CN117336832A - Intelligent body awakening system - Google Patents
Intelligent body awakening system Download PDFInfo
- Publication number
- CN117336832A CN117336832A CN202311278304.XA CN202311278304A CN117336832A CN 117336832 A CN117336832 A CN 117336832A CN 202311278304 A CN202311278304 A CN 202311278304A CN 117336832 A CN117336832 A CN 117336832A
- Authority
- CN
- China
- Prior art keywords
- volume
- module
- agent
- wake
- intelligent
- 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.)
- Granted
Links
- 230000004044 response Effects 0.000 claims abstract description 57
- 230000005236 sound signal Effects 0.000 claims abstract description 38
- 238000004891 communication Methods 0.000 claims abstract description 28
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 238000005070 sampling Methods 0.000 claims description 45
- 230000003044 adaptive effect Effects 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 17
- 230000002618 waking effect Effects 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0209—Power saving arrangements in terminal devices
- H04W52/0225—Power saving arrangements in terminal devices using monitoring of external events, e.g. the presence of a signal
- H04W52/0229—Power saving arrangements in terminal devices using monitoring of external events, e.g. the presence of a signal where the received signal is a wanted signal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/4401—Bootstrapping
- G06F9/4418—Suspend and resume; Hibernate and awake
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Multimedia (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention belongs to the field of voice processing, and discloses an agent awakening system which comprises a plurality of agent awakening devices, wherein each of the awakening devices comprises a monitoring module, an acquisition module, a near field communication module, a calculation module and a response module; when each intelligent agent is in a low-power-consumption running state, the wake-up device executes the following operation: the monitoring module acquires sound signals with the volume larger than the self-adaptive volume threshold value; acquiring the average volume of the sound signals calculated by the module; the near field communication module exchanges average volume with other agents; the calculating module calculates the response coefficient of the intelligent agent; the near field communication module exchanges response coefficients with other agents; and the response module wakes up the intelligent agent according to the response coefficient. The invention only responds to the awakening of the user by the agent with the largest response coefficient, so the invention can avoid the condition that a plurality of agents adopting the same awakening word are awakened at the same time, thereby realizing the intelligent awakening of the agents and effectively improving the experience of the user.
Description
Technical Field
The invention relates to the field of voice processing, in particular to an agent awakening system.
Background
To reduce power consumption, the agent may operate in a low power mode before it is not awakened. Waking up an agent by voice is a common technical means, but if a plurality of agents exist in a relatively small space (for example, a space below 10 square meters) at the same time, if the wake-up word is adopted for waking up, a situation that a plurality of agents answer at the same time may occur, which affects normal use of the user. This problem can be solved by setting different wake-up words for different agents, but when the number of agents is relatively large, setting a plurality of wake-up words easily causes the user to confuse the wake-up words when using, and possibly when using the device a, the wake-up words of the device B are adopted to wake up the device a, which seriously affects the user experience.
Therefore, how to realize intelligent wake-up of the agents becomes a technical problem to be solved when a plurality of agents exist.
Disclosure of Invention
The invention aims to disclose an agent wake-up system, which solves the problem of how to avoid that all agents respond to wake-up words to influence the use of users when a plurality of agents exist in a smaller space at the same time.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the invention provides an agent awakening system, which comprises a plurality of agent awakening devices, wherein each of the awakening devices comprises a monitoring module, an acquisition module, a near field communication module, a calculation module and a response module;
each agent performs the following operations when in a low power consumption operating state:
the monitoring module acquires sound signals with the volume larger than the self-adaptive volume threshold value;
acquiring the average volume of the sound signals calculated by the module;
the near field communication module sends the average volume acquired by the acquisition module to other intelligent agents in the communication range of the near field communication module; and receiving the average volume sent by other intelligent agents;
the calculating module calculates the response coefficient of the intelligent agent according to the average volume acquired by the acquiring module and the average volume sent by other intelligent agents;
the near field communication module also transmits the response coefficient calculated by the calculation module to other intelligent agents in the communication range of the near field communication module; and receiving response coefficients sent by other agents;
and when the response coefficient calculated by the calculation module is larger than the response coefficients sent by other intelligent agents, the response module judges whether the sound signal obtained by the monitoring module contains a preset awakening word, and if so, the intelligent agents are awakened according to a preset rule.
Optionally, the adaptive volume threshold is obtained by:
acquiring the environmental volume of sound of the environment where the intelligent agent is located by adopting a self-adaptive sampling interval;
an adaptive volume threshold is calculated based on the ambient volume and a preset base volume.
Optionally, the adaptive sampling interval is calculated as:
wherein, adptim a And adptim a+1 Representing the length of time, avrvol, of the a-th and a+1-th sampling intervals a And avrvol a-1 Respectively, represents the ambient volume obtained at the a-1 th and a-1 st sampling intervals, max represents the larger value in brackets, stbtim is the preset length of time, cmp represents the comparison function, cmp (avrvol a ,avrvol a-1 ) Represents avrvol a And avrvol a-1 The comparison value between the two values is calculated,k represents a predetermined auxiliary systemA number; k (0.1, 0.3);
if adptim a+1 <adptim min Then adptim is added a+1 Is modified to adptim min The method comprises the steps of carrying out a first treatment on the surface of the If adptim a+1 >adptim max Then adptim is added a+1 Is modified to adptim max ,adptim min And adptim max The lower and upper values of the sampling interval are indicated, respectively.
Optionally, calculating the adaptive volume threshold based on the environmental volume and the preset base volume includes:
the calculation function of the adaptive volume threshold is:
adpvol=avrvol+stdvol
adpvol represents the adaptive volume threshold, avrvol represents the ambient volume, stdvol represents the preset base volume.
Optionally, calculating the average volume between the agent and the sound source according to the sound signal acquired by the monitoring module includes:
mean volume is expressed by sigvolsigset represents a set of sampling instants of the sound signal, nsigset represents a total number of sampling instants in sigset, volume b The volume of the sound signal at time b,
the determination mode of the sampling time is as follows:
the sampling time interval of the sound signal is denoted by [ Tsigs, tsige ], in which Tsigs, tsige, starting from Tsigs, is one sampling instant every s seconds, tsigs and Tsige denote the start instant and the end instant of the sampling time interval, respectively.
Optionally, the function of calculating the response coefficient is:
resfac c representing response coefficient of agent c, alpha represents weight parameter with value range between 0 and 1, sigvol c Indicating acquisition of agent cThe average volume obtained by the module, sigvolU represents a set of average volumes sent by other agents received by the near field communication module, top (sigvolU) represents a maximum value of average volumes obtained from the sigvolU, and rank c Representing the rank of obstacle coefficients for agent c, nsigvolU represents the total number of average volumes in sigvolU.
Optionally, the determining of the ranking of the obstacle coefficients includes:
obtaining an obstacle coefficient of an intelligent agent corresponding to each element in the sigvolU;
and sequencing the obstacle coefficients from large to small to obtain the ranking of the obstacle coefficients of each agent.
Optionally, the response module includes a first judging unit, a second judging unit and a wake-up unit;
the first judging unit is used for judging whether the response coefficient calculated by the calculating module is larger than the response coefficient sent by other intelligent agents;
the second judging unit is used for judging whether the sound signal obtained by the monitoring module contains a preset wake-up word or not when the response coefficient calculated by the calculating module is larger than the response coefficient sent by other intelligent agents;
the wake-up unit is used for waking up the intelligent body according to a preset rule when the sound signal obtained by the monitoring module contains a preset wake-up word.
The beneficial effects are that:
when a plurality of agents exist in a smaller space at the same time, the invention acquires the sound signals of the environment where the agents are located through the wake-up device of the agents, then calculates the response coefficient based on the average volume of the sound signals, and the larger the response coefficient is, the larger the probability that the current agent is selected as the awakened agent is. The invention only responds to the awakening of the user by the agent with the largest response coefficient, so the invention can avoid the condition that a plurality of agents adopting the same awakening word are awakened at the same time, thereby realizing the intelligent awakening of the agents and effectively improving the experience of the user.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a wake-up device according to the present invention.
FIG. 2 is a schematic diagram of a response module according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides an agent awakening system, which comprises a plurality of agent awakening devices, as shown in figure 1, wherein each of the awakening devices comprises a monitoring module, an acquisition module, a near field communication module, a calculation module and a response module;
each agent performs the following operations when in a low power consumption operating state:
the monitoring module acquires sound signals with the volume larger than the self-adaptive volume threshold value;
acquiring the average volume of the sound signals calculated by the module;
the near field communication module sends the average volume acquired by the acquisition module to other intelligent agents in the communication range of the near field communication module; and receiving the average volume sent by other intelligent agents;
the calculating module calculates the response coefficient of the intelligent agent according to the average volume acquired by the acquiring module and the average volume sent by other intelligent agents;
the near field communication module also transmits the response coefficient calculated by the calculation module to other intelligent agents in the communication range of the near field communication module; and receiving response coefficients sent by other agents;
and when the response coefficient calculated by the calculation module is larger than the response coefficients sent by other intelligent agents, the response module judges whether the sound signal obtained by the monitoring module contains a preset awakening word, and if so, the intelligent agents are awakened according to a preset rule.
When a plurality of agents exist in a smaller space at the same time, the invention acquires the sound signals of the environment where the agents are located through the wake-up device of the agents, then calculates the response coefficient based on the average volume of the sound signals, and the larger the response coefficient is, the larger the probability that the current agent is selected as the awakened agent is. The invention only responds to the awakening of the user by the agent with the largest response coefficient, so the invention can avoid the condition that a plurality of agents adopting the same awakening word are awakened at the same time, thereby realizing the intelligent awakening of the agents and effectively improving the experience of the user.
In particular, the wake-up means may be implemented as a computing device by a low power chip, such as a co-processor.
Specifically, the low power consumption operation state refers to that the intelligent agent enters a sleep state except for necessary devices, for example, the main processor stops operating.
Optionally, the adaptive volume threshold is obtained by:
acquiring the environmental volume of sound of the environment where the intelligent agent is located by adopting a self-adaptive sampling interval;
an adaptive volume threshold is calculated based on the ambient volume and a preset base volume.
Specifically, the invention does not adopt a fixed sampling interval to acquire the environmental volume, because if the environmental volume does not change for a long time, if the sampling interval is set to be too small, more ineffective sampling is performed, obviously the energy consumption of the wake-up device is increased, and if the environmental volume changes more frequently, if the sampling interval is set to be too large, the real environmental volume is easily caused to be different from the acquired environmental volume, so that the monitoring module is not beneficial to acquire a correct sound signal containing a wake-up word of a user. For example, when the sampled environmental volume is greater than the actual environmental volume, the volume threshold will be greater, and at this time, if the user sends a sound that is less than the volume threshold, but the actual volume level already meets the volume requirement, the sound signal corresponding to the sound will not be correctly acquired because the volume is less than the volume threshold.
Therefore, the setting mode of the self-adaptive volume threshold can enable the volume threshold to change along with the change of the environmental volume, and the updated time interval also changes along with the change trend of the latest volume, so that when the environmental volume does not change for a long time, the self-adaptive volume threshold can be obtained by adopting a larger sampling interval, the effect of reducing the energy consumption of the awakening device of the intelligent body is achieved, and when the environmental volume changes frequently, the sampling interval is reduced, so that the volume difference between the sampled environmental sound and the latest environmental sound is as small as possible, and the probability of correctly obtaining the sound sent by a user is improved.
In particular, the near field communication module may be bluetooth.
Optionally, the adaptive sampling interval is calculated as:
wherein, adptim a And adptim a+1 Representing the length of time, avrvol, of the a-th and a+1-th sampling intervals a And avrvol a-1 Respectively, represents the ambient volume obtained at the a-1 th and a-1 st sampling intervals, max represents the larger value in brackets, stbtim is the preset length of time, cmp represents the comparison function, cmp (avrvol a ,avrvol a-1 ) Represents avrvol a And avrvol a-1 The comparison value between the two values is calculated,k represents a preset auxiliary coefficient; k (0.1, 0.3);
if adptim a+1 <adptim min Then adptim is added a+1 Is modified to adptim min The method comprises the steps of carrying out a first treatment on the surface of the If adptim a+1 >adptim max Then adptim is added a+1 Is modified to adptim max ,adptim min And adptim max The lower and upper values of the sampling interval are indicated, respectively.
Specifically, in the above calculation, the value of a is 2 or more, and when the present invention is just started to operate, the time length of the first two sampling intervals is a time length specified in advance, for example, 5 seconds.
Specifically, the value of the (a+1) th sampling interval is changed based on the change of the trend relationship between the first two sampling intervals, if the trend of the environment volume is changed, the greater the change degree is, the greater the change degree of the sampling interval is, so that the self-adaptive volume threshold can be updated in time, and the change mode is the direction of the value becoming smaller; if the trend of the environment volume is unchanged, the mode of the sampling interval of the invention is the direction of increasing the value.
Specifically, the stbtim may take a value of 5 seconds. The value of k may be 0.15. The lower and upper values of the sampling interval may be 3 seconds and 10 seconds, respectively.
Optionally, calculating the adaptive volume threshold based on the environmental volume and the preset base volume includes:
the calculation function of the adaptive volume threshold is:
adpvol=avrvol+stdvol
adpvol represents the adaptive volume threshold, avrvol represents the ambient volume, stdvol represents the preset base volume.
Specifically, when the basic sound volume is 0 and the distance between the sound source and the agent is a predetermined normal use distance, for example, 0.5 meters, the agent can correctly recognize the sound in the sound source, and the minimum value of the sound volume of the sound signal is obtained. The correct recognition here means that the accuracy of recognition reaches over 95%.
Specifically, the base volume may be 30dB.
Optionally, calculating the average volume between the agent and the sound source according to the sound signal acquired by the monitoring module includes:
mean volume is expressed by sigvolsigset represents a set of sampling instants of the sound signal, nsigset represents a total number of sampling instants in sigset, volume b The volume of the sound signal at time b,
the determination mode of the sampling time is as follows:
the sampling time interval of the sound signal is denoted by [ Tsigs, tsige ], in which Tsigs, tsige, starting from Tsigs, is one sampling instant every s seconds, tsigs and Tsige denote the start instant and the end instant of the sampling time interval, respectively.
Specifically, the value of s may be 2 seconds.
Optionally, the function of calculating the response coefficient is:
resfac c representing response coefficient of agent c, alpha represents weight parameter with value range between 0 and 1, sigvol c Representing the average volume obtained by the acquisition module of the agent c, the sigvolU represents a set of average volumes sent by other agents received by the near field communication module, the top (sigvolU) represents the maximum value of the average volume in the acquisition of the sigvolU, and the rank c Representing the rank of obstacle coefficients for agent c, nsigvolU represents the total number of average volumes in sigvolU.
Specifically, the invention does not only rely on the average volume to determine the agent responding to the wake-up sound made by the user, but also considers the obstacle coefficient, because the obstacle has a reflecting effect on the sound, and has a certain probability that the sound signal reflected by the obstacle is contained in the sound signal received by the agent, obviously, the value of the average volume can be increased, therefore, the response coefficient of the invention can obviously improve the probability of selecting the agent nearest to the user as the agent responding to the wake-up sound made by the user, and avoids selecting the agent actually farther away but having larger average volume as the agent responding to the user. The use experience of the user can be improved.
Optionally, the determining of the ranking of the obstacle coefficients includes:
obtaining an obstacle coefficient of an intelligent agent corresponding to each element in the sigvolU;
and sequencing the obstacle coefficients from large to small to obtain the ranking of the obstacle coefficients of each agent.
Specifically, the process of obtaining the obstacle coefficient is as follows:
when the intelligent body is in a state of non-low power consumption operation, acquiring a set D of distances between the intelligent body and surrounding objects based on a set of preset ranging angles;
calculating an obstacle coefficient based on set D:
the obscf represents the obstacle coefficient, β represents the variance weight, δ represents the number weight, dist j Represents the distance j in set D, nofD represents the total number of distances in set D, dist min Representing the minimum of the distances in set D, nbgave represents that set D is smaller thanIs a sum of distances of (a) and (b).
Specifically, the level remains the same as the distance is acquired from each ranging angle. The number weight may be 0.5 and the variance weight may be 0.5.
Specifically, the range finding can be realized by adopting an infrared range finding sensor carried on the intelligent body, and the infrared sensor can rotate in 360 degrees in the horizontal direction.
Specifically, in the direction of 90 ° in the north direction, the set of ranging angles may be {0 °,45 °,90 °,135 °,180 °,225 °,270 °,315 ° }.
Optionally, the response module includes a first judging unit, a second judging unit and a wake-up unit;
the first judging unit is used for judging whether the response coefficient calculated by the calculating module is larger than the response coefficient sent by other intelligent agents;
the second judging unit is used for judging whether the sound signal obtained by the monitoring module contains a preset wake-up word or not when the response coefficient calculated by the calculating module is larger than the response coefficient sent by other intelligent agents;
the wake-up unit is used for waking up the intelligent body according to a preset rule when the sound signal obtained by the monitoring module contains a preset wake-up word.
Specifically, the preset wake word format may be "hello, xx", where xx represents a call to an agent set by a user.
Specifically, waking up the intelligent agent according to a preset rule includes:
the agent is exited from the low power operating state and responded to the user.
The response modes comprise: the corresponding dialog box is displayed on the screen or the user is prompted in a voice playing mode, and the intelligent agent is awakened.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (8)
1. The intelligent agent awakening system is characterized by comprising a awakening device of a plurality of intelligent agents, wherein the awakening device comprises a monitoring module, an acquisition module, a near field communication module, a calculation module and a response module;
when each intelligent agent is in a low-power-consumption running state, the wake-up device executes the following operation:
the monitoring module acquires sound signals with the volume larger than the self-adaptive volume threshold value;
acquiring the average volume of the sound signals calculated by the module;
the near field communication module sends the average volume acquired by the acquisition module to other intelligent agents in the communication range of the near field communication module; and receiving the average volume sent by other intelligent agents;
the calculating module calculates the response coefficient of the intelligent agent according to the average volume acquired by the acquiring module and the average volume sent by other intelligent agents;
the near field communication module also transmits the response coefficient calculated by the calculation module to other intelligent agents in the communication range of the near field communication module; and receiving response coefficients sent by other agents;
and when the response coefficient calculated by the calculation module is larger than the response coefficients sent by other intelligent agents, the response module judges whether the sound signal obtained by the monitoring module contains a preset awakening word, and if so, the intelligent agents are awakened according to a preset rule.
2. The agent wake-up system of claim 1, wherein the adaptive volume threshold is obtained by:
acquiring the environmental volume of sound of the environment where the intelligent agent is located by adopting a self-adaptive sampling interval;
an adaptive volume threshold is calculated based on the ambient volume and a preset base volume.
3. An agent wake-up system according to claim 2, wherein the adaptive sampling interval is calculated as a function of:
wherein, adptim a And adptim a+1 Representing the length of time, avrvol, of the a-th and a+1-th sampling intervals a And avrvol a-1 Respectively, represents the ambient volume obtained at the a-1 th and a-1 st sampling intervals, max represents the larger value in brackets, stbtim is the preset length of time, cmp represents the comparison function, cmp (avrvol a ,avrvol a-1 ) Represents avrvol a And avrvol a-1 The comparison value between the two values is calculated,k represents a preset auxiliary coefficient; k (0.1, 0.3);
if adptim a+1 <adptim min Then adptim is added a+1 Is modified to adptim min The method comprises the steps of carrying out a first treatment on the surface of the If adptim a+1 >adptim max Then adptim is added a+1 Is modified to adptim max ,adptim min And adptim max The lower and upper values of the sampling interval are indicated, respectively.
4. The agent wake-up system of claim 2, wherein calculating the adaptive volume threshold based on the ambient volume and the preset base volume comprises:
the calculation function of the adaptive volume threshold is:
adpvol=avrvol+stdvol
adpvol represents the adaptive volume threshold, avrvol represents the ambient volume, stdvol represents the preset base volume.
5. The agent wake-up system of claim 1, wherein calculating an average volume between the agent and the sound source based on the sound signal obtained by the listening module comprises:
mean volume is expressed by sigvolsigset represents a set of sampling instants of the sound signal, nsigset represents a total number of sampling instants in sigset, volume b The volume of the sound signal at time b,
the determination mode of the sampling time is as follows:
the sampling time interval of the sound signal is denoted by [ Tsigs, tsige ], in which Tsigs, tsige, starting from Tsigs, is one sampling instant every s seconds, tsigs and Tsige denote the start instant and the end instant of the sampling time interval, respectively.
6. The agent wake-up system of claim 1 wherein the response coefficient is calculated as a function of:
resfac c representing response coefficient of agent c, alpha represents weight parameter with value range between 0 and 1, sigvol c Representing the average volume obtained by the acquisition module of the agent c, the sigvolU represents a set of average volumes sent by other agents received by the near field communication module, the top (sigvolU) represents the maximum value of the average volume in the acquisition of the sigvolU, and the rank c Representing the rank of obstacle coefficients for agent c, nsigvolU represents the total number of average volumes in sigvolU.
7. The agent wake system of claim 6 wherein the determination of the ranking of the obstacle coefficients comprises:
obtaining an obstacle coefficient of an intelligent agent corresponding to each element in the sigvolU;
and sequencing the obstacle coefficients from large to small to obtain the ranking of the obstacle coefficients of each agent.
8. The agent wake-up system of claim 1, wherein the response module comprises a first determination unit, a second determination unit, and a wake-up unit;
the first judging unit is used for judging whether the response coefficient calculated by the calculating module is larger than the response coefficient sent by other intelligent agents;
the second judging unit is used for judging whether the sound signal obtained by the monitoring module contains a preset wake-up word or not when the response coefficient calculated by the calculating module is larger than the response coefficient sent by other intelligent agents;
the wake-up unit is used for waking up the intelligent body according to a preset rule when the sound signal obtained by the monitoring module contains a preset wake-up word.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311278304.XA CN117336832B (en) | 2023-09-28 | Intelligent body awakening system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311278304.XA CN117336832B (en) | 2023-09-28 | Intelligent body awakening system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117336832A true CN117336832A (en) | 2024-01-02 |
CN117336832B CN117336832B (en) | 2024-06-07 |
Family
ID=
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN113485153A (en) * | 2021-08-20 | 2021-10-08 | 云知声(上海)智能科技有限公司 | Selective awakening method and system for intelligent equipment |
CN113489627A (en) * | 2020-03-16 | 2021-10-08 | 深圳市艾特智能科技有限公司 | Intelligent device voice awakening method and system, readable storage medium and electronic device |
CN114815635A (en) * | 2021-01-29 | 2022-07-29 | 星络家居云物联科技有限公司 | Computer readable storage medium, intelligent panel and voice interaction method thereof |
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN113489627A (en) * | 2020-03-16 | 2021-10-08 | 深圳市艾特智能科技有限公司 | Intelligent device voice awakening method and system, readable storage medium and electronic device |
CN114815635A (en) * | 2021-01-29 | 2022-07-29 | 星络家居云物联科技有限公司 | Computer readable storage medium, intelligent panel and voice interaction method thereof |
CN113485153A (en) * | 2021-08-20 | 2021-10-08 | 云知声(上海)智能科技有限公司 | Selective awakening method and system for intelligent equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108735209B (en) | Wake-up word binding method, intelligent device and storage medium | |
WO2020083110A1 (en) | Speech recognition and speech recognition model training method and apparatus | |
CN108711430B (en) | Speech recognition method, intelligent device and storage medium | |
CN109218535B (en) | Method and device for intelligently adjusting volume, storage medium and terminal | |
CN110148405B (en) | Voice instruction processing method and device, electronic equipment and storage medium | |
CN112420041B (en) | Control method and device for wake-up threshold of intelligent device, intelligent device and storage medium | |
CN109712621B (en) | Voice interaction control method and terminal | |
CN105575395A (en) | Voice wake-up method and apparatus, terminal, and processing method thereof | |
CN110349579B (en) | Voice wake-up processing method and device, electronic equipment and storage medium | |
CN105204628A (en) | Voice control method based on visual awakening | |
TW201421353A (en) | Voice-controlled device and voice control method | |
CN110890093A (en) | Intelligent device awakening method and device based on artificial intelligence | |
CN111128155B (en) | Awakening method, device, equipment and medium for intelligent equipment | |
CN112634895A (en) | Voice interaction wake-up-free method and device | |
CN111968644A (en) | Intelligent device awakening method and device and electronic device | |
CN110491373A (en) | Model training method, device, storage medium and electronic equipment | |
CN109432568B (en) | Sleep assisting method, device, storage medium and terminal | |
CN112562742A (en) | Voice processing method and device | |
CN113160815B (en) | Intelligent control method, device, equipment and storage medium for voice wakeup | |
CN113963695A (en) | Awakening method, awakening device, equipment and storage medium of intelligent equipment | |
CN111105792A (en) | Voice interaction processing method and device | |
CN112233676A (en) | Intelligent device awakening method and device, electronic device and storage medium | |
CN117336832B (en) | Intelligent body awakening system | |
CN110788866B (en) | Robot awakening method and device and terminal equipment | |
CN113066488B (en) | Voice wakeup intelligent control 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 | ||
GR01 | Patent grant |