Intelligent socket and sewing machine fault early warning method and system

Abstract

The embodiment of the invention relates to the field of smart home, and discloses a smart socket and a sewing machine fault early warning method. The method comprises the following steps: if an intelligent socket registration request is received, performing Bluetooth connection with an intelligent socket; acquiring first equipment information of the intelligent socket, and registering the intelligent socket to an Internet of Things platform according to the first equipment information and the Wi-Fi distribution network information; if the sewing machine registration request is received, second equipment information of the sewing machine connected to the intelligent socket is determined, and the sewing machine is registered to the Internet of Things platform; and monitoring whether the intelligent socket and the sewing machine have fault monitoring data in real time, if so, generating alarm information according to the fault monitoring data, and sending the alarm information to an intelligent terminal of a user. According to the scheme, through the functions of automatic equipment registration, real-time fault monitoring, intelligent alarm, remote management and the like, the intelligent management level of the equipment can be improved, the user experience is improved, the fault rate is reduced, the maintenance cost is saved, and the safety and reliability of the equipment are enhanced.

Description

Technical Field

[0001] This application relates to the technical field of smart home, and particularly to a method and system for fault warning of smart sockets and sewing machines. Background Art

[0002] With the rapid development of Internet of Things technology and the popularization of the concept of smart home, more and more household and industrial devices have started to be connected to the Internet of Things platform to achieve remote monitoring, control, and management of the devices. As important components of smart home and industrial devices, the intelligentization and networking requirements of smart sockets and sewing machines are increasing day by day. Smart sockets can not only remotely control the on-off state, but also serve as a power access point for other smart devices to achieve unified management of devices and energy optimization. And sewing machines, as important tools in traditional manufacturing, can achieve real-time monitoring of the production process, fault warning, and data analysis through connection to the Internet of Things, improving production efficiency and product quality.

[0003] Currently, there are already some registration and monitoring technologies for smart sockets and sewing machines in the market. These technologies usually register the devices to the Internet of Things platform by manually configuring device information such as MAC address, Wi-Fi password, etc. After the registration is completed, the Internet of Things platform can remotely control and monitor the status of the devices through the network. For smart sockets, the existing technologies usually use wireless communication technologies such as Wi-Fi or Bluetooth to achieve connection and data transmission with the Internet of Things platform. For sewing machines, some high-end models have built-in sensors and communication modules that can collect device status and fault information in real time and feedback it to users through the Internet of Things platform.

[0004] However, there are still some deficiencies in device registration, connection, and fault monitoring today, such as cumbersome registration processes, unstable connections, and incomplete fault monitoring. Summary of the Invention

[0005] An object of this application is to provide a method for fault warning of smart sockets and sewing machines, which is at least used to solve the problems that there are still some deficiencies in device registration, connection, and fault monitoring of smart sockets and sewing machines today, such as cumbersome registration processes, unstable connections, and incomplete fault monitoring.

[0006] To achieve the above object, some embodiments of this application provide the following aspects:

[0007] In a first aspect, some embodiments of this application also provide a method for fault warning of smart sockets and sewing machines, the method comprising:

[0008] If a smart socket registration request is received, determine the MAC address of the smart socket and the user's Wi-Fi network configuration information according to the smart socket registration request, and establish a Bluetooth connection with the smart socket according to the MAC address;

[0009] Obtain the first device information of the smart socket, and register the smart socket to the Internet of Things platform according to the first device information and the Wi-Fi network configuration information;

[0010] If a sewing machine registration request is received, determine the second device information of the sewing machine connected to the smart socket according to the sewing machine registration request, and register the sewing machine to the Internet of Things platform according to the second device information;

[0011] Real-time monitor whether the smart socket has first fault monitoring data, and real-time monitor whether the sewing machine has second fault monitoring data. If it is monitored that the smart socket has first fault monitoring data and / or the sewing machine has second fault monitoring data, generate an alarm message according to the first fault monitoring data and / or the second fault monitoring data, and send the alarm message to the user's smart terminal.

[0012] According to the second aspect of the present application, a smart socket and sewing machine fault warning system is provided. The system includes:

[0013] A Bluetooth connection module, which is used to, if a smart socket registration request is received, determine the MAC address of the smart socket and the user's Wi-Fi network configuration information according to the smart socket registration request, and establish a Bluetooth connection with the smart socket according to the MAC address;

[0014] A smart socket registration module, which is used to obtain the first device information of the smart socket, and register the smart socket to the Internet of Things platform according to the first device information and the Wi-Fi network configuration information;

[0015] A sewing machine registration module, which is used to, if a sewing machine registration request is received, determine the second device information of the sewing machine connected to the smart socket according to the sewing machine registration request, and register the sewing machine to the Internet of Things platform according to the second device information;

[0016] An early warning module, which is used to real-time monitor whether the smart socket has first fault monitoring data, and real-time monitor whether the sewing machine has second fault monitoring data. If it is monitored that the smart socket has first fault monitoring data and / or the sewing machine has second fault monitoring data, generate an alarm message according to the first fault monitoring data and / or the second fault monitoring data, and send the alarm message to the user's smart terminal.

[0017] Compared with related technologies, in the solution provided by the embodiments of the present application, if a smart socket registration request is received, the MAC address of the smart socket and the user's Wi-Fi network configuration information are determined according to the smart socket registration request, and a Bluetooth connection is established with the smart socket according to the MAC address; the first device information of the smart socket is obtained, and the smart socket is registered to the Internet of Things platform according to the first device information and the Wi-Fi network configuration information; if a sewing machine registration request is received, the second device information of the sewing machine connected to the smart socket is determined according to the sewing machine registration request, and the sewing machine is registered to the Internet of Things platform according to the second device information; the smart socket is monitored in real time for the first fault monitoring data, and the sewing machine is monitored in real time for the second fault monitoring data. If it is monitored that the smart socket has the first fault monitoring data and / or the sewing machine has the second fault monitoring data, an alarm information is generated according to the first fault monitoring data and / or the second fault monitoring data, and the alarm information is sent to the user's smart terminal. Through the above smart socket and sewing machine fault warning method, by realizing functions such as automated device registration, real-time fault monitoring, intelligent alarm and remote management, the intelligent management level of the device can be significantly improved, the user experience can be enhanced, the failure rate can be reduced, the maintenance cost can be saved, and at the same time, the security and reliability of the device can be enhanced. Description of the Drawings

[0018] One or more embodiments are exemplarily illustrated by the pictures in the corresponding drawings. These exemplary illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the drawings in the figures do not constitute a scale limitation.

[0019] Figure 1 It is an exemplary flowchart of a smart socket and sewing machine fault warning method provided according to some embodiments of the present application;

[0020] Figure 2 It is an exemplary flowchart of a smart socket and sewing machine fault warning method provided according to some embodiments of the present application;

[0021] Figure 3 It is an exemplary flowchart of a smart socket and sewing machine fault warning method provided according to some embodiments of the present application;

[0022] Figure 4 It is an exemplary structural diagram of a smart socket and sewing machine fault warning system provided according to some embodiments of the present application;

[0023] Figure 5 It is a block diagram of an exemplary electronic device provided according to some embodiments of the present application. Detailed Embodiments

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Apparently, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts shall fall within the scope of protection of this application.

[0025] First Embodiment

[0026] The first embodiment of this application relates to a method for fault warning of an intelligent socket and a sewing machine. As Figure 1 shown, the method may include the following steps:

[0027] S101, if an intelligent socket registration request is received, determine the MAC address of the intelligent socket and the user's Wi-Fi network configuration information according to the intelligent socket registration request, and establish a Bluetooth connection with the intelligent socket according to the MAC address.

[0028] In this solution, the intelligent socket registration request may be a request issued by a user or a system, aiming to add a certain intelligent socket device to the Internet of Things platform or control system. This request usually contains relevant identity information of the intelligent socket (such as device identification, network configuration information, etc.) and an instruction to request connection and registration with the Internet of Things platform.

[0029] An intelligent socket can be a power socket that can interact with intelligent devices through network connections (such as Wi-Fi, Bluetooth, etc.). Different from traditional sockets, intelligent sockets usually have functions such as remote control, energy efficiency monitoring, and timing control, and can be controlled through mobile devices (such as smartphones, tablets, etc.) or voice assistants. It can be interconnected with the smart home system to provide users with more intelligent power management.

[0030] The MAC address can be the unique hardware address of each network device, used to identify the device in the network. Each intelligent socket is assigned a unique MAC address during production, and this address can be used for device identification and network connection.

[0031] During the process of intelligent socket registration, the MAC address is used to identify and verify the socket device, ensure connection to the correct device, and correctly add the device to the network.

[0032] The Wi-Fi network configuration information may refer to the Wi-Fi information used by the user to connect an intelligent device (such as an intelligent socket) to a home or office network. Specifically, it may include the Wi-Fi network name (SSID): that is, the name of the network, used to identify the network. The Wi-Fi password: used to ensure network security and prevent unauthorized devices from connecting to the network.

[0033] When the user starts the device (such as through a smartphone APP, voice assistant, etc.) and sends a registration request, the system will receive data containing the identification information of the smart socket and the network configuration instruction. This request usually includes the unique identifier of the device (such as the MAC address) and the Wi-Fi network configuration information. When registering, the smart socket will provide its MAC address to the platform via Bluetooth or other means. Usually, when the user presses a button or scans a QR code on the device, the device will automatically send a registration request, and the platform can obtain the unique MAC address of this device. The Wi-Fi network configuration information is usually provided by the user. The user inputs the Wi-Fi network name (SSID) and password through the APP, smart terminal or voice assistant, and the device will receive this information and connect to the specified Wi-Fi network. After the device obtains the MAC address and Wi-Fi network configuration information, the system makes a preliminary connection between the device and the mobile phone or control platform via Bluetooth. Through Bluetooth, the device will provide confirmation information to ensure that the MAC address is correct and the device can perform subsequent Wi-Fi connections.

[0034] S102, obtain the first device information of the smart socket, and register the smart socket to the Internet of Things platform according to the first device information and the Wi-Fi network configuration information.

[0035] The first device information can be the basic information provided by the smart socket during the registration process. These information are usually used to uniquely identify and configure the smart socket so that the system can identify and manage the device. Specifically, the first device information can include device type: indicating the type of the device (such as a smart socket). Device ID (such as MAC address): the unique identifier of the device, used to ensure the distinction of different devices on the Internet of Things platform. Device model or version: the hardware or software version information of the device, helping the platform determine the functions and compatibility of the device. Hardware status: the current hardware condition of the device, such as whether it is running normally, whether there are faults, etc. Device name: the name specified by the user for the device, facilitating management and operation. Firmware version: the firmware version of the device, helping the platform confirm whether the device needs to be updated or repaired.

[0036] The Internet of Things (IoT) platform can be an integrated software system designed to support the connection, management, monitoring, and control of devices. The IoT platform connects multiple devices (such as smart plugs, sensors, home appliances, etc.) to the network through cloud computing technology and allows users to remotely operate and manage these devices through applications or web interfaces. The IoT platform typically has the following functions: Device management: Allows users to view device status, perform configurations, update firmware, etc. Data storage and analysis: Collects and analyzes device operation data, such as energy efficiency data, usage, etc. Control and automation: Users can remotely control the on / off, timing settings, etc. of devices and even achieve automated operations. Security: Ensures secure connection of devices and data protection through technologies such as encryption and authentication.

[0037] When a user registers a device, they need to enter the Wi-Fi network name (SSID) and password, and transmit this information to the device through the APP or smart terminal. The device connects to the home network through the Wi-Fi configuration protocol (such as WPS). The system will automatically configure the Wi-Fi network configuration parameters and perform network verification. After a successful Wi-Fi connection, the smart plug will connect to the IoT platform through the Internet. The IoT platform will uniquely identify the smart plug through the first device information of the device (such as device ID, MAC address, etc.). After receiving the information of the smart plug, the IoT platform registers the first device information of the device and the Wi-Fi network configuration information into the system together. At this time, the platform will assign a unique identification number to the device and classify it according to information such as the type and version of the device. Once the smart plug is successfully registered, the IoT platform will record the device status and allow users to perform remote control, monitoring, and management on the platform. For example, users can view device status, usage, energy efficiency data, etc., or control the on / off, timing tasks, etc. of the device through the platform.

[0038] S103, if a sewing machine registration request is received, determine the second device information of the sewing machine connected to the smart plug according to the sewing machine registration request, and register the sewing machine to the IoT platform according to the second device information.

[0039] The sewing machine registration request can refer to a request sent by a user through a certain method (such as through a smart terminal, APP, or other control interfaces) to connect and register the sewing machine device to the IoT platform. This request contains information about the sewing machine device to be registered (such as device identifier, connection method, etc.). Usually, this request is sent when the user first installs and wishes to use the sewing machine. The content of the request can include the model number, serial number, MAC address (if using wireless connection), or other identification information of the sewing machine.

[0040] The second device information can refer to specific information related to the sewing machine, which is used to register and identify the device on the Internet of Things (IoT) platform. The second device information usually includes the device identifier, model, version, and other data related to the device status or attributes. These information are used to ensure that the IoT platform can correctly identify, manage, and control the device. Specifically, it can include the device ID (such as serial number or MAC address): which uniquely identifies the sewing machine. Device model and version: such as the model of the sewing machine, firmware version, etc. Device status information: such as whether it is connected to the smart socket, whether it is in standby or working state, etc. Connection information: the connection method between the sewing machine and the smart socket, such as Bluetooth, Wi-Fi, etc.

[0041] A sewing machine can be a mechanical device used for sewing materials such as fabrics, and is usually used in fields such as clothing manufacturing and home textiles. In a smart home system, the sewing machine can be connected to the IoT platform and remotely controlled, monitored, and managed via the Internet. For example, users can view the usage status, fault warnings of the sewing machine, or start / stop the device through a smart terminal.

[0042] The user sends a sewing machine registration request through a smart terminal (such as a mobile phone, tablet, or PC), usually when the device is first configured or reconfigured. The second device information of the sewing machine first includes confirming whether the device has established a connection with the smart socket via Bluetooth or Wi-Fi. The connection between the smart socket and the sewing machine is usually carried out through a wireless protocol (such as Bluetooth, Wi-Fi). Through the Bluetooth or Wi-Fi protocol, the system will identify and obtain the unique identifier of the sewing machine (such as device ID, serial number, MAC address, etc.). This identifier will be part of the second device information. The system will also obtain the functional parameters, model, version information, etc. of the sewing machine. For example, information such as the modes supported by the device (such as normal sewing, acceleration mode, etc.), operating status (such as standby, running) of the sewing machine. The second device information of the sewing machine (such as device ID, model, status information, etc.) is transmitted to the IoT platform through the connection of the smart socket. This can be accomplished through Bluetooth, Wi-Fi, or other network communication protocols. After receiving the device information, the IoT platform will verify whether the device is a legitimate device and check whether the device conforms to the device list of the platform. The platform identifies and records the device information through the second device information. Once the second device information of the device is verified correctly, the IoT platform will assign a unique ID to the sewing machine and register it in the platform. At this time, the sewing machine becomes part of the IoT platform, and users can view the sewing machine status, operate the device, obtain fault reports, etc. through the platform.

[0043] S104, Monitor in real time whether there is first fault monitoring data for the smart socket, and monitor in real time whether there is second fault monitoring data for the sewing machine. If it is detected that there is first fault monitoring data for the smart socket and / or second fault monitoring data for the sewing machine, generate an alarm message according to the first fault monitoring data and / or the second fault monitoring data, and send the alarm message to the user's smart terminal.

[0044] The first fault monitoring data may refer to fault information or abnormal status data related to the smart socket. Specifically, these data may include abnormal current: the smart socket detects that the current exceeds the normal range, which may mean that the socket is overloaded or there is a problem with the circuit. Overheating: The temperature sensor of the smart socket monitors that the temperature exceeds the safe operating range, which may mean that the socket is overloaded or there is a fault. Voltage fluctuation: The socket detects that the voltage fluctuation exceeds the safe range, which may affect the connected devices or cause device damage. Abnormal connection: There is a problem with the connection between the smart socket and other devices (such as the sewing machine), such as disconnection or signal interference.

[0045] The second fault monitoring data may refer to fault information or abnormal status data related to the sewing machine. The second fault monitoring data may include mechanical fault: internal components of the sewing machine (such as the motor, spool, etc.) fail, affecting the normal operation of the sewing machine. Overheating: The sewing machine monitors that the temperature is too high, which may be due to equipment overload or cooling system failure. Electrical fault: The sewing machine detects abnormal current and voltage, which may be due to a fault in the electrical system. Sensor fault: The sensor of the sewing machine fails to work properly, resulting in the device being unable to accurately obtain or feedback status information.

[0046] The alarm message may refer to a notification generated by the monitoring system to remind the user. The alarm message may include fault type: describing the type of fault or abnormality, such as "smart socket overload" or "sewing machine overheating". Fault severity: The alarm message may indicate the severity of the fault, such as "urgent", "warning" or "information". Fault description: Briefly describe the specific situation of the fault to help the user understand the cause of the fault.

[0047] The smart terminal may refer to a device that can receive and display the alarm message, and may include a smart phone: the user receives the alarm message through the installed APP. Smart tablet: Also receive notifications through the application. Smart watch: Can also receive and display alarm notifications for the user to view at any time. Computer: Through a specific application or web page, the user can receive the alarm message.

[0048] Sensors (such as current, voltage, and temperature sensors) inside the smart socket monitor the operating status of the socket in real time. The collected data is analyzed through an embedded control system or an Internet of Things platform. For example, the system can calculate the load, voltage, and temperature of the socket in real time to determine if there are any abnormalities. Once the monitoring data of the smart socket exceeds the predetermined safety range (such as overload, overheat, abnormal current, etc.), the system identifies the fault and generates fault data. Based on the first fault monitoring data (such as current overload, temperature overheat, etc.), the system generates an alarm message to inform the user that the device has a fault or needs to be checked. Sensors (such as temperature, pressure, current sensors, etc.) inside the sewing machine monitor the status of the device in real time to detect if there are any abnormalities. The sensor data is analyzed through the control system to identify possible faults (such as motor faults, overheat, etc.). When the monitoring data of the sewing machine exceeds the predetermined safety value (such as overheat, abnormal voltage, etc.), the system considers that the sewing machine has a fault. Based on the second fault monitoring data, the system generates an alarm message to remind the user that the sewing machine may have a fault. Then, based on the fault data and monitoring results, the system generates a detailed alarm message (such as "Smart socket overload", "Sewing machine overheat"). Finally, the alarm message is sent to the user's smart terminal. Usually, this process is completed through a network (such as Wi-Fi, Bluetooth).

[0049] It is not difficult to find that, compared with the related technology, in the solution provided by the embodiment of the present application, if a smart socket registration request is received, the MAC address of the smart socket and the user's Wi-Fi network configuration information are determined according to the smart socket registration request, and a Bluetooth connection is established with the smart socket according to the MAC address; the first device information of the smart socket is obtained, and the smart socket is registered to the Internet of Things platform according to the first device information and the Wi-Fi network configuration information; if a sewing machine registration request is received, the second device information of the sewing machine connected to the smart socket is determined according to the sewing machine registration request, and the sewing machine is registered to the Internet of Things platform according to the second device information; it is monitored in real time whether the smart socket has the first fault monitoring data, and whether the sewing machine has the second fault monitoring data in real time. If it is monitored that the smart socket has the first fault monitoring data and / or the sewing machine has the second fault monitoring data, an alarm message is generated according to the first fault monitoring data and / or the second fault monitoring data, and the alarm message is sent to the user's smart terminal. Through the above smart socket and sewing machine fault warning method, by realizing functions such as automatic device registration, real-time fault monitoring, intelligent alarm, and remote management, it can significantly improve the intelligent management level of the device, improve the user experience, reduce the failure rate, save maintenance costs, and at the same time enhance the security and reliability of the device.

[0050] On the basis of the above technical solution, optionally, after the alarm message is sent to the user's smart terminal, the method further includes:

[0051] If a device switch control instruction from a user is received, determine a first target control device according to the device switch control instruction, and control the switch state of the first target control device according to the switch control instruction; wherein, the first target control device includes a smart socket and a sewing machine.

[0052] In this solution, the device switch control instruction can be an instruction sent by the user through a smart terminal (such as a mobile phone, a tablet, a voice assistant, etc.), and is usually used to control the switch state of a certain device. Such an instruction includes the target operation of the device (such as turning on or off) and the type or identifier of the device to be operated. For example, "turn on the smart socket" or "turn off the sewing machine". The instruction can be in the form of text, voice, or other input forms.

[0053] The first target control device refers to the specific device that needs to receive the switch control instruction. The first target control device can be any one of the smart socket and the sewing machine, specifically depending on the control instruction sent by the user. The smart socket and the sewing machine are regarded as device objects that can be controlled in the system.

[0054] The system receives a device switch control instruction from the user, which can be received through channels such as voice recognition, a mobile phone APP, or an Internet of Things platform. The system analyzes the received control instruction to determine the target device and the operation type of the instruction. For example, the instruction "turn on the smart socket" indicates that the target device is the "smart socket" and the operation is "turn on"; while the instruction "turn off the sewing machine" indicates that the target device is the "sewing machine" and the operation is "turn off". According to the analysis result, the system determines the device targeted by the instruction. For example, in the instruction "turn on the smart socket", the first target control device is the "smart socket"; in the instruction "turn off the sewing machine", the first target control device is the "sewing machine". Then the system can obtain the current status information of the first target control device to ensure that the device can normally receive the switch control. For example, the system checks whether the smart socket is in an online state and whether the sewing machine is in a standby mode, etc. According to the user's instruction, the system controls the switch state of the device. If the instruction is "turn on", the system will send a power-on command to the smart socket through the Internet of Things platform, or send a start command to the sewing machine; if the instruction is "turn off", a turn-off instruction will be sent.

[0055] In this solution, no matter where the user is, as long as there is an Internet connection, the user can remotely control the switch state of the devices at home. This provides more convenience and flexibility for users who often go out.

[0056] Based on the above technical solution, optionally, after sending the alarm information to the user's smart terminal, the method further includes:

[0057] If a voice command from a user is received, convert the voice command into a text command, and convert the text command into user intent data according to NLP technology;

[0058] Determine a second target control device according to the user intent data, generate a first operation command according to the user intent data, and control the second target control device according to the first operation command.

[0059] In this solution, the voice command can be a command or request input by the user through voice, usually expressed in natural language. For example: "Turn on the smart socket" or "Adjust the speed of the sewing machine".

[0060] The text command is the text form after the voice command is converted. After the voice recognition system converts the user's voice into text, a text command is formed. For example, if the user says "Turn on the smart socket", the voice recognition system converts it into the text command "Turn on the smart socket".

[0061] The user intent data can be the user's needs or purposes extracted from the text command through NLP technology. NLP technology analyzes the text command to identify the user's intent, task objective, and operation object. For example, for "Turn on the smart socket", NLP technology identifies that the user's intent is "Turn on" and the task objective is "smart socket".

[0062] The second target control device can be a device determined according to the user intent data, usually a specific device or apparatus that the user hopes to control through the command. For example, the target device that the user hopes to operate may be a "smart socket" or a "sewing machine".

[0063] The first operation command can be a specific control command generated according to the user intent data. It defines how to operate the target device. For example, "Turn on" or "Turn off" the smart socket, adjust the speed of the sewing machine, etc.

[0064] The user inputs commands via voice, and the system converts the voice into text through speech recognition technology (such as Google Speech-to-Text). For example, when the user says, "Turn on the smart socket," the speech recognition technology will convert it into a text command: "Turn on the smart socket." Then, natural language processing technology (NLP) is used to analyze the text command to extract the user's intention. NLP can identify the user's target operation (such as "turn on") and target device (such as "smart socket") from the text command through intention recognition and entity extraction technologies. For example, through NLP analysis, the text command "Turn on the smart socket" will generate user intention data: the intention is "turn on," and the target device is "smart socket." Then, based on the user intention data, the system determines the target device to be controlled. This device is the one related to the user's intention. For example, from the intention data "Turn on the smart socket," the system identifies the target device as "smart socket." Then, based on the user intention data, the system generates specific operation instructions for the target device. For example, according to the intention of "Turn on the smart socket," the first operation instruction generated by the system may be "turn on" or "activate" the smart socket. Finally, the system controls the operation of the target device according to the generated first operation instruction. For example, the system sends the "turn on" instruction to the smart socket device, and the smart socket executes the turn-on operation.

[0065] In this solution, through the combination of voice commands, text conversion, NLP technology, and intelligent control devices, users can enjoy a more convenient, efficient, intelligent, and accurate device control experience. It simplifies the traditional operation process, improves the user experience, and makes device management more intelligent.

[0066] Second Embodiment

[0067] The second embodiment of this application relates to a method for warning of faults in a smart socket and a sewing machine. The second implementation is an improvement based on the first embodiment. The second implementation is roughly the same as the first implementation, and the main difference is that it specifically includes the following steps:

[0068] S201, if a smart socket registration request is received, determine the MAC address of the smart socket and the user's Wi-Fi network configuration information according to the smart socket registration request, and establish a Bluetooth connection with the smart socket according to the MAC address.

[0069] S202, obtain the first device information of the smart socket, and register the smart socket to the Internet of Things platform according to the first device information and the Wi-Fi network configuration information.

[0070] S203, if a sewing machine registration request is received, determine the second device information of the sewing machine connected to the smart socket according to the sewing machine registration request, and register the sewing machine to the Internet of Things platform according to the second device information.

[0071] S204. Monitor in real time whether there is first fault monitoring data for the smart socket and whether there is second fault monitoring data for the sewing machine. If it is detected that there is first fault monitoring data for the smart socket and / or second fault monitoring data for the sewing machine, generate an alarm message according to the first fault monitoring data and / or the second fault monitoring data, and send the alarm message to the user's smart terminal.

[0072] S205. If the preset long-term analysis time interval is reached, obtain the device operation status, device performance, and fault and health data during the operation of the smart socket and the sewing machine, generate an operation data report according to the device operation status, device performance, and fault and health data, and send the operation data report to the user's smart terminal.

[0073] The preset long-term analysis time interval may refer to the time period preset by the system for periodically collecting and analyzing device data. This time interval may be set in ways such as daily, weekly, monthly, quarterly, or annually. For example, the system may automatically perform an analysis once a week, month, or quarter, collect the relevant operation data of the device, and generate a report.

[0074] The device operation status may be the working status of the device within a specific time period, such as whether the device is running, the load during operation, power consumption, working temperature, etc. These data help to evaluate whether the device is operating normally.

[0075] The device performance may include indicators such as the efficiency, output quality, and working stability of the device. For example, the power usage efficiency of the smart socket, the running speed and precision of the sewing machine. Through these performance data, the working quality of the device can be evaluated.

[0076] The fault and health data may be the fault information and health status data that occur during the operation of the device. For example, situations such as device overload, fault alarm, and abnormal temperature. These data help to judge the health status and potential risks of the device.

[0077] The operation data report may be a detailed document or chart report generated by the system based on the device operation status, performance, and health data. Specifically, it may include the working status record of the device (such as whether it is turned on, working duration, etc.), performance indicators (such as energy efficiency, running speed, precision, etc.), records of faults and abnormal situations (such as the types of faults that have occurred and their frequencies), health status analysis (whether there is wear, aging, or other risks in the device), and recommended maintenance or optimization measures (if applicable).

[0078] Smart sockets and sewing machines need to be equipped with various sensors (such as temperature sensors, current sensors, pressure sensors, load sensors, etc.) to monitor the operating status, performance, and fault and health data of the devices in real time. Embedded sensor technologies (such as current, voltage, and temperature sensors) can be used to obtain real-time device data, such as power, current, and temperature. Sensor data can be collected through an embedded system (such as an MCU or an embedded microprocessor) and transmitted to a cloud platform or a local server through an IoT gateway (such as a Wi-Fi or Bluetooth module). Using Internet of Things (IoT) technology, real-time data transmission between the device and the cloud platform is achieved through communication protocols such as Wi-Fi, Bluetooth, and Zigbee. The real-time status data of smart sockets and sewing machines (such as current, voltage, temperature, pressure, etc.) are uploaded to the cloud or a local system for centralized management. Then, big data analysis technologies (such as Spark and Hadoop) are used to process the operating data of the devices, and machine learning models (such as regression analysis and classification models) are used to analyze the health status, performance efficiency, and fault risks of the devices. Specifically, cloud computing platforms (such as AWS and Azure) and machine learning algorithms can be adopted for data storage and real-time analysis. The system can identify possible faults of the devices (such as current overload and overheating) and evaluate the health status of the devices, and provide repair or replacement suggestions. According to the collected device data, an operating data report is automatically generated, and the report content includes the device operating status, performance evaluation, fault analysis, etc. The report can be presented in the form of charts, trend graphs, etc. Specifically, data visualization tools (such as Power BI and Tableau) are used to present the device data as easy-to-understand charts (such as line charts, bar charts, and heat maps). The generated report shows the working conditions, energy efficiency trends, fault records, and health assessments of the devices. Then, the system automatically generates and updates the device operating data report at preset time intervals (such as daily and weekly). The report content includes the working status, fault diagnosis, and energy efficiency evaluation of the devices. Specifically, automated report generation tools (such as Apache FOP and JasperReports) can be used to generate reports in PDF or HTML format regularly. The content of the automatically generated and updated report is dynamically adjusted according to the working status and fault records of the devices to ensure that the report accurately reflects the health status of the devices, and the generated operating data report is pushed to the user's smart terminal.

[0079] S206, obtain the energy efficiency data during the operation of the smart socket and the sewing machine, generate an energy efficiency report according to the energy efficiency data, and send the energy efficiency report to the smart terminal of the user.

[0080] Energy efficiency data can be data related to energy usage collected during the operation of a device. Specifically, it can include power consumption data: the electric power (e.g., wattage) consumed by the device during operation. Current data: the magnitude of the current consumed by the device (e.g., amperes). Voltage data: the voltage values of the device under different operating conditions (e.g., volts). Efficiency data: the ratio of energy input to output during the actual operation of the device, representing the energy usage efficiency of the device.

[0081] An energy efficiency report can be a comprehensive report generated based on the energy efficiency data of a device over a certain period of time. Specifically, it can include total energy consumption: the total energy consumption data of the device over a certain period. Average power consumption: the average power consumption of the device over a period of time. Energy efficiency analysis: the energy efficiency of the device under different operating modes, which may include the efficiency of the device under different workloads.

[0082] Intelligent sockets and sewing machines need to integrate energy efficiency monitoring sensors internally. These sensors mainly include: Power sensor: used to measure the power (watts, W) consumed by the device during operation. Current sensor: used to monitor the current usage (amperes, A) of the device in real time. Voltage sensor: monitors the voltage (volts, V) changes of the device. Through these sensors, the device can continuously collect energy efficiency data, including real-time power, cumulative energy consumption, etc. Then, an embedded microcontroller (such as an MCU) is used to collect and process the sensor data in real time. The data is transmitted to the cloud platform or local server through Internet of Things protocols (such as Wi-Fi, Bluetooth). Then, the collected energy efficiency data is analyzed to evaluate the energy efficiency level of the device during different time periods. The analysis content includes: Total energy consumption: the total energy consumption of the device within a certain period of time. Average power consumption: the average power consumption of the device, indicating the working efficiency of the device. Energy efficiency trend: analyze the energy efficiency change trend of the device based on historical data. Energy efficiency indicators are generated according to the data analysis results, and it is evaluated whether the device is in a high-efficiency operating state. Specifically, big data analysis and algorithms can be used: Use big data processing frameworks such as Apache Spark and Hadoop to aggregate and analyze the data. Machine learning algorithms: Machine learning can be used to model the data, identify the relationship between the device operating state and energy efficiency, and perform predictive analysis. Then, an energy efficiency report is generated based on the analyzed data. The report should include the following content: Device energy efficiency overview: Energy efficiency data of intelligent sockets and sewing machines within a specified time, such as total energy consumption, average power, etc. Energy efficiency trend analysis: The change trend of the device's energy efficiency, whether there is a problem of energy efficiency decline. Energy-saving suggestions: Give energy-saving suggestions based on the device operating conditions, such as turning off some functions in certain modes, adjusting the working mode, etc. Specifically, data visualization tools can be used: Use visualization tools such as Tableau and Power BI to convert energy efficiency data into easy-to-understand charts (for example, line charts, pie charts). Report generation tools: Use Python libraries such as Matplotlib, Plotly, Jupyter Notebook, etc. to generate report content, or use commercial tools such as Power BI to generate customized reports. Finally, use report generation tools (such as LaTeX, ReportLab) or generate reports that meet the requirements through database query tools. Use push services (such as Firebase Cloud Messaging, Apple Push Notification Service) to push the report to the user's mobile devices (such as mobile phones, tablets, PCs, etc.).

[0083] In this embodiment, the efficiency of device management is improved. Additionally, through long-term monitoring of energy efficiency and performance data, it helps users optimize energy consumption, extend the lifespan of devices, prevent failures, and reduce maintenance costs, thereby achieving a more intelligent, energy-efficient, and high-performance device usage experience. Moreover, the automated data analysis and report generation functions also provide users with simple and real-time device status and health monitoring, enhancing the user experience.

[0084] Based on the above technical solution, optionally, after sending the energy efficiency report to the user's smart terminal, the method further includes:

[0085] Collect the operation data report and energy efficiency report within a preset evaluation period, and determine the intelligent operation periods of the smart socket and the sewing machine according to the operation data report within the preset evaluation period;

[0086] Determine the energy consumption optimization periods of the smart socket and the sewing machine according to the energy efficiency report within the preset evaluation period;

[0087] Collect the historical external environment data within a preset evaluation period, and collect the future external environment data within a preset scheduling period. Determine the environmental adaptation periods of the smart socket and the sewing machine according to the historical external environment data and the future external environment data;

[0088] Obtain the user preference data, determine the scheduling data of the smart socket and the sewing machine according to the intelligent operation periods, energy consumption optimization periods, environmental adaptation periods, and user preference data, and send the scheduling data to the user's smart terminal.

[0089] In this solution, the preset evaluation period can refer to a time window set in advance in the system, usually a certain number of days, weeks, or months. This period is used for regular evaluation and analysis of the operation data and energy efficiency data of the smart socket and the sewing machine, in order to draw conclusions regarding performance, energy efficiency, etc.

[0090] The intelligent operation period can be the time period determined according to the operation data report of the device, during which the device performs best and has the highest working efficiency. During this period, the operation status, workload, functions, etc. of the device are optimized to ensure efficient and stable working performance.

[0091] The energy consumption optimization period can refer to the time period of high-efficiency operation of the device identified according to the energy efficiency report, usually the period when the power consumption is the lowest and the device operation efficiency is the highest. This period helps to maximize the energy use efficiency and reduce energy waste.

[0092] The historical external environment data can refer to data such as climate, temperature, humidity, air quality, weather, etc. of the environment where the device is located in the past period of time. These data help to analyze the impact of environmental conditions on the device performance.

[0093] Future external environment data may refer to data based on a prediction model or provided by an external environment data provider (such as a weather service), which predicts future environmental conditions such as weather, climate, temperature, etc. These data usually have a certain time span and prediction accuracy.

[0094] The environmental adaptation period may refer to the time period determined according to historical external environment data and future external environment data during which the device is most suitable for operating under specific environmental conditions.

[0095] User preference data may refer to the preference settings of users regarding device usage habits, working hours, energy efficiency requirements, environmental adaptation, etc. These data are usually automatically collected through the user's historical operations, manual input, or the learning function of intelligent devices.

[0096] Scheduling data may be the specific work arrangements of the smart socket and the sewing machine generated based on the intelligent operation period, energy consumption optimization period, environmental adaptation period, and user preference data.

[0097] The operation data report and energy efficiency report within a preset evaluation period can be read from the Internet of Things platform or the local database. The time series model (such as ARIMA or LSTM) is used to analyze the device operation status in the operation data report, and the working trend and status fluctuation of the device are obtained. For example, the model will predict whether the device will fail at a certain future moment based on the status data in the past period. Then, the fault and health data are analyzed to determine the healthy operation period. Specifically, time series prediction models such as ARIMA and LSTM are used to analyze the historical fault and health data of the device to predict the health status of the device in certain periods. The classification algorithm (such as random forest, decision tree) is used to predict the device health status based on historical data to find the healthiest operation period of the device. For example, by analyzing the fault data, it may be found that the failure rate of the device is relatively low and the health status is good during the period from 7 am to 9 am, and this period is the healthy operation period. By analyzing the time series changes of the device performance data (power consumption, efficiency, etc.) and the device operation status (such as high load, low load status) in the device operation data report, the future energy efficiency performance of the device is predicted to find the optimal operation period of the device. Specifically, the collected device operation status and device performance data can be cleaned and sorted to ensure the consistency of the data format, and the missing values and outliers are processed. The ARIMA model is used to analyze the power consumption and load change rules of the device to predict the change trend of the future energy efficiency of the device. The LSTM model is used to analyze the time series changes of the device operation status and performance data to capture the long-term dependence relationship and predict the future high-efficiency operation period. The ARIMA or LSTM model is trained through historical data, and the model is used to predict the change trends of parameters such as the power consumption and load of the device to find the optimal energy efficiency period of the device. Based on the time series analysis, it may be found that the load of the device is relatively low from 1 pm to 3 pm, the power consumption gradually decreases, and the efficiency increases, so this time period is determined as the high-efficiency operation period. According to the intersection of the healthy operation period and the high-efficiency operation period of the device, the most suitable period for the device to operate is determined. For example, if the healthy operation period is from 9 am to 11 am and the high-efficiency operation period is from 1 pm to 3 pm, then the intelligent operation period may choose from 1 pm to 3 pm to ensure that the device operates at the lowest load and the best health status.

[0098] Through cluster analysis, identify the high-efficiency operation periods of the equipment in the energy efficiency report within the preset evaluation period, that is, the periods when the equipment has the highest operating efficiency and the lowest energy consumption within certain periods. Specifically, by using regression models such as linear regression or support vector regression (SVR), analyze the energy efficiency performance of the equipment under different conditions such as load, efficiency, and power consumption. This helps to find out the periods with the optimal energy efficiency under different operating conditions. By analyzing the energy efficiency data of the equipment, obtain the relationship between the power consumption and efficiency of the equipment in each time period, so as to determine in which periods the equipment has the optimal energy efficiency. For example, the equipment has low power consumption and high efficiency from 9 o'clock to 11 o'clock, which belongs to the high-efficiency operation period. Time series models such as ARIMA or LSTM can also be used to analyze the power consumption and load changes of the equipment in different time periods. By analyzing the patterns of historical energy efficiency data, predict the periods with the optimal future energy efficiency of the equipment. For example, through time series analysis, it may be concluded that the power consumption of the equipment is stable and the efficiency is high from 2 pm to 4 pm, so it is identified as the period with the optimal energy efficiency.

[0099] Then determine the periods when the external environment has a significant impact on the operation of the equipment. Especially when the environment changes extremely, the equipment may need to reduce the load or stop working to avoid failures or reduced efficiency. Specifically, the external environment data (such as temperature, humidity, etc.) can be combined with the performance data of the equipment such as power consumption and efficiency, and multiple regression analysis is used to determine the impact of environmental factors on the equipment performance. By analyzing the changes of these factors, predict the operation performance of the equipment under specific external environments. An adaptation model based on external environmental conditions can also be created to simulate the operation performance of the equipment under different environmental conditions (such as the possibility of reduced equipment efficiency under high temperature and high humidity conditions). This helps to determine the periods when the equipment should avoid high-load operation. According to the analysis of the external environment data, determine that the equipment needs to reduce the load or adjust the operation mode during high-temperature or high-humidity periods to avoid equipment failures or performance degradation. By determining the environmental adaptation periods, the equipment can better cope with environmental changes and ensure reliable operation under adverse environmental conditions.

[0100] Finally, according to the importance of each time period and the user's usage preferences, the weighted average method can be used to set the weights of the priorities of these time periods. For example, if the user hopes that the device runs efficiently, the weight of the intelligent operation time period is larger; if the user prefers energy conservation, the weight of the energy consumption optimization time period is larger. Optimization algorithms such as genetic algorithms and particle swarm optimization (PSO) can also be used to determine the best scheduling time period based on the comprehensive time period data and user preference data. The weights of each time period are automatically adjusted by the algorithm to generate the optimal scheduling data. Through the weighted comprehensive method or optimization algorithm, the scheduling data of the device is finally determined. Elements of the scheduling data: Intelligent operation time period: The time period when the device runs healthily and efficiently, avoiding high load and failure risks. Energy efficiency optimization time period: The time period when the device is the most energy-efficient, with the minimum power consumption and the highest efficiency. Environment adaptation time period: Adjust the device operation according to the changes in the external environment (such as temperature, humidity, etc.) to ensure that the device works during the time period that adapts to the external environment and avoid negative impacts of the environment on the device performance. User preference data: Adjust the working time period of the device based on the user's needs (such as working hours, operation frequency, etc.) to ensure that the device works in line with the user's needs. Assume the scheduling data of a smart socket and a sewing machine are as follows: Smart socket:

[0101] Intelligent operation time period: 8 am to 10 am (the device runs healthily, with low load and low failure rate).

[0102] Energy efficiency optimization time period: 1 pm to 3 pm (the device has high efficiency and low power consumption).

[0103] Environment adaptation time period: 12 pm to 1 pm (the external temperature is relatively low, and the device runs with the best efficiency).

[0104] User preference data: The user prefers the smart socket to run between 6 pm and 8 pm and hopes that the device has the best energy efficiency during this time period.

[0105] Final scheduling data: Smart socket working hours: 8 am to 10 am (intelligent operation time period), 1 pm to 3 pm (energy efficiency optimization time period), 6 pm to 8 pm (adjusted according to user needs).

[0106] Sewing machine: Intelligent operation time period: 9 am to 11 am (the device runs in good condition, with moderate load and stable performance).

[0107] Energy efficiency optimization time period: 2 pm to 4 pm (the minimum power consumption and the highest efficiency).

[0108] Environment adaptation time period: According to the future temperature prediction, it is expected that the device will work at the best environmental temperature from 2 pm to 4 pm.

[0109] User preference data: The user hopes that the sewing machine can complete some processes from 4 pm to 6 pm.

[0110] Final scheduling data: Sewing machine working hours: 9 am to 11 am (intelligent operation period), 2 pm to 4 pm (energy efficiency optimization period), 4 pm to 6 pm (adjustable according to user needs).

[0111] In this solution, through reasonable intelligent analysis and scheduling, users can enjoy intelligent devices with low energy consumption, high energy efficiency, low failure rate, and long-term stable operation, improving the usage experience, reducing costs, and achieving higher equipment usage efficiency and equipment health management.

[0112] Based on the above technical solution, optionally, determine the intelligent operation periods of the intelligent socket and the sewing machine according to the operation data report within the preset evaluation period, including:

[0113] Determine the fault and health data of the operation data report within the preset evaluation period, and determine the healthy operation periods of the intelligent socket and the sewing machine according to the fault and health data;

[0114] Determine the equipment operation status and equipment performance of the operation data report within the preset evaluation period, and determine the high-efficiency operation periods of the intelligent socket and the sewing machine according to the equipment operation status and equipment performance;

[0115] Determine the intelligent operation periods of the intelligent socket and the sewing machine according to the healthy operation periods and the high-efficiency operation periods.

[0116] In this solution, the healthy operation period can refer to the time period when the equipment can operate stably and reliably under the condition of good state, no faults or overloads. The main goal is to ensure that the equipment operates without failures or excessive wear, thereby extending its service life.

[0117] The high-efficiency operation period can refer to the time period when the equipment has the optimal energy efficiency, during which the equipment can operate with the lowest energy consumption or the best working efficiency. These periods are usually when the equipment can maintain a high performance output while consuming the least amount of energy.

[0118] The operating data report and energy efficiency report within a preset evaluation period can be read from the Internet of Things platform or the local database, and the fault and health data can be analyzed to determine the healthy operating period. Specifically, time series prediction models such as ARIMA and LSTM are used to analyze the historical fault and health data of the device to predict the health status of the device at certain times. Classification algorithms (such as random forest and decision tree) are used to predict the health status of the device based on historical data to find the healthiest operating period of the device. For example, by analyzing the fault data, it may be found that the failure rate of the device is relatively low and the health status is good during the period from 7 am to 9 am, and this period is the healthy operating period. By analyzing the temporal changes of the device performance data (power consumption, efficiency, etc.) and the device operating status (such as high load and low load status) in the device operating data report, the future energy efficiency performance of the device is predicted to find the optimal operating period of the device. Specifically, the collected device operating status and device performance data can be cleaned and sorted to ensure consistent data formats and handle missing values and outliers. The ARIMA model is used to analyze the power consumption and load change rules of the device to predict the future change trend of the device energy efficiency. The LSTM model is used to analyze the time series changes of the device operating status and performance data to capture long-term dependencies and predict the future high-efficiency operating period. The ARIMA or LSTM model is trained through historical data, and the model is used to predict the change trends of parameters such as the power consumption and load of the device to find the optimal energy efficiency period of the device. Based on the time series analysis, it may be found that the load of the device is relatively low, the power consumption gradually decreases, and the efficiency increases from 1 pm to 3 pm, so this time period is determined as the high-efficiency operating period. According to the intersection of the healthy operating period and the high-efficiency operating period of the device, the most suitable period for the device to operate, that is, the intelligent operating period, is determined. For example, if the healthy operating period is from 9 am to 11 am and the high-efficiency operating period is from 1 pm to 3 pm, then the intelligent operating period may be selected from 1 pm to 3 pm to ensure that the device operates at low load and with the best health status.

[0119] In this solution, the determination of the healthy operating period is based on the fault and health data of the device, which ensures that the device operates without overloading and in a healthy state, can effectively reduce the frequency of faults, and extend the service life of the device. The determination of the high-efficiency operating period is based on the device operating status and performance data, ensuring that the device operates during the period with the optimal energy efficiency. At this time, the device has the best energy efficiency performance, the lowest consumption, and the optimal performance.

[0120] The Third Embodiment

[0121] The third embodiment of this application relates to a method for fault warning of an intelligent socket and a sewing machine. The third implementation is an improvement based on the first embodiment, and the specific improvement lies in the following steps:

[0122] S301, if a smart socket registration request is received, determine the MAC address of the smart socket and the user's Wi-Fi network configuration information according to the smart socket registration request, and establish a Bluetooth connection with the smart socket according to the MAC address.

[0123] S302, obtain the first device information of the smart socket, and register the smart socket to the Internet of Things platform according to the first device information and the Wi-Fi network configuration information.

[0124] S303, if a sewing machine registration request is received, determine the second device information of the sewing machine connected to the smart socket according to the sewing machine registration request, and register the sewing machine to the Internet of Things platform according to the second device information.

[0125] S304, monitor in real time whether there is first fault monitoring data for the smart socket and whether there is second fault monitoring data for the sewing machine. If it is detected that there is first fault monitoring data for the smart socket and / or second fault monitoring data for the sewing machine, generate an alarm message according to the first fault monitoring data and / or the second fault monitoring data, and send the alarm message to the user's smart terminal.

[0126] S305, if the user's gesture image data is received, determine the third target control device and the second operation instruction of the gesture image data according to the pre-trained gesture recognition model, and control the third target control device according to the second operation instruction.

[0127] The gesture image data can be a gesture image captured by an image acquisition device (such as a camera or a depth sensor). The image contains a specific posture or action of the user's hand, and it can be a single picture or a video frame. The gesture image data is the data input to the recognition system, and the system analyzes these images to understand the user's intention. For example: when the user makes a "waving" gesture, the image captured by the camera is the gesture image data.

[0128] The pre-trained gesture recognition model can be a deep learning model trained by using a large number of gesture image data sets. These models have learned to recognize different gestures from images and can output corresponding operations or intentions according to the characteristics of the gestures. Common gesture recognition models include convolutional neural networks (CNNs) or more complex deep learning frameworks such as convolutional-long short-term memory networks (CNN-LSTMs). For example: the model has learned various gestures (such as waving, pointing, thumbs up, etc.) through training and can predict the operation that the user wants to perform when receiving new gesture image data.

[0129] The third target control device can be a device that the user hopes to control through gesture instructions, specifically including smart sockets, sewing machines, etc. The system will determine the target device that the user wants to operate according to the recognized gesture type. For example, the user controls the switch of a smart socket through a certain gesture (such as a gesture of swiping to the right), or starts or stops a sewing machine through another gesture (such as an up-and-down swinging gesture).

[0130] The second operation instruction can be a specific control instruction generated by the gesture recognition system according to the user's gesture image data, and is used to operate the third target control device. Each gesture corresponds to a different operation instruction, and the instructions include operations such as turning the device on and off, adjusting, etc.

[0131] The user's gesture image data can be received through a camera or a sensor device. These image data are usually pictures or video frames of the user's hand movements taken by the camera, and may include information such as the user's gestures and actions. Before using the pre-trained gesture recognition model, it is necessary to preprocess the received gesture image data. The preprocessing steps usually include: Image scaling: Resize the image to a fixed size for input into the model. Normalization: Normalize the pixel values of the image so that they are within a standard range (for example, between 0 and 1). Image enhancement: Improve the robustness of the model and avoid overfitting through image enhancement techniques (such as rotation, translation, flipping). Feature extraction: Key features in the image may be extracted using techniques such as convolutional neural networks (CNNs). Then, the preprocessed image data is input into the pre-trained gesture recognition model, and the model will perform inference on the input image and output the gesture category (such as "raising the hand", "pointing to the right", "waving"). During the training process, the mapping relationship between gestures and operations can be preset. For example: raising the hand → "starting the sewing machine", pointing to the right → "turning on the smart socket", waving → "turning off the smart socket". When the model outputs the gesture category, the system converts the gesture category into a specific operation instruction (the second operation instruction) and the target device (the third target control device) according to these rules. For example, if the model recognizes the gesture category of "raising the hand", the system will judge that the target device is the sewing machine according to the rules and generate the operation instruction "starting the sewing machine". Then, according to the generated second operation instruction, the system sends a control signal to the corresponding third target control device (such as a sewing machine or a smart socket). After receiving the control signal, the device performs the corresponding operation (such as starting, stopping, turning on, turning off, etc.). For example, the system may send a "start" signal to the sewing machine to start the sewing machine.

[0132] In this solution, controlling devices through gesture recognition can not only provide a more natural, intuitive and efficient interaction method, but also improve operation safety, save time and enhance the intelligent level. It provides users with a more convenient and flexible control method, especially suitable for scenarios that require contactless operation or quick response.

[0133] Optionally, on the basis of the above technical solution, after controlling the third target control device according to the second operation instruction, the method further includes:

[0134] Obtain the current working state of the target device, input the current working state and the second operation instruction into a pre-trained gesture recognition model, and determine whether the instruction needs to be updated;

[0135] If the instruction needs to be updated, update the second operation instruction through the pre-trained gesture recognition model;

[0136] Correspondingly, controlling the third target control device according to the second operation instruction includes:

[0137] Control the third target control device according to the updated second operation instruction.

[0138] In this solution, the current working state may include: Whether the device is working properly: Whether the device is currently in an enabled state, or in a state of failure, shutdown, etc. The load state of the device: The current working load of the device. For example, a smart socket may report whether it is carrying a heavy load, and a sewing machine may show whether a complex sewing task is in progress. Device performance indicators: Such as key performance data such as power consumption, efficiency, and temperature of the device. Through these data, it can be understood whether the device is working in an efficient state, or whether problems such as overload and overheating occur. The control mode or operation mode of the device: For example, whether the device is in a standby mode, a normal working mode, a maintenance mode, etc.

[0139] Many intelligent devices are built with sensors that can monitor their working status in real time. For example, a smart socket can monitor the current through a current sensor, and a sewing machine can monitor its status through temperature and load sensors. Then, the current working status of the target device, together with the second operation instruction, is provided as input to a pre-trained gesture recognition model. Based on the current working status and operation instruction, the model conducts reasoning and judgment to determine whether the current instruction is suitable for the working status of the current device. The model will evaluate whether there are potential performance issues, uneven device loads, etc., and decide whether to adjust or update the instruction. For example, if the device is in a high-load state and the user's instruction is to start a high-load operation, the model may judge it as not suitable for the current state, so the instruction needs to be updated. If the model determines that the current operation instruction is not suitable for the device's working status (such as high load, high temperature, etc.), it will adjust or update the operation instruction according to the device's current state and a predetermined strategy. This update may include reducing the device load, changing the operation mode, delaying certain operations, etc. If an instruction needs to be updated, the gesture recognition model will generate a new operation instruction according to the device's current state and the set rules, and provide it to the device for execution. For example: Current working status: The sewing machine has a high current temperature, a large load, and is performing a complex sewing task. Second operation instruction: The user issued an instruction of "speed up" through gestures. Inference of the pre-trained gesture recognition model: The model inputs the instruction of "speed up" and the current working status of the sewing machine (high temperature, high load) into the model. The model determines that the instruction is not suitable for the current state and may cause the device to overheat or malfunction. Updated instruction: Based on the working status of the device, the model recommends "slow down" and increase the cooling time, and updates the operation instruction to "slow down and take intermittent breaks". Execution of the update: After receiving the updated instruction, the device starts to execute the new operation mode, reducing the load and temperature.

[0140] The training process of the pre-trained gesture recognition model includes:

[0141] Collect the gesture images or video frame data of the user. To ensure diversity, the data should include variations in different backgrounds, lighting, angles, and gestures. For example, gestures such as "raising the hand", "pointing to the right", "waving", etc. Each gesture category should contain at least several hundred samples. Label each image with the corresponding label (e.g., "raising the hand", "pointing to the right"). Resize each image to a fixed size, such as 224×224 pixels, to meet the input requirements of the model. Scale the image pixel values (0 - 255) to between 0 and 1 to accelerate training. Apply data augmentation techniques, such as random rotation, translation, flipping, cropping, etc., to increase the diversity of the training data and improve the robustness of the model. Then collect the real-time working state data of the device, such as temperature, load, current, working mode, etc. This data can be obtained through the built-in sensors of the device. Label the current state of the device on each device state data set. For example, the temperature of the sewing machine is too high, the current is too large, etc. Ensure that the device state data matches the gesture data in format for convenient subsequent joint training. To enable the system to understand the relationship between gestures and device states, a set of predefined device response rules need to be set for each gesture (e.g., raising the hand to start the device, pointing to the right to turn on the device, etc.). Each training sample will include: Image data: The gesture image of the user. Device state: The current working state data of the device. Operation instruction: The operation instruction corresponding to the gesture and its target device. Then, based on classical image processing networks such as convolutional neural networks (CNNs) (e.g., ResNet, VGG, MobileNet), perform the gesture recognition task. Use the prepared gesture image data for training. The goal of the model is to classify the input image and output the gesture category label (e.g., "raising the hand", "pointing to the right"). During the training process, use the cross-entropy loss function to calculate the error between the prediction result and the true label. The model uses an optimization algorithm (such as Adam) to update the weights through gradient descent. Then design the input and output data. Input: The real-time working state data of the device and the operation instruction recognized by gesture. Output: The adjusted judgment result of the instruction. This output can be binary classification (whether the instruction needs to be updated) or multi-class classification (the category of the updated operation instruction). Deep neural networks (DNNs), reinforcement learning, or decision tree models can be used to judge whether the instruction is suitable for the current device state. Input the device state data and the instruction corresponding to the gesture into the model. During the training process, the model learns the relationship between the device state and the instruction through reinforcement learning or supervised learning. The goal is to enable the model to judge whether the given instruction is suitable for the current state of the device. If not, generate a new instruction. Use model evaluation metrics (such as accuracy, recall, F1 score, etc.) to monitor the training effect. In practical applications, gesture recognition and instruction update are not completely independent. The result of gesture recognition directly affects the judgment of instruction update. Therefore, it is possible to consider jointly training the two models so that they cooperate with each other when processing a sample.The training process may be as follows: First, use the gesture recognition model to recognize gestures, then input the recognition results together with the device status into the instruction update model, and finally adjust the instructions according to the judgment results of the model. Use an independent test set to evaluate the gesture recognition model to ensure its accuracy in different scenarios. Use evaluation metrics such as confusion matrix, accuracy, and recall to evaluate the performance of the model. During the evaluation process, check whether the model can accurately judge whether the instruction is suitable for the current device status and the accuracy of its adjusted instructions. Through the test of the combination of device status and operation instructions, ensure that the model can flexibly update the instructions. Optimize the hyperparameters of the model through methods such as grid search and random search. Ensure the diversity and balance of the training data to avoid the model being biased towards a certain category due to uneven data. Then integrate the gesture recognition model and the instruction update judgment model into the system and test the performance of the entire system in a real environment. Continuously optimize the performance of the model through system feedback. For example, whether the user's operations are executed as expected and whether there are any incorrect operations. Deploy the trained gesture recognition model and instruction update judgment model to an embedded system or server for users to use in real time.

[0142] In this solution, by dynamically adjusting the instructions according to the current device status, the system can adapt to different working environments and requirements. Whether the temperature is too high, the load is too large, or the device cannot continue to execute tasks under certain special circumstances, the system can optimize the operation process by updating the instructions. The model not only executes operations based on gestures, but also combines real-time device status information for more intelligent judgment. This adaptive mechanism makes the system more flexible and accurate, and can handle more complex operating environments.

[0143] It should be noted that the third embodiment of this application can also be an improvement based on the second embodiment.

[0144] The step division of the above various methods is only for clear description. When implemented, they can be combined into one step or some steps can be split into multiple steps. As long as the same logical relationship is included, they are all within the protection scope of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of its algorithm and process are all within the protection scope of this patent.

[0145] Fourth Embodiment

[0146] The fourth embodiment of this application relates to an intelligent socket and sewing machine fault warning system, which specifically includes the following:

[0147] A Bluetooth connection module 401, configured to, if receiving an intelligent socket registration request, determine the MAC address of the intelligent socket and the user's Wi-Fi network configuration information according to the intelligent socket registration request, and perform Bluetooth connection with the intelligent socket according to the MAC address;

[0148] The intelligent socket registration module 402 is configured to obtain the first device information of the intelligent socket and register the intelligent socket to the Internet of Things platform according to the first device information and the Wi-Fi network configuration information.

[0149] The sewing machine registration module 403 is configured to, if a sewing machine registration request is received, determine the second device information of the sewing machine connected to the intelligent socket according to the sewing machine registration request, and register the sewing machine to the Internet of Things platform according to the second device information.

[0150] The warning module 404 is configured to monitor in real time whether there is first fault monitoring data of the intelligent socket and whether there is second fault monitoring data of the sewing machine. If it is monitored that there is first fault monitoring data of the intelligent socket and / or second fault monitoring data of the sewing machine, an alarm message is generated according to the first fault monitoring data and / or the second fault monitoring data, and the alarm message is sent to the user's intelligent terminal.

[0151] It is not difficult to find that this embodiment is a system embodiment corresponding to the first embodiment, and this embodiment can be implemented in cooperation with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment. To avoid repetition, they will not be elaborated here. Correspondingly, the relevant technical details mentioned in this embodiment can also be applied in the first embodiment.

[0152] It is worth mentioning that each module involved in this embodiment is a logical module. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovative part of this application, units that are not closely related to solving the technical problems proposed in this application are not introduced in this embodiment, but this does not mean that there are no other units in this embodiment.

[0153] In addition, some embodiments of this application also provide an electronic device. The electronic device can be various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and so on. The electronic device can also be various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0154] The electronic device includes: one or more processors; and a memory storing computer program instructions, where the computer program instructions, when executed, cause the processors to execute the steps of the method provided in any one or more of the above embodiments. Figure 5 An exemplary structural diagram of the electronic device is disclosed. As Figure 5As shown, the electronic device includes: one or more processors 1101, a memory 1102, and interfaces for connecting the components, including a high-speed interface and a low-speed interface. Each component is interconnected using different buses and can be mounted on a common motherboard or otherwise mounted as required. The processor can process instructions executed within the electronic device, including instructions stored in or on the memory for graphical information to be displayed on an external input / output device (such as a display device coupled to the interface) to display a GUI. In some other embodiments, multiple processors and / or multiple buses can be used in conjunction with multiple memories if needed. Similarly, multiple electronic devices can be connected, with each device providing a portion of the necessary operations (such as an array of servers, a set of blade servers, or a multi-processor system). Herein, the components shown, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described herein and / or claimed.

[0155] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103, and the output device 1104 can be connected via a bus or other means. Figure 5 Taking connection via a bus as an example.

[0156] The input device 1103 can receive input digital or character information and generate key signal inputs related to user settings and function controls of the electronic device, such as input devices like a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 1104 can include a display device, an auxiliary lighting device (such as an LED), and a haptic feedback device (such as a vibration motor), etc. The display device can include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device can be a touch screen.

[0157] To provide interaction with the user, the electronic device can be a computer. The computer has: a display device for displaying information to the user (such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (such as a mouse or a trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (such as visual feedback, auditory feedback, or haptic feedback); and input from the user can be received in any form (including voice input, speech input, or haptic input).

[0158] The flowcharts or block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of devices, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0159] The scope of the present application is defined by the appended claims rather than the above description. Therefore, all changes that fall within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference numerals in the claims should not be construed as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The multiple elements or devices stated in the apparatus claims may also be implemented by one element or device through software or hardware. The words "first", "second", etc. are only used for descriptive distinction and do not represent any specific order, nor can they be construed as indicating or implying relative importance.

[0160] As described above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily make changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.

Claims

1. A smart socket and sewing machine fault warning method, characterized in that: The method comprises: If a smart socket registration request is received, the MAC address of the smart socket and the user's Wi-Fi network configuration information are determined according to the smart socket registration request, and a Bluetooth connection is established with the smart socket according to the MAC address; Acquire first device information of the smart socket, and register the smart socket to the Internet of Things platform according to the first device information and Wi-Fi network configuration information; If a sewing machine registration request is received, determining second device information of the sewing machine connected to the smart socket according to the sewing machine registration request, and registering the sewing machine to the Internet of Things platform according to the second device information; Real-time monitoring is performed on the smart socket to determine whether there is first fault monitoring data, and real-time monitoring is performed on the sewing machine to determine whether there is second fault monitoring data. If it is detected that the smart socket has first fault monitoring data and / or the sewing machine has second fault monitoring data, an alarm message is generated based on the first fault monitoring data and / or the second fault monitoring data, and the alarm message is sent to the user's smart terminal.

2. The intelligent socket and sewing machine fault warning method according to claim 1, characterized in that: After sending the alarm information to the user's smart terminal, the method further includes: If the preset long-term analysis time interval is reached, the device operation status, device performance, and fault and health data of the smart socket and the sewing machine during operation are obtained, an operation data report is generated according to the device operation status, device performance, and fault and health data, and the operation data report is sent to the user's smart terminal; The energy efficiency data of the smart socket and the sewing machine during operation are obtained, an energy efficiency report is generated according to the energy efficiency data, and the energy efficiency report is sent to the user's smart terminal.

3. The intelligent socket and sewing machine fault warning method according to claim 1, characterized in that: After sending the alarm information to the user's smart terminal, the method further includes: If a device switch control instruction from the user is received, a first target control device is determined according to the device switch control instruction, and the switch state of the first target control device is controlled according to the switch control instruction; wherein the first target control device includes a smart socket and a sewing machine.

4. The intelligent socket and sewing machine fault warning method according to claim 2, characterized in that: After sending the energy efficiency report to the user's smart terminal, the method further includes: Collecting operation data reports and energy efficiency reports within a preset evaluation period, and determining the intelligent operation time period of the smart socket and the sewing machine according to the operation data reports within the preset evaluation period; Determine the energy consumption optimization period of the smart socket and the sewing machine according to the energy efficiency report within the preset evaluation period; Collect historical external environment data within a preset evaluation period, and collect future external environment data within a preset scheduling period, and determine the environmental adaptation period of the smart socket and the sewing machine according to the historical external environment data and the future external environment data; Obtain user preference data, determine the scheduling data of the smart socket and the sewing machine according to the smart operation time period, energy consumption optimization time period, environmental adaptation time period and user preference data, and send the scheduling data to the user's smart terminal.

5. The intelligent socket and sewing machine fault warning method according to claim 4, characterized in that: The intelligent operation time period of the smart socket and the sewing machine is determined according to the operation data report within the preset evaluation period, including: Determine the fault and health data of the operation data report within a preset evaluation period, and determine the healthy operation period of the smart socket and the sewing machine according to the fault and health data; Determine the equipment operation status and equipment performance of the operation data report within a preset evaluation period, and determine the efficient operation time period of the smart socket and the sewing machine according to the equipment operation status and equipment performance; The smart operating time period of the smart socket and the sewing machine is determined according to the healthy operating time period and the efficient operating time period.

6. The intelligent socket and sewing machine fault early warning method according to claim 1, characterized in that: After sending the alarm information to the user's smart terminal, the method further includes: If a user's voice command is received, the voice command is converted into a text command, and the text command is converted into user intention data according to NLP technology; A second target manipulation device is determined according to the user intention data, a first operation instruction is generated according to the user intention data, and the second target manipulation device is controlled according to the first operation instruction.

7. The intelligent socket and sewing machine fault warning method according to claim 1, characterized in that: After sending the alarm information to the user's smart terminal, the method further includes: If gesture image data of the user is received, a third target control device and a second operation instruction of the gesture image data are determined according to a pre-trained gesture recognition model, and the third target control device is controlled according to the second operation instruction.

8. The intelligent socket and sewing machine fault early warning method according to claim 7, characterized in that: After controlling the third target manipulation device according to the second operation instruction, the method further includes: Acquire the current working state of the target device, input the current working state and the second operation instruction into the pre-trained gesture recognition model, and determine whether the instruction needs to be updated; If the instruction needs to be updated, the second operation instruction is updated through the pre-trained gesture recognition model; Correspondingly, controlling the third target control device according to the second operation instruction includes: The third target operating device is controlled according to the updated second operating instruction.

9. A smart socket and sewing machine fault warning system, characterized in that: The system comprises: A Bluetooth connection module, for determining the MAC address of the smart socket and the user's Wi-Fi network configuration information according to the smart socket registration request if a smart socket registration request is received, and performing a Bluetooth connection with the smart socket according to the MAC address; A smart socket registration module, used to obtain first device information of the smart socket, and register the smart socket to the Internet of Things platform according to the first device information and Wi-Fi network configuration information; A sewing machine registration module, configured to, if a sewing machine registration request is received, determine second device information of the sewing machine connected to the smart socket according to the sewing machine registration request, and register the sewing machine to the Internet of Things platform according to the second device information; The early warning module is used to monitor in real time whether the smart socket has the first fault monitoring data, and to monitor in real time whether the sewing machine has the second fault monitoring data. If it is detected that the smart socket has the first fault monitoring data and / or the sewing machine has the second fault monitoring data, an alarm message is generated according to the first fault monitoring data and / or the second fault monitoring data, and the alarm message is sent to the user's smart terminal.

10. An electronic device, characterized in that: The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 8.

Images