CN114299951A - Control method and device - Google Patents
Control method and device Download PDFInfo
- Publication number
- CN114299951A CN114299951A CN202111676133.7A CN202111676133A CN114299951A CN 114299951 A CN114299951 A CN 114299951A CN 202111676133 A CN202111676133 A CN 202111676133A CN 114299951 A CN114299951 A CN 114299951A
- Authority
- CN
- China
- Prior art keywords
- target
- candidate
- determining
- target object
- spatial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Stereophonic System (AREA)
Abstract
The application discloses a control method and a control device, which comprise the following steps: in response to receiving the target audio information, determining a target object generating the target audio information and a candidate device corresponding to the target audio information; determining a spatial position relationship corresponding to the target object and each candidate device; based on the spatial positional relationship, a target device is determined among the candidate devices such that the target device responds to the target audio information. When a plurality of candidate devices are provided, the device closest to the target object can be determined to respond through the spatial position relation.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to a control method and apparatus.
Background
With the development of artificial intelligence, more and more families have a plurality of devices supporting voice awakening. However, since the smart devices may wake up based on the same wake-up word or the same wake-up model, when a user desires to wake up a certain device, other devices may also wake up, which causes inaccurate wake-up of the device and reduces experience effect.
Disclosure of Invention
In view of the above, the present application provides a control method and apparatus, as follows:
a control method, comprising:
in response to receiving target audio information, determining a target object generating the target audio information and a candidate device corresponding to the target audio information;
determining a spatial position relationship corresponding to the target object and each candidate device;
determining a target device among the candidate devices based on the spatial positional relationship such that the target device is responsive to the target audio information.
Optionally, the candidate devices at least include a first device that satisfies a target condition, and the determining the spatial position relationship between the target object and each of the candidate devices includes:
determining a first spatial position relation of the target object and a first device based on the first device; acquiring a second spatial position relation between the first equipment and candidate equipment except the first equipment;
determining a spatial positional relationship between the target object and each of the candidate devices based on the first spatial positional relationship and the second spatial positional relationship.
Optionally, the candidate devices at least include a first device that satisfies a target condition, and the determining the spatial position relationship between the target object and each of the candidate devices includes:
determining a first spatial location of the target object based on the first device; and determining a second spatial location of a candidate device other than the first device based on the first device;
based on the first and second spatial locations, a spatial positional relationship between the target object and each candidate device other than the first device is determined.
Optionally, the candidate devices include at least one first device, and the determining a spatial position relationship between the target object and each candidate device includes:
determining a third spatial position of the target object based on the first device and obtaining a fourth spatial position of the first device;
determining a spatial position relationship between the target object and the first device based on the third spatial position and the fourth spatial position;
the determining, based on the spatial location relationship, a target device among the candidate devices includes:
and if the spatial position relation between the target object and the first equipment meets a specified condition, determining the first equipment as target equipment.
Optionally, the determining, based on the spatial position relationship, a target device among the candidate devices includes:
determining whether each candidate device is in the same subspace as the target object based on the spatial position relationship;
and determining candidate equipment in the same subspace with the target object as target equipment.
Optionally, the candidate devices in the same subspace as the target object include at least one device, and the determining, as the target device, the candidate device in the same subspace as the target object includes:
acquiring distance information between each candidate device and the target object;
determining a target device among candidate devices in the same subspace as the target object based on the distance information.
Optionally, the determining, as the target device, the candidate device in the same subspace as the target object includes:
acquiring the device characteristics of each candidate device in the same subspace with the target device and the attribute characteristics of the target audio information;
determining a target device among candidate devices in the same subspace as the target object based on the device feature and the attribute feature.
Optionally, the determining a spatial position relationship corresponding to the target object and each candidate device includes:
acquiring a first space image of a space where the target object and each candidate device are located;
and determining the spatial position relation of the target object and each candidate device based on the first spatial image.
Optionally, the determining a spatial position relationship corresponding to the target object and each candidate device includes:
acquiring audio frequency spectrum information corresponding to the target audio frequency information;
determining a transmission medium corresponding to the target audio information transmitted to each candidate device based on the audio spectrum information;
and determining the spatial position relation of the target object and each candidate device based on the transmission medium.
A control device, comprising:
a first determination unit, configured to determine, in response to receiving target audio information, a target object that generates the target audio information and a candidate device corresponding to the target audio information;
a second determining unit, configured to determine a spatial position relationship between the target object and each of the candidate devices;
a third determining unit configured to determine a target device among the candidate devices based on the spatial positional relationship so that the target device responds to the target audio information.
An electronic device, comprising:
a memory for storing a program;
and the processor is used for calling and executing the program in the memory, and executing the program to realize the steps of the control method.
A readable storage medium, having stored thereon a computer program which, when executed by a processor, carries out the steps of the control method of any one of the preceding claims.
As can be seen from the above technical solutions, a control method and apparatus disclosed in the present application include: in response to receiving the target audio information, determining a target object generating the target audio information and a candidate device corresponding to the target audio information; determining a spatial position relationship corresponding to the target object and each candidate device; based on the spatial positional relationship, a target device is determined among the candidate devices such that the target device responds to the target audio information. When a plurality of candidate devices are available, the device closest to the target object can be determined to respond through the spatial position relation, and the efficiency and accuracy of the device to respond to the audio are improved, and the experience effect is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flowchart of a control method according to an embodiment of the present disclosure;
fig. 2 is a schematic plan view of an application scenario provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a control device according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The control method provided by the embodiment of the application is mainly applied to a target scene, and a plurality of devices can respond to relevant information, so that the optimal target device capable of responding to the information is determined according to the spatial position relation between each device and a target object, the problem that the devices respond simultaneously or the response effect is poor is avoided, and the experience effect is improved.
Referring to fig. 1, a schematic flow chart of a control method according to an embodiment of the present disclosure is shown, where the method includes the following steps:
s101, in response to receiving the target audio information, determining a target object generating the target audio information and candidate equipment corresponding to the target audio information.
S102, determining the corresponding spatial position relation of the target object and each candidate device.
S103, determining the target device in the candidate devices based on the spatial position relation, so that the target device responds to the target audio information.
In step S101, the target audio information is generated by a target object, and correspondingly, the target object may be a user who uttered the target audio information, i.e. the target audio information is speech information. The target object may also be an electronic device capable of playing audio information, for example, a user may record and transmit specific audio information in advance, or a user may transmit audio information to the electronic device based on his own terminal device, for example, output the target audio information through an audio device of the indoor monitoring device. The target audio information is audio capable of directly or indirectly waking up the electronic device, and different electronic devices can be wakened up by different audio information. For example, the target audio information may be a wake word for waking up the electronic device, such as "hello, speaker", or may be audio information for controlling the electronic device to output, such as "speaker plays a song".
By analyzing the audio characteristics of the target audio information, a target object that generates the target audio information and candidate devices that can respond to control instructions in the target audio information can be determined. In the embodiment of the application, at least one candidate device capable of responding to the target audio information is provided. It is necessary to determine the target device that best meets the requirements of the application scenario among the candidate devices.
In step S102, determining the spatial position relationship between the target object and each candidate device is to determine a three-dimensional spatial position relationship, and it is necessary to clarify the angle and distance relationship between each candidate device and the target object, and in order to accurately determine the position relationship between the target object and the candidate device, it is necessary to further determine whether there is another obstacle between the candidate device and the target object, so as to avoid the existence of the obstacle from affecting the response of the candidate device to the target audio information. The obstacle may include an indoor wall, furniture, and the like. The candidate device is a device capable of responding to the target audio information, and may be a sound box, or an electronic device with an audio output function, such as a notebook computer, an intelligent home appliance, and the like.
In step S103, when determining the target device among the candidate devices based on the spatial positional relationship, it may be determined whether the target object generating the target audio information is in the same subspace as the candidate device based on the spatial positional relationship, and the candidate device in the same subspace as the target object may be determined as the target device. Therefore, the problem that even though the absolute positions of the candidate device and the target object are close, the wall body is not in the same subspace and is awakened between the candidate device and the target object can be avoided, and the problem that the response effect is poor after the device is awakened by the target audio information is solved.
In one implementation of the embodiment of the present application, the candidate devices include at least a first device that satisfies a target condition. The target condition may be a condition determined based on a current application scenario, and may be a condition of a device network state, a condition of a device operating state, a condition of device storage information, or the like. For example, the first device may be a master device in a current network, or may be a device already in a standby operating state in a current scenario.
Wherein the determining the spatial position relationship corresponding to the target object and each candidate device comprises: determining a first spatial position relation of a target object and first equipment based on the first equipment; acquiring a second spatial position relation between the first equipment and candidate equipment except the first equipment; based on the first spatial positional relationship and the second spatial positional relationship, a spatial positional relationship between the target object and each candidate device is determined.
In this embodiment, the first device may be a master device among the candidate devices, which acquires and determines a spatial positional relationship between the target object and each of the candidate devices. The first device determines the spatial position relationship between the target object and the first device to determine the direction and distance information between the target object and the first device, and can also determine whether the first device and the target object are in the same subspace due to the spatial position relationship, that is, whether an obstacle capable of influencing audio propagation exists between the first device and the target object, for example, whether a wall exists between the first device and the target object. Further, a second spatial position relationship between the first device and candidate devices other than the first device is obtained, and with the first device as a reference, a spatial position relationship between the target object and each candidate device can be obtained.
The first device can obtain the spatial position relation with the target object and other candidate devices through own image acquisition devices, TOF sensors and other devices. Correspondingly, the first device may further store an absolute position relationship of each device in the current space. An absolute position refers to the position of an object in space represented by a scientific coordinate system, which is more accurate than a relative position. The spatial position relationship between the target object and each candidate device can be determined by the absolute position information. Further, the determining the spatial position relationship of the target object corresponding to each candidate device includes: determining a first spatial position of the target object based on the first device and determining a second spatial position with a candidate device other than the first device based on the first device; based on the first spatial location and the second spatial location, a relationship is determined between the target object and each candidate apparatus other than the first apparatus.
In this embodiment, the spatial positional relationship can be determined based on absolute positional information, which is the spatial position of the target object and the candidate device. Specifically, the spatial positions of the target object and the candidate device may be obtained by collecting and analyzing images of the space where the target object and the candidate device are located or by recording and storing position information. The determination of the spatial position can be more accurate than the relative position, so that the target device determined based on the spatial position relation can better meet the response requirement of the target audio information.
In another embodiment of the present application, the candidate devices include at least one first device, and the determining the spatial position relationship between the target object and each candidate device includes: determining a third spatial position of the target object based on the first device, and obtaining a fourth spatial position of the first device; and determining the spatial position relation of the target object and the first equipment based on the third spatial position and the fourth spatial position.
Correspondingly, the determining the target device from the candidate devices based on the spatial position relationship includes: and if the spatial position relation between the target object and the first equipment meets a specified condition, determining the first equipment as the target equipment.
In this embodiment, each candidate device is a device that can respond to the target audio information, and there is no master-slave device relationship between the respective devices. After the spatial position relationship between each candidate device and the target object is determined, each candidate device, namely the first device, judges whether the candidate device can respond to the target audio information or not according to the spatial position relationship and the formulated conditions. And if the condition is that the candidate device and the target object are in the same subspace, when the first device judges that the candidate device and the target object are in the same subspace, the first device serves as the target device responding to the target audio information to respond to the target audio information.
Specifically, in an implementation manner of the embodiment of the present application, the determining, based on the spatial position relationship, the target device in the candidate devices includes: determining whether each candidate device is in the same subspace with the target object based on the spatial position relationship; and determining candidate equipment in the same subspace with the target object as the target equipment.
When different subspaces exist in the target application scene and each candidate device is possibly positioned in different subspaces, the candidate device of which the candidate device and the target object are positioned in the same subspace is determined as the target device. This may avoid the problem of poor performance of executing the target audio information even if the candidate device is closer to the target object but not in the same subspace. Wherein, the same subspace means that there is no obstacle between the target object and the candidate device, which affects audio transmission, or there is no object that changes the audio transmission medium. That is, each subspace is independent to another subspace, for example, different subspaces are separated by a wall, when the determined target device receives the target audio information generated by the target object, the target audio information can be directly acquired, and the target audio information does not need to be transmitted to the target device through the wall, so that the rapid response of the audio information is ensured, and the audio information output by the target device based on the target audio information can be transmitted to the target object without passing through other subspaces or barriers (such as walls) between the spaces, so as to provide a better audio experience effect for the target object.
If there is only one candidate device in the same subspace as the target object, the candidate device may be directly determined as the target device. If the candidate device in the same subspace with the target object includes at least one device, that is, if there are a plurality of candidate devices in the same subspace with the target object, the distance information between each candidate device and the target object can be obtained; based on the distance information, a target device is determined among candidate devices in which the target object is in the same subspace. For example, the candidate device closest to the target object in the same subspace is determined as the target device.
In another implementation manner, the device characteristics of each candidate device in the same subspace as the target device and the attribute characteristics of the target audio information may be obtained; and determining the target equipment in the candidate equipment in the same subspace with the target object based on the equipment characteristic and the attribute characteristic.
The device characteristics may include parameter characteristics, state characteristics, network characteristics, and the like of the candidate device, for example, audio playing parameters, connection network information, playing history information, and the like of the candidate device. The attribute features of the target audio information include features of a target object that produced the target audio, and a corresponding target object identification may be determined. For example, the candidate devices in the same subspace as the target object include a first candidate device and a second candidate device, both of which may respond to the target audio information, but the first candidate device is connected to the server through the mobile network, and the second candidate device is connected to the server based on the wireless network of the current room, and the second candidate device may respond to the target audio information as the target device based on the network cost condition. If the audio playing effect corresponding to the audio playing parameter of the first candidate device is better than that of the second candidate device, the first candidate device may be determined as the target device based on the audio effect condition. If the target object is the user A and the audio playing device frequently used by the user A is the first candidate device obtained by identifying the attribute characteristics of the target audio information, determining the first candidate device as the target device. Correspondingly, if the attribute characteristics corresponding to the target audio information are analyzed, the target audio information including information indicating playing of the audio story B is obtained, the audio story B is played last time by the second candidate device, and in order to quickly play the audio story B, the second candidate device is determined as the target device this time, and the audio story B is continuously played.
The following describes a processing method for determining whether a target object and a candidate device are in the same subspace in the embodiment of the present application.
In one embodiment, a captured image including objects in the current application scene may be obtained based on an image capturing device in the current application scene, and the objects may be analyzed based on the captured image, wherein the objects include a target object generating target audio information and a candidate device capable of responding to the target audio information.
Specifically, the determining, as the target device, the candidate device in the same subspace as the target object includes: acquiring a first space image of a space where the target object and each candidate device are located; and determining the spatial position relation of the target object and each candidate device based on the first spatial image.
It should be noted that the first spatial image may be an image spliced based on images acquired in each subspace, or may be a plurality of sub-images of the first spatial image, where each sub-image corresponds to a word space in the current scene. For example, the first spatial image is a current floor plan of user a, and the floor plan includes a sub-image corresponding to each room, and the sub-image includes candidate devices existing in the currently corresponding room. The feature recognition may be performed on the first space image to obtain an image area corresponding to the target object and each candidate device in the first space image, so as to determine a spatial position relationship corresponding to the target object and each candidate device, and further determine whether the target object and the candidate device are located in the same subspace.
In another embodiment, the position relationship between the target object and each candidate device may be determined by analyzing the audio spectrum feature corresponding to the target audio information. Specifically, audio frequency spectrum information corresponding to the target audio frequency information is obtained; determining a transmission medium corresponding to the target audio information transmitted to each candidate device based on the audio frequency spectrum information; and determining the spatial position relation of the target object and each candidate device based on the transmission medium.
Since audio is transmitted in different transmission media, corresponding spectral characteristics are different, for example, frequencies, peaks, and other information in the spectrum are different between the transmission medium of air and the transmission medium of solid. The target audio information obtained by each candidate device may be analyzed based on the spectral characteristics corresponding to the target audio information to determine whether the target audio information is transmitted through the wall by transmitting the target audio information to the transmission medium corresponding to the candidate device. To determine whether the target object is in the same subspace as the candidate device.
Specifically, an audio recognition model may be established, and the spectral features corresponding to different transmission media are used as training samples to perform neural network model training to obtain the audio recognition model, so that the spectral features corresponding to the target audio information are input to the audio recognition model to obtain the transmission media corresponding to the audio recognition model. The method can also be used for training a neural network model based on a large number of audio frequency spectrums propagated through a wall and audio frequency spectrums propagated through a non-wall as training samples to obtain a corresponding recognition model, inputting the frequency spectrums corresponding to target audio information into the recognition model and obtaining whether the target audio information is transmitted through the wall.
The control method provided by the embodiment of the application can be applied to the situation that when more candidate devices can respond to the target audio information in the scene, the judgment is carried out based on the spatial position relation, the nearest candidate device in the same subspace is determined to serve as the target device to respond to the target audio information, more intelligent nearby awakening is achieved, and the user experience effect is improved.
In a scenario embodiment, when a plurality of control devices are located indoors, a plurality of photos can be taken based on the angle of the devices when the devices are initialized, and the devices perform indoor space modeling through the photos to obtain a corresponding spatial layout diagram and device information contained in each subspace in the current space. Therefore, when a user in the subspace where the equipment is located wakes up the equipment, whether the user is located in the same subspace as the user is determined according to the sound direction of the user, if so, the equipment is woken up, and subsequent audio output is executed. In another mode, when the sound of one subspace reaches another subspace, a wall needs to be penetrated generally, the reverberation frequency of the sound penetrating the wall changes to a certain extent, and based on the principle, a model for judging whether the sound penetrates through the wall can be trained, so that whether the sound is emitted from the same subspace is judged, and therefore the nearby awakening is assisted. Specifically, when a user speaks a wake-up instruction, multiple devices receive the wake-up instruction in a space, and first, the devices can judge whether the user and the devices are in the same subspace through the two implementation modes. The devices in the same subspace are arranged in the same subspace, and are sequenced according to SIGNAL to NOISE RATIOs (SNR) corresponding to received audio information, the combination with the largest awakening SNR is achieved, if the device with the largest SNR is the device which determines the device, the device is directly awakened, if other devices, corresponding awakening control SIGNALs are sent to other devices, or the device is awakened after meeting awakening conditions, and awakened SIGNALs are broadcast to other devices, so that the other devices do not respond to awakening of the current user. Further, if the device is not in the same subspace as the user, waiting for whether a signal of the device which is awakened is received, and if so, not awakening. And if not, awakening the equipment with the largest signal-to-noise ratio in all the equipment which are not in the same subspace. The signal-to-noise ratio refers to a ratio of a signal to noise in an electronic device or an electronic system, and the signal-to-noise ratio of the wake-up voice can represent the sound pickup performance of the voice interaction device. The greater the signal-to-noise ratio, the better the pickup performance of the device that identified the wake-up audio, which may reflect the closer the device is to the user that uttered the wake-up audio.
Referring to fig. 2, a schematic plan view of an application scenario provided in the embodiment of the present application is an indoor scenario, and the application scenario includes three subspaces, that is, a subspace 1, a subspace 2, and a subspace 3, where the subspace 1 includes a sound box 201 and a sound box 202, the subspace 2 includes a sound box 203, and the subspace 3 includes a sound box 204 and a sound box 205. When the user is in the subspace 1 to send out the audio information, it can be found that if the condition that whether the audio information is in the same subspace is not considered, the sound box 203 is closest to the user, but if the audio information sent by the user is transmitted to the sound box 203, the audio information needs to pass through the wall 206 between the subspace 1 and the subspace 2, and similarly, if the audio information output by the sound box 203 is acquired by the user, the audio information also passes through the wall 206, which may reduce the effect of audio transmission, such as reducing the volume of audio transmission or the response rate of audio interaction. Therefore, it is necessary to determine the speaker box responding to the audio information generated by the user in subspace 1, and if speaker box 201 is closer to the user than speaker box 202, then speaker box 201 is determined as the target device responding to the user, and further audio interaction is performed with the user. If the user utters a wake up word in subspace 2, then loudspeaker 203 responds as the target device. If the user sends out the wake-up word in the subspace 3, since the subspace 3 includes two speakers, the distance between each speaker and the position of the user needs to be further determined, and the corresponding target device is determined according to the distance.
For another example, the sound box 203 in the subspace 2 is a main control device in the current room, that is, the device analyzes all audio information, determines a device capable of responding to the current audio information, and sends a wake-up instruction to the device. When the user sends a wake-up command in the subspace 1, the speakers in the subspace 1, the subspace 2 and the subspace 3 all satisfy the wake-up condition corresponding to the wake-up word. And loudspeaker 203 in subspace 2 recognizes that the wake word is through the wall when it is transmitted to itself, it cannot respond to the wake word as the target device. And the sound box 203 stores the spatial position information of each sound box, the frequency spectrum analysis is performed through the awakening words transmitted by the user, the user can be determined to be in the subspace 1 by combining the collected spatial images, and the sound box closest to the user in the subspace 1 is determined to be the sound box 201, at this moment, the sound box 203 sends an awakening instruction to the sound box 201, so that the sound box 201 is awakened based on the awakening instruction, and a subsequent audio interaction processing flow is executed.
In another embodiment of the present application, there is also provided a control apparatus, referring to fig. 3, the apparatus may include:
a first determining unit 301, configured to determine, in response to receiving target audio information, a target object that generates the target audio information and a candidate device corresponding to the target audio information;
a second determining unit 302, configured to determine a spatial position relationship between the target object and each of the candidate devices;
a third determining unit 302, configured to determine a target device among the candidate devices based on the spatial position relationship, so that the target device responds to the target audio information.
In the control device provided by the embodiment of the application, in response to receiving the target audio information, a target object generating the target audio information and a candidate device corresponding to the target audio information are determined; determining a spatial position relationship corresponding to the target object and each candidate device; based on the spatial positional relationship, a target device is determined among the candidate devices such that the target device responds to the target audio information. When a plurality of candidate devices are available, the device closest to the target object can be determined to respond through the spatial position relation, and the efficiency and accuracy of the device to respond to the audio are improved, and the experience effect is improved.
In one embodiment, when the candidate devices include at least a first device satisfying a target condition, the second determining unit includes:
the first determining subunit is configured to determine, based on the first device, a first spatial position relationship corresponding to the target object and the first device; acquiring a second spatial position relation between the first equipment and candidate equipment except the first equipment;
a second determining subunit, configured to determine, based on the first spatial position relationship and the second spatial position relationship, a spatial position relationship between the target object and each of the candidate devices.
Further, the candidate devices include at least a first device that satisfies a target condition, and the second determination unit includes:
a third determining subunit for determining a first spatial position of the target object based on the first device; and determining a second spatial location of a candidate device other than the first device based on the first device;
a fourth determining subunit, configured to determine, based on the first spatial position and the second spatial position, a spatial position relationship between the target object and each candidate device other than the first device.
Optionally, the candidate devices include at least one first device, and the second determining unit is specifically configured to:
determining a third spatial position of the target object based on the first device and obtaining a fourth spatial position of the first device;
determining a spatial position relationship between the target object and the first device based on the third spatial position and the fourth spatial position;
wherein the third determining unit is specifically configured to:
and if the spatial position relation between the target object and the first equipment meets a specified condition, determining the first equipment as target equipment.
Optionally, the third determining unit includes:
a fifth determining subunit, configured to determine, based on the spatial position relationship, whether each candidate device is in the same subspace as the target object;
a sixth determining subunit, configured to determine, as the target device, a candidate device in the same subspace as the target object.
Further, the candidate devices in the same subspace as the target object include at least one device, and the sixth determining subunit is specifically configured to:
acquiring distance information between each candidate device and the target object;
determining a target device among candidate devices in the same subspace as the target object based on the distance information.
Further, the sixth determining subunit is further configured to:
acquiring the device characteristics of each candidate device in the same subspace with the target device and the attribute characteristics of the target audio information;
determining a target device among candidate devices in the same subspace as the target object based on the device feature and the attribute feature.
Optionally, the second determining unit is further configured to:
acquiring a first space image of a space where the target object and each candidate device are located;
and determining the spatial position relation of the target object and each candidate device based on the first spatial image.
Further, the second determination unit is specifically configured to:
acquiring audio frequency spectrum information corresponding to the target audio frequency information;
determining a transmission medium corresponding to the target audio information transmitted to each candidate device based on the audio spectrum information;
and determining the spatial position relation of the target object and each candidate device based on the transmission medium.
It should be noted that, for the specific implementation of each unit in the present embodiment, reference may be made to the corresponding content in the foregoing, and details are not described here.
Referring to fig. 4, a schematic structural diagram of an electronic device provided in another embodiment of the present application is shown, where the electronic device may include:
a memory for storing a program;
and the processor is used for calling and executing the program in the memory, and executing the program to realize the steps of the control method.
Correspondingly, in another embodiment of the present application, a readable storage medium is further provided, on which a computer program is stored, which, when being executed by a processor, implements the steps of the control method according to any one of the above.
It should be noted that, in the present embodiment, reference may be made to the corresponding contents in the foregoing, and details are not described here.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A control method, comprising:
in response to receiving target audio information, determining a target object generating the target audio information and a candidate device corresponding to the target audio information;
determining a spatial position relationship corresponding to the target object and each candidate device;
determining a target device among the candidate devices based on the spatial positional relationship such that the target device is responsive to the target audio information.
2. The method of claim 1, the candidate devices comprising at least a first device satisfying a target condition, the determining a spatial positional relationship of the target object to each of the candidate devices comprising:
determining a first spatial position relation of the target object and a first device based on the first device; acquiring a second spatial position relation between the first equipment and candidate equipment except the first equipment;
determining a spatial positional relationship between the target object and each of the candidate devices based on the first spatial positional relationship and the second spatial positional relationship.
3. The method of claim 1, the candidate devices comprising at least a first device satisfying a target condition, the determining a spatial positional relationship of the target object to each of the candidate devices comprising:
determining a first spatial location of the target object based on the first device; and determining a second spatial location of a candidate device other than the first device based on the first device;
based on the first and second spatial locations, a spatial positional relationship between the target object and each candidate device other than the first device is determined.
4. The method of claim 1, the candidate devices comprising at least one first device, the determining a spatial positional relationship of the target object to each of the candidate devices comprising:
determining a third spatial position of the target object based on the first device and obtaining a fourth spatial position of the first device;
determining a spatial position relationship between the target object and the first device based on the third spatial position and the fourth spatial position;
the determining, based on the spatial location relationship, a target device among the candidate devices includes:
and if the spatial position relation between the target object and the first equipment meets a specified condition, determining the first equipment as target equipment.
5. The method of claim 1, the determining a target device among the candidate devices based on the spatial location relationship, comprising:
determining whether each candidate device is in the same subspace as the target object based on the spatial position relationship;
and determining candidate equipment in the same subspace with the target object as target equipment.
6. The method of claim 5, wherein the candidate devices in the same subspace as the target object comprise at least one device, the determining a candidate device in the same subspace as the target object as a target device comprises:
acquiring distance information between each candidate device and the target object;
determining a target device among candidate devices in the same subspace as the target object based on the distance information.
7. The method of claim 6, the determining candidate devices that are in the same subspace as the target object as target devices, comprising:
acquiring the device characteristics of each candidate device in the same subspace with the target device and the attribute characteristics of the target audio information;
determining a target device among candidate devices in the same subspace as the target object based on the device feature and the attribute feature.
8. The method of claim 1, the determining a spatial positional relationship of the target object corresponding to each candidate apparatus, comprising:
acquiring a first space image of a space where the target object and each candidate device are located;
and determining the spatial position relation of the target object and each candidate device based on the first spatial image.
9. The method of claim 1, the determining a spatial positional relationship of the target object corresponding to each candidate apparatus, comprising:
acquiring audio frequency spectrum information corresponding to the target audio frequency information;
determining a transmission medium corresponding to the target audio information transmitted to each candidate device based on the audio spectrum information;
and determining the spatial position relation of the target object and each candidate device based on the transmission medium.
10. A control device, comprising:
a first determination unit, configured to determine, in response to receiving target audio information, a target object that generates the target audio information and a candidate device corresponding to the target audio information;
a second determining unit, configured to determine a spatial position relationship between the target object and each of the candidate devices;
a third determining unit configured to determine a target device among the candidate devices based on the spatial positional relationship so that the target device responds to the target audio information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111676133.7A CN114299951A (en) | 2021-12-31 | 2021-12-31 | Control method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111676133.7A CN114299951A (en) | 2021-12-31 | 2021-12-31 | Control method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114299951A true CN114299951A (en) | 2022-04-08 |
Family
ID=80975713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111676133.7A Pending CN114299951A (en) | 2021-12-31 | 2021-12-31 | Control method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299951A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117176507A (en) * | 2023-11-02 | 2023-12-05 | 上海鉴智其迹科技有限公司 | Data analysis method, device, electronic equipment and storage medium |
| WO2023240636A1 (en) * | 2022-06-17 | 2023-12-21 | 北京小米移动软件有限公司 | Sound box playing control method, sound box playing control apparatus, and storage medium |
-
2021
- 2021-12-31 CN CN202111676133.7A patent/CN114299951A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023240636A1 (en) * | 2022-06-17 | 2023-12-21 | 北京小米移动软件有限公司 | Sound box playing control method, sound box playing control apparatus, and storage medium |
| CN117176507A (en) * | 2023-11-02 | 2023-12-05 | 上海鉴智其迹科技有限公司 | Data analysis method, device, electronic equipment and storage medium |
| CN117176507B (en) * | 2023-11-02 | 2024-02-23 | 上海鉴智其迹科技有限公司 | Data analysis method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108351872B (en) | Method and system for responding to user speech | |
| US10672387B2 (en) | Systems and methods for recognizing user speech | |
| US11551683B2 (en) | Electronic device and operation method therefor | |
| CN107799126B (en) | Voice endpoint detection method and device based on supervised machine learning | |
| US11138977B1 (en) | Determining device groups | |
| CN114299951A (en) | Control method and device | |
| JP4086280B2 (en) | Voice input system, voice input method, and voice input program | |
| CN113096658A (en) | Terminal equipment, awakening method and device thereof and computer readable storage medium | |
| JP2016080750A (en) | Voice recognition device, voice recognition method, and voice recognition program | |
| EP3866158A1 (en) | Systems and methods for generating a singular voice audio stream | |
| JP2002182688A (en) | Method and system for device control using voice recognition | |
| WO2022111579A1 (en) | Voice wakeup method and electronic device | |
| WO2021196612A1 (en) | Device driving method and apparatus, and computer device and computer readable storage medium | |
| CN107977187B (en) | Reverberation adjusting method and electronic equipment | |
| CN114121024A (en) | Wake-up recognition method, audio device and audio device group | |
| JP6678315B2 (en) | Voice reproduction method, voice interaction device, and voice interaction program | |
| US10070244B1 (en) | Automatic loudspeaker configuration | |
| JP6755843B2 (en) | Sound processing device, voice recognition device, sound processing method, voice recognition method, sound processing program and voice recognition program | |
| CN116129942A (en) | Voice interaction device and voice interaction method | |
| WO2022052691A1 (en) | Multi-device voice processing method, medium, electronic device, and system | |
| CN113990312A (en) | Equipment control method and device, electronic equipment and storage medium | |
| KR101863098B1 (en) | Apparatus and method for speech recognition | |
| CN114690113A (en) | Method and device for determining position of equipment | |
| WO2019246314A1 (en) | Acoustic aware voice user interface | |
| CN113571038B (en) | Voice dialogue method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |