Smart home control method and smart home system

Abstract

The present invention provides a smart home control method and a smart home system, which relate to the field of artificial intelligence technology. The smart home control method includes: generating a user habit script; storing the user habit script in a smart home AI cloud; a home edge computing center device reports the real-time home status to the smart home AI cloud; the smart home AI cloud calculates the similarity between the preset home status in the user habit script and the real-time home status; the smart home AI cloud determines whether the similarity is greater than the similarity threshold; if the similarity is greater than the similarity threshold, the smart home AI cloud recommends the user habit script to the home edge computing center device; the home edge computing center device deploys the user habit script, and controls each smart home terminal device according to the preset control method in the user habit script. The technical solution of the present invention can automatically control multiple smart home terminal devices according to user habits, thereby improving the user experience.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a smart home control method and a smart home system. Background Art

[0002] With the increasing popularity of the Internet, the integration trend of consumer electronics, computers and communications is becoming increasingly obvious. Modern smart homes are becoming a new fashion in modern society and families due to their safety, convenience, efficiency, speed and intelligence. Smart homes use residential buildings as a platform, integrate facilities related to home life using integrated wiring technology, network communication technology, automatic control technology, audio and video technology, build an efficient management system for residential facilities and family schedules, improve home safety, convenience, comfort and artistry, and achieve an environmentally friendly and energy-saving living environment.

[0003] Existing smart home terminal devices require users to control them one by one through the smart control panel. Users usually set scenes on the operation interface, such as turning on the air conditioner when the temperature in the living room is higher than 24 degrees Celsius, turning off the lights in the bedroom at 11 pm, and turning on the water heater in the bathroom at 8 pm. However, the setting process is usually complicated, and users need to set up multiple smart devices controlled by the smart home to match different scenes, which is a lot of work. In some cases, due to improper operation by the user, the set scene does not conform to the user's living habits, affecting the user experience. Summary of the invention

[0004] The present invention provides a smart home control method and a smart home system, which can automatically control multiple smart home terminal devices according to user habits and improve user experience.

[0005] In a first aspect, the present invention provides a smart home control method, which adopts the following technical solution:

[0006] The smart home control method comprises:

[0007] Step S1, representing user habits in a script-based manner to generate a user habit script, wherein the user habit script includes a preset home state and a preset control method for at least one smart home terminal device under the preset home state;

[0008] Step S2: storing the user habit script in the smart home AI cloud;

[0009] Step S3, the home edge computing center device reports the real-time home status to the smart home AI cloud;

[0010] Step S4, the smart home AI cloud computing calculates the similarity between the preset family status in the user habit script and the real-time family status;

[0011] Step S5: the smart home AI cloud determines whether the similarity is greater than a similarity threshold;

[0012] Step S6: If the similarity is greater than the similarity threshold, the smart home AI cloud recommends the user habit script to the home edge computing center device;

[0013] Step S7: The home edge computing center device deploys the user habit script and controls each of the smart home terminal devices according to a preset control method in the user habit script.

[0014] Optionally, step S7 specifically includes:

[0015] The home edge computing center device performs human-computer interaction with the user;

[0016] Deploy the user habit script according to the human-computer interaction result;

[0017] Each of the smart home terminal devices is controlled according to the preset control method in the user habit script.

[0018] Optionally, the human-computer interaction between the home edge computing center device and the user specifically includes:

[0019] According to the magnitude of the similarity, the similarity is divided into multiple similarity levels;

[0020] Setting a corresponding human-computer interaction mode for each similarity level;

[0021] According to the calculated similarity, a corresponding human-computer interaction method is selected;

[0022] The home edge computing center device performs human-computer interaction with the user according to the selected human-computer interaction mode.

[0023] Optionally, the preset family status and the real-time family status both include: time, place, task, props, conditions and preset control mode;

[0024] The smart home control method further includes the following steps performed after step S7:

[0025] Step S8, recording the user operation changes and condition changes within a certain period of time;

[0026] Step S9: If the user operation and conditions remain unchanged, the home edge computing center device saves the user habit script;

[0027] Step S10: If the user operation and / or conditions change, the home edge computing center device updates the user habit script according to the changes;

[0028] Step S11, the home edge computing center device saves the updated user habit script;

[0029] Step S12: The home edge computing center device uploads the updated user habit script to the smart home AI cloud, and updates the user habit script in the smart home AI cloud.

[0030] Optionally, step S10 specifically includes:

[0031] If the user operation changes, the home edge computing center device adds the changed user operation to the preset control mode of the user's habit script;

[0032] If the conditions change, the home edge computing center device modifies the conditions in the user habit script according to the changed conditions;

[0033] If both the user operation and the conditions change, the home edge computing center device will add the changed user operation to the preset control method of the user habit script, and modify the conditions in the user habit script according to the changed conditions.

[0034] In a second aspect, the present invention provides a smart home system, which adopts the following technical solution:

[0035] The smart home system includes: a smart home AI cloud, a home edge computing center device and at least one smart home terminal device, wherein:

[0036] The smart home AI cloud is used to store user habit scripts, wherein the user habit scripts are generated by performing knowledge representation in a manner of representing user habits in a script, and the user habit scripts include a preset home state and a preset control method for at least one smart home terminal device under the preset home state;

[0037] The home edge computing center device is used to report the real-time home status to the smart home AI cloud;

[0038] The smart home AI cloud is also used to calculate the similarity between the preset family status in the user habit script and the real-time family status, determine whether the similarity is greater than a similarity threshold, and recommend the user habit script to the home edge computing center device when the similarity is greater than the similarity threshold;

[0039] The home edge computing center device is also used to deploy the user habit script and control each of the smart home terminal devices according to the preset control method in the user habit script.

[0040] Optionally, the smart home system also includes a home gateway, the smart home terminal device accesses the home gateway through an Internet of Things device, the home edge computing center device accesses the home gateway through a home network, and the home edge computing center device accesses the smart home AI cloud.

[0041] Optionally, the home edge computing center device uses a CPU with an Arm64 instruction architecture and a Linux operating system.

[0042] Optionally, the user habit script is encapsulated in json format and stored in the smart home AI cloud.

[0043] The present invention provides a smart home control method and a smart home system. In the smart home control method, first, user habits are represented by a script to generate a user habit script, and the user habit script is stored in the smart home AI cloud. Then, the home edge computing center device reports the real-time home status to the smart home AI cloud. The smart home AI cloud calculates the similarity between the preset home status in the user habit script and the real-time home status, and determines whether the similarity is greater than the similarity threshold. When the similarity is greater than the similarity threshold, the smart home AI cloud recommends the user habit script to the home edge computing center device. Finally, the home edge computing center device deploys the user habit script and controls each smart home terminal device according to the preset control method in the user habit script. Therefore, through the above smart home control method, multiple smart home terminal devices can be automatically controlled according to user habits, and the user does not need to control each smart home terminal device separately, and the automatic control result conforms to the user habit, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0045] Figure 1 The process of the smart home control method provided by the embodiment of the present invention Figure 1 ;

[0046] Figure 2 The process of the smart home control method provided by the embodiment of the present invention Figure 2 ;

[0047] Figure 3 A module diagram of a smart home system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be noted that the various technical features in the embodiments of the present invention can be combined with each other without conflict.

[0050] The embodiment of the present invention provides a smart home control method, specifically, as follows Figure 1 As shown, Figure 1 The process of the smart home control method provided by the embodiment of the present invention Figure 1 , the smart home control method includes:

[0051] Step S1, represent user habits in a script-based manner to generate a user habit script, where the user habit script includes a preset home state and a preset control method (or action) for at least one smart home terminal device under the preset home state.

[0052] Exemplarily, the preset home status may include: time, place, task, props and conditions.

[0053] Exemplarily, the user habit script is as follows:

[0054]

[0055]

[0056]

[0057] Step S2: Store the user habit script in the smart home AI cloud.

[0058] Exemplarily, the user habit script is encapsulated in json format and stored in the smart home AI cloud.

[0059] Step S3: The home edge computing center device reports the real-time home status to the smart home AI cloud.

[0060] The real-time home status reported by the home edge computing center device to the smart home AI cloud can be perceived by each smart home terminal device. The specific content of the reported real-time home status can be determined based on the content of the preset home status in the user's habit script, and in principle should not be less than the content of the preset home status.

[0061] Exemplarily, the real-time family status in the embodiment of the present invention includes: time, place, task, props and conditions.

[0062] For example, the device and environment status expressions in the preset home status and real-time home status conditions in the embodiments of the present invention can adopt a fuzzy membership representation method. For example, the temperature is divided into hot, slightly hot, normal, slightly cold, and cold. Specifically, the fuzzy function can be selected as a Gaussian function to make the gear division more refined. The Gaussian function can be specifically as follows:

[0063] Among them, the parameter σ is usually positive, and the parameter c is used to determine the center of the curve.

[0064] Step S4: Similarity between the preset home status and the real-time home status in the smart home AI cloud computing user habit script.

[0065] Optionally, the smart home AI cloud uses a cosine similarity formula to calculate the similarity between the preset home state in the user's habit script and the real-time home state. The cosine similarity formula is as follows:

[0066]

[0067] Among them A i , B i They represent the components of vector A and vector B respectively. Vector A and vector B are vectors generated according to the contents in the preset family status and the real-time family status respectively.

[0068] Step S5: The smart home AI cloud determines whether the similarity is greater than a similarity threshold.

[0069] The similarity threshold can be set by the user according to actual needs and is not limited here.

[0070] Step S6: If the similarity is greater than the similarity threshold, the smart home AI cloud recommends the user habit script to the home edge computing center device.

[0071] Step S7: The home edge computing center device deploys the user habit script and controls each smart home terminal device according to the preset control method in the user habit script.

[0072] Optionally, step S7 specifically includes: the home edge computing center device performs human-computer interaction with the user; deploys a user habit script based on the human-computer interaction result; and controls each smart home terminal device according to a preset control method in the user habit script.

[0073] There are many ways of human-computer interaction. For example, in an embodiment of the present invention, the human-computer interaction between the home edge computing center device and the user specifically includes:

[0074] According to the magnitude of the similarity, the similarity is divided into multiple similarity levels;

[0075] Set the corresponding human-computer interaction mode for each similarity level;

[0076] According to the calculated similarity, a corresponding human-computer interaction method is selected;

[0077] The home edge computing center device interacts with the user according to the selected human-computer interaction method.

[0078] For example, the similarity threshold above is 80, and the similarity exceeding the similarity threshold is divided into two levels, the first level corresponds to above 90, and the second level corresponds to 80-90; the human-computer interaction method corresponding to the first level is that the home edge computing center device emits a beep, prompting the user to deploy the user habit script, and the human-computer interaction method corresponding to the second level is that the home edge computing center device emits a voice to ask whether to deploy the user habit script, and determines whether to deploy the user habit script based on the user voice reply; the similarity calculated this time is 92, corresponding to the first level, the home edge computing center device emits a beep, prompting the user to deploy the user habit script. The user does not perform any operation, and directly deploys the user habit script, and controls each smart home terminal device according to the preset control method in the user habit script.

[0079] The present invention provides a smart home control method and a smart home system. In the smart home control method, first, user habits are represented by a script to generate a user habit script, and the user habit script is stored in the smart home AI cloud. Then, the home edge computing center device reports the real-time home status to the smart home AI cloud. The smart home AI cloud calculates the similarity between the preset home status in the user habit script and the real-time home status, and determines whether the similarity is greater than the similarity threshold. When the similarity is greater than the similarity threshold, the smart home AI cloud recommends the user habit script to the home edge computing center device. Finally, the home edge computing center device deploys the user habit script and controls each smart home terminal device according to the preset control method in the user habit script. Therefore, through the above smart home control method, multiple smart home terminal devices can be automatically controlled according to user habits, and the user does not need to control each smart home terminal device separately, and the automatic control result conforms to the user habit, thereby improving the user experience.

[0080] Alternatively, if Figure 2 As shown, Figure 2 The process of the smart home control method provided by the embodiment of the present invention Figure 2 Under the premise that both the preset home status and the real-time home status include: time, place, task, props and conditions, the smart home control method further includes: the following steps performed after step S7:

[0081] Step S8: Record whether the user operation and conditions have changed within a certain period of time.

[0082] The above certain time can be set according to user needs, for example, the certain time is 15 seconds. The user operation change can be that the user turns on or off the smart home terminal device, and the condition change can be that the temperature is increased by one level, such as from hot to hot.

[0083] Step S9: If the user operation and conditions remain unchanged, the home edge computing center device saves the user habit script.

[0084] Step S10: If the user operation and / or conditions change, the home edge computing center device updates the user habit script according to the changes.

[0085] Optionally, step S10 specifically includes:

[0086] If the user operation changes, the home edge computing center device adds the changed user operation to the preset control mode (or action) of the user's habit script;

[0087] If the conditions change, the home edge computing center device modifies the conditions in the user's habit script according to the changed conditions;

[0088] If both user operations and conditions change, the home edge computing center device will add the changed user operations to the preset control method of the user habit script, and modify the conditions in the user habit script according to the changed conditions.

[0089] Step S11: The home edge computing center device saves the updated user habit script.

[0090] Step S12: The home edge computing center device uploads the updated user habit script to the smart home AI cloud, and updates the user habit script in the smart home AI cloud.

[0091] Through the above-mentioned smart home control method further including steps S8 to S12, it is possible to quickly learn user habits through the cloud-edge collaborative learning algorithm, further improving the user experience. The cloud-edge collaborative learning algorithm includes the user habit knowledge representation algorithm (step S1), the user habit recommendation algorithm (step S6), and the script optimization algorithm (steps S8 to S11) used in each step.

[0092] In addition, an embodiment of the present invention further provides a smart home system, specifically, Figure 3 As shown, Figure 3 A module diagram of a smart home system provided by an embodiment of the present invention, the smart home system comprises: a smart home AI cloud 10, a home edge computing center device 20 and at least one smart home terminal device 30, wherein:

[0093] The smart home AI cloud 10 is used to store user habit scripts, where the user habit scripts are generated by representing user habits in a script-based manner, and the user habit scripts include a preset home state and a preset control method for at least one smart home terminal device in the preset home state;

[0094] The home edge computing center device 20 is used to report the real-time home status to the smart home AI cloud 10;

[0095] The smart home AI cloud 10 is also used to calculate the similarity between the preset home state and the real-time home state in the user habit script, determine whether the similarity is greater than the similarity threshold, and recommend the user habit script to the home edge computing center device when the similarity is greater than the similarity threshold;

[0096] The home edge computing center device 20 is also used to deploy user habit scripts and control each smart home terminal device 10 according to the preset control method in the user habit script.

[0097] The application process of the above smart home system is as follows: First, the user habit script is stored in the smart home AI cloud 10. The process of generating the user habit script can be executed outside the smart home system. Then, the home edge computing center device 20 reports the real-time home status to the smart home AI cloud 10. The smart home AI cloud 10 calculates the similarity between the preset home status in the user habit script and the real-time home status, and determines whether the similarity is greater than the similarity threshold. When the similarity is greater than the similarity threshold, the smart home AI cloud 10 recommends the user habit script to the home edge computing center device 20. Finally, the home edge computing center device 20 deploys the user habit script and controls each smart home terminal device 30 according to the preset control method in the user habit script. In the above process, multiple smart home terminal devices 30 can be automatically controlled according to user habits. The user does not need to control each smart home terminal device 30 separately, and the automatic control result conforms to the user habit, thereby improving the user experience.

[0098] Alternatively, if Figure 3 As shown, the smart home system in the embodiment of the present invention also includes a home gateway 40, the smart home terminal device 30 is connected to the home gateway 40 through the Internet of Things device, the home edge computing center device 20 is connected to the home gateway 40 through the home network, and the home edge computing center device 20 is connected to the smart home AI cloud 10.

[0099] Specifically, the smart home terminal device 30 has an Internet of Things interface, which can sense the light intensity, temperature, human movement, gas leakage, etc. inside the home, and realize home lighting, temperature, shading, and air quality control. The home gateway 40 has an Internet of Things interface, which can allow the smart home terminal device 30 to access and provide home status data to the home edge computing center device 20.

[0100] Optionally, the home edge computing center device 20 uses a CPU with an Arm64 instruction architecture and a Linux operating system.

[0101] Optionally, the user habit script is encapsulated in json format and stored in the smart home AI cloud 10.

[0102] Optionally, the smart home terminal device 30 can also record whether the user operation and conditions have changed within a certain period of time. If the user operation and conditions have not changed, the home edge computing center device 20 saves the user habit script. If the user operation and / or conditions have changed, the home edge computing center device 20 updates the user habit script according to the changes. After the home edge computing center device 20 updates the user habit script according to the changes, the home edge computing center device 20 saves the updated user habit script and uploads the updated user habit script to the smart home AI cloud 10, updating the user habit script in the smart home AI cloud 10. The above-mentioned smart home system can further improve the user experience by realizing rapid learning of user habits.

[0103] It should be noted that the specific contents of the smart home control method in the embodiment of the present invention are applicable to the corresponding devices or modules in the smart home system and will not be described in detail here.

[0104] In order for those skilled in the art to more clearly understand the technical content of the embodiments of the present invention, the following embodiments are specifically described in detail.

[0105] Assume that Xiao Zhao's family consists of two people, a young couple, living in a two-bedroom, one-living room house. A smart home system with cloud-edge collaborative learning function is installed in the living room, entrance, and outdoors.

[0106] The process of controlling smart home terminal devices through the smart home system is as follows:

[0107] Step 1: The home edge computing center device sends real-time home status to the smart home AI cloud, including time, place, task, props (furniture, appliances, etc.) and other information.

[0108] Step 2: The smart home AI cloud uses the cosine similarity formula to calculate the similarity between the preset home status and the real-time home status in the user habit script saved in the smart home AI cloud.

[0109] Step 3: The smart home AI cloud compares the similarity with the similarity threshold C. If it is greater than the similarity threshold C, it recommends the user habit script to the home edge computing center device.

[0110] The user's customary script is as follows (the actions in the script are the preset control methods):

[0111]

[0112]

[0113] Step 4: The home edge computing center device deploys the user habit script and controls each smart home terminal device according to the preset control method in the user habit script.

[0114] Step 5: Record the user operations and condition changes within 15 seconds. Within 15 seconds, Xiao Zhao turned on the light strip.

[0115] Step 6: The home edge computing center device adds Xiao Zhao's operation to the script's actions and updates the user habit script.

[0116] The updated user habit script is as follows:

[0117]

[0118]

[0119] Step 7: The home edge computing center device saves the updated user habit script, uploads the updated user habit script to the smart home AI cloud, and updates the user habit script in the smart home AI cloud.

[0120] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0121] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be completed by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0122] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart home control method, characterized in that: include: Step S1, representing user habits in a script-based manner to generate a user habit script, wherein the user habit script includes a preset home state and a preset control method for at least one smart home terminal device under the preset home state; Step S2: storing the user habit script in the smart home AI cloud; Step S3: The home edge computing center device reports the real-time home status to the smart home AI cloud, where both the preset home status and the real-time home status include: time, place, person, props and conditions; Step S4, the smart home AI cloud computing calculates the similarity between the preset family status in the user habit script and the real-time family status; Step S5: the smart home AI cloud determines whether the similarity is greater than a similarity threshold; Step S6: If the similarity is greater than the similarity threshold, the smart home AI cloud recommends the user habit script to the home edge computing center device; Step S7, the home edge computing center device deploys the user habit script, and controls each of the smart home terminal devices according to a preset control method in the user habit script, specifically including: The home edge computing center device performs human-computer interaction with the user, specifically: According to the magnitude of the similarity, the similarity is divided into multiple similarity levels; Setting a corresponding human-computer interaction mode for each similarity level; According to the calculated similarity, a corresponding human-computer interaction method is selected; The home edge computing center device performs human-computer interaction with the user according to the selected human-computer interaction mode; Step S8, recording the user operation changes and condition changes within a certain period of time; Step S9: If the user operation and conditions remain unchanged, the home edge computing center device saves the user habit script; Step S10: If the user operation and / or conditions change, the home edge computing center device updates the user habit script according to the changes; Step S11, the home edge computing center device saves the updated user habit script; Step S12: The home edge computing center device uploads the updated user habit script to the smart home AI cloud, and updates the user habit script in the smart home AI cloud.

2. The smart home control method according to claim 1, characterized in that: Step S7 also includes: Deploy the user habit script according to the human-computer interaction result; Each of the smart home terminal devices is controlled according to the preset control method in the user habit script.

3. The smart home control method according to claim 2, characterized in that: Step S10 specifically includes: If the user operation changes, the home edge computing center device adds the changed user operation to the preset control mode of the user's habit script; If the conditions change, the home edge computing center device modifies the conditions in the user habit script according to the changed conditions; If both the user operation and the conditions change, the home edge computing center device will add the changed user operation to the preset control method of the user habit script, and modify the conditions in the user habit script according to the changed conditions.

4. A smart home system, using the method according to any one of claims 1 to 3, characterized in that: It includes: a smart home AI cloud, a home edge computing center device and at least one smart home terminal device, wherein: The smart home AI cloud is used to store user habit scripts, wherein the user habit scripts are generated by performing knowledge representation in a manner of representing user habits in a script, and the user habit scripts include a preset home state and a preset control method for at least one smart home terminal device under the preset home state; The home edge computing center device is used to report the real-time home status to the smart home AI cloud; The smart home AI cloud is also used to calculate the similarity between the preset family status in the user habit script and the real-time family status, determine whether the similarity is greater than a similarity threshold, and recommend the user habit script to the home edge computing center device when the similarity is greater than the similarity threshold; The home edge computing center device is also used to deploy the user habit script and control each of the smart home terminal devices according to the preset control method in the user habit script.

5. The smart home system according to claim 4, characterized in that: It also includes a home gateway, the smart home terminal device is connected to the home gateway through the Internet of Things device, the home edge computing center device is connected to the home gateway through the home network, and the home edge computing center device is connected to the smart home AI cloud.

6. The smart home system according to claim 4, characterized in that: The home edge computing center device adopts a CPU with an Arm64 instruction architecture and a Linux operating system.

7. The smart home system according to claim 4, characterized in that: The user habit script is encapsulated in json format and stored in the smart home AI cloud.

Images