on the environmental information of the area where the target object is located, the control intention, and the historical control status of the multiple controllable devices, a control command is generated; wherein, the control command includes the device to be controlled and the control parameters of the device to be controlled; The control command is sent to the device to be controlled in order to control the operation of the device.

2. The control method for the device according to claim 1, characterized in that, The step of generating control commands based on environmental information of the area where the target object is located, the control intent, and the historical control status of the multiple controllable devices includes: Based on the control intent and the historical control status of the multiple controllable devices, the device to be controlled is determined; Obtain environmental information of the area where the target object is located; wherein, the environmental information includes temperature information and light information; Based on the temperature information and the illumination information, the control parameters of the device to be controlled are determined to generate the control command.

3. The control method for the device according to claim 2, characterized in that, The step of determining the device to be controlled based on the control intent and the historical control status of the plurality of controllable devices includes: Based on the control intent, a plurality of alternative devices related to the control intent are determined; Based on the historical control status of the plurality of controllable devices, a first device is determined from the plurality of candidate devices; Based on the first device and a preset device linkage relationship table, a second device that has a linkage relationship with the first device is determined; wherein, the device linkage relationship table includes linkage relationships between multiple devices, and the device to be controlled includes the first device and the second device.

4. The control method for the device according to claim 3, characterized in that, Sending the control command to the device to be controlled to control the operation of the device to be controlled includes: Based on the historical control status of the multiple controllable devices and the preset home appliance linkage sequence table, the first control sequence of the devices to be controlled is determined; Adjust the first control sequence according to the environmental information, and determine the second control sequence of the device to be controlled; The control command is sent to the device to be controlled according to the second control sequence to control the operation of the device to be controlled.

5. The control method for the device according to any one of claims 1-4, characterized in that, The method further includes: Based on historical data, multiple scenarios corresponding to different environmental information are generated; wherein each scenario includes control commands for multiple devices, and the historical data includes voice commands issued by the target object in different environmental conditions and the corresponding actions of the devices to be controlled. In response to the scene selection instruction of the target object, the target scene is determined; Control multiple devices to execute control commands indicated by the target scenario.

6. The control method for the device according to claim 5, characterized in that, After controlling multiple devices to execute the control commands indicated by the target scenario, the method further includes: If a new voice command is received from the target object after the target scenario has been executed, the control command corresponding to the new voice command is determined. Update the target scene according to the control command.

7. The control method for the device according to claim 5, characterized in that, The method further includes: Based on the historical data, determine the triggering environmental conditions for each scenario; If the environmental information of the area where the target object is located meets the triggering environmental conditions corresponding to the target scene, control multiple devices to execute the control instructions indicated by the target scene.

8. The control method for the device according to any one of claims 1-4, characterized in that, The step of determining the identification information of the target object and the control intent of the target object based on the natural language expression includes: The natural language expression is parsed to determine the feature information of the target object and the control intent contained in the voice command; Based on the characteristic information of the target object, determine the identification information of the target object; Based on the identification information, a preset device list is queried to determine multiple controllable devices associated with the identification information.

9. A control device for an equipment, characterized in that, include: The instruction acquisition module is used to, upon receiving a voice instruction from a target object, invoke a pre-trained natural language model to construct a corresponding natural language expression based on the voice instruction. The natural language model is pre-trained using a training set that includes voice instructions and control strategies, so as to match the corresponding control strategy according to the input voice instruction and convert the control strategy into a natural language expression. The instruction parsing module is used to determine the identification information of the target object and the control intention of the target object based on the natural language expression; wherein the identification information corresponds to multiple controllable devices; the control instruction generation module is used to generate control instructions based on the environmental information of the area where the target object is located, the control intention, and the historical control status of the multiple controllable devices; wherein the control instructions include the device to be controlled and the control parameters of the device to be controlled; The control module is used to send the control commands to the device to be controlled in order to control the operation of the device to be controlled.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 8.

11. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 8 through the computer program.

Images