Scene switching method, terminal and storage medium

Abstract

The present application discloses a scene switching method, a terminal, and a storage medium, which include the steps of: determining whether a user has moved from a first scene to a second scene; if the user has moved to the second scene, collecting voiceprint information of the user in the second scene; determining each switching target device in the first scene based on the voiceprint information and acquiring the corresponding operating status; and determining the corresponding operating status of each target device in the second scene. The switching of device operating parameters between different scenes is realized.

Description

[Technical Field]

[0001] The present application relates to the technical field of voice interaction, and in particular to a scene switching method, a terminal, and a storage medium.

[0002] This application claims priority from a Chinese patent application filed with the China Patent Office on September 14, 2020, bearing application number 202010965434.0 and entitled "Scene switching method, terminal and storage medium," the entire contents of which are incorporated herein by reference. [Background technology]

[0003] With the development of far-field voice recognition technology, far-field devices have become widely used, and some users may have multiple far-field devices in their homes. When a user wakes up a far-field device with far-field voice, the far-field device automatically operates according to parameters preset by the user or default parameters. For example, if the scene where the user is currently located is the living room, the far-field device in the living room can be turned on upon receiving the wake-up word by querying the wake-up word "Xiao T Xiao T." When the user leaves the living room and enters a room, the far-field device in the room can be turned on again by querying the wake-up word "Xiao T Xiao T." However, because no cooperative relationship is established between the far-field devices in different scenes within the home, when the user enters a new scene, the far-field device that is turned on in the new scene continues to operate according to the parameters preset by the user or default parameters. Summary of the Invention [Problem to be solved by the invention]

[0004] However, since there is no coordination between the long-range devices in different scenes within the home, when the user enters a new scene, the long-range devices that are turned on in the new scene continue to operate according to the parameters preset by the user or default parameters. [Means for solving the problem]

[0005] The embodiments of the present application provide a scene switching method, a terminal, and a storage medium for solving the problem that when a user moves from a first scene to a second scene, a remote device that is turned on in the second scene continues to operate according to parameters preset by the user or default parameters.

[0006] In order to achieve the above object, one aspect of the present application provides a scene switching method, the scene switching method comprising: determining whether a user has moved from a first scene to a second scene; When the user moves to the second scene, collecting voiceprint information of the user in the second scene; determining each switching target device in the first scene based on the voiceprint information in the second scene, and acquiring driving state information corresponding to each switching target device; and determining driving state information corresponding to each of the target devices in the second scene based on driving state information corresponding to each of the switching target devices; Here, each of the target devices matches each of the switching target devices.

[0007] Furthermore, to achieve the above object, another aspect of the present application further provides a terminal including a memory, a processor, and a scene switching program stored in the memory and executed on the processor, wherein when the processor executes the scene switching program, determining whether a user has moved from a first scene to a second scene; When the user moves to the second scene, collect voiceprint information of the user in the second scene; determining each switching target device in the first scene based on the voiceprint information in the second scene, and acquiring driving state information corresponding to each switching target device; Determine driving state information corresponding to each of the target devices in the second scene based on driving state information corresponding to each of the switching target devices; Here, each of the target devices matches each of the switching target devices.

[0008] Furthermore, to achieve the above object, another aspect of the present application further provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to: determining whether a user has moved from a first scene to a second scene; When the user moves to the second scene, collect voiceprint information of the user in the second scene; determining each switching target device in the first scene based on the voiceprint information in the second scene, and acquiring driving state information corresponding to each switching target device; Determining driving state information corresponding to each of the target devices in the second scene based on driving state information corresponding to each of the switching target devices; Here, each of the target devices matches each of the switching target devices. [Effects of the Invention]

[0009] In this embodiment, when it is determined that a user has moved from a first scene to a second scene, voiceprint information of the user in the second scene is collected, each switching target device in the first scene is determined based on the voiceprint information, driving state information corresponding to each switching target device is acquired, the driving state information corresponding to each switching target device is transmitted to each target device in the second scene, and driving parameters corresponding to the driving state information are set for each target device. Thus, even when the user moves from the first scene to the second scene, the long-distance devices that are turned on in the second scene continue to be driven according to the parameters preset by the user in the first scene or default parameters, and the cooperation between the long-distance devices realizes switching of device driving parameters between different scenes. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a schematic diagram illustrating a terminal structure of a hardware operating environment according to an embodiment of the present application; [Figure 2] 1 is a flowchart of a first embodiment of a scene switching method of the present invention. [Figure 3] 10 is a flowchart of a second embodiment of the scene switching method of the present invention. [Figure 4] 10 is a flowchart of a third embodiment of the scene switching method of the present invention. [Figure 5] 1 is a flowchart for determining whether a user has moved from a first scene to a second scene in the scene switching method of the present application. [Figure 6] 10 is a flowchart illustrating a process for collecting voiceprint information of the user in the second scene when the scene has been moved to the second scene in the scene switching method of the present application. [Figure 7] 10 is a flowchart illustrating a method for determining each device to be switched in the first scene based on the voiceprint information in the scene switching method of the present application. [Figure 8]In the scene switching method of the present application, if the voiceprint information in the first scene matches the voiceprint information in the second scene, this is a flowchart after the step of obtaining the turned-on device that matches the target device from among the turned-on devices, and determining the turned-on device that matches the target device as the device to be switched in the first scene. [Figure 9] 10 is a flowchart for determining driving state information corresponding to each of the target devices in the second scene based on driving state information corresponding to each of the switching target devices in the scene switching method of the present application. [Figure 10] This is a flowchart after the step of transmitting driving state information corresponding to each of the switching target devices to each of the target devices in the second scene and setting driving parameters corresponding to the driving state information to each of the target devices in the scene switching method of the present application.

[0011] The achievement of the objects, functional features and advantages of the present application will be further explained in connection with the embodiments and with reference to the drawings. DETAILED DESCRIPTION OF THE INVENTION

[0012] It should be understood that the specific examples described herein are for the purpose of interpreting the present application, and are not intended to limit the present application.

[0013] The main solution of the embodiments of the present application is to determine whether a user has moved from a first scene to a second scene, and if moved to the second scene, collect voiceprint information of the user in the second scene, determine each switching target device in the first scene based on the voiceprint information in the second scene, obtain driving state information corresponding to each of the switching target devices, and determine driving state information corresponding to each of the target devices in the second scene based on the driving state information corresponding to each of the switching target devices, where each of the target devices matches each of the switching target devices.

[0014] Because no linkage relationship is established between long-range devices in different scenes within a home, when a user enters a new scene, the long-range devices that are turned on in the new scene continue to operate according to parameters preset by the user or default parameters. In contrast, when the present application determines that a user has moved from a first scene to a second scene, it collects voiceprint information of the user in the second scene, determines each switching target device in the first scene based on the voiceprint information, obtains driving state information corresponding to each switching target device, transmits the driving state information corresponding to each switching target device to each target device in the second scene, and sets driving parameters corresponding to the driving state information for each target device. The linkage relationship between the long-range devices enables switching of driving parameters of the long-range devices between different user scenes.

[0015] As shown in FIG. 1, FIG. 1 is a schematic diagram showing a terminal structure of a hardware operating environment according to an embodiment of the present application.

[0016] As shown in FIG. 1, the terminal may include a processor 1001, e.g., a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to connect and communicate between these components. The user interface 1003 may include input units such as a display and a keyboard, and the selectable user interface 1003 may further include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (e.g., a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory such as a disk memory. The memory 1005 may optionally be a storage device independent of the processor 1001.

[0017] Optionally, the terminal may further include a camera, an RF (Radio Frequency) circuit, a sensor, a remote control, an audio circuit, a WiFi module, a detector, etc. Of course, the terminal may further include other sensors such as a gyroscope, a barometer, a hygrometer, a temperature sensor, etc., and detailed descriptions thereof will be omitted here.

[0018] Those skilled in the art will understand that the terminal structure shown in FIG. 1 does not constitute a limitation on the terminal device, which may include more or fewer components than those shown, combine some components, or arrange the components differently.

[0019] As shown in FIG. 1, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a scene switching program.

[0020] In the terminal shown in FIG. 1, the network interface 1004 is mainly used to connect to a background server and perform data communication with the background server, the user interface 1003 is mainly used to connect to a client (user side) and perform data communication with the client, and the processor 1001 calls a scene switching program stored in the memory 1005, determining whether a user has moved from a first scene to a second scene; When the user moves to the second scene, collect voiceprint information of the user in the second scene; determining each switching target device in the first scene based on the voiceprint information in the second scene, and acquiring driving state information corresponding to each switching target device; can be used to perform an operation of determining driving state information corresponding to each of the target devices in the second scene based on driving state information corresponding to each of the switching target devices; Here, each of the target devices matches each of the switching target devices.

[0021] Referring to FIG. 2, FIG. 2 is a flowchart of a first embodiment of the scene switching method of the present application, which includes the following steps:

[0022] Step S10: Determine whether the user has moved from the first scene to the second scene.

[0023] As people's quality of life improves, more and more users prefer to have multiple long-range devices, such as speakers, air conditioners, televisions, etc., in their homes that form a wireless voice interaction system. Generally, in the wireless voice interaction system, a user selects one long-range device as a master device and another long-range device as a slave device, and the master device is connected to the slave device wirelessly or via a wireless hotspot located in the environment.

[0024] In this embodiment, the scenes include, but are not limited to, a living room, a room (bedroom), a kitchen, etc., and the first scene refers to the scene that exists before the user enters the current scene, and the second scene refers to the scene in which the user currently exists.

[0025] Before performing a scene switching operation, it is first necessary to determine whether the scene in which the user is currently located has changed. For example, multiple cameras are arranged in different scenes to capture images / videos of the scene in which the user is located, and device identifiers for the scene, such as the identifier 01 for the air conditioner in the living room and the identifier 02 for the air conditioner in the bedroom, are obtained from the captured images / videos. The device identifiers can be set according to the user's needs, and are not limited thereto. Based on the device identifiers, it is determined whether the scene in which the user is located has changed, where the device identifiers are pre-associated with corresponding scene information and stored. Alternatively, it is determined whether the user has moved from a first scene to a second scene based on positioning information of different scenes. In one embodiment, referring to FIG. 5, the step of determining whether the user has moved from a first scene to a second scene includes the following steps:

[0026] Step S11: Obtain location information corresponding to each of the turned-on devices in the first scene and location information corresponding to each of the target devices in the second scene.

[0027] Step S12: Determine whether the location information corresponding to each of the turned-on devices is the same as the location information corresponding to each of the target devices.

[0028] The long-range device in each scene has a built-in positioning module, and when the long-range device is turned on, the master device acquires the network identification parameters of the long-range device through the network connected to the long-range device, acquires the satellite positioning information of the long-range device based on the satellite positioning module of the long-range device, and further acquires the location information of the long-range device based on the network identification parameters and combined with the satellite positioning information, and can determine the scene in which the user is currently located based on the location information. In a similar manner, the master device acquires location information corresponding to each turned-on device in the first scene and location information corresponding to each target device in the second scene, and further determines whether the location information corresponding to each turned-on device and the location information corresponding to each target device are identical, thereby determining whether the scene in which the user is located has changed, i.e., whether the user has moved from the first scene to the second scene.

[0029] The target device is a device to be woken up in the second scene, and the device to be woken up is a device whose operating parameters have not been acquired.

[0030] Step S20: When the user moves to the second scene, collect voiceprint information of the user in the second scene.

[0031] When it is determined that the user has moved from a first scene to a second scene, for example, when the user has moved from the living room to the bedroom, whether or not the user's voice information is received is detected in real time, and when the user's voice information is received, voiceprint information of the user in the bedroom is collected based on the voice information. In one embodiment, referring to FIG. 6, when the user has moved to the second scene, the step of collecting the user's voiceprint information in the second scene includes the following steps:

[0032] Step S21: If the location information corresponding to each of the turned-on devices is different from the location information corresponding to each of the target devices, it is determined that the user has moved from the first scene to the second scene.

[0033] Step S22: It is determined whether a scene change command has been received.

[0034] Step S23: When the scene change command is received, collect voiceprint information of the user in the second scene.

[0035] If the location information corresponding to each turned-on device in the first scene is different from the location information corresponding to each target device in the second scene, it indicates that the user has moved from the first scene to the second scene. If the location information corresponding to each turned-on device in the first scene is the same as the location information corresponding to each target device in the second scene, it indicates that the scene in which the user is currently located has not changed. When the user enters the second scene, the slave device detects in real time whether it has received a scene change command transmitted by the user via far-field voice. Upon receiving the scene change command transmitted by the user, it further acquires the user's voiceprint information in the second scene. Specifically, after a far-field device in the second scene is turned on, the voice detection unit built into the slave device detects in real time an audio signal within the operating range of the slave device. Upon receiving the "scene change" command transmitted by the user via far-field voice, it determines that the user needs to switch from the first scene to the second scene, acquires the user's voice information corresponding to the scene change command, performs voiceprint recognition on the voice information to extract voiceprint feature information, and acquires the user's voiceprint information based on the voiceprint feature information.

[0036] Furthermore, the remote devices in the second scene are turned on based on the long-distance control command sent by the user. Specifically, when the user moves from the first scene to the second scene, the slave device uses a built-in voice detection unit to detect voice signals within the slave device's operating range in real time. Upon receiving the wake-up word "Xiao T Xiao T" sent by the user through far-distance voice, multiple far-distance devices in this scene are turned on. The wake-up word is preset by the user as needed and is not limited herein. When the slave device detects the wake-up word, it performs voice wake-up processing to wake up the algorithm unit in a standby state. After the algorithm unit is woken up, i.e., after changing from a standby state to an active state, the voice detection unit transmits the acquired voice signal to the algorithm unit. In response, the algorithm unit performs calculations on the acquired voice signal according to a predetermined method, including echo cancellation, reverberation cancellation, sound source localization, etc., to finally obtain a clear voice signal, which can be transmitted to the control system of the smart device. The control system of the smart device uploads the acquired voice signal to a server / cloud, the server / cloud performs voice recognition on the acquired voice signal, generates a corresponding on command based on the voice recognition result, and sends it back to the control system of the smart device, and the control system of the smart device turns on the remote device in this scene according to the on command.

[0037] Alternatively, the voice detection unit may be a low-power microphone unit with a wake-up function. Low power consumption means that the microphone unit consumes little power. Using such a microphone can reduce power consumption. Furthermore, the microphone unit may be a microphone array including at least two microphones. Using multiple microphones can improve the microphone unit's collection sensitivity for voice signals. For example, one microphone may be located at each of three positions below the far-field device: left, center, and right. This allows the user's voice signal to be optimally collected regardless of whether the user is directly facing, to the left, or to the right of the far-field device. When any microphone in the microphone array detects a wake-up word, it can wake up an algorithm unit that is in a standby state. For example, when any microphone detects a wake-up word, it can issue a wake-up signal (interrupt signal) to the algorithm unit, activating the algorithm unit to perform computational functions such as echo cancellation, reverberation cancellation, and sound source localization.

[0038] Step S30: Determine each switching target device in the first scene based on the voiceprint information, and obtain driving state information corresponding to each switching target device.

[0039] In this embodiment, the operating state information includes an on state, an off state, a recovery state, etc., and the operating state information differs depending on the device. For example, the operating state information of an air conditioner includes a cooling operating state, a heating operating state, a dehumidifying operating state, a defrosting operating state, etc., and the operating state information of a fan includes an operating state such as a natural wind operating mode, an operating state of a wind speed range, whether or not timing is present, etc.

[0040] The master device acquires each turned-on device in the first scene based on the voiceprint information, and further acquires driving status information corresponding to each turned-on device in the first scene from the storage module. For example, when the master device receives an instruction to acquire driving status information of turned-on devices, it acquires status information corresponding to each turned-on device in the first scene from the storage module based on the acquisition instruction. The acquisition instruction is triggered by the master device after receiving the voiceprint information of a user in the second scene, and the slave device performs data collection for each turned-on long-range device via the data collection module, and transmits the collected status information to the master device for storage. Furthermore, it matches the status information of each turned-on device in the first scene with device information corresponding to each target device in the second scene, determines each switching target device in the first scene based on the matching operation, and acquires driving status information corresponding to each switching target device. Therefore, referring to FIG. 7, the step of determining each switching target device in the first scene based on the voiceprint information in the second scene includes the following steps:

[0041] Step S31: Obtain device information corresponding to each of the turned-on devices in the first scene and device information corresponding to each of the target devices in the second scene.

[0042] Step S32: Match the voiceprint information in the first scene with the voiceprint information in the second scene, and match the device information corresponding to each of the turned-on devices with the device information corresponding to each of the target devices.

[0043] Step S33: If the voiceprint information in the first scene matches the voiceprint information in the second scene, obtain the turned-on device among the turned-on devices that matches the target device, and determine the turned-on device that matches the target device as the device to be switched in the first scene.

[0044] When the master device obtains the device information corresponding to each turned-on device in the first scene and the device information corresponding to each of the target devices in the second scene, the master device first matches the voiceprint information in the first scene with the voiceprint information in the second scene. If the voiceprint information in the first scene does not match the voiceprint information in the second scene, it needs to send audio prompt information to prompt the user that the current voiceprint information does not match, indicating that the user who turned on the remote device in the first scene and the user who woke up the remote device in the second scene are not the same person. If the voiceprint information in the first scene matches the voiceprint information in the second scene, the master device further matches the device information corresponding to each turned-on device with the device information corresponding to each of the target devices, where the device information includes the device type, device capabilities, device usage time, etc. If the device information corresponding to each turned-on device does not match the device information corresponding to each of the target devices, it sends audio prompt information to prompt the user to confirm the scene that currently needs conversion. If the device information corresponding to each turned-on device matches or partially matches the device information corresponding to each target device, the turned-on device that matches the target device is obtained from among the turned-on devices, and the turned-on device that matches the target device is determined to be the switching target device in the first scene. Here, when matching, the turned-on devices in the first scene are matched with the devices to be woken up in the second scene. For example, if the turned-on devices in the first scene are an air conditioner, a television, a lamp, and a speaker, and the devices to be woken up in the second scene are an air conditioner, a lamp, and a speaker, the first scene is matched with the air conditioner, the lamp, and the speaker in the second scene.If all of the devices satisfy the matching conditions, the air conditioner, lamp, and speaker are determined as the devices to be switched in the first scene, and the operating status information corresponding to each of the devices to be switched is obtained from the storage module of the master device. Here, the storage module of the master device stores the operating status information corresponding to each of the turned-on devices in the first scene as shown in Table 1. [Table 1]

[0045] Table 1 lists only some of the device information stored, and the device information also includes other operating states and operating parameters, which are not listed here.

[0046] From Table 1, the operating status and operating parameter information corresponding to each switching target device in the first scene can be obtained, for example, the air conditioner is in cooling mode, the cooling operating temperature is 26°C, the wind speed range is mid-range and the dehumidification mode is on, the current brightness range of the lamp is mid-range, the light mode is soft light mode, the speaker volume size is adjusted to 60%, and the playback mode is Bluetooth playback mode.

[0047] Furthermore, if a video playback device exists among the devices to be switched in the first scene, the playback content and playback progress of the video playback device need to be recorded. Therefore, referring to FIG. 8, after the step of obtaining the turned-on device that matches the target device among the turned-on devices and determining the turned-on device that matches the target device as the device to be switched in the first scene when the voiceprint information in the first scene matches the voiceprint information in the second scene, the method further includes the following steps:

[0048] Step S320: If a video playback device is included in the switching target devices in the first scene, obtain the playback content and playback progress of the video playback device.

[0049] Step S321: Send the playback content and the playback progress status to the video playback device in the second scene, and make the video playback device in the second scene display the playback content according to the playback progress status.

[0050] When the master device detects that the switching target device in the first scene is a video playback device such as a television, it acquires the television's current playback content and playback progress information, and when a scene switching operation is performed, it transmits the playback content and playback progress information to the television in the second scene and displays the playback content on the television in the second scene according to the playback progress. For example, the television in the first scene is playing a content on the CCTV-5 sports channel about the Chinese women's volleyball team winning an award after winning, and the playback progress is two minutes into the award-winning process. When a scene switching is performed, the television in the second scene also plays a content on the CCTV-5 sports channel about the Chinese women's volleyball team winning an award after winning, and starts playing from the second minute into the award-winning process.

[0051] Step S40: Based on the driving state information corresponding to each of the switching target devices, determine the driving state information corresponding to each of the target devices in the second scene, where each of the target devices matches each of the switching target devices.

[0052] In this embodiment, the driving state information corresponding to each target device in the second scene is determined based on the driving state information corresponding to each switching target device in the first scene, where a match between each target device and each switching target device means that the device type, device capability, device usage time, etc. between the target device and the switching target device match. Specifically, the master device determines driving parameters corresponding to each target device based on driving parameters in the driving state information corresponding to each switching target device in the first scene. In one embodiment, referring to FIG. 9, the step of determining driving state information corresponding to each target device in the second scene based on driving state information corresponding to each switching target device includes the following steps:

[0053] Step S41: Send driving state information corresponding to each of the switching target devices to each of the target devices in the second scene, and set driving parameters corresponding to the driving state information to each of the target devices.

[0054] The master device obtains corresponding operating parameters based on the operating state information corresponding to each switching target device in the first scene, and the operating parameters include operating condition parameters and operating state parameters. For example, the operating condition parameters of an air conditioner include some or all of the operating mode, power-on temperature, indoor temperature, and outdoor temperature, and the operating state parameters include some or all of the exhaust temperature, operating current, exhaust pressure, evaporation temperature, and condensation temperature.

[0055] The master device distributes the acquired operating parameters corresponding to each of the switching target devices to the corresponding wake-up devices in the second scene. After receiving the operating parameters, each of the wake-up devices in the second scene sets its current operation based on the operating parameters. For example, the currently acquired cooling operation temperature of the switching target air conditioner in the first scene is 26°C, the air speed is mid-range, the sweeping method is up / down sweep, the switching target lamp is in warm light mode, the brightness range is mid-range, the switching target fan's air speed is 3-speed, and the swing mode is left / right swing. The acquired operating parameters of the switching target air conditioner, switching target lamp, and switching target fan are transmitted to each target device in the second scene so that the cooling operation temperature of the air conditioner in the second scene is 26°C, the air speed is mid-range, the sweeping method is up / down sweep, the switching target lamp is in warm light mode, the brightness range is mid-range, the fan's air speed is 3-speed, and the swing mode is left / right swing.

[0056] Further, referring to FIG. 10 , after the step of transmitting driving state information corresponding to each of the switching target devices to each of the target devices in the second scene and setting driving parameters corresponding to the driving state information to each of the target devices, the method includes the following steps:

[0057] Step S42: Receive result information fed back from each of the target devices in the second scene, and determine based on the result information whether the driving status information corresponding to each of the switching target devices in the first scene has been successfully switched to each of the target devices in the second scene.

[0058] Step S43: If the operating status information corresponding to each of the switching target devices is successfully switched to each of the target devices in the second scene, send a control command to turn off each of the switching target devices in the first scene.

[0059] Step S44: If the driving status information corresponding to each of the switching target devices is not successfully switched to each of the target devices in the second scene, repeat the step of sending the driving status information corresponding to each of the switching target devices to each of the target devices in the second scene.

[0060] After the scene switching operation is performed, each woken-up device in the second scene transmits operating parameter switching result information to the master device, including operating state information, operating parameter information, etc. of each woken-up device. Based on the received result information, the master device determines whether the operating state information corresponding to each of the switching target devices in the first scene has been successfully switched to each of the target devices in the second scene. For example, it determines whether the operating state information corresponding to each of the switching target devices in the first scene is identical to the operating state information corresponding to each of the target devices in the second scene. If they are identical, it indicates that the operating state information corresponding to each of the switching target devices has been successfully switched to each of the target devices in the second scene, and the master device needs to transmit a control command to turn off each of the switching target devices in the first scene. If they are different, it indicates that the operating state information corresponding to each of the switching target devices has not been successfully switched to each of the target devices in the second scene, and repeats the step of transmitting the operating state information corresponding to each of the switching target devices to each of the target devices in the second scene.

[0061] Before switching scenes, it is necessary to determine the conditions for constructing the scene, including the following conditions:

[0062] 1. Deploy multiple long-range devices.

[0063] 2. Recognize long-distance devices using lightweight protocols such as mDNS or upnp, and define master devices and slave devices in the home, where the master device includes a storage module for storing voiceprint information, device information, scene information, etc. sent by the slave devices, and a matching module for matching the voiceprint information and device information in the first scene and the second scene, and the slave devices include devices such as smart air conditioners, smart TVs, smart fans, and smart speakers.

[0064] 3. A UDP connection is established between the master device and the slave device, and the connection between the master device and the slave device is detected by a heartbeat packet. The UDP (User Datagram Protocol) is a connectionless transport layer protocol in the OSI reference model, and provides a transaction-oriented, simple, and reliable information transfer service.

[0065] 4. Multiple long-distance devices are woken up, and location registration and scene division are performed for each device according to the device type or supplemented by the user.

[0066] 5. Set the scene change wake-up statement and scene change statement of the remote device, such as "Xiao T Xiao T" and "Scene Change".

[0067] In this embodiment, when it is determined that a user has moved from a first scene to a second scene, the system collects the user's voiceprint information in the second scene, determines each of the target devices in the first scene based on the voiceprint information, obtains driving status information corresponding to each of the target devices, transmits the driving status information corresponding to each of the target devices in the second scene, and sets driving parameters corresponding to the driving status information for each of the target devices. By establishing a link relationship between the long-distance devices, the driving parameters of the long-distance devices can be switched between different user scenes. Furthermore, by automatically turning on the long-distance devices through the transmission of long-distance voice, the user's operation complexity is reduced, and intelligent perception and intelligent linkage of the long-distance devices are realized, providing the user with a more comfortable and convenient home environment.

[0068] Furthermore, referring to FIG. 3, a second embodiment of the scene switching method of the present invention is proposed.

[0069] The difference between the second embodiment of the scene switching method and the first embodiment of the scene switching method is that the second embodiment of the scene switching method includes the following steps before the step of determining whether the user has moved from the first scene to the second scene:

[0070] Step S13: Obtain a device-on command in the first scene, and obtain the voiceprint information in the first scene according to the device-on command.

[0071] Step S14: Associate the voiceprint information in the first scene with the first scene.

[0072] When the slave device receives the wake-up word "Xiao T Xiao T" transmitted by the user in the far-field voice, it wakes up the multiple far-field devices in the first scene according to the wake-up word, and for each of the woken-up far-field devices, sets operating parameters for turning on each of the woken-up far-field devices. Furthermore, the master device obtains information such as device capabilities and device states corresponding to each of the turned-on devices, pre-processes the obtained user voice, removes non-voice signals and silent voice signals to obtain pre-processed voice, and further divides the pre-processed voice into frames and performs Mel frequency reverse scanning of the voice signal of each frame. The method includes a pre-enhancement step for subtracting the audio signal, a sound framing step for dividing the audio data into frames, a Hamming window step for adding a window to each frame's signal to reduce the influence of the Gibbs effect, a fast Fourier transform step for converting the time-domain signal into its power spectrum, a triangular bandpass filter step for simulating the masking effect of the human ear by approximating the range covered by the triangular filter to one critical bandwidth of the human ear, and a discrete cosine transform step for removing correlations between each dimensional signal and mapping the signal to a low-dimensional space.Furthermore, voice dynamic characteristic parameters are obtained from the extracted MFCC parameters as the user's voiceprint feature information, thereby obtaining the user's voiceprint information in the first scene.

[0073] The slave device associates the acquired voiceprint information of the first scene with the first scene. For example, if the scene in which the user is currently located is the living room, the voiceprint information currently acquired in the living room can be bound to the living room scene. When the user enters another scene, the voiceprint information of the first scene can be used to determine that the previous scene was the living room based on the voiceprint information in the first scene. Optionally, the voiceprint information can be associated with the user's personal information. For example, the user information and voiceprint feature information of each family member in the household, such as grandfather, grandmother, father, mother, and children, can be collected and associated with the user information and user voiceprint feature information. For example, the user information of the father can be associated with the user voiceprint feature information of the father. Furthermore, the master device acquires information on the binding of the voiceprint information and the scene (e.g., the living room scene + voiceprint object) sent by the slave device and device status information for this scene, and stores the acquired information in a corresponding storage unit.

[0074] In this embodiment, by associating the voiceprint information in the first scene with the first scene, when the voiceprint information in the first scene is acquired, scene information corresponding to the voiceprint information is simultaneously acquired.

[0075] Furthermore, referring to FIG. 4, a third embodiment of the scene switching method of the present invention is proposed.

[0076] The difference between the third embodiment of the scene switching method and the first and second embodiments of the scene switching method is that when the scene switching command is received, the step of collecting the user's voiceprint information in the second scene includes the following steps:

[0077] Step S230: If a plurality of the scene change commands are received, obtain voiceprint information corresponding to each of the scene change commands.

[0078] Step S231: Match the voiceprint information corresponding to each of the scene change commands with each of the target voiceprint information, and obtain the voiceprint information that matches the target voiceprint information.

[0079] Step S232: If there is voiceprint information corresponding to each of the scene switching commands that matches each of the target voiceprint information, the scene switching command corresponding to the voiceprint information that matches the target information is determined as the target scene switching command, and the user corresponding to the target scene switching command is the target user.

[0080] Step S233: Collect the scene switching command of the target user and use it as the voiceprint information of the user in the second scene.

[0081] When multiple users simultaneously send a scene change command for "scene change" using long-distance voice, the slave device sends multiple scene change commands to the master device, and the master device extracts user voiceprint information from the voice information corresponding to each of the scene change commands, sequentially matches each extracted voiceprint information with each target voiceprint information, and if there is voiceprint information matching each target voiceprint information in the voiceprint information corresponding to each of the scene change commands, determines the scene change command corresponding to the voiceprint information matching the target information as the target scene change command, and the user corresponding to the target scene change command is the target user, and collects the scene change command of the target user as the voiceprint information of the user in the second scene.

[0082] Alternatively, a registration voiceprint library can be pre-built, allowing each user to pre-register their own voice. For example, a registered user registers their voice through the setting interface of the smart device, uttering a voice within the range that the smart device can collect. After collecting the registered user's voice, the smart device uses a voiceprint model to extract registration voiceprint feature information from the registered user's voice and stores the registered user's registration voiceprint feature information in the registration voiceprint library. Here, the voiceprint model is pre-built, and the parameters of the extracted voiceprint feature information are the same for each user. The voice spoken by the user may be any word or a specified word, with the specific content of the voice being set by the user. By building the voiceprint library, it is possible to quickly obtain the voiceprint feature information of a target user, and it is also possible to inquire whether the received voiceprint information of multiple users is pre-stored in the voiceprint library. If the voiceprint information is pre-stored in the voiceprint library, the corresponding voiceprint feature information can be directly retrieved and matched with the target voiceprint feature information, thereby quickly determining the target user and shortening the matching operation time.

[0083] In this embodiment, when scene change commands sent by multiple users are received, voiceprint information corresponding to each scene change command is obtained, and the voiceprint information corresponding to each scene change command is matched with each target voiceprint information to determine the target user corresponding to the target scene change command, thereby making it possible to collect voiceprint information corresponding to the target user in a timely manner.

[0084] The present application further provides a terminal including a memory, a processor, and a scene switching program stored in the memory and executed on the processor, wherein the terminal, upon receiving a device-on command transmitted by a user through far-field voice, turns on a plurality of far-field devices in the home based on the on command, determines a scene in which the user is currently located based on location information corresponding to each turned-on far-field device, and further obtains the user's voiceprint information in this scene and device information (e.g., device operating parameters, device type, device capability, etc.) corresponding to each turned-on device, and when the user moves from a first scene to a second scene, the terminal Upon receiving a scene switching command transmitted by far-field voice, the system acquires the user's voiceprint information in the second scene and the device information corresponding to each of the woken-up devices, matches the voiceprint information in the first scene with the voiceprint information in the second scene, matches the device information corresponding to each of the turned-on devices with the device information corresponding to each of the target devices to determine each of the devices to be switched to in the first scene, transmits driving state information corresponding to each of the turned-on devices to each of the target devices in the second scene, and sets driving parameters corresponding to the driving state information for each of the target devices. This embodiment realizes user scene switching by transmitting far-field voice, reduces the user's operation complexity, realizes intelligent perception and intelligent cooperation of far-field devices, and provides the user with a more comfortable and convenient home environment.

[0085] The present application also provides a computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements the steps of the scene switching method described above.

[0086] Those skilled in the art should recognize that the embodiments of the present application may be provided as a method, a system, or a computer program product. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0087] The present application will be described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, are implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to create a machine, and the instructions executed by the processor of the computer or other programmable data processing device create an apparatus for implementing the function specified in one or more of the flow or blocks in the flowcharts and / or block diagrams.

[0088] These computer program instructions may be stored in a computer-readable memory that can cause a computer or other programmable data processing device to operate in a particular manner, and the instructions stored in the computer-readable memory may produce an article of manufacture that includes an instruction apparatus that performs the functions specified in one or more flows of the flowcharts and / or one or more blocks of the block diagrams.

[0089] These computer program instructions may be loaded into a computer or other programmable data processing device, and a series of operational steps may be executed on the computer or other programmable device to produce a computer-implemented process, such that the instructions executing on the computer or other programmable device provide steps for implementing the functions specified in one or more flows of the flowcharts and / or one or more blocks of the block diagrams.

[0090] It should be noted that in the claims, reference signs placed between parentheses shall not be construed as limiting the scope of the claim. The word "comprises" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware comprising several distinct elements and by means of a suitably programmed computer. In a unit claim enumerating several devices, several of these devices may be embodied by one and the same item of hardware. The use of words such as first, second, and third does not indicate an order; these words can be interpreted as names.

[0091] Although alternative embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments upon recognizing the basic creative concept. Therefore, it is intended that the appended claims be interpreted to include the alternative embodiments and all changes and modifications that are within the scope of the present application.

[0092] It is apparent that those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and equivalent technologies, the present application intends to include these modifications and variations. [Explanation of symbols]

[0093] 1001 processor 1002 communication bus 1003 User Interface 1004 Network Interface 1005 memory

Claims

1. determining whether a user has moved from a first scene to a second scene; When the user moves to the second scene, collecting voiceprint information of the user in the second scene; determining each switching target device in the first scene based on the voiceprint information in the second scene, and acquiring driving state information corresponding to each switching target device; determining driving state information corresponding to each of the target devices in the second scene based on driving state information corresponding to each of the switching target devices; wherein each of the target devices matches each of the switching target devices in terms of device type, device capability, and device usage time, The step of determining each switching target device in the first scene based on the voiceprint information in the second scene includes: obtaining device information corresponding to each of the turned-on devices in the first scene and device information corresponding to each of the target devices in the second scene; Matching the voiceprint information in the first scene with the voiceprint information in the second scene, and matching device information corresponding to each of the turned-on devices with device information corresponding to each of the target devices; If the voiceprint information in the first scene matches the voiceprint information in the second scene, acquiring the turned-on device that matches the target device from among the turned-on devices, and determining the turned-on device that matches the target device as the switching target device in the first scene; The step of determining driving state information corresponding to each of the target devices in the second scene based on driving state information corresponding to each of the switching target devices includes: transmitting driving state information corresponding to each of the switching target devices to each of the target devices in the second scene, and setting driving parameters corresponding to the driving state information to each of the target devices; How to switch scenes.

2. The step of determining whether the user has moved from a first scene to a second scene comprises: obtaining location information corresponding to each of the turned-on devices in the first scene and location information corresponding to each of the target devices in the second scene; determining whether location information corresponding to each of the turned-on devices is the same as location information corresponding to each of the target devices; The scene switching method according to claim 1 .

3. When the user moves to the second scene, the step of collecting voiceprint information of the user in the second scene includes: determining that a user has moved from the first scene to the second scene if location information corresponding to each of the turned-on devices and location information corresponding to each of the target devices are different; detecting whether a scene change command has been received; and collecting voiceprint information of the user in the second scene when the scene change command is received. The scene switching method according to claim 1 .

4. After transmitting driving state information corresponding to each of the switching target devices to each of the target devices in the second scene and setting driving parameters corresponding to the driving state information to each of the target devices, receiving result information fed back from each of the target devices in the second scene, and determining, based on the result information, whether the driving state information corresponding to each of the switching target devices in the first scene has been successfully switched to each of the target devices in the second scene; When the driving state information corresponding to each of the switching target devices is successfully switched to each of the target devices in the second scene, transmitting a control command to turn off each of the switching target devices in the first scene; When the driving state information corresponding to each of the switching target devices is not successfully switched to each of the target devices in the second scene, repeating the step of transmitting the driving state information corresponding to each of the switching target devices to each of the target devices in the second scene. The scene switching method according to claim 1 .

5. prior to the step of determining whether the user has moved from a first scene to a second scene, obtaining a device-on command in the first scene, and obtaining the voiceprint information in the first scene according to the device-on command; and associating the voiceprint information in the first scene with the first scene. The scene switching method according to claim 1 .

6. When the scene change command is received, the step of collecting voiceprint information of the user in the second scene includes: When a plurality of the scene change commands are received, acquiring voiceprint information corresponding to each of the scene change commands; matching voiceprint information corresponding to each of the scene change commands with each of the target voiceprint information to obtain the voiceprint information that matches the target voiceprint information; determining a scene change command corresponding to the voiceprint information that matches the target voiceprint information as a target scene change command when the voiceprint information corresponding to each of the scene change commands matches the target voiceprint information, and determining that the user corresponding to the target scene change command is a target user; collecting the scene switching command of the target user and using it as voiceprint information of the user in the second scene; The scene switching method according to claim 3 .

7. If the voiceprint information in the first scene matches the voiceprint information in the second scene, after a step of acquiring the turned-on device that matches the target device from among the turned-on devices and determining the turned-on device that matches the target device as the switching target device in the first scene, If a video playback device is included in the switching target device in the first scene, acquiring the playback content and playback progress of the video playback device; transmitting the playback content and the playback progress status to a video playback device in the second scene, and causing the video playback device in the second scene to display the playback content according to the playback progress status; The scene switching method according to claim 1 .

8. A terminal including a memory, a processor, and a scene switching program stored in the memory and executed on the processor, wherein when the processor executes the scene switching program, determining whether a user has moved from a first scene to a second scene; When the user moves to the second scene, collect voiceprint information of the user in the second scene; determining each switching target device in the first scene based on the voiceprint information in the second scene, and acquiring driving state information corresponding to each switching target device; determining driving state information corresponding to each of the target devices in the second scene based on driving state information corresponding to each of the switching target devices; wherein each of the target devices matches each of the switching target devices in terms of device type, device capability, and device usage time, When the processor executes the scene switching program, Obtaining device information corresponding to each of the turned-on devices in the first scene and device information corresponding to each of the target devices in the second scene; Matching the voiceprint information in the first scene with the voiceprint information in the second scene, and matching device information corresponding to each of the turned-on devices with device information corresponding to each of the target devices; If the voiceprint information in the first scene matches the voiceprint information in the second scene, obtain the turned-on device that matches the target device from among the turned-on devices, and determine the turned-on device that matches the target device as the switching target device in the first scene; When the processor executes the scene switching program, transmitting driving state information corresponding to each of the switching target devices to each of the target devices in the second scene, and setting driving parameters corresponding to the driving state information to each of the target devices; Terminal.

9. When the processor executes the scene switching program, Obtaining location information corresponding to each of the turned-on devices in the first scene and location information corresponding to each of the target devices in the second scene; determining whether the location information corresponding to each of the turned-on devices is the same as the location information corresponding to each of the target devices; The terminal according to claim 8.

10. When the processor executes the scene switching program, determining that the user has moved from the first scene to the second scene if the location information corresponding to each of the turned-on devices is different from the location information corresponding to each of the target devices; Detecting whether a scene change command has been received; When the scene change command is received, collecting voiceprint information of the user in the second scene. The terminal according to claim 8.

11. When the processor executes the scene switching program, receiving result information fed back from each of the target devices in the second scene, and determining, based on the result information, whether the driving state information corresponding to each of the switching target devices in the first scene has been successfully switched to each of the target devices in the second scene; When the driving state information corresponding to each of the switching target devices is successfully switched to each of the target devices in the second scene, transmitting a control command to turn off each of the switching target devices in the first scene; If the driving status information corresponding to each of the switching target devices is not successfully switched to each of the target devices in the second scene, repeating the step of transmitting the driving status information corresponding to each of the switching target devices to each of the target devices in the second scene; The terminal according to claim 8.

12. When the processor executes the scene switching program, Obtaining a device-on command in the first scene, and obtaining the voiceprint information in the first scene according to the device-on command; associating the voiceprint information in the first scene with the first scene; The terminal according to claim 8.

13. When the processor executes the scene switching program, When a plurality of the scene change commands are received, voiceprint information corresponding to each of the scene change commands is acquired; matching voiceprint information corresponding to each of the scene change commands with each of the target voiceprint information, and obtaining the voiceprint information that matches the target voiceprint information; If voiceprint information corresponding to each of the scene change commands includes voiceprint information that matches each of the target voiceprint information, the scene change command corresponding to the voiceprint information that matches the target voiceprint information is determined as a target scene change command, and the user corresponding to the target scene change command is a target user; collecting the scene switching command of the target user and using it as voiceprint information of the user in the second scene; The terminal according to claim 10.

14. When the processor executes the scene switching program, If a video playback device is present in the switching target device in the first scene, obtain the playback content and playback progress of the video playback device; transmitting the playback content and the playback progress status to a video playback device in the second scene, and causing the video playback device in the second scene to display the playback content according to the playback progress status; The terminal according to claim 8.

15. A computer-readable storage medium storing a computer program, the computer program being executed by a processor to realize the scene switching method according to any one of claims 1 to 7. A computer-readable storage medium.

Images