CN110740083A - Voice equipment awakening method and device, household appliance and readable storage medium - Google Patents
Voice equipment awakening method and device, household appliance and readable storage medium Download PDFInfo
- Publication number
- CN110740083A CN110740083A CN201911010582.0A CN201911010582A CN110740083A CN 110740083 A CN110740083 A CN 110740083A CN 201911010582 A CN201911010582 A CN 201911010582A CN 110740083 A CN110740083 A CN 110740083A
- Authority
- CN
- China
- Prior art keywords
- voice
- candidate
- awakening
- energy value
- current
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 43
- 230000006870 function Effects 0.000 claims description 37
- 230000004044 response Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 9
- 230000002618 waking effect Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/282—Controlling appliance services of a home automation network by calling their functionalities based on user interaction within the home
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/2821—Avoiding conflicts related to the use of home appliances
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The application provides voice device awakening methods, devices, household appliances and readable storage media, wherein the method comprises the steps of recording receiving time corresponding to an IP identification and a candidate awakening energy value when receiving the awakened candidate voice device and sending the candidate awakening energy value corresponding to the IP identification in a device IP list, comparing the current awakening energy value of the current voice device with the candidate awakening energy value corresponding to each receiving time when acquiring an awakening trigger instruction of the current voice device, sending the current awakening energy value to the candidate voice device corresponding to the IP identification and waiting for reply when the current awakening energy value is larger than the candidate awakening energy value, and carrying out voice recognition processing on voice information input after awakening when the current awakening energy value is confirmed to be maximum.
Description
Technical Field
The application relates to the technical field of household appliances, in particular to a method and a device for waking up voice devices, a household appliance and a readable storage medium.
Background
With the continuous popularization of intelligent household appliances, household appliances controlled by voice are more and more, for example, a plurality of line controllers supporting natural voice recognition are installed at home, a user shouting a wakeup word at home, which may cause the voice control devices of the whole house to respond simultaneously, and it can be understood that wakeup actions of the household appliances are all occurring simultaneously, which may cause storm in instant lan, and affect the lan communication environment.
Disclosure of Invention
The application provides voice equipment awakening methods, through monitoring all voice equipment in the LAN, maintains the equipment IP list, after discerning the word of awakening, to the logical processing of voice energy, reduces as far as possible the unicast number of times in the LAN, improves LAN communication quality, has solved among the prior art when the user shouts the word of awakening the whole room voice control equipment simultaneously the response influence LAN communication environment's technical problem.
The embodiment of the aspect of the present application provides a voice device waking method, including:
searching identifiers of equipment with a voice awakening function in a local area network to generate an equipment IP list, and recording a plurality of receiving times corresponding to the IP identifiers and the candidate awakening energy values when receiving the candidate awakening energy values which are sent by other awakened candidate voice equipment and correspond to the IP identifiers in the equipment IP list;
traversing the receiving time corresponding to each IP identification, and if the awakening trigger instruction of the current voice equipment is acquired within a preset time period, comparing the current awakening energy value of the current voice equipment with the candidate awakening energy value corresponding to each receiving time;
if the current awakening energy value of the current voice equipment is larger than the candidate awakening energy value, sending the current awakening energy value to the candidate voice equipment corresponding to the IP identification and waiting for replying;
and if the preset system processing time is reached, confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices, and performing voice recognition processing on the voice information input after awakening.
As an possible implementation manner of the embodiment of the present application, after generating a device IP list by using an identifier of a device having a voice wakeup function in the local area network, the method further includes:
when the IP identification containing the candidate awakening energy value sent by other awakened candidate voice devices does not exist in the device IP list, the identification of the device with the voice awakening function in the local area network is searched again to refresh the device IP list.
As a second possible implementation manner of the embodiment of the present application, after traversing the receiving time corresponding to each IP identifier, the method further includes:
and if the awakening trigger instruction of the current voice equipment is not received within the preset time period, sending zero response to the candidate voice equipment corresponding to the IP identification.
As a third possible implementation manner of the embodiment of the present application, after comparing the current wake-up energy value of the current speech device with the candidate wake-up energy value corresponding to each receiving time, the method further includes:
and if the current awakening energy value of the current voice equipment is less than or equal to the candidate awakening energy value, not sending the current energy value to the candidate voice equipment corresponding to the IP identification.
As a fourth possible implementation manner of the embodiment of the present application, before the preset system processing time is reached, the method further includes:
receiving notification information which is sent by other candidate voice equipment and contains candidate awakening energy values;
if the current energy value is smaller than the candidate awakening energy value in the notification message, closing the current voice equipment, and sending a shutdown response message to the corresponding candidate voice equipment.
According to the voice device awakening method, the IP list of the device is generated by searching the identification of the device with the voice awakening function in the local area network, and when the candidate awakening energy value which is sent by other awakened candidate voice devices and corresponds to the IP identification in the IP list of the device is received, a plurality of receiving times which correspond to the IP identification and the candidate awakening energy value are recorded; traversing the receiving time corresponding to each IP identification, and if the awakening trigger instruction of the current voice equipment is acquired within a preset time period, comparing the current awakening energy value of the current voice equipment with the candidate awakening energy value corresponding to each receiving time; if the current awakening energy value of the current voice equipment is larger than the candidate awakening energy value, sending the current awakening energy value to the candidate voice equipment corresponding to the IP identification and waiting for replying; and if the preset system processing time is reached, confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices, and performing voice recognition processing on the voice information input after awakening. Therefore, the technical problem that the whole-house voice control equipment simultaneously responds to the influence on the communication environment of the local area network when a user shouts the awakening word in the prior art is solved, all voice equipment in the local area network is monitored, an equipment IP list is maintained, after the awakening word is identified, the voice energy is logically processed, the unicast times in the local area network are reduced as much as possible, and the communication quality of the local area network is improved.
The embodiment of the second aspect of the present application provides an voice device wake-up apparatus, including:
the generating module is used for searching the identification of the equipment with the voice awakening function in the local area network to generate an equipment IP list;
the recording module is used for recording a plurality of receiving times corresponding to the IP identifications and the candidate awakening energy values when receiving the candidate awakening energy values which are sent by other awakened candidate voice devices and correspond to the IP identifications in the device IP list;
the traversing module is used for traversing the receiving time corresponding to each IP identification;
the comparison module is used for comparing the current awakening energy value of the current voice equipment with the candidate awakening energy value corresponding to each receiving time if the awakening trigger instruction of the current voice equipment is acquired within a preset time period;
sending module, configured to send the current wake-up energy value to a candidate voice device corresponding to the IP identifier and wait for a reply if it is known that the current wake-up energy value of the current voice device is greater than the candidate wake-up energy value;
and the processing module is used for confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices if the preset system processing time is reached, and then carrying out voice recognition processing on the voice information input after awakening.
As an th possible implementation manner of the embodiment of the present application, the apparatus further includes:
and the generating module is further configured to search again the identifier of the device with the voice wakeup function in the local area network to refresh the device IP list when the IP identifier containing the candidate wakeup energy value sent by the other awakened candidate voice devices does not exist in the device IP list.
As a second possible implementation manner of the embodiment of the present application, the apparatus further includes:
and the second sending module is used for sending zero response to the candidate voice equipment corresponding to the IP identifier if the awakening trigger instruction of the current voice equipment is not received within the preset time period.
As a third possible implementation manner of the embodiment of the present application, the apparatus further includes:
and the determining module is used for not sending the current energy value to the candidate voice equipment corresponding to the IP identification if the current awakening energy value of the current voice equipment is less than or equal to the candidate awakening energy value.
As a fourth possible implementation manner of the embodiment of the present application, the apparatus further includes:
the receiving module is used for receiving notification information which is sent by other candidate voice equipment and contains the candidate awakening energy value;
and the closing module is used for closing the current voice equipment and sending a shutdown response message to the corresponding candidate voice equipment if the current energy value is determined to be smaller than the candidate awakening energy value in the notification message.
According to the voice equipment awakening device, the equipment IP list is generated by searching the identification of the equipment with the voice awakening function in the local area network, and when the candidate awakening energy value which is sent by other awakened candidate voice equipment and corresponds to the IP identification in the equipment IP list is received, a plurality of receiving times corresponding to the IP identification and the candidate awakening energy value are recorded; traversing the receiving time corresponding to each IP identification, and if the awakening trigger instruction of the current voice equipment is acquired within a preset time period, comparing the current awakening energy value of the current voice equipment with the candidate awakening energy value corresponding to each receiving time; if the current awakening energy value of the current voice equipment is larger than the candidate awakening energy value, sending the current awakening energy value to the candidate voice equipment corresponding to the IP identification and waiting for replying; and if the preset system processing time is reached, confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices, and performing voice recognition processing on the voice information input after awakening. Therefore, the technical problem that the whole-house voice control equipment simultaneously responds to the influence on the communication environment of the local area network when a user shouts the awakening word in the prior art is solved, all voice equipment in the local area network is monitored, an equipment IP list is maintained, after the awakening word is identified, the voice energy is logically processed, the unicast times in the local area network are reduced as much as possible, and the communication quality of the local area network is improved.
The third embodiment of the present application provides home devices, which include a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the processor implements the voice device wake-up method as proposed in the above embodiments of the present application.
A fourth embodiment of the present application provides non-transitory computer-readable storage media, on which a computer program is stored, where the computer program is configured to, when executed by a processor, implement a method for waking up a voice device as set forth in the above-mentioned embodiment of the present application.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart illustrating a voice device wake-up method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a voice device wake-up method according to a second embodiment of the present application;
fig. 3 is a schematic flowchart of a voice device wake-up method according to a third embodiment of the present application;
fig. 4 is a schematic structural diagram of a voice device wake-up apparatus according to a fourth embodiment of the present application;
fig. 5 is a schematic structural diagram of a voice device wake-up apparatus according to a fifth embodiment of the present application;
fig. 6 is a schematic structural diagram of a voice device wake-up apparatus according to a sixth embodiment of the present application;
fig. 7 is a schematic structural diagram of a speech device wake-up apparatus according to a seventh embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
For the description of the background art, a user shouting a wakeup word at home may cause the whole-house voice control devices to respond simultaneously, that is, the simultaneous occurrence of the wakeup actions of the household appliances may cause an instant storm in the lan , which affects the lan communication environment.
In order to solve the above problems, an embodiment of the present application provides voice device wake-up methods, which include generating a device IP list by searching identifiers of devices having a voice wake-up function in a local area network, recording a plurality of receiving times corresponding to IP identifiers and candidate wake-up energy values when receiving candidate wake-up energy values corresponding to IP identifiers in the device IP list sent by other awakened candidate voice devices, traversing the receiving time corresponding to each IP identifier, comparing a current wake-up energy value of a current voice device with the candidate wake-up energy value corresponding to each receiving time if a wake-up trigger instruction of the current voice device is obtained within a preset time period, sending the current wake-up energy value to the candidate voice device corresponding to the IP identifier and waiting for a reply if the current wake-up energy value of the current voice device is known to be greater than the candidate wake-up energy value, and performing voice recognition processing on voice information input after wake-up if the current wake-up energy value is confirmed to be the maximum according to reply information of all candidate voice devices when a preset system processing time is reached.
The following describes a voice device wake-up method, apparatus, home device, and readable storage medium according to embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a voice device wake-up method according to an embodiment of the present application.
As shown in fig. 1, the voice device wake-up method may include the following steps:
It can be understood that or a plurality of devices with a voice wakeup function can be connected to lans, and after the devices are powered on, service listening ports can be arbitrarily opened to search for an identifier with a voice wakeup function in a lan to generate an IP list of the devices in a broadcast manner.
Wherein, the identifier can represent only devices, that is, different identifiers correspond to different devices, for example, the IP (internet protocol address) of a device can be obtained by determining the device 1 through the identifier 1, and thus, a plurality of devices with voice wakeup function can obtain a plurality of device IPs and generate a device IP list.
, the thread private can receive the candidate wake-up energy values of other devices with voice wake-up function in the lan, and the received candidate wake-up energy values and the receiving time are stored with the IP identifier as an index, such as storing IP identifier 1, candidate wake-up energy value 1 and receiving time 1 as columns for storage, etc.
Specifically, a preset time period, for example, 2 seconds, may be set as required, and a wake-up trigger instruction of the current voice device is obtained within the preset time period, that is, the current voice device is wakened up and triggered, it is understood that the current voice device is wakened up to generate a current wake-up energy value, and therefore, the current wake-up energy value may be compared with candidate wake-up energy values corresponding to every receiving times, that is, the current voice device's own energy value is compared with each received candidate wake-up energy value.
And 103, if the current awakening energy value of the current voice equipment is larger than the candidate awakening energy value, sending the current awakening energy value to the candidate voice equipment corresponding to the IP identifier and waiting for replying.
And step 104, if the preset system processing time is reached, confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices, and performing voice recognition processing on the voice information input after awakening.
Specifically, the current wake-up energy value of the current voice device may be smaller than, equal to, or larger than each candidate wake-up energy, and in the process of comparing , when it is known that the current wake-up energy value of the current voice device is larger than the candidate wake-up energy value, the candidate voice device that acquires the candidate wake-up energy value corresponding to the IP identifier sends the current wake-up energy value and waits for a reply.
, when the preset system processing time is reached, according to the reply information of all candidate voice devices, confirming that the current wake-up energy value is maximum, then performing voice recognition processing on the voice information input after wake-up, wherein the preset system processing time can be set as required, that is, when the set system processing time is reached, the device can be woken up by judging the wake-up energy of the device to be the maximum in the device list, and performing subsequent semantic recognition operation.
According to the voice device awakening method, the IP list of the device is generated by searching the identification of the device with the voice awakening function in the local area network, and when the candidate awakening energy value which is sent by other awakened candidate voice devices and corresponds to the IP identification in the IP list of the device is received, a plurality of receiving times which correspond to the IP identification and the candidate awakening energy value are recorded; traversing the receiving time corresponding to each IP identification, and if the awakening trigger instruction of the current voice equipment is acquired within a preset time period, comparing the current awakening energy value of the current voice equipment with the candidate awakening energy value corresponding to each receiving time; if the current awakening energy value of the current voice equipment is larger than the candidate awakening energy value, sending the current awakening energy value to the candidate voice equipment corresponding to the IP identification and waiting for replying; and if the preset system processing time is reached, confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices, and performing voice recognition processing on the voice information input after awakening. Therefore, the technical problem that the whole-house voice control equipment simultaneously responds to the influence on the communication environment of the local area network when a user shouts the awakening word in the prior art is solved, all voice equipment in the local area network is monitored, an equipment IP list is maintained, after the awakening word is identified, the voice energy is logically processed, the unicast times in the local area network are reduced as much as possible, and the communication quality of the local area network is improved.
Fig. 2 is a flowchart illustrating a voice device wake-up method according to a second embodiment of the present application.
As shown in fig. 2, the method comprises the steps of:
It can be understood that or a plurality of devices with a voice wakeup function can be connected to lans, and after the devices are powered on, service listening ports can be arbitrarily opened to search for an identifier with a voice wakeup function in a lan to generate an IP list of the devices in a broadcast manner.
Wherein, the identifier can represent only devices, that is, different identifiers correspond to different devices, for example, the IP (internet protocol address) of a device can be obtained by determining the device 1 through the identifier 1, and thus, a plurality of devices with voice wakeup function can obtain a plurality of device IPs and generate a device IP list.
, the thread private can receive the candidate wake-up energy values of other devices with voice wake-up function in the lan, and the received candidate wake-up energy values and the receiving time are stored with the IP identifier as an index, such as storing IP identifier 1, candidate wake-up energy value 1 and receiving time 1 as columns for storage, etc.
It should be noted that, there may be a new device powered on to access the local area network after searching the generated device IP list, and therefore, when the IP identifier containing the candidate wake-up energy value sent by the other woken candidate voice devices does not exist in the device IP list, the device IP list needs to be refreshed by searching the identifier of the device with the voice wake-up function in the local area network again, so as to further improve the maintenance of the device IP list.
In step 205, if the wake-up trigger command of the current voice device is obtained within the preset time period, the current wake-up energy value of the current voice device is compared with the candidate wake-up energy value corresponding to each receiving time.
Specifically, a preset time period, for example, 2 seconds, may be set as required, and a wake-up trigger instruction of the current voice device is obtained within the preset time period, that is, the current voice device is wakened up and triggered, it is understood that the current voice device is wakened up to generate a current wake-up energy value, and therefore, the current wake-up energy value may be compared with candidate wake-up energy values corresponding to every receiving times, that is, the current voice device's own energy value is compared with each received candidate wake-up energy value.
It should be noted that if the wake-up trigger instruction of the current voice device is not received within the preset time period, a zero response is sent to the candidate voice device corresponding to the IP identifier.
And step 208, if it is known that the current wake-up energy value of the current voice device is less than or equal to the candidate wake-up energy value, not sending the current energy value to the candidate voice device corresponding to the IP identifier.
Specifically, the current wake-up energy value of the current voice device may be smaller than, equal to, or larger than each candidate wake-up energy, and in the process of comparing , when it is known that the current wake-up energy value of the current voice device is larger than the candidate wake-up energy value, the candidate voice device that acquires the candidate wake-up energy value corresponding to the IP identifier sends the current wake-up energy value and waits for a reply.
It can be understood that, when it is known that the current wake-up energy value of the current voice device is less than or equal to the candidate wake-up energy value, the current energy value is not sent to the candidate voice device corresponding to the IP identifier, that is, if the valid energy value is received within 2s and the current wake-up energy value is less than or equal to the candidate wake-up energy value, the device is skipped, otherwise, the current wake-up energy value is unicast using UDP (user datagram Protocol), and a reply is waited until all IP identifiers are traversed, and if the reply is waited for, the refreshing device is searched again.
Specifically, notification information containing candidate wake-up energy values sent by other candidate voice devices may also be received, the candidate wake-up energy values are obtained through analysis of the notification information, the current voice device is turned off when the current energy value is judged to be smaller than the candidate wake-up energy value in the notification information, and a shutdown response message is sent to the corresponding candidate voice device, that is, when the later wake-up device knows that the energy value of the earlier wake-up device is larger, the energy value is not transmitted, so as to save the communication bandwidth.
And step 210, if the preset system processing time is reached, confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices, and performing voice recognition processing on the voice information input after awakening.
Specifically, when the preset system processing time is reached, the current maximum awakening energy value is confirmed according to the reply information of all candidate voice devices, and then voice recognition processing is performed on the voice information input after awakening, wherein the preset system processing time can be set as required, that is, when the set system processing time is reached, the device can be awakened by judging that the awakening energy of the device is the maximum in the device list, and subsequent semantic recognition operation is performed.
The voice device awakening method of the embodiment of the application generates a device IP list by searching the identification of the device with the voice awakening function in the local area network, records a plurality of receiving times corresponding to the IP identification and the candidate awakening energy value when receiving the candidate awakening energy value which is sent by other awakened candidate voice devices and corresponds to the IP identification in the device IP list, re-searches the identification refreshing device IP list of the device with the voice awakening function in the local area network when receiving the IP identification which is sent by other awakened candidate voice devices and contains the candidate awakening energy value and does not exist in the device IP list, traverses the receiving time corresponding to each IP identification, and compares the current awakening energy value of the current voice device with the candidate awakening energy value corresponding to each receiving time if acquiring the awakening trigger instruction of the current voice device in a preset time period, if the wake-up trigger instruction of the current voice equipment is not received within the preset time period, sending a zero response to the candidate voice equipment corresponding to the IP identification, if the current wake-up energy value of the current voice equipment is known to be larger than the candidate wake-up energy value, sending the current wake-up energy value to the candidate voice equipment corresponding to the IP identification and waiting for a reply, if the current wake-up energy value of the current voice equipment is known to be smaller than or equal to the candidate wake-up energy value, not sending the current energy value to the candidate voice equipment corresponding to the IP identification, receiving notification information containing the candidate wake-up energy values sent by other candidate voice equipment, if the current energy value is determined to be smaller than the candidate wake-up energy value in the notification information, closing the current voice equipment and sending a shutdown response message to the corresponding candidate voice equipment, and if the preset system processing time is reached, determining that the current wake-up energy value is maximum according to the reply information of, voice recognition processing is performed on the voice information input after the wake-up. Therefore, the technical problem that the whole-house voice control equipment simultaneously responds to the influence on the communication environment of the local area network when a user shouts the awakening word in the prior art is solved, all voice equipment in the local area network is monitored, an equipment IP list is maintained, after the awakening word is identified, the voice energy is logically processed, the unicast times in the local area network are reduced as much as possible, the communication quality of the local area network is improved, and when the energy value of the equipment awakened earlier is larger, the energy value is not transmitted by the back awakening equipment, so that the communication bandwidth is saved.
Based on the above description of the embodiments, in order to make the above process more clear to those skilled in the art, the following detailed description is made by taking the apparatus 1, the apparatus 2 and the apparatus as examples in fig. 3 as follows:
fig. 3 is a flowchart illustrating a voice device wake-up method according to a third embodiment of the present application.
As shown in fig. 3, the method includes:
step 1, after the device is powered on, service monitoring ports are opened by default, a broadcasting mode is used for searching the devices with the voice awakening function in the local area network, and an IP list of the devices with the voice awakening function is recorded.
And 2, starting threads for receiving candidate awakening energy values of other devices in the local area network by special , storing the received candidate awakening energy values and the receiving time by taking the device IP as an index, if the candidate awakening energy values are awakened in 2s, taking the self energy as a reply, if the candidate awakening energy values are not awakened in 2s, replying 0 energy, and if the candidate awakening energy values of unknown IP are received, restarting to search the voice device and refreshing a device IP list.
Step 3, the equipment is awakened and triggered, firstly, an energy value list of a local cache is inquired, if the target IP identification receives an effective energy value in 2s and the energy value of the target IP identification is smaller than the received candidate awakening energy value, the equipment is skipped, otherwise, the current awakening energy value is unicast by using UDP and waits for reply until all IPs are traversed, and if the waiting reply is overtime, the equipment is searched and refreshed again.
And 4, when the overtime time is up, judging that the current awakening energy value is the maximum value in the equipment list, awakening the equipment and carrying out subsequent semantic recognition.
Therefore, all voice devices in the local area network are monitored through the service monitoring port, device IP lists are maintained, after awakening words are identified, the UDP unicast confirmation reply method is used, on the premise that the message is determined to be reliable as much as possible, unicast times in the local area network are reduced as much as possible through logic processing of voice energy, the communication quality of the local area network is improved, and when the later awakening device learns that the energy value of the device awakened earlier is larger, energy value transmission is not carried out, so that the communication bandwidth is saved.
In order to implement the above embodiments, the present application also provides kinds of voice device wake-up apparatuses.
Fig. 4 is a schematic structural diagram of a voice device wake-up apparatus according to a fifth embodiment of the present application.
As shown in fig. 4, the voice device wake-up apparatus includes: a detection module 110 and a display module 120.
The generating module 401 is configured to search for an identifier of a device with a voice wakeup function in a local area network, and generate a device IP list.
A recording module 402, configured to record a plurality of receiving times corresponding to the IP identifier and the candidate wake-up energy value when receiving the candidate wake-up energy value corresponding to the IP identifier in the device IP list sent by another awakened candidate voice device.
And a traversing module 403, configured to traverse the receiving time corresponding to each IP identifier.
A comparing module 404, configured to compare the current wake-up energy value of the current voice device with the candidate wake-up energy value corresponding to each receiving time if the wake-up trigger instruction of the current voice device is obtained within a preset time period.
A sending module 405, configured to send the current wake-up energy value to a candidate voice device corresponding to the IP identifier and wait for a reply if it is known that the current wake-up energy value of the current voice device is greater than the candidate wake-up energy value.
And the processing module 406 is configured to, if the preset system processing time is reached, confirm that the current wake-up energy value is maximum according to the reply information of all candidate voice devices, and perform voice recognition processing on the voice information input after wake-up.
As possible implementation manners, the generating module 401 is further configured to, when the IP identifier that includes the candidate wake-up energy value and is sent by the other woken candidate voice devices does not exist in the device IP list, re-search the identifier of the device with a voice wake-up function in the lan to refresh the device IP list.
As a second possible implementation manner of the embodiment of the present application, as shown in fig. 5, on the basis of fig. 4, the apparatus further includes: a second sending module 407.
The second sending module 407 is configured to send a zero response to the candidate voice device corresponding to the IP identifier if the wake-up trigger instruction of the current voice device is not received within the preset time period.
As a third possible implementation manner of the embodiment of the present application, as shown in fig. 6, on the basis of fig. 4, the apparatus further includes: a module 408 is determined.
A determining module 408, configured to not send the current energy value to the candidate voice device corresponding to the IP identifier if it is known that the current wake-up energy value of the current voice device is less than or equal to the candidate wake-up energy value.
As a fourth possible implementation manner of the embodiment of the present application, as shown in fig. 7, on the basis of fig. 4, the apparatus further includes: a receiving module 409 and a shutdown module 410.
A receiving module 409, configured to receive notification information that includes the candidate wake-up energy value and is sent by other candidate voice devices.
A closing module 410, configured to close the current voice device and send a shutdown response message to a corresponding candidate voice device if it is determined that the current energy value is smaller than the candidate wake-up energy value in the notification message.
It should be noted that the foregoing explanation on the embodiment of the voice device wake-up method is also applicable to the voice device wake-up apparatus of this embodiment, and the implementation principle thereof is similar, and is not described herein again.
The voice device wake-up apparatus of the embodiment of the application searches for an identifier of a device with a voice wake-up function in a local area network to generate a device IP list, records a plurality of receiving times corresponding to IP identifiers and candidate wake-up energy values when receiving the candidate wake-up energy values corresponding to the IP identifiers in the device IP list sent by other awakened candidate voice devices, re-searches for an identifier of a device with a voice wake-up function in a local area network to refresh the device IP list when receiving that the IP identifiers containing the candidate wake-up energy values sent by other awakened candidate voice devices do not exist in the device IP list, traverses the receiving time corresponding to each IP identifier, and compares the current wake-up energy value of the current voice device with the candidate wake-up energy value corresponding to each receiving time if acquiring a wake-up trigger instruction of the current voice device within a preset time period, if the wake-up trigger instruction of the current voice equipment is not received within the preset time period, sending a zero response to the candidate voice equipment corresponding to the IP identification, if the current wake-up energy value of the current voice equipment is known to be larger than the candidate wake-up energy value, sending the current wake-up energy value to the candidate voice equipment corresponding to the IP identification and waiting for a reply, if the current wake-up energy value of the current voice equipment is known to be smaller than or equal to the candidate wake-up energy value, not sending the current energy value to the candidate voice equipment corresponding to the IP identification, receiving notification information containing the candidate wake-up energy values sent by other candidate voice equipment, if the current energy value is determined to be smaller than the candidate wake-up energy value in the notification information, closing the current voice equipment and sending a shutdown response message to the corresponding candidate voice equipment, and if the preset system processing time is reached, determining that the current wake-up energy value is maximum according to the reply information of, voice recognition processing is performed on the voice information input after the wake-up. Therefore, the technical problem that the whole-house voice control equipment simultaneously responds to the influence on the communication environment of the local area network when a user shouts the awakening word in the prior art is solved, all voice equipment in the local area network is monitored, an equipment IP list is maintained, after the awakening word is identified, the voice energy is logically processed, the unicast times in the local area network are reduced as much as possible, the communication quality of the local area network is improved, and when the energy value of the equipment awakened earlier is larger, the energy value is not transmitted by the back awakening equipment, so that the communication bandwidth is saved.
In order to implement the foregoing embodiments, the present application further provides home devices, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the voice device wake-up method as set forth in the foregoing embodiments of the present application.
In order to implement the above embodiments, the present application further proposes non-transitory computer readable storage media having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the voice device wake-up method as proposed in the above embodiments of the present application.
In the description herein, reference to the terms " embodiments," " embodiments," "examples," "specific examples," or " examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least embodiments or examples of the application.
Thus, a feature defined as "", "second" may or may not include at least of that feature.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present application.
For the purposes of this description, a "computer-readable medium" can be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device (e.g., a computer-based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions).
If implemented in hardware and in another implementation, for example, any of the following items or combinations thereof are known in the art, discrete logic circuitry having logic circuitry for implementing logic functions on data signals, application specific integrated circuitry having appropriate combinational logic circuitry, programmable arrays (PGAs), field programmable arrays (FPGAs), and the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware associated with instructions of a program, which may be stored in computer readable storage media, and when executed, the program includes or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated into processing modules, or each unit may exist alone physically, or two or more units are integrated into modules.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1, A voice device wake-up method, characterized by comprising the following steps:
searching identifiers of equipment with a voice awakening function in a local area network to generate an equipment IP list, and recording a plurality of receiving times corresponding to the IP identifiers and the candidate awakening energy values when receiving the candidate awakening energy values which are sent by other awakened candidate voice equipment and correspond to the IP identifiers in the equipment IP list;
traversing the receiving time corresponding to each IP identification, and if the awakening trigger instruction of the current voice equipment is acquired within a preset time period, comparing the current awakening energy value of the current voice equipment with the candidate awakening energy value corresponding to each receiving time;
if the current awakening energy value of the current voice equipment is larger than the candidate awakening energy value, sending the current awakening energy value to the candidate voice equipment corresponding to the IP identification and waiting for replying;
and if the preset system processing time is reached, confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices, and performing voice recognition processing on the voice information input after awakening.
2. The method of claim 1, wherein after searching for the device IP list generated by the identity of the voice wake up capable device within the local area network, further comprising:
when the IP identification containing the candidate awakening energy value sent by other awakened candidate voice devices does not exist in the device IP list, the identification of the device with the voice awakening function in the local area network is searched again to refresh the device IP list.
3. The method of claim 1, wherein after said traversing the receive time corresponding to each of the IP identifications, further comprising:
and if the awakening trigger instruction of the current voice equipment is not received within the preset time period, sending zero response to the candidate voice equipment corresponding to the IP identification.
4. The method of claim 1, after comparing a current wake-up energy value of the current speech device to a candidate wake-up energy value for each of the receive times, further comprising:
and if the current awakening energy value of the current voice equipment is less than or equal to the candidate awakening energy value, not sending the current energy value to the candidate voice equipment corresponding to the IP identification.
5. The method of claim 1, prior to said reaching a preset system processing time, further comprising:
receiving notification information which is sent by other candidate voice equipment and contains candidate awakening energy values;
if the current energy value is smaller than the candidate awakening energy value in the notification message, closing the current voice equipment, and sending a shutdown response message to the corresponding candidate voice equipment.
A voice device wake-up device of type, comprising:
the generating module is used for searching the identification of the equipment with the voice awakening function in the local area network to generate an equipment IP list;
the recording module is used for recording a plurality of receiving times corresponding to the IP identifications and the candidate awakening energy values when receiving the candidate awakening energy values which are sent by other awakened candidate voice devices and correspond to the IP identifications in the device IP list;
the traversing module is used for traversing the receiving time corresponding to each IP identification;
the comparison module is used for comparing the current awakening energy value of the current voice equipment with the candidate awakening energy value corresponding to each receiving time if the awakening trigger instruction of the current voice equipment is acquired within a preset time period;
sending module, configured to send the current wake-up energy value to a candidate voice device corresponding to the IP identifier and wait for a reply if it is known that the current wake-up energy value of the current voice device is greater than the candidate wake-up energy value;
and the processing module is used for confirming that the current awakening energy value is maximum according to the reply information of all candidate voice devices if the preset system processing time is reached, and then carrying out voice recognition processing on the voice information input after awakening.
7. The apparatus of claim 6, further comprising:
and the generating module is further configured to search again the identifier of the device with the voice wakeup function in the local area network to refresh the device IP list when the IP identifier containing the candidate wakeup energy value sent by the other awakened candidate voice devices does not exist in the device IP list.
8. The apparatus of claim 6, further comprising:
and the second sending module is used for sending zero response to the candidate voice equipment corresponding to the IP identifier if the awakening trigger instruction of the current voice equipment is not received within the preset time period.
An appliance device of the type 9, , comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the voice device wake-up method of any of claims 1-5, wherein is defined as a sound device wake-up method.
Non-transitory computer readable storage medium , having stored thereon a computer program, characterized in that the program, when being executed by a processor, implements a method for waking up a speech device according to any of the claims 1-5 from .
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911010582.0A CN110740083A (en) | 2019-10-23 | 2019-10-23 | Voice equipment awakening method and device, household appliance and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911010582.0A CN110740083A (en) | 2019-10-23 | 2019-10-23 | Voice equipment awakening method and device, household appliance and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110740083A true CN110740083A (en) | 2020-01-31 |
Family
ID=69270993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911010582.0A Pending CN110740083A (en) | 2019-10-23 | 2019-10-23 | Voice equipment awakening method and device, household appliance and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110740083A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111540360A (en) * | 2020-05-09 | 2020-08-14 | 宁波奥克斯电气股份有限公司 | Equipment awakening method and equipment awakening system |
| CN114553625A (en) * | 2022-02-17 | 2022-05-27 | 青岛海尔科技有限公司 | Response device determination method and apparatus, storage medium, and electronic apparatus |
| WO2023273747A1 (en) * | 2021-06-29 | 2023-01-05 | 青岛海尔科技有限公司 | Wake-up method and apparatus for smart device, storage medium, and electronic device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104202221A (en) * | 2014-08-19 | 2014-12-10 | 中兴通讯股份有限公司 | Method and device for awakening household interconnected device |
| CN108766422A (en) * | 2018-04-02 | 2018-11-06 | 青岛海尔科技有限公司 | Response method, device, storage medium and the computer equipment of speech ciphering equipment |
| CN109391528A (en) * | 2018-08-31 | 2019-02-26 | 百度在线网络技术（北京）有限公司 | Awakening method, device, equipment and the storage medium of speech-sound intelligent equipment |
| US20190147904A1 (en) * | 2017-11-16 | 2019-05-16 | Baidu Online Network Technology (Beijing) Co., Ltd | Method, device and apparatus for selectively interacting with multi-devices, and computer-readable medium |
-
2019
- 2019-10-23 CN CN201911010582.0A patent/CN110740083A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104202221A (en) * | 2014-08-19 | 2014-12-10 | 中兴通讯股份有限公司 | Method and device for awakening household interconnected device |
| US20190147904A1 (en) * | 2017-11-16 | 2019-05-16 | Baidu Online Network Technology (Beijing) Co., Ltd | Method, device and apparatus for selectively interacting with multi-devices, and computer-readable medium |
| CN108766422A (en) * | 2018-04-02 | 2018-11-06 | 青岛海尔科技有限公司 | Response method, device, storage medium and the computer equipment of speech ciphering equipment |
| CN109391528A (en) * | 2018-08-31 | 2019-02-26 | 百度在线网络技术（北京）有限公司 | Awakening method, device, equipment and the storage medium of speech-sound intelligent equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111540360A (en) * | 2020-05-09 | 2020-08-14 | 宁波奥克斯电气股份有限公司 | Equipment awakening method and equipment awakening system |
| WO2023273747A1 (en) * | 2021-06-29 | 2023-01-05 | 青岛海尔科技有限公司 | Wake-up method and apparatus for smart device, storage medium, and electronic device |
| CN114553625A (en) * | 2022-02-17 | 2022-05-27 | 青岛海尔科技有限公司 | Response device determination method and apparatus, storage medium, and electronic apparatus |
| CN114553625B (en) * | 2022-02-17 | 2024-03-22 | 青岛海尔科技有限公司 | Method and device for determining response equipment, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11825246B2 (en) | Electrical panel for identifying devices using power data and network data | |
| US10735829B2 (en) | Identifying device state changes using power data and network data | |
| US9800958B1 (en) | Training power models using network data | |
| CN110740083A (en) | Voice equipment awakening method and device, household appliance and readable storage medium | |
| EP3010289A1 (en) | Method and apparatus for controlling signal transmission and electronic device | |
| WO2017206725A1 (en) | Smart refrigerator, server and language control system and method | |
| KR20170093629A (en) | A Voice Recognition Device And Method, A Voice Recognition System | |
| EP3586521B1 (en) | Identifying device state changes using power data and network data | |
| CN110111789B (en) | Voice interaction method and device, computing equipment and computer readable medium | |
| US20200349952A1 (en) | Hub device, multi-device system including the hub device and plurality of devices, and method of operating the same | |
| CN109639692B (en) | Offline login method, device, equipment, system and storage medium | |
| CN111754997B (en) | Control device and operation method thereof, and voice interaction device and operation method thereof | |
| CN109671426A (en) | A kind of sound control method, device, storage medium and air-conditioning | |
| WO2015188433A1 (en) | Application starting device and method | |
| US11289090B2 (en) | Systems and methods for addressing possible interruption during interaction with digital assistant | |
| WO2019227370A1 (en) | Method, apparatus and system for controlling multiple voice assistants, and computer-readable storage medium | |
| CN111048086A (en) | Voice wake-up method among multiple devices, and auto-negotiation voice wake-up method, device and system | |
| US20230121623A1 (en) | Method for notifying a message of a smart home based on a smart screen Apparatus and Smart screen | |
| US10531236B2 (en) | Universal mute for internet of things enabled devices | |
| CN111862965A (en) | Awakening processing method and device, intelligent sound box and electronic equipment | |
| CN104093199B (en) | Timer method to set up and terminal | |
| CN112328740A (en) | Chat record query method, device, equipment and storage medium | |
| CN111818621A (en) | Bluetooth device awakening method, device and system and electronic device | |
| WO2022160642A1 (en) | Method and apparatus for monitoring air conditioner, and monitoring device | |
| CN112130907A (en) | Session processing method and device and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200131 |