CN116110389A - Internet electrical appliance control method and system based on self-learning technology - Google Patents
Internet electrical appliance control method and system based on self-learning technology Download PDFInfo
- Publication number
- CN116110389A CN116110389A CN202310019182.6A CN202310019182A CN116110389A CN 116110389 A CN116110389 A CN 116110389A CN 202310019182 A CN202310019182 A CN 202310019182A CN 116110389 A CN116110389 A CN 116110389A
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- self
- gender
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- H04L12/282—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
- G10L2015/223—Execution procedure of a spoken command
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses an Internet electrical appliance control method and system based on a self-learning technology, and relates to the technical field of intelligent electrical appliance control. The method comprises the following specific steps: when a user wakes up the device through voice, voice input signals of the user are collected in real time; speaker recognition is performed according to the voice input signal; the equipment invokes corresponding automatic configuration information according to different speakers, converts the automatic configuration information into control signals and transmits the control signals to the electrical equipment, and completes the setting or closing of the opening and using information of the electrical equipment. The invention records the household appliance use condition of each user, stores the use preference of each user through the self-learning technology, identifies the speaker in the process of controlling the Internet appliance by the user voice, and can control the appliance equipment to operate according to the preference of the user without user operation, thereby improving the user experience.
Description
Technical Field
The invention relates to the technical field of intelligent control of electric appliances, in particular to an internet electric appliance control method and system based on a self-learning technology.
Background
The voice interaction technology is a technology for human and machine interaction with voice, and realizes the voice interaction experience similar to natural dialogue. Human-computer interaction is performed from mouse and keyboard interaction in the computer era to direct interaction of a touch screen in the smart phone era, the human-computer interaction is simpler and simpler, and the interaction threshold is lower and lower. Voice interactions can be divided into two scenarios: one wakeup of one interaction and one wakeup of successive interactions. In the process of realizing voice interaction, voice recognition is generally performed on the collected voice signals, and corresponding information is recognized therefrom for realizing interaction control. Taking an air conditioner as an example, in general, each user has its own preferred on-off time, temperature, wind speed, etc. In the prior art, in order to achieve the preferred on-off time, temperature and wind speed every day, the user can only control the air conditioner by voice every day. The control mode depends on repeated manual operation of the user every day, automatic intelligent operation of the household appliances cannot be actively realized according to the preference of the user, and the experience of the user is affected. Therefore, how to make the electric appliance automatically run according to the preference of the user so as to improve the user experience is a technical problem to be solved urgently for those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides a self-learning technology-based internet appliance control method and system to solve the problems set forth in the background art.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the Internet appliance control method based on the self-learning technology comprises the following specific steps:
when a user wakes up the device through voice, voice input signals of the user are collected in real time;
speaker recognition is performed according to the voice input signal;
the equipment invokes corresponding automatic configuration information according to different speakers, converts the automatic configuration information into control signals and transmits the control signals to the electrical equipment, and completes the setting or closing of the opening and using information of the electrical equipment.
Optionally, the automatic configuration information is the device usage behavior of the user, and the self-learning step of the device usage behavior of the user is:
the control terminal collects and identifies user identity information in real time;
according to the user identity information, calling the historical running state of the equipment controlled by the user to perform self-identification of the user use behavior;
and learning the historical data by establishing a hidden Markov model, obtaining a user use behavior recognition result by utilizing a learning algorithm and a decoding algorithm, obtaining the user equipment use behavior, establishing a control model for different users, and storing the control model into a neural network control model.
Optionally, the step of performing speaker recognition according to the voice input signal includes:
extracting gender features and accent features of the voice input signal;
extracting tone characteristics of the voice input signal based on a CNN network of the trained multi-source attention network;
constructing a gender auxiliary feature using the gender feature and the timbre feature based on the gender attention network of the trained multi-source attention network;
constructing an accent auxiliary feature by using the accent feature and the tone feature based on the accent attention network of the trained multi-source attention network;
and combining the tone color feature, the gender auxiliary feature and the accent auxiliary feature to identify the speaker.
Optionally, the training steps of the gender attention network are as follows:
constructing a first training set, wherein the first training set comprises voice fragments of known gender labels;
carrying out framing treatment on the voice fragments, extracting MFCC characteristics from each frame, and splicing the MFCC characteristics of all frames in the voice fragments in the time direction to obtain the MFCC frequency spectrum of the voice fragments;
and training the gender classification network by taking the MFCC frequency spectrum as an input value of the gender classification network and taking the known gender label as an ideal output value of the gender classification network to obtain the gender classification network after training.
Optionally, the method further comprises the step of correcting the voice input signal, and the steps are as follows:
extracting features of the voice input signal to obtain a first voice feature to be recognized;
identifying the first voice feature to be identified through a voice correction model corresponding to the user to obtain a corresponding first identification text,
acquiring an updated text input by a user aiming at the first identification text;
and updating the voice correction model according to the updated text and the first voice feature to be recognized.
Optionally, extracting acoustic features of the voice input signal to obtain a voice instruction recognition result; matching the voice command word in the voice command recognition result with a voice command word list pre-stored locally, and outputting a corresponding voice control command if the matching is successful; if the matching is unsuccessful, marking the voice command words in the voice command recognition result, uploading the voice command words to a cloud background and storing the voice command words.
On the other hand, the Internet electrical appliance control system based on the self-learning technology comprises a voice signal acquisition module, an identification module and a control module which are connected in sequence; wherein, the liquid crystal display device comprises a liquid crystal display device,
the voice signal acquisition module is used for acquiring voice input signals of a user in real time after the user wakes up the equipment through voice;
the recognition module is used for recognizing a speaker according to the voice input signal;
the control module is used for the equipment to call corresponding automatic configuration information according to different speakers, and converts the automatic configuration information into control signals to be transmitted to the electrical equipment, so as to finish the setting or closing of the opening and using information of the electrical equipment.
Optionally, the system further comprises a voice correction module connected with the voice signal acquisition module and used for correcting the voice input signal.
Compared with the prior art, the invention discloses an Internet electrical appliance control method and system based on a self-learning technology, which have the following beneficial technical effects: the household appliance service conditions of all users are recorded, the service preference of each user is stored through a self-learning technology, and a speaker is identified in the process of controlling the Internet appliance through user voice, so that the appliance equipment can be controlled to operate according to the preference of the user without user operation, the user experience can be improved, and the intelligent control of the household appliance is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention;
fig. 2 is a system configuration diagram of 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 embodiment of the invention discloses an Internet electrical appliance control method based on a self-learning technology, which is shown in fig. 1, and comprises the following specific steps:
s1, after a user wakes up equipment through voice, voice input signals of the user are collected in real time;
s2, carrying out speaker recognition according to the voice input signal;
s3, the equipment invokes corresponding automatic configuration information according to different speakers, converts the automatic configuration information into control signals and transmits the control signals to the electrical equipment, and completes the opening of the electrical equipment and the setting or closing of the use information of the electrical equipment.
Further, the automatic configuration information, namely the device use behavior of the user, comprises the following steps of:
s31, the control terminal collects and identifies user identity information in real time;
s32, calling the historical running state of the equipment controlled by the user according to the user identity information to perform self-identification of the user use behavior;
s33, learning the historical data by establishing a hidden Markov model, obtaining a user use behavior recognition result by utilizing a learning algorithm and a decoding algorithm, obtaining a user equipment use behavior, establishing a control model for different users, and storing the control model into a neural network control model.
Further, the step of speaker recognition according to the voice input signal comprises:
s21, extracting gender characteristics and accent characteristics of a voice input signal;
s22, extracting tone characteristics of a voice input signal based on a CNN (carbon network) of the trained multi-source attention network;
s23, based on the gender attention network of the multi-source attention network after training, utilizing the gender characteristics and the tone characteristics to construct gender auxiliary characteristics;
s24, constructing an accent auxiliary feature by using accent features and tone features based on the accent attention network of the trained multi-source attention network;
s25, combining the tone color feature, the gender auxiliary feature and the accent auxiliary feature to identify the speaker.
Further, the training steps of the gender attention network are as follows:
s231, constructing a first training set, wherein the first training set comprises voice fragments of known gender labels;
s232, carrying out framing treatment on the voice fragments, extracting MFCC characteristics from each frame, and splicing the MFCC characteristics of all frames in the voice fragments in the time direction to obtain an MFCC frequency spectrum of the voice fragments;
s233, using the MFCC frequency spectrum as an input value of the gender classification network, using a known gender label as an ideal output value of the gender classification network, and training the gender classification network to obtain the trained gender classification network.
Further, the method also comprises the step of correcting the voice input signal, and comprises the following steps:
s11, extracting features of voice input signals to obtain first voice features to be recognized;
s12, identifying the first voice feature to be identified through a voice correction model corresponding to the user to obtain a corresponding first identification text,
s13, acquiring an updated text which is input by a user and aims at the first identification text;
and S14, updating the voice correction model according to the updated text and the first voice feature to be identified.
The working principle of the electrical equipment is controlled by voice: extracting acoustic features of the voice input signals to obtain voice instruction recognition results; matching the voice command word in the voice command recognition result with a voice command word list which is locally pre-stored, and outputting a corresponding voice control command if the matching is successful; if the matching is unsuccessful, marking the voice command words in the voice command recognition result, uploading the voice command words to the cloud background and storing the voice command words.
On the other hand, an internet electrical appliance control system based on a self-learning technology is provided, as shown in fig. 2, and comprises a voice signal acquisition module, an identification module and a control module which are connected in sequence; wherein, the liquid crystal display device comprises a liquid crystal display device,
the voice signal acquisition module is used for acquiring voice input signals of the user in real time after the user wakes up the equipment through voice;
the recognition module is used for recognizing a speaker according to the voice input signal;
and the control module is used for the equipment to call corresponding automatic configuration information according to different speakers, convert the automatic configuration information into control signals and transmit the control signals to the electrical equipment, and finish the opening of the electrical equipment and the setting or closing of the use information of the electrical equipment.
Further, the system also comprises a voice correction module which is connected with the voice signal acquisition module and is used for correcting the voice input signal.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The Internet electrical appliance control method based on the self-learning technology is characterized by comprising the following specific steps of:
when a user wakes up the device through voice, voice input signals of the user are collected in real time;
speaker recognition is performed according to the voice input signal;
the equipment invokes corresponding automatic configuration information according to different speakers, converts the automatic configuration information into control signals and transmits the control signals to the electrical equipment, and completes the setting or closing of the opening and using information of the electrical equipment.
2. The internet appliance control method based on the self-learning technology according to claim 1, wherein the automatic configuration information is a device usage behavior of a user, and the self-learning step of the device usage behavior of the user is:
the control terminal collects and identifies user identity information in real time;
according to the user identity information, calling the historical running state of the equipment controlled by the user to perform self-identification of the user use behavior;
and learning the historical data by establishing a hidden Markov model, obtaining a user use behavior recognition result by utilizing a learning algorithm and a decoding algorithm, obtaining the user equipment use behavior, establishing a control model for different users, and storing the control model into a neural network control model.
3. The internet appliance control method based on the self-learning technology as claimed in claim 1, wherein the step of performing speaker recognition according to the voice input signal comprises the steps of:
extracting gender features and accent features of the voice input signal;
extracting tone characteristics of the voice input signal based on a CNN network of the trained multi-source attention network;
constructing a gender auxiliary feature using the gender feature and the timbre feature based on the gender attention network of the trained multi-source attention network;
constructing an accent auxiliary feature by using the accent feature and the tone feature based on the accent attention network of the trained multi-source attention network;
and combining the tone color feature, the gender auxiliary feature and the accent auxiliary feature to identify the speaker.
4. The internet appliance control method based on the self-learning technology as claimed in claim 3, wherein the training step of the gender attention network is as follows:
constructing a first training set, wherein the first training set comprises voice fragments of known gender labels;
carrying out framing treatment on the voice fragments, extracting MFCC characteristics from each frame, and splicing the MFCC characteristics of all frames in the voice fragments in the time direction to obtain the MFCC frequency spectrum of the voice fragments;
and training the gender classification network by taking the MFCC frequency spectrum as an input value of the gender classification network and taking the known gender label as an ideal output value of the gender classification network to obtain the gender classification network after training.
5. The internet appliance control method based on the self-learning technology according to claim 1, further comprising the step of correcting the voice input signal, comprising the steps of:
extracting features of the voice input signal to obtain a first voice feature to be recognized;
identifying the first voice feature to be identified through a voice correction model corresponding to the user to obtain a corresponding first identification text,
acquiring an updated text input by a user aiming at the first identification text;
and updating the voice correction model according to the updated text and the first voice feature to be recognized.
6. The internet appliance control method based on the self-learning technology according to claim 1, wherein acoustic feature extraction is performed on the voice input signal to obtain a voice command recognition result; matching the voice command word in the voice command recognition result with a voice command word list pre-stored locally, and outputting a corresponding voice control command if the matching is successful; if the matching is unsuccessful, marking the voice command words in the voice command recognition result, uploading the voice command words to a cloud background and storing the voice command words.
7. The Internet electrical appliance control system based on the self-learning technology is characterized by comprising a voice signal acquisition module, an identification module and a control module which are connected in sequence; wherein, the liquid crystal display device comprises a liquid crystal display device,
the voice signal acquisition module is used for acquiring voice input signals of a user in real time after the user wakes up the equipment through voice;
the recognition module is used for recognizing a speaker according to the voice input signal;
the control module is used for the equipment to call corresponding automatic configuration information according to different speakers, and converts the automatic configuration information into control signals to be transmitted to the electrical equipment, so as to finish the setting or closing of the opening and using information of the electrical equipment.
8. The internet appliance control system based on the self-learning technology according to claim 7, further comprising a voice correction module connected to the voice signal acquisition module for correcting the voice input signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310019182.6A CN116110389A (en) | 2023-01-06 | 2023-01-06 | Internet electrical appliance control method and system based on self-learning technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310019182.6A CN116110389A (en) | 2023-01-06 | 2023-01-06 | Internet electrical appliance control method and system based on self-learning technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116110389A true CN116110389A (en) | 2023-05-12 |
Family
ID=86263238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310019182.6A Pending CN116110389A (en) | 2023-01-06 | 2023-01-06 | Internet electrical appliance control method and system based on self-learning technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116110389A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107978311A (en) * | 2017-11-24 | 2018-05-01 | 腾讯科技（深圳）有限公司 | A kind of voice data processing method, device and interactive voice equipment |
| CN108320753A (en) * | 2018-01-22 | 2018-07-24 | 珠海格力电器股份有限公司 | Control method, the device and system of electrical equipment |
| CN112786027A (en) * | 2021-01-06 | 2021-05-11 | 浙江大学 | Voice input correction processing method and device, electronic equipment and storage medium |
| CN113077797A (en) * | 2021-03-22 | 2021-07-06 | 山东师范大学 | Speaker identification method and system based on multi-source attention network |
| US20230056680A1 (en) * | 2021-08-18 | 2023-02-23 | International Business Machines Corporation | Integrating dialog history into end-to-end spoken language understanding systems |
-
2023
- 2023-01-06 CN CN202310019182.6A patent/CN116110389A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107978311A (en) * | 2017-11-24 | 2018-05-01 | 腾讯科技（深圳）有限公司 | A kind of voice data processing method, device and interactive voice equipment |
| CN108320753A (en) * | 2018-01-22 | 2018-07-24 | 珠海格力电器股份有限公司 | Control method, the device and system of electrical equipment |
| CN112786027A (en) * | 2021-01-06 | 2021-05-11 | 浙江大学 | Voice input correction processing method and device, electronic equipment and storage medium |
| CN113077797A (en) * | 2021-03-22 | 2021-07-06 | 山东师范大学 | Speaker identification method and system based on multi-source attention network |
| US20230056680A1 (en) * | 2021-08-18 | 2023-02-23 | International Business Machines Corporation | Integrating dialog history into end-to-end spoken language understanding systems |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107370649B (en) | Household appliance control method, system, control terminal and storage medium | |
| CN107199572B (en) | Robot system and method based on intelligent sound source positioning and voice control | |
| CN106814639A (en) | Speech control system and method | |
| CN108039988B (en) | Equipment control processing method and device | |
| CN106054644B (en) | A kind of intelligent home furnishing control method and system | |
| CN110992932B (en) | Self-learning voice control method, system and storage medium | |
| CN111161714B (en) | Voice information processing method, electronic equipment and storage medium | |
| CN109284386A (en) | Customized intension recognizing method and device | |
| CN111197841A (en) | Control method, control device, remote control terminal, air conditioner, server and storage medium | |
| CN109166576A (en) | A kind of intelligent home control system based on voice control | |
| CN104252287A (en) | Interactive device and method for improving expressive ability on basis of same | |
| CN112735418A (en) | Voice interaction processing method and device, terminal and storage medium | |
| CN108762512A (en) | Human-computer interaction device, method and system | |
| CN113611306A (en) | Intelligent household voice control method and system based on user habits and storage medium | |
| CN113096653A (en) | Personalized accent voice recognition method and system based on artificial intelligence | |
| CN114925163A (en) | Intelligent equipment and intention recognition model training method | |
| CN104898589B (en) | A kind of intelligent response method and apparatus for intelligent steward robot | |
| CN116566760B (en) | Smart home equipment control method and device, storage medium and electronic equipment | |
| CN117348434A (en) | Intelligent home management system based on user living habit | |
| CN116110389A (en) | Internet electrical appliance control method and system based on self-learning technology | |
| CN109976169B (en) | Internet television intelligent control method and system based on self-learning technology | |
| CN114627859A (en) | Method and system for recognizing electronic photo frame in offline semantic manner | |
| CN115713936A (en) | Voice control method and device based on smart home | |
| CN110867106B (en) | Chinese teaching system | |
| CN114999496A (en) | Audio transmission method, control equipment and terminal 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 |