CN112951229A - Voice wake-up method, system and storage medium for physical therapy robot - Google Patents
Voice wake-up method, system and storage medium for physical therapy robot Download PDFInfo
- Publication number
- CN112951229A CN112951229A CN202110179883.7A CN202110179883A CN112951229A CN 112951229 A CN112951229 A CN 112951229A CN 202110179883 A CN202110179883 A CN 202110179883A CN 112951229 A CN112951229 A CN 112951229A
- Authority
- CN
- China
- Prior art keywords
- information
- voiceprint
- awakening
- user
- preset
- 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
- 238000000554 physical therapy Methods 0.000 title claims abstract description 146
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 83
- 230000006870 function Effects 0.000 claims description 34
- 238000012216 screening Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002618 waking effect Effects 0.000 abstract description 3
- 230000009191 jumping Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
Images
Classifications
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/008—Manipulators for service tasks
- B25J11/009—Nursing, e.g. carrying sick persons, pushing wheelchairs, distributing drugs
-
- 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)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Nursing (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
Abstract
The application relates to a voice awakening method, a system and a storage medium of a physical therapy robot, belonging to the field of physical therapy robots, wherein the method comprises the steps of acquiring an awakening instruction and voiceprint detection information of a current user; comparing and detecting text information in the awakening instruction according to a preset awakening word bank; if the text information in the awakening instruction is detected to contain a plurality of awakening words in the awakening word bank, the awakening words in the awakening word bank are contrasted and screened according to the awakening instruction to form a target awakening word list; matching detection is carried out on voiceprint detection information according to user identification information in the target awakening word list and a plurality of corresponding preset voiceprint recognition libraries; and if the voiceprint detection information is matched with the voiceprint characteristic information in any preset voiceprint recognition library, switching the use state information according to the current use state information. This application helps improving the user and uses the relatively poor problem of feeling to waking up of physiotherapy robot.
Description
Technical Field
The present application relates to the field of robots, and in particular, to a method, a system, and a storage medium for voice wake-up of a physical therapy robot.
Background
Nowadays, people often feel tired due to the fact that the bodies of people are in a high-pressure state for a long time due to the acceleration of life rhythm and the increase of working pressure. Meanwhile, the technology of the physical therapy robot is gradually developed and matured, and people can perform physical therapy through the physical therapy robot to relieve fatigue, relax the body and mind, improve blood circulation and accelerate metabolism of the human body, so that the aims of enhancing immunity, health care and health preservation are fulfilled.
The related art physiotherapy robot is generally used in a physiotherapy shop or the like, and generally carries a physiotherapy assembly by a robot arm to perform physiotherapy on a human body. General physiotherapy robot can carry on different function button, before carrying out different physiotherapy functions to people, need to awaken up physiotherapy robot through the function button earlier, just can carry out corresponding physiotherapy function, and the user is used the impression relatively poor to awakening up of physiotherapy robot.
Disclosure of Invention
In order to solve the problem that a user feels poor when the physiotherapy robot is awakened, the application provides a voice awakening method, a voice awakening system and a storage medium of the physiotherapy robot.
In a first aspect, the present application provides a voice wake-up method for a physical therapy robot, which adopts the following technical scheme:
a voice wake-up method of a physiotherapy robot based on a physiotherapy robot having a physiotherapy function includes:
acquiring a wake-up instruction and voiceprint detection information of a current user, wherein the wake-up instruction comprises text information generated by identifying voice information sent by the current user;
comparing and detecting text information in the wake-up instruction according to a preset wake-up word bank, wherein the wake-up word bank comprises preset wake-up words corresponding to different users;
if the text information in the awakening instruction is detected to contain a plurality of awakening words in the awakening word bank, comparing and screening the awakening words in the awakening word bank according to the awakening instruction to form a target awakening word list, wherein the target awakening word list contains the awakening words contained in the text information of the awakening instruction and corresponding user identification information;
matching detection is carried out on voiceprint detection information according to user identification information in the target awakening word list and a plurality of corresponding preset voiceprint recognition libraries, and the user identification information and the voiceprint feature information which are related to each other are stored in each preset voiceprint recognition library;
and if the voiceprint detection information is matched with the voiceprint characteristic information in any preset voiceprint recognition library, switching the use state information according to the current use state information.
Through adopting above-mentioned technical scheme, the physiotherapy robot is according to real-time detection user's speech information to judge whether user's the word of awaking matches with the vocal print characteristic information that corresponds, if detect the word of awaking that current user said and the vocal print characteristic information that corresponds matches simultaneously, then this physiotherapy robot can awaken up automatically, for current user's service, help improving physiotherapy robot's intelligent degree, thereby help improving user's the relatively poor problem of use impression of awaking up to physiotherapy robot.
Optionally, the acquiring the wake-up instruction and the voiceprint information of the current user specifically includes:
acquiring voice detection information of the current user in real time;
dividing the voice detection information into a plurality of sub-voice detection information according to a preset pause time period;
and analyzing each sub-voice detection information in sequence to form a corresponding awakening instruction and corresponding voiceprint detection information.
By adopting the technical scheme, the physiotherapy robot acquires the voice information spoken by the current user in real time, and analyzes and judges the voice information one by one, so that the success rate of awakening the physiotherapy robot by the voice of the user is improved.
Optionally, the switching the use state information according to the current use state information specifically includes:
acquiring current use state information, wherein the use state information is one of a standby state and a working state;
judging whether the use state information is in a standby state;
and if the use state information is in a standby state, automatically entering a working state.
By adopting the technical scheme, only if the use state of the current physiotherapy robot at the current time node is in a standby state, the current physiotherapy robot can be automatically awakened by the current user, and otherwise, the current working state is continuously maintained.
Optionally, the matching detection is performed on the voiceprint detection information according to the user identification information in the target wake-up vocabulary and a plurality of preset voiceprint recognition libraries, and the method specifically includes:
and if the voiceprint information is not matched with the voiceprint characteristic information in the preset voiceprint recognition library, feeding back an error notice to the current user.
By adopting the technical scheme, when the voiceprint information of the current user is not matched with the voiceprint recognition library corresponding to the awakening words, the current physical therapy robot can remind the awakening words of the current user not to correspond, and the use experience of the user on the physical therapy robot is improved.
Optionally, before the switching the use state information according to the current use state information, the method further includes:
defining the voiceprint recognition library matched with the voiceprint detection information as a target recognition library;
and updating and storing the voiceprint detection information of the current user in a target recognition base.
By adopting the technical scheme, after the awakening words spoken by the current user are detected to be matched with the corresponding voiceprint characteristic information at the same time, the voiceprint detection information of the current user can be automatically updated and stored in the corresponding voiceprint recognition library, so that the voiceprint characteristic information in the voiceprint recognition library of the corresponding user is increased, and the successful recognition rate of the voiceprint detection information of the user is improved.
Optionally, after the switching of the use state information according to the current use state information, the method further includes:
and executing the physiotherapy function corresponding to the corresponding user grade to the current user according to the preset user grade in the target identification library.
By adopting the technical scheme, after the physiotherapy robot is awakened, the physiotherapy robot can automatically execute a corresponding physiotherapy function for the current user according to the identification information of the user, and the user experience is improved.
Optionally, before executing the physiotherapy function corresponding to the corresponding user grade to the current user according to the preset user grade in the target recognition library, the method further includes:
and acquiring a corresponding preset physiotherapy record table according to the user identification information corresponding to the target identification library, wherein the physiotherapy record table comprises the total physiotherapy times of the corresponding user and time information for executing the physiotherapy function of the corresponding user before the current time node.
Judging whether the current user has the number of times of physical therapy capable of executing the physical therapy function according to the physical therapy record table;
if the current user does not have the number of times of physical therapy capable of executing the physical therapy function, feeding a reminding notice back to the current user;
and if the current user is judged to have the number of times of physical therapy capable of executing the physical therapy function, executing the physical therapy function corresponding to the corresponding user grade to the current user.
Through adopting above-mentioned technical scheme, before carrying out corresponding physiotherapy function to current user, detect current user's executable physiotherapy function, if current user does not have the number of times of executable physiotherapy function, then can remind current user to acquire the number of times of executable physiotherapy function automatically, otherwise then carry out corresponding physiotherapy function automatically, help improving physiotherapy robot's intelligent degree.
In a second aspect, the present application provides a voice wake-up system of a physical therapy robot, which adopts the following technical scheme:
a voice awakening system of a physical therapy robot, which comprises,
the voice acquisition module is used for acquiring the awakening instruction and the voiceprint detection information of the current user;
the storage module is used for storing a preset awakening word list and a plurality of preset voiceprint recognition libraries;
awakening word detection module: the awakening instruction is used for detecting whether an awakening word is contained in the awakening instruction or not according to the preset awakening word bank;
the awakening word screening module is used for screening the awakening instruction to form a target awakening word list;
the voiceprint detection module is used for carrying out matching detection on the voiceprint detection information according to the target awakening word list;
a processing module for performing the following processes,
and when the voiceprint detection information is matched with the voiceprint characteristic information in one preset voiceprint recognition library, switching the use state information according to the current use state information. By adopting the technical scheme, the physiotherapy robot automatically detects the voice information of the current user in a standby state, and timely identifies and detects the voice information of the current user, so that the voice awakening response rate of the current user is improved, and the problem of poor awakening use feeling of the user on the physiotherapy robot is solved.
In a third aspect, the present application provides a physiotherapy robot terminal, which adopts the following technical scheme:
a physio-robotic terminal comprising a memory and a processor, the memory having stored thereon a computer program that can be loaded by the processor and carry out the method of the first aspect.
Through adopting above-mentioned technical scheme, the physiotherapy robot is to user's speech information automatic identification and detection to improve the user and use the relatively poor problem of feeling to waking up of physiotherapy robot.
In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium storing a computer program capable of being loaded by a processor and performing the method according to the first aspect as described above.
By adopting the above technical solution, after the computer-readable storage medium is loaded into any computer, the computer can execute the voice wake-up method of the physiotherapy robot as provided in the first aspect.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the physiotherapy robot detects voice information of a user in real time and judges whether a wake-up word of the user is matched with corresponding voiceprint characteristic information or not, if the fact that the wake-up word spoken by the current user is matched with the corresponding voiceprint characteristic information is detected, the physiotherapy robot can automatically wake up to serve the current user, the intellectualization degree of the physiotherapy robot is improved, and therefore the problem that the user feels poor in awakening use of the physiotherapy robot is improved;
2. when the voiceprint information of the current user is not matched with the voiceprint recognition library corresponding to the awakening words, the current physical therapy robot can remind that the awakening words of the current user do not correspond to each other, and the user experience is improved;
3. after the physiotherapy robot is awakened, the physiotherapy robot can automatically execute corresponding physiotherapy functions for the current user according to the identification information of the user, and the use experience of the user on the physiotherapy robot is favorably optimized.
Drawings
Fig. 1 is a flowchart illustrating a voice wake-up method of a physiotherapeutic robot according to an embodiment of the present application.
Fig. 2 is a schematic flowchart of an acquisition manner for embodying a wake-up instruction according to an embodiment of the present application.
Fig. 3 is a flowchart illustrating a physiotherapy function automatically performed by the physiotherapy robot according to the embodiment of the present application.
Fig. 4 is a block diagram illustrating a voice wake-up system of a physiotherapeutic robot according to an embodiment of the present application.
Description of reference numerals: 1. a voice acquisition module; 11. a voice detection submodule; 12. a voice analysis submodule; 2. a storage module; 3. a wake word detection module; 4. a wake-up word screening module; 5. a voiceprint detection module; 51. a voiceprint screening submodule; 52. a voiceprint detection sub-module; 6. a processing module; 7. and a feedback module.
Detailed Description
The present application is described in further detail below with reference to figures 1-4.
The embodiment of the application discloses a voice awakening method of a physiotherapy robot, which is based on the physiotherapy robot carrying different physiotherapy functions. Referring to fig. 1, the voice wake-up method of the physiotherapy robot includes:
s100: and acquiring a wake-up instruction and voiceprint detection information of the current user.
Wherein the wake-up instruction comprises text information generated by recognizing voice information uttered by the current user.
Referring to fig. 2, the specific processing steps of S100 are as follows:
s110: and implementing the acquisition of the voice detection information of the current user.
Specifically, the voice detection information includes voice information spoken by the current user, the voice detection information is voice information within a period of time, and the voice information includes a plurality of voice character segments and corresponding voiceprint information. The time period is on the order of seconds, and may be 5 seconds, and the length of the time period may be set according to actual needs, which is not specifically limited in this application.
S120: and dividing the voice detection information into a plurality of sub-voice detection information according to a preset pause time period.
Specifically, the pause time period is, for example, milliseconds, and may be 10 ms. It should be noted that the setting of the pause time period may be performed in other manners according to actual needs, and the present application is not limited to this.
Based on the preset pause time period, the specific processing procedure of S120 is as follows:
and judging the interval time between two adjacent voice character segments in the voice detection information according to a preset pause time period, and judging whether a certain or a plurality of adjacent voice character segments can form corresponding sub-voice detection information. Wherein, the interval time is the time length of the two phonetic character segments in the mute state. For example, A, B, C, D, E and F are each phonetic character segments in the speech detection information and are arranged in order according to the acquired time sequence. If the interval time between the voice character segment A and the voice character segment B is larger than the preset pause time segment, storing the voice character segment A and the corresponding voiceprint information to form sub-voice detection information; if the interval time between the voice character segment A and the voice character segment B is smaller than the preset pause time segment, the interval time between two adjacent voice character segments after the voice character segment B is continuously detected, and meanwhile, if the interval time between the voice character segment E and the voice character segment F is only detected to be larger than the preset pause time segment in the subsequent detection process, the voice character segment B, the voice character segment C, the voice character segment D, the voice character segment E and the corresponding voiceprint information are stored together to form sub-voice detection information.
S130: and analyzing the plurality of sub-voice detection information in sequence to form a corresponding awakening instruction and corresponding voiceprint detection information.
The voice wake-up instruction is generated by the following method: and performing character recognition on the voice character segment in the corresponding sub-voice detection information to generate text information, and forming a voice awakening instruction according to the text information, wherein the voiceprint detection information is formed by extracting and storing the voiceprint information in the corresponding sub-voice detection information.
Based on the wake-up command and the corresponding voiceprint detection information generated in S130, the following steps are sequentially performed in the order of time of generation.
S200: comparing and detecting text information in the awakening instruction according to a preset awakening word bank; if the text information in the awakening instruction is detected to contain a plurality of awakening words in the awakening word bank, jumping to S300; otherwise, no processing is performed.
The preset awakening word bank comprises awakening words which are customized and set by different users for the current physical therapy robot and corresponding user identification information.
S300: and comparing and screening the text information in the awakening instruction according to a preset awakening word bank to form a target awakening word list.
Specifically, the data items in the target wake-up word list are a plurality of wake-up words in a wake-up word bank included in text information in the voice wake-up instruction, and corresponding user identification information.
S400: and screening and redefining a plurality of preset voiceprint recognition libraries according to a plurality of user identification information in the target awakening word list to form a plurality of first recognition libraries.
Specifically, each voiceprint recognition library stores corresponding user identification information and a plurality of voiceprint characteristic information of corresponding users in advance, wherein the voiceprint characteristic information is voiceprint detection information of corresponding awakening words preset and input by corresponding users, and the first recognition library is formed by redefining the voiceprint recognition libraries corresponding to all user identification information in the target awakening word list.
S500: matching detection is carried out on voiceprint detection information according to voiceprint characteristic information in the first recognition libraries, if the voiceprint detection information is detected to be matched with the voiceprint characteristic information in any one first recognition library, the matched first recognition library is redefined as a target recognition library, and then S600 is skipped; and if the voiceprint detection information is not matched with the voiceprint characteristic information in all the first recognition libraries, skipping to S900.
S600: and updating and storing the voiceprint detection information in the target recognition base.
S700: identifying the use state information of the current physical therapy robot at the current time node, and if the use state information of the current physical therapy robot is identified to be in a standby state, jumping to S800; and if the service state information of the current physical therapy robot is identified as the working state, ending the operation.
The current use state information of the robot is one of a standby state and a working state.
S800: and entering a working state.
S900: and entering a working state and feeding back an error notice to the current user.
For example, when the reminding notification is a "your information is not consistent, please wake up again" audio, the current physiotherapeutic robot automatically plays the audio through a preset speaker module; when the reminding notification is text information of 'your information is not consistent and please wake up again', the current physical therapy robot displays characters through a preset display module. It should be noted that the format of the error notification and the corresponding content information may be set according to actual needs, and the present application is not limited to this.
In order to improve the user experience, referring to fig. 3, after S800, the method further includes:
s11: and acquiring a corresponding preset physical therapy record table according to the user identification information corresponding to the target identification library.
Each preset physiotherapy record table comprises the total physiotherapy times of the corresponding user and time information of each physiotherapy function executed on the corresponding user by the current physiotherapy robot before the current time node.
S12: counting the times of the time information in the obtained physiotherapy record table to form the completion times;
s13: comparing and judging the completion times with the total physical therapy times in the obtained physical therapy record table, and if the completion times are judged to be smaller than the total physical therapy times in the obtained physical therapy record table, jumping to S14; if the completion times are judged to be equal to the total physical therapy times in the acquired physical therapy record table, jumping to S15;
s14: and executing the physiotherapy function corresponding to the corresponding user grade to the current user according to the preset user grade in the target recognition library, and then finishing.
Specifically, each voiceprint recognition library is preset with user grades corresponding to different users, wherein the user grades represent different physical therapy functions purchased by the corresponding users, for example, the physical therapy functions can be different behaviors such as neck massage, waist massage, vibration physical therapy, temperature control physical therapy and the like.
S15: and feeding back a reminding notice to the current user, and then ending.
For example, when the reminding notification is an audio of "your physiotherapy times is insufficient, and if you still need to continue to enjoy the physiotherapy and need to purchase", the current physiotherapy robot automatically plays the audio through a preset speaker module; when the reminding notification is text information of 'your physiotherapy times are not enough, if you still need to continue to enjoy and need to purchase', the current physiotherapy robot displays the text information through a preset display module. It should be noted that the format of the reminder notification and the corresponding content information may be set according to actual needs, and this is not specifically limited in this application.
After S15, the definition of the target recognition library is automatically reset to update the stored voiceprint recognition library for use by other users.
The embodiment of the application also discloses a wake-up system of the physiotherapy robot. Referring to fig. 4, the wake-up system of the robot for physical therapy includes:
the voice acquisition module 1 comprises a voice acquisition module,
the voice detection submodule 11 is used for acquiring voice detection information of a user;
the voice analysis submodule 12 is used for analyzing the voice detection information to form a wake-up instruction and voiceprint detection information;
the storage module 2 is used for storing a preset awakening word bank, a plurality of preset voiceprint recognition banks and a plurality of physiotherapy record tables;
the awakening word detection module 3 is used for detecting whether the awakening instruction contains the awakening words or not according to the awakening word bank;
the awakening word screening module 4 is used for screening the awakening instruction to form a target awakening word list;
the voiceprint detection module 5 comprises, in combination,
the voiceprint screening submodule 51 is used for screening and redefining a plurality of preset voiceprint recognition libraries according to the target awakening word list to form a plurality of first recognition libraries;
the voiceprint detection submodule 52 is configured to detect whether there is a matched first identification library in the voiceprint detection information of the current user;
a processing module 6 for performing the following processes,
if the voiceprint detection information is detected to be matched with the voiceprint feature information in any first recognition library, redefining the matched first recognition library as a target recognition library;
updating and storing the voiceprint detection information in a target recognition base;
judging the use state of the current physical therapy robot, and entering a working state if the use state is judged to be a standby state;
acquiring a corresponding preset physical therapy record table according to user identification information corresponding to the target identification library;
counting the times of the time information in the obtained physiotherapy record table to form the completion times;
judging the completion times and the total physical therapy times in the obtained physical therapy record table, and if the completion times are judged to be more than the total physical therapy times in the obtained physical therapy record table, executing a physical therapy function corresponding to the corresponding user grade to the current user according to the preset user grade in the target recognition library; if the completion times are judged to be more than the total physical therapy times in the acquired physical therapy record table, the feedback module 7 feeds back the current user,
and the feedback module 7 is used for feeding back the error notification and the reminding notification to the user.
The embodiment of the application also discloses a physiotherapy robot terminal, which comprises a memory and a processor, wherein the memory is stored with a computer program which can be loaded by the processor and can execute the physiotherapy robot awakening method.
An embodiment of the present application further discloses a computer-readable storage medium, which stores a computer program that can be loaded by a processor and execute the waking method of the physiotherapy robot as described above, and the computer-readable storage medium includes, for example: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above examples are only used to illustrate the technical solutions of the present application, and do not limit the scope of protection of the application. It is to be understood that the embodiments described are only some of the embodiments of the present application and not all of them. All other embodiments, which can be derived by a person skilled in the art from these embodiments without making any inventive step, are within the scope of the present application.
Claims (10)
1. A voice wake-up method of a physiotherapy robot based on a physiotherapy robot with a physiotherapy function is characterized by comprising the following steps:
acquiring a wake-up instruction and voiceprint detection information of a current user, wherein the wake-up instruction comprises text information generated by identifying voice information sent by the current user;
comparing and detecting text information in the wake-up instruction according to a preset wake-up word bank, wherein the wake-up word bank comprises preset wake-up words corresponding to different users;
if the text information in the awakening instruction is detected to contain a plurality of awakening words in the awakening word bank, comparing and screening the awakening words in the awakening word bank according to the awakening instruction to form a target awakening word list, wherein the target awakening word list contains the awakening words contained in the text information of the awakening instruction and corresponding user identification information;
matching detection is carried out on voiceprint detection information according to user identification information in the target awakening word list and a plurality of corresponding preset voiceprint recognition libraries, and the user identification information and the voiceprint feature information which are related to each other are stored in each preset voiceprint recognition library;
and if the voiceprint detection information is matched with the voiceprint characteristic information in any preset voiceprint recognition library, switching the use state information according to the current use state information.
2. The voice wake-up method for a physical therapy robot according to claim 1, wherein the acquiring the wake-up instruction and the voiceprint information of the current user specifically comprises:
acquiring voice detection information of the current user in real time;
dividing the voice detection information into a plurality of sub-voice detection information according to a preset pause time period;
and analyzing each sub-voice detection information in sequence to form a corresponding awakening instruction and corresponding voiceprint detection information.
3. The voice wake-up method for a physiotherapy robot according to claim 1, wherein the switching of the use state information according to the current use state information specifically comprises:
acquiring current use state information, wherein the use state information is one of a standby state and a working state;
judging whether the use state information is in a standby state;
and if the use state information is in a standby state, automatically entering a working state.
4. The voice wake-up method for a physical therapy robot according to claim 1, wherein the matching detection of the voiceprint detection information is performed according to the user identification information in the target wake-up vocabulary and a plurality of corresponding preset voiceprint recognition libraries, and specifically comprises:
and if the voiceprint information is not matched with the voiceprint characteristic information in the preset voiceprint recognition library, feeding back an error notice to the current user.
5. The voice wake-up method for a physiotherapy robot according to claim 1, wherein the switching of the use state information according to the current use state information further comprises:
defining the voiceprint recognition library matched with the voiceprint detection information as a target recognition library;
and updating and storing the voiceprint detection information of the current user in a target recognition base.
6. The voice wake-up method of a physio-robot according to claim 5,
the switching of the use state information according to the current use state information further comprises:
and executing the physiotherapy function corresponding to the corresponding user grade to the current user according to the preset user grade in the target identification library.
7. The voice wake-up method for a physiotherapy robot according to claim 5, wherein before performing a physiotherapy function corresponding to a corresponding user level to the current user according to a preset user level in the target recognition library, the method further comprises:
acquiring a corresponding preset physiotherapy record table according to the user identification information corresponding to the target identification library, wherein the physiotherapy record table comprises the total physiotherapy times of the corresponding user and time information for executing the physiotherapy function on the corresponding user before the current time node;
judging whether the current user has the number of times of physical therapy capable of executing the physical therapy function according to the physical therapy record table;
if the current user does not have the number of times of physical therapy capable of executing the physical therapy function, feeding a reminding notice back to the current user;
and if the current user is judged to have the number of times of physical therapy capable of executing the physical therapy function, executing the physical therapy function corresponding to the corresponding user grade to the current user.
8. A voice wake-up system of a physical therapy robot is characterized by comprising,
the voice acquisition module (1) is used for acquiring the awakening instruction and the voiceprint detection information of the current user;
the storage module (2) is used for storing a preset awakening word list and a plurality of preset voiceprint recognition libraries;
wake word detection module (3): the awakening instruction is used for detecting whether an awakening word is contained in the awakening instruction or not according to the preset awakening word bank;
the awakening word screening module (4) is used for screening the awakening instruction to form a target awakening word list;
the voiceprint detection module (5) is used for carrying out matching detection on the voiceprint detection information according to the target awakening word list;
a processing module (6) for performing the following processes,
and when the voiceprint detection information is matched with the voiceprint characteristic information in one preset voiceprint recognition library, switching the use state information according to the current use state information.
9. A physiotherapeutic robot terminal, comprising a memory and a processor, the memory having stored thereon a computer program that can be loaded by the processor and that executes the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which can be loaded by a processor and which executes the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110179883.7A CN112951229A (en) | 2021-02-07 | 2021-02-07 | Voice wake-up method, system and storage medium for physical therapy robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110179883.7A CN112951229A (en) | 2021-02-07 | 2021-02-07 | Voice wake-up method, system and storage medium for physical therapy robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112951229A true CN112951229A (en) | 2021-06-11 |
Family
ID=76244963
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110179883.7A Pending CN112951229A (en) | 2021-02-07 | 2021-02-07 | Voice wake-up method, system and storage medium for physical therapy robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112951229A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113611294A (en) * | 2021-06-30 | 2021-11-05 | 展讯通信（上海）有限公司 | Voice wake-up method, apparatus, device and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107134074A (en) * | 2017-05-23 | 2017-09-05 | 崔俊新 | Storing collaborative share method, storing equipment and computer-readable recording medium |
| CN108831464A (en) * | 2018-06-29 | 2018-11-16 | 上海与德通讯技术有限公司 | Eyeshade based on voice control and the method based on voice control eyeshade |
| US20180350372A1 (en) * | 2015-11-30 | 2018-12-06 | Zte Corporation | Method realizing voice wake-up, device, terminal, and computer storage medium |
| CN111326161A (en) * | 2020-02-26 | 2020-06-23 | 北京声智科技有限公司 | Voiceprint determination method and device |
| CN111354357A (en) * | 2018-12-24 | 2020-06-30 | 中移（杭州）信息技术有限公司 | Audio resource playing method and device, electronic equipment and storage medium |
| CN111557560A (en) * | 2020-05-07 | 2020-08-21 | 浙江荣泰健康电器有限公司 | Application method and equipment of multifunctional massage chair with intelligent cinema system |
| CN111710332A (en) * | 2020-06-30 | 2020-09-25 | 北京达佳互联信息技术有限公司 | Voice processing method and device, electronic equipment and storage medium |
| CN111862946A (en) * | 2019-05-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Order processing method and device, electronic equipment and storage medium |
-
2021
- 2021-02-07 CN CN202110179883.7A patent/CN112951229A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180350372A1 (en) * | 2015-11-30 | 2018-12-06 | Zte Corporation | Method realizing voice wake-up, device, terminal, and computer storage medium |
| CN107134074A (en) * | 2017-05-23 | 2017-09-05 | 崔俊新 | Storing collaborative share method, storing equipment and computer-readable recording medium |
| CN108831464A (en) * | 2018-06-29 | 2018-11-16 | 上海与德通讯技术有限公司 | Eyeshade based on voice control and the method based on voice control eyeshade |
| CN111354357A (en) * | 2018-12-24 | 2020-06-30 | 中移（杭州）信息技术有限公司 | Audio resource playing method and device, electronic equipment and storage medium |
| CN111862946A (en) * | 2019-05-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Order processing method and device, electronic equipment and storage medium |
| CN111326161A (en) * | 2020-02-26 | 2020-06-23 | 北京声智科技有限公司 | Voiceprint determination method and device |
| CN111557560A (en) * | 2020-05-07 | 2020-08-21 | 浙江荣泰健康电器有限公司 | Application method and equipment of multifunctional massage chair with intelligent cinema system |
| CN111710332A (en) * | 2020-06-30 | 2020-09-25 | 北京达佳互联信息技术有限公司 | Voice processing method and device, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113611294A (en) * | 2021-06-30 | 2021-11-05 | 展讯通信（上海）有限公司 | Voice wake-up method, apparatus, device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10702991B2 (en) | Apparatus, robot, method and recording medium having program recorded thereon | |
| CA3065391A1 (en) | Systems and methods for providing a virtual assistant | |
| CN106782536A (en) | A kind of voice awakening method and device | |
| JP2004310034A (en) | Interactive agent system | |
| CN113380234B (en) | Method, device, equipment and medium for generating form based on voice recognition | |
| JP5294315B2 (en) | Dialogue activation robot | |
| JP2017173546A (en) | Learning support device, robot, learning support system, learning support method, and program | |
| JP5189858B2 (en) | Voice recognition device | |
| CN110598611A (en) | Nursing system, patient nursing method based on nursing system and readable storage medium | |
| KR101221188B1 (en) | Assistive robot with emotional speech synthesizing function, method of synthesizing emotional speech for the assistive robot, and recording medium | |
| CN110480656B (en) | Accompanying robot, accompanying robot control method and accompanying robot control device | |
| JP2022088791A (en) | Solution provision system | |
| CN112951229A (en) | Voice wake-up method, system and storage medium for physical therapy robot | |
| US12105876B2 (en) | System and method for using gestures and expressions for controlling speech applications | |
| JP2010149757A (en) | Awakening continuance support system | |
| KR102423257B1 (en) | Supporting system for service about processing record data of dementia patient | |
| JP6967777B2 (en) | Language function training system and equipment | |
| JP4007069B2 (en) | Robot apparatus, control method and program for robot apparatus | |
| CN109616109A (en) | A kind of voice awakening method, apparatus and system | |
| KR101270010B1 (en) | Method and the system of learning words based on speech recognition | |
| CN113633870A (en) | Emotional state adjusting system and method | |
| US20210202096A1 (en) | Method and systems for speech therapy computer-assisted training and repository | |
| JP6963669B1 (en) | Solution providing system and mobile terminal | |
| JP2005258235A (en) | Interaction controller with interaction correcting function by feeling utterance detection | |
| JP7061714B1 (en) | Solution provision system and mobile terminal |
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 |