Device control method and apparatus, electronic device, and storage medium

Abstract

The application relates to a device control method and device, a control device and a storage medium, wherein the method comprises: if a first motion state detected by a current device meets a voice wake-up condition, starting a voice recognition function to analyze received voice information to obtain a control instruction, and controlling a corresponding target device based on the control instruction; and if a second motion state detected by the current device meets a device control condition, analyzing the action of the current device to obtain a control instruction, and controlling the corresponding target device based on the control instruction. Therefore, a user can directly speak a voice instruction or make an action on the current device to control the target device, the target device can be controlled without operating physical keys on a remote controller, and the convenience of controlling the target device is improved.

Description

Technical Field

[0001] This invention relates to the field of electrical control, and more specifically to a device control method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the increasing prevalence of smart appliances, users need to control their on / off switches and functions. Traditionally, controlling devices like air conditioners, lights, and electric curtains requires pressing physical buttons on a remote control. Typically, one button corresponds to only one command, requiring different buttons to be pressed for different functions, resulting in inconvenience. Summary of the Invention

[0003] Therefore, it is necessary to provide a device control method, apparatus, electronic device, and storage medium that can improve ease of use.

[0004] A device control method, the device control method comprising: If the first motion state detected by the current device meets the voice wake-up condition, the voice recognition function is activated to parse the received voice information to obtain control commands, and to control the corresponding target device based on the control commands. If the second motion state detected by the current device meets the device control conditions, the current device's action is parsed to obtain control instructions, and the corresponding target device is controlled based on the control instructions.

[0005] A device control apparatus, comprising: The voice control module is used to enable the voice recognition function if the first motion state detected by the current device meets the voice wake-up condition, so as to parse the received voice information to obtain control commands, and control the corresponding target device based on the control commands. The motion control module is used to parse the motion of the current device to obtain control instructions if the second motion state detected by the current device meets the device control conditions, so as to control the corresponding target device based on the control instructions.

[0006] In one embodiment, the first motion state includes the motion state of the target object relative to the current device; The voice control module is also used to enable voice recognition if the current device detects that the distance between the target object and the current device is within a preset range.

[0007] In one embodiment, the first motion state includes the current motion state of the device; The voice control module is also used to determine the action of the current device based on the current device's motion state. If the current device's action is the same as the preset voice wake-up action, then the voice recognition function is activated.

[0008] In one embodiment, the second motion state includes the current motion trajectory of the device itself; The motion control module is also used to determine the motion of the current device based on its own motion trajectory. If the motion of the current device is the same as the preset device control motion, the motion of the current device is parsed to obtain control instructions.

[0009] In one embodiment, the voice control module is further configured to, during the process of receiving voice information, if a third motion state of the current device is detected, reacquire the voice information, parse the acquired voice information to obtain control commands, and control the corresponding target device based on the control commands.

[0010] In one embodiment, the control commands include voice control commands and motion control commands; The voice control module is also used to parse the received voice information to obtain voice control commands, and send the voice control commands to the target device through the first communication link or the second communication link to control the target device; The motion control module is also used to parse the current device's motion to obtain motion control instructions, and send the motion control instructions to the target device through the second communication link to control the target device.

[0011] In one embodiment, the device control device further includes a mode switching module, which is used to detect the motion state of the current device when the current device is in sleep mode. If the motion state of the current device is detected to be in a first motion state and / or a second motion state, the current device is switched from sleep mode to wake-up mode.

[0012] In one embodiment, the mode switching module is further configured to switch the wake-up mode of the current device to sleep mode if the current device is in wake-up mode and no motion state of the current device is detected to be in a first motion state or a second motion state within a preset time.

[0013] An electronic device, comprising: The motion recognition unit is used to detect the current motion state of the device; Voice acquisition unit, used to receive voice information; The processor, connected to the motion recognition unit and the voice acquisition unit, is used to detect the motion state of the current device through the motion recognition unit. If the detected first motion state meets the voice wake-up condition, the voice recognition function is activated to receive voice information through the voice acquisition unit, parse the received voice information to obtain control commands, and control the corresponding target device based on the control commands. If the detected second motion state meets the device control condition, the current device's motion is parsed to obtain control commands, and the corresponding target device is controlled based on the control commands.

[0014] In one embodiment, the first motion state includes the motion state of the target object relative to the current device; The processor is also configured to enable the voice recognition function if the distance between the target object and the current device is detected to be within a preset range.

[0015] In one embodiment, the first motion state includes the current motion state of the device itself; The processor is also used to determine the action of the current device based on its own motion state. If the action of the current device is the same as the preset voice wake-up action, then the voice recognition function is activated.

[0016] In one embodiment, the second motion state includes the current motion trajectory of the device itself; The processor is also used to determine the action of the current device based on the motion trajectory of the current device itself. If the action of the current device is the same as the preset device control action, the processor will parse the action of the current device to obtain control instructions.

[0017] In one embodiment, the processor is further configured to, during the process of receiving voice information, if a second motion state of the current device is detected, reacquire the voice information, parse the acquired voice information to obtain control instructions, and control the corresponding target device based on the control instructions.

[0018] In one embodiment, the control commands include voice control commands and motion control commands; The processor is also configured to parse the received voice information to obtain voice control commands, and send the voice control commands to the target device through a first communication link or a second communication link to control the target device; and to parse the current device's actions to obtain action control commands, and send the action control commands to the target device through the second communication link to control the target device.

[0019] In one embodiment, the processor is further configured to detect the motion state of the current device when the current device is in sleep mode, and if the motion state of the current device is detected to be in a first motion state and / or a second motion state, then switch the sleep mode of the current device to a wake-up mode.

[0020] In one embodiment, the processor is further configured to switch the wake-up mode of the current device to a sleep mode if, when the current device is in wake-up mode, no motion state of the current device is detected to be in a first motion state or a second motion state within a preset time.

[0021] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the device control methods of various embodiments of this application.

[0022] A computer program product or computer program includes computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, it implements the steps of the device control methods in the embodiments of this application.

[0023] According to the device control method, apparatus, electronic device, and storage medium of the above embodiments, if the first motion state detected by the current device meets the voice wake-up condition, the voice recognition function is activated to parse the received voice information to obtain control commands, and the corresponding target device is controlled based on the control commands, thereby allowing the user to directly speak voice commands to control the target device; if the second motion state detected by the current device meets the device control condition, the action of the current device is parsed to obtain control commands, and the corresponding target device is controlled based on the control commands, thereby allowing the user to perform actions on the current device to control the target device. Thus, the user can control the target device without operating physical buttons on the remote control, improving the convenience of operating the target device. Attached Figure Description

[0024] Figure 1 This is an application environment diagram of a device control method in one embodiment; Figure 2 A flowchart of a device control method in one embodiment; Figure 3 This is a schematic diagram of the transmission of voice control commands via a first communication link in one embodiment; Figure 4 This is a schematic diagram of the transmission of voice control commands via a second communication link in one embodiment; Figure 5This is a schematic diagram of the transmission of action control commands via the second communication link in one embodiment; Figure 6 This is a flowchart illustrating the working logic of a device control method in one embodiment; Figure 7 This is a schematic diagram of the structure of a device control device in one embodiment; Figure 8 This is a schematic diagram of the device control apparatus in another embodiment; Figure 9 This is a schematic diagram of the structure of an electronic device in one embodiment; Figure 10 This is a schematic diagram of the structure of an electronic device in another embodiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0026] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0027] The serial numbers assigned to components in this document, such as "first" and "second," are used only to distinguish the described objects and have no sequential or technical meaning. The terms "connection" and "linkage" used in this application, unless otherwise specified, include both direct and indirect connections (linkages).

[0028] The device control method provided in this application can be applied to Figure 1 The implementation environment shown is an Internet of Things (IoT) platform, which includes terminal devices 100, servers 400, gateways 200, and IoT devices 300 deployed in gateways 200. The number of gateways 200 and the number of IoT devices 300 are both one or more. Figure 1 The IoT devices 300 include smart air conditioners, smart curtains, smart lights, and other devices. If there are multiple gateways 200, different gateways 200 can also communicate with each other.

[0029] The terminal device 100 may be a smartphone, a smart remote control, a Rubik's Cube controller, a smart control panel, a smart speaker, etc., and may implement the device control methods of the embodiments of this application.

[0030] A network connection is established between the terminal device 100 and the gateway 200. In one embodiment, the terminal device 100 and the gateway 200 establish a network connection via communication path A, such as a local area network (LAN) path, including Wi-Fi, ZigBee, or Bluetooth. The terminal device 100 and the gateway 200 can also establish a network connection via communication path B, such as a wide area network (WAN) path, including 2G / 3G / 4G / 5G, Wi-Fi, etc. Through this network connection, the terminal device 100 interacts with the gateway 200, enabling the user to control the IoT device 300 connected to the gateway 200 to perform corresponding actions.

[0031] IoT device 300 connects to gateway 200 in the IoT platform and communicates with gateway 200 through its own configured communication modules (such as Zigbee module, WIFI module, Bluetooth communication module, etc.), thereby being controlled by gateway 200. In one embodiment, IoT device 300 connects to gateway 200 via a local area network (LAN), thus being deployed within gateway 200. The process of IoT device 300 connecting to gateway 200 via LAN includes gateway 200 first establishing a LAN, and IoT device 300 connecting to gateway 200 to access the LAN established by gateway 200. IoT device 300 can be a smart home device, specifically a smart air conditioner, smart light, electric curtains, etc., without limitation.

[0032] Server 400 can be implemented using a standalone server or a server cluster consisting of multiple servers. Server 400 can be a local server or a cloud server. Gateway 200 and server 400 can establish a wireless communication connection to exchange information, thereby enabling server 400 to further interact with terminal device 100 and IoT device 300 through gateway 200. Information or instructions sent by terminal device 100 can be sent to IoT device 300 through gateway 200, or through gateway 200 and server 400.

[0033] Figure 2 This is a flowchart of a device control method in one embodiment. The following description uses the application of this method to an electronic device as an example. Specifically, the electronic device may be... Figure 1 Terminal device 100, such as Figure 2 As shown, the method includes steps 110 to 150, which are described in detail below.

[0034] Step 110: The current device detects the motion status.

[0035] The current device refers to the electronic device being used by the user to control the target device. This electronic device controls the target device by executing the device control method of the embodiments of this application. The target device is the device that the user wants to control and is also the executor of the instructions issued by the current device. The target device receives control instructions sent by the current device and performs corresponding actions according to the control instructions, thereby being controlled by the current device. The target device can be... Figure 1 The IoT devices 300 mentioned can specifically include smart air conditioners, smart lights, electric curtains, etc., without being limited here.

[0036] Motion state refers to the state of an object relative to a reference object when it is performing mechanical motion. It indicates the type of motion the object is undergoing, including changes in its position and posture. The reference object can be the current device or a target object. Here, motion state refers to the motion state that the current device can perceive; it can be the motion state of the current device itself or the motion state of a specific target object. Users can perform different actions on the current device to put it into different motion states. The target object is an object other than the current device itself, and the current device can issue control commands based on the motion state of that object; for example, the target object can be a human body, an animal, etc.

[0037] The motion state that a device can sense depends on the motion sensor it is equipped with. The device can detect motion through this motion sensor. Motion sensors include triaxial accelerometers, six-axis sensors, proximity sensors, and PIR (Passive Infrared Radiation) sensors. Among them, triaxial accelerometers and six-axis sensors can detect the motion state of the current device, while proximity sensors and PIR sensors can detect the motion state of the target object.

[0038] Specifically, the current device detects motion by acquiring parameters or signals generated by the motion sensor due to the movement of the current device or target object. Based on the triggerable control method, motion states can be pre-categorized into different types; in this embodiment, the control method may include voice control and motion control.

[0039] Voice control refers to controlling a target device based on user-inputted voice information, while motion control refers to controlling a target device based on user actions performed on the current device. Accordingly, motion states can be categorized into a first motion state, a second motion state, and other motion states. The first motion state is one that can trigger voice control, the second motion state is one that can trigger motion control, and other motion states are those that neither trigger voice control nor motion control. It should be noted that the first and second motion states do not necessarily directly trigger the corresponding control methods; certain conditions must be met for the corresponding control methods to be triggered.

[0040] Motion sensors generate different parameters or signals for different motion states, and the current device can make a judgment on the motion state based on these parameters or signals.

[0041] Step 120: Determine whether the first motion state meets the voice wake-up conditions.

[0042] If the current device detects the first motion state, then step 120 is executed. The voice wake-up condition refers to the conditions that must be met to activate the voice recognition function of the current device; specifically, it can be the position, posture, or orientation of the current device or target object.

[0043] Specifically, the device can determine whether the first motion state meets the voice wake-up condition based on the parameters or signals of the first motion state. If the parameters are within a preset range, or the trend of signal amplitude change conforms to a preset trend, the first motion state is determined to meet the voice wake-up condition. The preset range and preset trend are set according to the parameters and signal amplitude change trend corresponding to the first motion state that can wake up the device's voice recognition function, respectively.

[0044] Step 130: Enable the voice recognition function to parse the received voice information to obtain control commands, and control the corresponding target device based on the control commands.

[0045] If the first motion state detected by the current device meets the voice wake-up condition, then step 130 is executed. At this time, the voice recognition function of the current device is activated, the user speaks a voice command to the current device, the current device receives the voice information, and the voice information is parsed to obtain the control command.

[0046] Voice information parsing refers to the process of performing semantic analysis on the voice information to determine the corresponding control commands. Voice information parsing can be done locally, including parsing on the current device, or the current device can send the voice information to... Figure 1The gateway 200 can parse the voice information, or the voice information can be sent to the server 400 for parsing. The current device, gateway 200, or server 400 can use AI (Artificial Intelligence) voice recognition to parse the voice information. Before parsing, the voice information can also be preprocessed such as noise reduction and compression.

[0047] The control command indicates the action to be performed and the target device to perform the action. The current device or gateway 200 sends the control command to the target device so that the target device performs the action, thereby realizing the control of the target device.

[0048] Step 140: Determine whether the second motion state meets the equipment control conditions.

[0049] If the current device detects a second motion state, then step 140 is executed. The device control conditions are the conditions that must be met to analyze the current device's actions, specifically the position, attitude, orientation, etc., of the current device or target object.

[0050] Specifically, the current device can determine whether the second motion state meets the device control conditions based on the parameters or signals of the second motion state. If the parameters are within a preset range, or the trend of signal amplitude change conforms to a preset trend, then the second motion state is determined to meet the device control conditions. The preset range and preset trend are set according to the parameters and signal amplitude change trends corresponding to the second motion state that enable the current device's action to be parsed and control commands to be obtained.

[0051] Step 150: Analyze the current device's actions to obtain control commands, and control the corresponding target device based on the control commands.

[0052] If the second motion state detected by the current device meets the device control conditions, step 150 is executed. At this time, the current device determines its action based on the second motion state, parses the action of the current device to obtain control commands, and controls the corresponding target device based on the control commands.

[0053] Parsing the actions of the current device refers to the process of determining the corresponding control commands based on the correspondence between the current device's actions and control commands. Parsing the actions of the current device can be done locally, including parsing on the current device itself and when the current device sends voice information to... Figure 1 The gateway 200 in the process performs parsing. The correspondence between the current device's actions and control commands can be pre-established and stored in the current device or gateway 200. The current device or gateway 200 obtains the control commands by looking up the control commands corresponding to the current device's actions.

[0054] The control command indicates the action to be performed and the target device to perform the action. The current device or gateway 200 sends the control command to the target device so that the target device performs the action, thereby realizing the control of the target device.

[0055] The device control method of this embodiment, if the first motion state detected by the current device meets the voice wake-up condition, then the voice recognition function is activated to parse the received voice information to obtain control commands, and the corresponding target device is controlled based on the control commands. This allows the user to perform actions on the current device to activate the voice recognition function, and then directly speak voice commands to control the target device. If the second motion state detected by the current device meets the device control condition, then the actions of the current device are parsed to obtain control commands, and the corresponding target device is controlled based on these control commands. This allows the user to perform actions on the current device to control the target device. Therefore, the user can control the target device without operating physical buttons on the remote control, improving the convenience of operating the target device. Furthermore, operation is possible even in non-visual environments, allowing users unfamiliar with technology to easily operate the smart device.

[0056] In one embodiment, the first motion state includes the motion state of the target object relative to the current device, such as the target object approaching or moving away from the current device. In step 130, if the first motion state detected by the current device satisfies the voice wake-up condition, then the voice recognition function is activated, including: if the current device detects that the distance between the target object and the current device is within a preset range, then the voice recognition function is activated.

[0057] Specifically, the current device can detect the motion state of the target object relative to the current device through proximity sensors, PIR sensors, etc., and determine the distance between the target object and the current device based on the strength of the electromagnetic signals transmitted by the proximity sensors and PIR sensors. When the strength of the electromagnetic signals is within a certain range, it is determined that the distance between the target object and the current device is within a preset range, and then the voice recognition function is activated.

[0058] In this embodiment, when the distance between the target object and the current device is within a preset range, the current device activates the voice recognition function, allowing the user to control the target device by speaking voice commands as they approach the current device, without the need for manual operation, thus further improving ease of use.

[0059] In one embodiment, the first motion state includes the current motion state of the device. In step 130, if the first motion state detected by the current device satisfies the voice wake-up condition, then the voice recognition function is activated, including: determining the action of the current device based on its motion state; if the action of the current device is the same as a preset voice wake-up action, then the voice recognition function is activated. The current motion state of the device includes the motion state of the current device relative to the target object, and the motion trajectory of the current device itself.

[0060] The current motion state of the device relative to the target object can be a rising, falling, approaching, or moving away motion. For example, if a user picks up the device, the device's motion state relative to the user changes from stationary to rising. The device determines its action based on its motion state relative to the target object. For instance, if the device is detected to be rising relative to the user, it can be determined that the user has picked it up.

[0061] The current device's trajectory is the path it takes from its starting position to its ending position as it moves through space. Different user actions trigger different trajectories. For example, tapping the device results in a slightly undulating curve; shaking it results in a undulating curve; and pushing it results in a straight line parallel to the horizontal plane, and so on. The device determines the user's action based on its trajectory. For instance, detecting slight up-and-down undulations indicates a tap; detecting left-and-right undulations indicates shaking; and detecting movement along a straight line parallel to the horizontal plane indicates pushing, and so on.

[0062] If the current device's action matches the preset voice wake-up action, the voice recognition function is activated, allowing the user to initiate the voice recognition function by performing that action. The voice wake-up action could be picking up the device, tapping the device, etc., and can be customized according to the user's habits. Specifically, the current device's action matching the preset voice wake-up action could mean that the parameters acquired by the device's motion sensor fall within the parameter range corresponding to the voice wake-up action, or that the parameter change curve is the same as the parameter change curve corresponding to the voice wake-up action.

[0063] In this embodiment, the current device can determine its action based on its own motion state. If the current device's action is the same as the preset voice wake-up action, the current device will activate the voice recognition function. This allows the user to activate the voice recognition function simply by performing the preset voice wake-up action on the current device, without needing to operate a physical button. The voice recognition function can be easily activated even in dark environments, making the use of the voice recognition function simpler and its application scenarios more extensive.

[0064] In one embodiment, the second motion state includes the motion trajectory of the current device itself. In step 130, if the second motion state detected by the current device satisfies the device control conditions, then the action of the current device is parsed to obtain a control command, including: determining the action of the current device based on its own motion trajectory; if the action of the current device is the same as a preset device control action, then the action of the current device is parsed to obtain a control command.

[0065] For information on determining the action of a device based on its own motion trajectory, please refer to the explanation above; it will not be repeated here.

[0066] If the current device's action is the same as the preset device control action, the action is parsed to obtain the control command, allowing the user to control the target device by performing that action. Device control actions can include shaking, flipping, or pushing the current device, and can be set according to user habits. Different device control actions correspond to different control commands, controlling different target devices to perform different actions. For actions like flipping and rotating, different angles constitute different device control actions. For example, pushing the current device can turn on a light, flipping it 90° can turn on an air conditioner, and flipping it 180° can close curtains. Specifically, the current device's action being the same as the preset device control action can mean that the parameters acquired by the motion sensor of the current device fall within the parameter range corresponding to the device control action, or that the parameter change curve is the same as the parameter change curve corresponding to the device control action.

[0067] In this embodiment, the current device can determine its action based on its own motion trajectory. If the current device's action is the same as the preset device control action, the current device's action is parsed to obtain the control command. Different device control actions correspond to different control commands, allowing users to control different target devices to perform different actions by performing different device control actions on the current device. Unlike existing remote controls, users do not need to search for the button corresponding to the function they want to achieve among a large number of buttons, making the control of the target device simpler and more convenient.

[0068] In one embodiment, the device control method of this application further includes: during the process of receiving voice information, if a third motion state of the current device is detected, the voice information is reacquired, the acquired voice information is parsed to obtain control instructions, and the corresponding target device is controlled based on the control instructions.

[0069] Once the device has voice recognition enabled, it receives voice information. If a third motion state of the device is detected during this process, the voice information is reacquired. At this time, the previously received voice information is parsed to obtain a control command, and the reacquired voice information is also parsed to obtain another control command. This allows the user to record multiple voice messages and issue multiple control commands in one voice recognition process.

[0070] Specifically, the current device can reacquire voice information upon detecting any third motion state, or it can determine the current device's action based on the third motion state, such as determining the current device's action based on its own motion trajectory. If the current device's action is the same as a preset sentence segmentation action, then the voice information is reacquired. Sentence segmentation actions can include shaking the current device, tapping the current device, etc.

[0071] In this embodiment, when a user wants to perform multiple controls simultaneously while recording voice information, they can perform an action that puts the current device into a third motion state to achieve sentence segmentation and continuously input multiple voice messages without having to repeatedly start the voice recognition function, which is convenient to use and further improves convenience.

[0072] In one embodiment, the control commands include voice control commands and action control commands. The step of parsing the received voice information to obtain the control commands and controlling the corresponding target device based on the control commands includes: parsing the received voice information to obtain the voice control commands, and sending the voice control commands to the target device via a first communication link or a second communication link to control the target device; the step of parsing the actions of the current device to obtain the control commands and controlling the corresponding target device based on the control commands includes: parsing the actions of the current device to obtain action control commands, and sending the action control commands to the target device via the second communication link to control the target device.

[0073] In this embodiment, control commands can be transmitted to the target device through two communication links: a first communication link and a second communication link. Voice control commands can be sent to the target device through either the first or second communication link, while action control commands can be sent to the target device through the second communication link. The first communication link can be a wide area network (WAN) communication link, such as 2G / 3G / 4G / 5G, or Wi-Fi; or it can be a local area network (LAN) communication link, such as Wi-Fi, ZigBee, or Bluetooth.

[0074] Please refer to Figure 3 The first communication link can consist of a current device, a relay device, a server, and a target device. The relay device connects the current device, the server, and the target device to enable network communication among them. The current device first establishes a connection with the relay device and sends the acquired voice information to the relay device. The relay device then sends the voice information to the server, which performs semantic parsing to obtain the corresponding control commands. The server then sends the control commands to the relay device, which in turn sends the control commands to the target device to control it.

[0075] Please refer to Figure 4 and Figure 5 The second communication link can consist of the current device, a relay device, and the target device. For example... Figure 4 As shown, when a voice control command is sent through the second communication link, the current device first establishes a connection with the relay device and sends the acquired voice information to the relay device. The relay device performs semantic parsing to obtain the corresponding control command, and then sends the control command to the target device to control the target device.

[0076] like Figure 5 As shown, when an action control command is sent through the second communication link, the current device first establishes a connection with the relay device and sends the action information of the current device to the relay device. The relay device then parses the action information of the current device to obtain the corresponding control command, and then sends the control command to the target device to control the target device.

[0077] Among them, relay equipment can be Figure 1 Gateway 200, etc., the server can be Figure 1 The server in question is 400, etc. Specifically, the server could be a cloud server, in which case the first communication link is... Figure 1 Communication link B in the middle, the second communication link is Figure 1 Communication link A in the middle.

[0078] Because the amount of voice information data is large, this embodiment sets up two communication links to parse the voice information and transmit voice control commands. When one of the communication links cannot transmit the voice control commands normally due to failure, blockage, etc., it can be transmitted through the other communication link. Furthermore, the transmission links for voice control commands and action control commands can be the same or different, thereby avoiding communication congestion and making the transmission of voice control commands stable and reliable, ensuring that the target device can receive both voice control commands and action control commands.

[0079] The device control method in one embodiment of this application further includes: when the current device is in sleep mode, detecting the motion state of the current device; if the motion state of the current device is detected to be in a first motion state and / or a second motion state, then switching the sleep mode of the current device to a wake-up mode.

[0080] In this embodiment, the current device has a sleep mode and a wake-up mode. In sleep mode, the current device is temporarily powered off and in a non-working state, which saves power consumption. In wake-up mode, the current device can work normally, and the user can control the target device by recording voice or performing actions on the current device. When the current device is in sleep mode, its own motion state is detected. If the current device detects that its own motion state is in a first motion state and / or a second motion state, it switches from sleep mode to wake-up mode so that the user can use the current device to control the target device normally.

[0081] Based on the above embodiments, the device control method of this application further includes: when the current device is in wake-up mode, if no motion state of the current device in the first motion state or the second motion state is detected within a preset time, then the wake-up mode of the current device is switched to sleep mode. The preset time may be, for example, 3 seconds.

[0082] If the device is in wake-up mode and no movement state of the device in the first or second motion state is detected within a preset time, it can be determined that the device has stopped and the user has put the device down, and is likely not using the device for the time being. Therefore, the wake-up mode is switched to sleep mode to save power.

[0083] This application also provides an application scenario, which can specifically be a smart home scenario, and the above-mentioned device control method is applied in this application scenario as follows: Specifically, the current device is a wireless remote control device equipped with a six-axis sensor and / or a three-axis accelerometer, as well as a proximity sensor. The six-axis sensor and / or the three-axis accelerometer are used to detect the motion state of the wireless remote control device itself to identify the user's actions on the device. The proximity sensor is used to detect the distance between the target object and the wireless remote control device; the target object is a human body. Controlled target devices include air conditioners, lights, curtains, etc.

[0084] When the distance between the human body and the wireless remote control device is within the preset range, the wireless remote control device will activate the voice recognition function. The preset voice wake-up action is to pick up the device, the preset sentence interruption action is to shake the device, and the preset device control actions include gently pushing the device, rotating the device, flipping the device 180°, flipping the device 90°, etc.

[0085] Please refer to Figure 6 Initially, the wireless remote control device is in sleep mode. When a user approaches the device, the voice recognition function is activated, and the wireless remote control device switches to wake-up mode. When the user picks up the device, the six-axis sensor and / or three-axis accelerometer detect the action of picking up the device from a stationary position, and the wireless remote control device activates the voice recognition function and switches to wake-up mode.

[0086] Once the voice recognition function is enabled, the user can say "turn on the living room light" to the wireless remote control device. The wireless remote control device receives the voice information, which is then preprocessed such as noise reduction and compression before semantic parsing. The voice information is then recognized as "turn on the living room light," and the device sends the command to turn on the light in the living room.

[0087] After the user says "Turn on the living room light," they shake the device and continue saying "Open the bedroom curtains." The six-axis sensor and / or three-axis accelerometer detect the shaking action, which the wireless remote control device interprets as a sentence segmentation action. Thus, the voice information is parsed and recognized as "Open the bedroom curtains," and an open command is sent to the bedroom curtains, causing them to open.

[0088] After the message is sent, if the wireless remote control device does not detect the voice information, voice wake-up action, sentence segmentation action, or device control action within a preset time, it is determined that the device is stationary and the user has put the device down. At this time, the voice recognition function is stopped, and the device re-enters sleep mode to save power.

[0089] Initially, when a user performs a device control action, the wireless remote control switches to wake-up mode. In this mode, voice recognition is disabled; the user's actions are analyzed to obtain the corresponding control commands, which are then sent to the target device for control. For example, if initially configured to turn on a light by gently pushing the device and close the bedroom curtains by rotating it 180°, then after the user gently pushes the wireless remote control, it sends an "on" command to the light, turning it on. Similarly, after the user rotates the device 180°, it sends a "close" command to the bedroom curtains, closing them.

[0090] After the message is sent, if the wireless remote control device does not detect the voice wake-up action, sentence interruption action, or device control action within a preset time, it is determined that the device is stationary and the user has put the device down. At this time, the voice recognition function is stopped, and the device re-enters sleep mode to save power.

[0091] The communication links for transmitting voice control commands and action control commands are different.

[0092] When parsing voice information, if the wireless remote control device receives the voice information, it first establishes a connection with the gateway and transmits the voice information directly to the gateway. The gateway, acting as a relay device, uploads the voice information to the cloud. The cloud's AI voice recognition function parses the semantics, analyzes and obtains the corresponding voice control command, and then the cloud sends the voice control command to the gateway. The gateway then sends the voice control command to the target device, enabling the target device to perform the corresponding operation.

[0093] For example, a wireless remote control device receives a voice message and sends it to the gateway. After the gateway uploads the voice message to the cloud, it analyzes the semantics and interprets it as "turn on the living room light." This gives the cloud a voice control command to turn on the light in the living room. The cloud then sends this voice control command to the gateway, which in turn sends the command to turn on the light in the living room.

[0094] Alternatively, voice parsing can be performed locally on the gateway, without needing to connect to the cloud for processing. When the wireless remote control device enables voice recognition, it first establishes a connection with the gateway, transmitting the voice information to the gateway. The gateway's local AI voice recognition function directly parses the semantics, analyzes and obtains the corresponding voice control commands, and then sends the voice control commands to the target device, enabling the target device to perform the corresponding operations.

[0095] When parsing user actions, if the wireless remote control device detects a device control action, it establishes a connection with the gateway and sends the action information to the gateway. The gateway parses the action to obtain the corresponding action control command, and then sends the action control command to the target device to enable the target device to perform the corresponding operation.

[0096] For example, the initial configuration might show that rotating the device 180° will close the bedroom curtains. When the user rotates the device 180°, the wireless remote control transmits this action information to the gateway. The gateway then parses this action and sends a closing command to the bedroom curtains.

[0097] Existing remote control solutions use physical buttons to control target devices. Control commands can only be issued by pressing physical buttons on the remote control, and each button can only correspond to one command. There are many buttons, making operation inconvenient.

[0098] The device control method of this embodiment eliminates the need for physical buttons on the wireless remote control device. Users can activate the voice recognition function simply by approaching or picking up the wireless remote control device and perform different device control actions to control different target devices to perform different actions. This eliminates the need to search for the corresponding button among numerous buttons, making the control of the target device simpler and more convenient. It overcomes the limitation of the limited number of buttons and thus the limited commands that can be issued by traditional remote controls. Furthermore, it can be operated even in non-visual environments, allowing users who are not familiar with technology to easily operate smart devices.

[0099] Secondly, when users want to perform multiple controls simultaneously while recording voice information, they can shake the wireless remote control device to continuously input multiple voice messages without having to repeatedly activate the voice recognition function, making it convenient to use and further improving ease of use.

[0100] In addition, this embodiment sets up two communication links to parse voice information and transmit voice control commands. When one of the communication links cannot transmit voice control commands normally due to failure, blockage, etc., it can be transmitted through the other communication link. Furthermore, the transmission links for voice control commands and action control commands can be the same or different, thereby avoiding communication congestion and making the transmission of voice control commands stable and reliable, ensuring that the target device can receive voice control commands and action control commands.

[0101] Finally, when the device is wirelessly controlled, it switches to sleep mode to save power.

[0102] This application also provides an equipment control device, please refer to... Figure 7 In one embodiment, the device includes a voice control module 71 and a motion control module 72, which are described below.

[0103] The voice control module 71 is used to enable the voice recognition function if the first motion state detected by the current device meets the voice wake-up condition, so as to parse the received voice information to obtain control commands, and control the corresponding target device based on the control commands.

[0104] The motion control module 72 is used to parse the motion of the current device to obtain a control command if the second motion state detected by the current device meets the device control conditions, so as to control the corresponding target device based on the control command.

[0105] In one embodiment, the first motion state includes the motion state of the target object relative to the current device, and the voice control module 71 is further configured to enable the voice recognition function if the current device detects that the distance between the target object and the current device is within a preset range.

[0106] In one embodiment, the first motion state includes the current motion state of the device. The voice control module 71 is further configured to determine the action of the current device based on the current motion state. If the action of the current device is the same as the preset voice wake-up action, then the voice recognition function is activated.

[0107] In one embodiment, the second motion state includes the motion trajectory of the current device itself. The motion control module 72 is further configured to determine the motion of the current device based on the motion trajectory of the current device itself. If the motion of the current device is the same as the preset device control motion, the motion of the current device is parsed to obtain control instructions.

[0108] In one embodiment, the voice control module 71 is further configured to, during the process of receiving voice information, if a second motion state of the current device is detected, reacquire the voice information, parse the acquired voice information to obtain control instructions, and control the corresponding target device based on the control instructions.

[0109] In one embodiment, the control commands include voice control commands and action control commands; the voice control module 71 is further configured to parse the received voice information to obtain voice control commands, and send the voice control commands to the target device through a first communication link or a second communication link to control the target device; the action control module 72 is further configured to parse the current device's actions to obtain action control commands, and send the action control commands to the target device through a second communication link to control the target device.

[0110] Please refer to Figure 8 In one embodiment, the device control device further includes a mode switching module 73. The mode switching module 73 is used to detect the motion state of the current device when the current device is in sleep mode. If the motion state of the current device is detected to be in a first motion state and / or a second motion state, the current device's sleep mode is switched to wake-up mode.

[0111] In one embodiment, the mode switching module 73 is further configured to switch the wake-up mode of the current device to sleep mode if the current device is in wake-up mode and no motion state of the current device is detected to be in the first motion state or the second motion state within a preset time.

[0112] This application also provides an electronic device, please refer to... Figure 9 In one embodiment, the electronic device includes an action recognition unit 91, a voice acquisition unit 92, and a processor 93. When the processor executes a computer program, it implements the steps in the above-described method embodiments. These will be described separately below.

[0113] The motion recognition unit 91 is used to detect the current motion state of the device. The motion recognition unit 91 can be a motion sensor, specifically a three-axis accelerometer, a six-axis sensor, a proximity sensor, a PIR sensor, etc. The three-axis accelerometer and six-axis sensor can detect the motion state of the electronic device, while the proximity sensor and PIR sensor can detect the motion state of the target object. There can be one or more motion recognition units 91.

[0114] The voice acquisition unit 92 is used to receive voice information. Specifically, the voice acquisition unit 92 may be a microphone (MIC), etc.

[0115] The processor 93 is connected to the motion recognition unit 91 and the voice acquisition unit 92. It is used to detect the motion state of the current device through the motion recognition unit 91. If the detected first motion state meets the voice wake-up condition, the voice recognition function is activated so as to receive voice information through the voice acquisition unit 92, parse the received voice information to obtain control commands, and control the corresponding target device based on the control commands. If the detected second motion state meets the device control condition, the current device motion is parsed to obtain control commands, and the corresponding target device is controlled based on the control commands.

[0116] The processor 93 can be implemented in at least one of the following hardware forms: microprocessor (MCU), digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA).

[0117] In one embodiment, the first motion state includes the motion state of the target object relative to the current device, and the processor 93 is further configured to enable the voice recognition function if the distance between the target object and the current device is detected to be within a preset range.

[0118] In one embodiment, the first motion state includes the current motion state of the device itself. The processor 93 is further configured to determine the action of the current device based on the current motion state of the device itself. If the action of the current device is the same as the preset voice wake-up action, then the voice recognition function is enabled.

[0119] In one embodiment, the second motion state includes the motion trajectory of the current device itself. The processor 93 is further configured to determine the action of the current device based on the motion trajectory of the current device itself. If the action of the current device is the same as the preset device control action, the action of the current device is parsed to obtain control instructions.

[0120] In one embodiment, the processor 93 is further configured to, during the process of receiving voice information, if a second motion state of the current device is detected, reacquire the voice information, parse the acquired voice information to obtain control instructions, and control the corresponding target device based on the control instructions.

[0121] In one embodiment, the control instructions include voice control instructions and action control instructions. The processor 93 is further configured to parse the received voice information to obtain voice control instructions, and send the voice control instructions to the target device through a first communication link or a second communication link to control the target device; and to parse the current device's actions to obtain action control instructions, and send the action control instructions to the target device through a second communication link to control the target device.

[0122] In one embodiment, the processor 93 is further configured to detect the motion state of the current device when the current device is in sleep mode, and if the current device is detected to be in a first motion state and / or a second motion state, switch the current device from sleep mode to wake-up mode.

[0123] In one embodiment, the processor 93 is further configured to switch the wake-up mode of the current device to sleep mode if the current device is in wake-up mode and no motion state of the current device is detected to be in the first motion state or the second motion state within a preset time.

[0124] For specific limitations regarding the processor 93 of the electronic device, please refer to the limitations on the device control method mentioned above, which will not be repeated here.

[0125] Please refer to Figure 10 In one embodiment, the electronic device further includes a power supply unit 94 and a wireless transmission unit 95.

[0126] The power supply unit 94 is used to supply power to various hardware units on the electronic device. Specifically, the power supply unit 94 can be a lithium battery or the like.

[0127] The wireless transmitter 95 is connected to the processor 93 and is used to receive control commands sent by the processor 93, and then send these control commands to the target device to control the target device. The wireless transmitter 95 can be a wireless communication module such as ZigBee, Bluetooth, or Wi-Fi. Please refer to [reference needed]. Figure 10 In one embodiment, the processor 94 and the wireless transmitter unit 95 can be integrated on the MCU (Microcontroller Unit).

[0128] Those skilled in the art will understand that Figure 9-10 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device may also include components that are more... Figure 9-10 The more or fewer components shown, or having the same Figure 9-10 The different configurations shown.

[0129] In one embodiment of this application, a computer-readable storage medium is provided, storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0130] In one embodiment of this application, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, it implements the steps in the device control methods of various embodiments of this application.

[0131] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0132] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A device control method, characterized in that, The equipment control method includes: The current device detects the motion status; If the first motion state detected by the current device meets the voice wake-up condition, the voice recognition function of the current device is activated to parse the received voice information to obtain the first control command, and to control the corresponding target device based on the first control command; If the second motion state detected by the current device satisfies the device control conditions, the action of the current device is parsed to obtain a second control command, so as to control the corresponding target device based on the second control command; The first control command is sent to the target device via a first communication link or a second communication link, and the second control command is sent to the target device via the second communication link; the first communication link is a path to the target device via a relay device and a server, and the second communication link is a path to the target device via the relay device. During the process of receiving voice information, if the third motion state of the current device is detected, the voice information is reacquired, and the acquired voice information is parsed to obtain control commands. The corresponding target device is controlled based on the control commands, wherein the action of the current device determined according to the third motion state is the same as the preset sentence segmentation action.

2. The equipment control method as described in claim 1, characterized in that, The first motion state includes the motion state of the target object relative to the current device; If the first motion state detected by the current device satisfies the voice wake-up condition, then the voice recognition function of the current device is activated, including: If the current device detects that the distance between the target object and the current device is within a preset range, then the voice recognition function of the current device is activated.

3. The equipment control method as described in claim 1, characterized in that, The first motion state includes the current motion state of the device; If the first motion state detected by the current device satisfies the voice wake-up condition, then the voice recognition function of the current device is activated, including: The action of the current device is determined based on the current device's motion state. If the current device's action is the same as the preset voice wake-up action, then the voice recognition function is activated.

4. The equipment control method as described in claim 1, characterized in that, The second motion state includes the current motion trajectory of the device itself; If the second motion state detected by the current device satisfies the device control conditions, then the action of the current device is parsed to obtain control commands, including: The action of the current device is determined based on its own motion trajectory. If the current device's action is the same as the preset device control action, then the current device's action is parsed to obtain the control command.

5. The equipment control method as described in claim 1, characterized in that, The first control command includes voice control commands; the second control command includes action control commands. The step of parsing the received voice information to obtain control commands, and controlling the corresponding target device based on the control commands, includes: The received voice information is parsed to obtain voice control commands, and the voice control commands are sent to the target device through the first communication link or the second communication link to control the target device; Parsing the current device's actions to obtain control commands, and then controlling the corresponding target device based on the control commands, including: The actions of the current device are parsed to obtain action control commands, and the action control commands are sent to the target device through the second communication link to control the target device.

6. The equipment control method according to any one of claims 1 to 5, characterized in that, The equipment control method further includes: When the current device is in sleep mode, the motion state of the current device is detected; If the current motion state of the device is detected to be in the first motion state and / or the second motion state, the current device's sleep mode will be switched to wake-up mode.

7. The equipment control method as described in claim 6, characterized in that, The equipment control method further includes: If the current device is in wake-up mode and no motion state of the current device is detected in the first motion state or the second motion state within a preset time, the wake-up mode of the current device will be switched to sleep mode.

8. A device control apparatus, characterized in that, include: The voice control module is used to enable the voice recognition function of the current device if the first motion state detected by the current device meets the voice wake-up condition, so as to parse the received voice information to obtain the first control command, and control the corresponding target device based on the first control command. The motion control module is used to parse the motion of the current device to obtain a second control command if the second motion state detected by the current device meets the device control conditions, so as to control the corresponding target device based on the second control command; Wherein, the first control command is sent to the target device via a first communication link or a second communication link, and the second control command is sent to the target device via the second communication link; the first communication link is a path to the target device via a relay device and a server, and the second communication link is a path to the target device via the relay device; The voice control module is further configured to, during the process of receiving voice information, if a third motion state of the current device is detected, reacquire the voice information, parse the acquired voice information to obtain control commands, and control the corresponding target device based on the control commands, wherein the action of the current device determined according to the third motion state is the same as the preset sentence segmentation action.

9. An electronic device, characterized in that, include: The motion recognition unit is used to detect the current motion state of the device; Voice acquisition unit, used to receive voice information; The processor, connected to the motion recognition unit and the voice acquisition unit, is used to detect the motion state of the current device through the motion recognition unit. If the detected first motion state meets the voice wake-up condition, the voice recognition function of the current device is activated to receive voice information through the voice acquisition unit, parse the received voice information to obtain a first control command, and control the corresponding target device based on the first control command. If the detected second motion state meets the device control condition, the motion of the current device is parsed to obtain a second control command, and the corresponding target device is controlled based on the second control command. Wherein, the first control command is sent to the target device via a first communication link or a second communication link, and the second control command is sent to the target device via the second communication link; the first communication link is a path to the target device via a relay device and a server, and the second communication link is a path to the target device via the relay device; The processor is further configured to, during the process of the voice acquisition unit receiving voice information, if the action recognition unit detects the third motion state of the current device, control the voice acquisition unit to reacquire the voice information, parse the acquired voice information to obtain control instructions, and control the corresponding target device based on the control instructions, wherein the action of the current device determined according to the third motion state is the same as the preset sentence segmentation action.

10. The electronic device as claimed in claim 9, characterized in that, The first control command includes voice control commands; the second control command includes action control commands. The processor is used to parse the received voice information to obtain voice control commands, and send the voice control commands to the target device through a first communication link or a second communication link to control the target device; The system analyzes the actions of the current device to obtain action control commands, and sends the action control commands to the target device through the second communication link to control the target device.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the device control method as described in any one of claims 1 to 7.

Images