CN114743554A - Intelligent household interaction method and device based on Internet of things - Google Patents

Intelligent household interaction method and device based on Internet of things Download PDF

Info

Publication number
CN114743554A
CN114743554A CN202210647573.8A CN202210647573A CN114743554A CN 114743554 A CN114743554 A CN 114743554A CN 202210647573 A CN202210647573 A CN 202210647573A CN 114743554 A CN114743554 A CN 114743554A
Authority
CN
China
Prior art keywords
interactive
equipment
target
voice
interaction
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
Application number
CN202210647573.8A
Other languages
Chinese (zh)
Inventor
胡成松
薛莲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Technology and Business University
Original Assignee
Wuhan Technology and Business University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Technology and Business University filed Critical Wuhan Technology and Business University
Priority to CN202210647573.8A priority Critical patent/CN114743554A/en
Publication of CN114743554A publication Critical patent/CN114743554A/en
Pending legal-status Critical Current

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • 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
    • G10L15/08—Speech classification or search
    • G10L15/16—Speech classification or search using artificial neural networks
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/80—Homes; Buildings
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/30—Control
    • G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
    • 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)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Architecture (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Structural Engineering (AREA)
  • Civil Engineering (AREA)
  • Medical Informatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The invention relates to the field of data transmission, and discloses an intelligent home interaction method and device based on the Internet of things, which comprises the following steps: converting the interactive voice into a text format to obtain an interactive text; performing entity extraction on the interactive text to obtain an interactive object name, and performing intention identification on the interactive text to obtain an interactive action text; screening all preset intelligent household equipment according to the interactive object name to obtain target equipment; constructing an equipment interaction instruction according to the interaction action text and a pre-constructed command template data table; acquiring the equipment address of the target equipment, and constructing a target channel according to the equipment address; and sending the device interaction instruction to the target device by using the target channel so as to enable the target device to execute the device interaction instruction. The invention improves the interaction efficiency of the intelligent household equipment.

Description

Intelligent household interaction method and device based on Internet of things
Technical Field
The invention relates to the technical field of information security, in particular to an intelligent home interaction method and device based on the Internet of things.
Background
With the rapid development of the internet of things technology, the concept of smart home is more and more appeared in the life of people. The intelligent home is characterized in that various devices (such as audio and video devices, lighting systems, air conditioner control, network home appliances and the like) in the home are connected together through the Internet of things technology, and multiple functions and means such as home appliance control, lighting control, telephone remote control, indoor and outdoor remote control, programmable timing control and the like are provided. Compared with the common home, the intelligent home has the traditional living function, integrates the functions of building, network communication, information household appliances and equipment automation, provides an all-around information interaction function, and even saves funds for various energy expenses.
However, the current smart home interaction method can only rely on interaction programs to interact with the smart home, and different smart homes can realize normal interaction only by searching for corresponding interaction programs, so that the interaction efficiency of the smart homes is low.
Disclosure of Invention
The invention provides an intelligent home interaction method and device based on the Internet of things, and mainly aims to solve the problem of low interaction efficiency of intelligent home.
In order to achieve the above object, the invention provides an intelligent home interaction method based on the internet of things, which is applied to an interactive voice sending end and comprises the following steps:
the method comprises the steps of obtaining interactive voice of a user, carrying out digital sampling on the interactive voice to obtain a standard digital voice signal, and framing the standard digital voice signal to obtain a plurality of voice frames;
and constructing a conversion function to convert the time domain characteristics of the voice frame into frequency domain characteristics to obtain a voice frame frequency spectrum, wherein the conversion function is as follows:
Figure 211872DEST_PATH_IMAGE002
wherein N is the number of all the speech frames, N is the sequence of the speech frames in the standard digital speech signal, j is a preset transformation weight value,
Figure 635025DEST_PATH_IMAGE004
the frequency of the voice frame with the sequence of n in the standard digital voice signal is shown, and D is the voice frame frequency spectrum of the voice frame with the sequence of m in the standard digital voice signal.
Performing power cepstrum on the voice frame frequency spectrum to obtain a voice frequency spectrogram, and identifying all the voice frequency spectrograms by using a trained deep learning model to obtain an interactive text;
performing entity extraction on the interactive text to obtain an interactive object name, and performing intention identification on the interactive text to obtain an interactive action text;
and sending the interactive object name and the interactive action text to an Internet of things equipment control server.
Optionally, the recognizing all the speech spectrogram by using the trained deep learning model to obtain an interactive text includes:
recognizing the voice frequency spectrogram by using the deep learning model to obtain recognized characters;
and combining all the recognition characters according to the sequence of the voice frame corresponding to the voice frequency spectrogram in the standard digital voice signal to obtain the interactive text.
Optionally, the recognizing the speech spectrogram by using the trained deep learning model to obtain recognized characters includes:
performing feature extraction on the voice frequency spectrogram by using a convolutional neural network in the deep learning model to obtain a first frequency spectrum feature;
performing feature conversion on the first spectrum feature by using a multilayer recurrent neural network in the deep learning model to obtain a second spectrum feature;
calculating a probability value of the second spectrum feature mapping to each character in a preset voice recognition dictionary by utilizing a softmax activation function of a full connection layer in the deep learning model; and determining the character with the maximum probability value as the identification character.
Optionally, the performing entity extraction on the interactive text to obtain an interactive object name includes:
performing word segmentation on the interactive text to obtain a plurality of word segmentation words;
converting the word segmentation words into vectors to obtain word segmentation word vectors;
performing feature extraction on the word segmentation word vectors by using a BilSTM model to obtain corresponding entity probability;
determining the participle words corresponding to the participle word vector with the entity probability being greater than a preset entity threshold as entity words;
and calculating the sequence coefficient of each entity word by using a sequence labeling algorithm, and combining the entity words according to the sequence coefficient to obtain the interactive object name.
In order to achieve the above object, the invention provides an intelligent home interaction method based on the internet of things, which is applied to an internet of things equipment control server and comprises the following steps:
receiving an interactive object name and an interactive action text sent by the interactive voice sending end;
screening all preset intelligent household equipment according to the interactive object name to obtain target equipment;
constructing an equipment interaction instruction according to the interaction action text and a pre-constructed command template data table;
acquiring the equipment address of the target equipment, and constructing a target channel according to the equipment address;
and sending the device interaction instruction to the target device by using the target channel so as to enable the target device to execute the device interaction instruction.
Optionally, the screening all the preset smart home devices according to the name of the interactive object to obtain a target device includes:
converting the interactive object name into a vector to obtain an interactive object vector;
converting the equipment name of the intelligent household equipment into a vector to obtain a household equipment vector;
calculating the similarity between the interactive object vector and the household equipment vector to obtain equipment similarity;
determining the household equipment vector corresponding to the maximum equipment similarity as a target household equipment vector;
determining the device name corresponding to the target household device vector as a target device name;
and determining the intelligent household equipment to which the name of the target equipment belongs as the target equipment.
Optionally, the constructing a target channel according to the device address includes:
judging whether the instruction size of the equipment interaction instruction is larger than a preset capacity threshold value or not, and screening transmission protocols in a preset transmission protocol set according to a judgment result to obtain a target transmission protocol;
and replacing the transmission object address in the target transmission protocol with the equipment address to obtain the target channel.
Optionally, the determining whether the instruction size of the device interaction instruction is larger than a preset capacity threshold, and screening transmission protocols in a preset transmission protocol set according to a determination result to obtain a target transmission protocol includes:
when the instruction size is larger than the capacity threshold value, determining a TCP transmission protocol in the transmission protocol set as the target transmission protocol;
when the instruction size is not larger than the capacity threshold, determining a UDP transmission protocol in the transmission protocols as the target transmission protocol.
Optionally, the constructing an equipment interaction instruction according to the interaction action text and the pre-constructed command template data table includes:
acquiring the data type of the command template in the command template data table to obtain a target data type;
and converting the interactive action text into the target data type to obtain the equipment interactive instruction.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the intelligent home interaction method based on the Internet of things.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, where at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the method for smart home interaction based on the internet of things.
The embodiment of the invention extracts the entity of the interactive text to obtain the name of the interactive object, and identifies the intention of the interactive text to obtain the interactive action text; screening all preset intelligent household equipment according to the interactive object name to obtain target equipment; constructing an equipment interaction instruction according to the interaction action text and a pre-constructed command template data table; acquiring the equipment address of the target equipment, and constructing a target channel according to the equipment address; and sending the device interaction instruction to the target device by using the target channel so as to enable the target device to execute the device interaction instruction. The corresponding intelligent home equipment can be directly positioned and screened according to the voice of the user to transmit the corresponding interactive instruction for interactive operation, and interaction is carried out without calling and running the corresponding interactive program, so that the interactive efficiency of the intelligent home equipment is improved; therefore, the intelligent home interaction method and device based on the Internet of things can improve the interaction efficiency of the intelligent home equipment.
Drawings
Fig. 1 is a schematic flow chart of an intelligent home interaction method based on the internet of things according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of an internet-of-things-based smart home interaction method applied to an interactive voice sending end according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of an internet-of-things-based smart home interaction method applied to an internet-of-things device control end according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of one step in the embodiment of FIG. 3;
fig. 5 is a schematic structural diagram of an electronic device for implementing the intelligent home interaction method based on the internet of things according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides an intelligent home interaction method based on the Internet of things. The execution subject of the intelligent home interaction method based on the internet of things includes but is not limited to at least one of electronic devices, such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the application. In other words, the smart home interaction method based on the internet of things may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Example 1:
referring to fig. 1, a schematic flow chart of an intelligent home interaction method based on the internet of things is provided in an embodiment of the present invention. In this embodiment, the smart home interaction method based on the internet of things includes:
the interactive voice sending end obtains interactive voice of a user, performs digital sampling on the interactive voice to obtain a standard digital voice signal, and performs framing on the standard digital voice signal to obtain a plurality of voice frames;
the interactive voice sending end constructs a conversion function to convert the time domain characteristics of the voice frame into frequency domain characteristics to obtain a voice frame frequency spectrum;
the interactive voice sending end performs power cepstrum on the voice frame frequency spectrum to obtain a voice frequency spectrogram, and identifies all the voice frequency spectrograms by using a trained deep learning model to obtain an interactive text;
the interactive voice sending end performs entity extraction on the interactive text to obtain an interactive object name, and performs intention identification on the interactive text to obtain an interactive action text;
and sending the interactive object name and the interactive action text to an Internet of things equipment control server.
The Internet of things equipment control server receives the interactive object name and the interactive action text;
the Internet of things equipment control server screens all preset intelligent household equipment according to the interactive object names to obtain target equipment;
the Internet of things equipment control server builds an equipment interaction instruction according to the interaction action text and a pre-built command template data table;
the Internet of things equipment control server acquires the equipment address of the target equipment and constructs a target channel according to the equipment address;
the Internet of things equipment control server sends the equipment interaction instruction to the target equipment by using the target channel so that the target equipment executes the equipment interaction instruction.
Fig. 2 is a schematic flow chart of an intelligent home interaction method based on the internet of things and applied to an interactive voice sending end according to an embodiment of the present invention. In this embodiment, the smart home interaction method based on the internet of things includes:
s11, acquiring interactive voice of a user, performing digital sampling on the interactive voice to obtain a standard digital voice signal, and framing the standard digital voice signal to obtain a plurality of voice frames;
in the embodiment of the present invention, the interactive voice is a voice that a user wants to interact with a certain home device, for example: turning on the lamp of the living room, pulling the curtain open and adjusting the temperature of the air conditioner a little bit.
Further, since the interactive voice is an analog signal, in order to better recognize the interactive voice, digital sampling of the interactive voice is required.
In detail, in the embodiment of the present invention, performing digital sampling on the interactive voice to obtain a standard digital voice signal, and performing framing on the standard digital voice signal to obtain a plurality of voice frames, includes:
sampling the interactive voice by using an analog-to-digital converter to obtain a digital voice signal;
pre-emphasis is carried out on the digital voice signal to obtain a standard digital voice signal;
since the human voice pronunciation system can suppress the high frequency part, in this embodiment, the digital voice signal can be compensated by pre-emphasis operation to increase the energy of the high frequency part, so that the voice energy of the high frequency part and the voice energy of the low frequency part have similar amplitudes, the frequency spectrum of the signal becomes flat, and the same signal-to-noise ratio can be maintained in the whole frequency band from low frequency to high frequency.
Specifically, the embodiment of the present invention may perform a pre-emphasis operation on the digital speech signal through a function y (t) = x (t) — μ x (t-1), where x (t) is the digital speech signal, t is time, y (t) is the standard digital speech signal, μ is an adjustment value of the pre-emphasis operation, and μ has a value range of [0.9,1.0 ].
S12, constructing a conversion function to convert the time domain characteristics of the voice frame into frequency domain characteristics to obtain a voice frame frequency spectrum, wherein the conversion function is as follows:
Figure 430812DEST_PATH_IMAGE006
wherein N is the number of all the speech frames, N is the sequence of the speech frames in the standard digital speech signal, j is a preset transformation weight value,
Figure 230403DEST_PATH_IMAGE004
the frequency of the voice frame with the sequence of n in the standard digital voice signal is shown, and D is the voice frame frequency spectrum of the voice frame with the sequence of m in the standard digital voice signal.
S13, performing power cepstrum on the voice frame frequency spectrum to obtain a voice frequency spectrogram, and recognizing all the voice frequency spectrogram by using the trained deep learning model to obtain an interactive text;
optionally, in the embodiment of the present invention, a mel cepstrum algorithm may be used to perform power cepstrum on the voice frame spectrum to obtain the voice spectrogram.
Further, the method for recognizing the voice spectrogram by using the trained deep learning model in the embodiment of the present invention to obtain an interactive text includes:
recognizing the voice frequency spectrogram by using the deep learning model to obtain recognized characters;
and combining all the recognition characters according to the sequence of the voice frame corresponding to the voice spectrogram in the standard digital voice signal to obtain the interactive text.
Further, in the embodiment of the present invention, recognizing the speech spectrogram by using the deep learning model to obtain recognized characters includes:
performing feature extraction on the voice frequency spectrogram by using a convolutional neural network in the deep learning model to obtain a first frequency spectrum feature;
performing feature conversion on the first spectrum feature by using a multilayer recurrent neural network in the deep learning model to obtain a second spectrum feature;
calculating a probability value of the second spectrum feature mapping to each character in a preset voice recognition dictionary by utilizing a softmax activation function of a full connection layer in the deep learning model; and determining the character with the maximum probability value as the identification character.
Optionally, the deep learning model in the embodiment of the present invention is formed by a convolutional neural network, a multi-layer recursive neural network, and a fully-connected layer in series, and a loss function of the deep learning model is a CTC (connection temporal classification) function.
S14, performing entity extraction on the interactive text to obtain an interactive object name, and performing intention identification on the interactive text to obtain an interactive action text;
in the embodiment of the present invention, in order to more accurately utilize the interactive voice of the user, the interactive object that the user wants to interact and the interactive operation performed on the interactive object are known, so that the entity extraction is performed on the interactive text to obtain the name of the interactive object, and the intention recognition is performed on the interactive text to obtain the interactive action text, for example: the interactive text is 'adjust the air conditioner temperature in the living room a bit higher'. Then the corresponding interactive object name is "air conditioner in living room" and the corresponding interactive action text is "turn up temperature".
Specifically, in the embodiment of the present invention, performing entity extraction on the interactive text to obtain an interactive object name includes:
segmenting the interactive text to obtain a plurality of segmented words;
converting the word segmentation words into vectors to obtain word segmentation word vectors;
optionally, in the embodiment of the present invention, the word segmentation words may be converted into vectors by using a word2vec model, an One-Hot algorithm, or another model or algorithm, and a specific method for converting into vectors is not limited in the embodiment of the present invention.
Performing feature extraction on the word-divided word vectors by using a BilSTM model to obtain corresponding entity probability;
determining the participle words corresponding to the participle word vector with the entity probability being greater than a preset entity threshold as entity words;
and calculating the sequence coefficient of each entity word by using a sequence labeling algorithm, and combining the entity words according to the sequence coefficient to obtain the interactive object name.
In the embodiment of the invention, because the entity words are only isolated words, in order to correctly combine the entity words, the sequence of the entity words also needs to be determined, so that the sequence label of each entity word is calculated by using the sequence labeling algorithm, wherein the sequence label is a mark for marking the sequence of the entity words. For example: the interactive object name obtained by combining the entity words according to the sequence coefficients is called the air conditioner in the living room; in the embodiment of the present invention, the sequence coefficient may also be identified by text, such as: and combining the corresponding entity words according to the sequence of text representation to obtain the interactive object name.
Further, in the embodiment of the present invention, the intention recognition is performed on the interactive text, so as to recognize the interactive action that the user wants to perform on the corresponding smart home device, and make the interactive action more standard, if the obtained interactive action text is "turn up the air conditioner temperature in the living room by a little", the corresponding interactive action text may be "turn up the temperature", optionally, in the embodiment of the present invention, the intention recognition model that is trained may be used to perform the intention recognition on the interactive text, and the intention recognition model may be a bert model.
And S15, sending the interactive object name and the interactive action text to an Internet of things equipment control server.
In the embodiment of the invention, the interactive object name and the interactive action text are sent to the internet of things equipment control server, wherein the internet of things equipment control server is a signaling server and can be used for establishing channels with all intelligent home equipment registered in the internet of things equipment control server, transmitting interactive commands and occupying less channel resources.
Fig. 3 is a schematic flow chart of an internet-of-things-based smart home interaction method applied to an internet-of-things device control server according to an embodiment of the present invention. In this embodiment, the smart home interaction method based on the internet of things includes:
s21, receiving the name of the interactive object and the interactive action text sent by the interactive voice sending end;
in detail, the interactive voice sending end in the embodiment of the present invention is a terminal device that collects and processes the interactive voice of the user, and the terminal device includes, but is not limited to, a mobile phone, a computer, a tablet, and the like.
S22, screening all preset intelligent household equipment according to the interactive object name to obtain target equipment;
in the embodiment of the invention, the preset intelligent household equipment is the intelligent household equipment registered in the service end of the equipment of the Internet of things.
Further, in the embodiment of the present invention, an equipment name of the smart home equipment is obtained; and determining the intelligent household equipment with the equipment name consistent with the interactive object name as the target equipment.
In order to avoid a situation that the target device cannot be determined due to a difference between an interactive object name described by the user and a device name of the smart home device, in another embodiment of the present invention, the screening all preset smart home devices according to the interactive object name to obtain the target device includes:
converting the interactive object name into a vector to obtain an interactive object vector;
optionally, in the embodiment of the present invention, the name of the interactive object may be converted into a vector by using a word2vec model, an One-Hot algorithm, or another model or algorithm, and a specific method for converting into a vector is not limited in the embodiment of the present invention.
Converting the equipment name of the intelligent household equipment into a vector to obtain a household equipment vector;
calculating the similarity between the interactive object vector and the household equipment vector to obtain equipment similarity;
determining the household equipment vector corresponding to the maximum equipment similarity as a target household equipment vector;
determining the device name corresponding to the target household device vector as a target device name;
and determining the intelligent household equipment to which the target equipment name belongs as the target equipment.
S23, constructing equipment interaction instructions according to the interaction action text and the pre-constructed command template data table;
in the embodiment of the invention, in order to make the target device unable to directly understand the interactive action text, the interactive action text needs to be converted into a machine instruction which can be understood by a machine, so that the device interactive instruction is constructed according to the interactive action text.
In an embodiment of the present invention, the constructing an equipment interaction instruction according to the interaction text and the pre-constructed command template data table includes:
acquiring a label of each command template in the command template data table;
converting the label into a vector to obtain a label vector;
optionally, in the embodiment of the present invention, the label may be converted into a vector by using a word2vec model, an One-Hot algorithm, and other models or algorithms, and a specific method for converting into a vector in the embodiment of the present invention is not limited.
Converting the interactive action text into a vector to obtain an interactive action vector;
calculating the association degree of the label vector and the interactive action vector;
optionally, in the embodiment of the present invention, the association degree between the tag vector and the interaction vector may be calculated by using algorithms such as euclidean distance and pearson correlation coefficient.
Determining the label vector corresponding to the maximum association degree as a target label vector;
determining the label corresponding to the target label vector as a target label;
and determining a command template corresponding to the target tag as the equipment interaction instruction.
Further, in another embodiment of the present invention, a numeric value in the interactive action text may replace a placeholder preset in a command template corresponding to the target tag, so as to obtain the device interaction instruction.
In another embodiment of the present invention, the constructing the device interaction instruction according to the interaction text and the pre-constructed command template data table includes: acquiring the data type of the command template in the command template data table to obtain a target data type; and converting the interactive action text into the target data type to obtain the equipment interactive instruction.
S24, acquiring the equipment address of the target equipment, and constructing a target channel according to the equipment address;
optionally, in the embodiment of the present invention, the device address is an IP address of the target device.
Further, in order to transmit the device interaction instruction to the target device, in the embodiment of the present invention, a target channel needs to be constructed for transmitting the device interaction instruction.
In detail, referring to fig. 4, acquiring a device address of the target device and constructing a target channel according to the device address in the embodiment of the present invention includes:
s41, judging whether the instruction size of the equipment interaction instruction is larger than a preset capacity threshold value or not, and screening transmission protocols in a preset transmission protocol set according to the judgment result to obtain a target transmission protocol;
s42, replacing the transmission object address in the target transmission protocol with the equipment address to obtain the target channel.
Specifically, the determining whether the instruction size of the device interaction instruction is larger than a preset capacity threshold, and screening transmission protocols in a preset transmission protocol set according to the determination result to obtain a target transmission protocol in the embodiment of the present invention includes:
when the instruction size is larger than the capacity threshold value, determining a TCP transmission protocol in the transmission protocol set as the target transmission protocol;
when the instruction size is not larger than the capacity threshold, determining a UDP transmission protocol in the transmission protocols as the target transmission protocol.
S25, sending the device interaction instruction to the target device by using the target channel so as to enable the target device to execute the device interaction instruction.
In detail, in the embodiment of the present invention, the device interaction instruction is sent to the target device by using the target channel, so that the target device executes the device interaction instruction.
For example: if the device interaction instruction is 'turn the brightness down a little', the target channel sends the device interaction instruction to the target device so that the target device executes the device interaction instruction and turns down the brightness of the target device.
In another embodiment of the present invention, the internet of things device control end and different smart home devices may be in a channel long connection state, and therefore, the step S24 may be replaced by the following step S26:
s26, performing channel screening in a preset channel set according to the target equipment to obtain a target channel;
in detail, the channel set in the embodiment of the invention is a set of channels connecting an internet of things device control server and different smart home devices.
Further, in the embodiment of the present invention, performing channel screening in a preset channel set according to the target device to obtain a target channel, includes:
acquiring a channel connection device name corresponding to each channel in the channel set;
in the embodiment of the present invention, the channel set is a set of channels in which a signaling server is connected to different audio receiving devices, and the channel connection device ID is a device ID corresponding to the different audio receiving devices connected to the signaling server.
For example: the channel set comprises two channels, namely a channel A and a channel B, wherein the channel A is a channel for connecting the Internet of things equipment control server and the intelligent household equipment A, the equipment name of the intelligent household equipment A is '123', the channel B is a channel for connecting the Internet of things equipment control server and the intelligent household equipment B, the equipment name of the intelligent household equipment B is '456', the channel corresponding to the channel A is '123', and the channel corresponding to the channel B is '456'.
And screening the channels of which the channel connection equipment names are the equipment names of the target equipment in the channel set to obtain the target channels.
Example 2:
as shown in fig. 5, the structural schematic diagram of the electronic device for implementing the smart home interaction method based on the internet of things is provided in an embodiment of the present invention.
The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further include a computer program, such as an internet of things-based smart home interaction program, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used to store not only application software installed in the electronic device and various data, such as codes of an internet-of-things-based smart home interaction program, but also temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., smart home interaction programs based on the internet of things, etc.) stored in the memory 11 and calling data stored in the memory 11.
The communication bus 12 may be a PerIPheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The communication bus 12 is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
Fig. 5 shows only an electronic device having components, and those skilled in the art will appreciate that the structure shown in fig. 5 does not constitute a limitation of the electronic device, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power source may also include any component of one or more dc or ac power sources, recharging devices, power failure classification circuits, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Optionally, the communication interface 13 may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used to establish a communication connection between the electronic device and other electronic devices.
Optionally, the communication interface 13 may further include a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally, a standard wired interface and a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
Optionally, when the electronic device is an interactive voice sending end, the smart home interaction program based on the internet of things stored in the memory 11 of the electronic device is a combination of a plurality of computer programs. When running in the processor 10, it is possible to implement:
the method comprises the steps of obtaining interactive voice of a user, carrying out digital sampling on the interactive voice to obtain a standard digital voice signal, and framing the standard digital voice signal to obtain a plurality of voice frames;
constructing a conversion function to convert the time domain characteristics of the voice frame into frequency domain characteristics to obtain a voice frame frequency spectrum, wherein the conversion function is as follows:
Figure 178767DEST_PATH_IMAGE006
wherein N is the number of all the speech frames, N is the sequence of the speech frames in the standard digital speech signal, j is a preset transformation weight value,
Figure 271357DEST_PATH_IMAGE008
the speech frequency of the speech frame with the sequence of n in the standard digital speech signal is obtained, and D is the speech frame frequency spectrum of the speech frame with the sequence of m in the standard digital speech signal.
Performing power cepstrum on the voice frame frequency spectrum to obtain a voice frequency spectrogram, and identifying all the voice frequency spectrograms by using a trained deep learning model to obtain an interactive text;
performing entity extraction on the interactive text to obtain an interactive object name, and performing intention identification on the interactive text to obtain an interactive action text;
and sending the interactive object name and the interactive action text to an Internet of things equipment control server.
Optionally, when the electronic device is an internet of things device control server, the smart home interaction program based on the internet of things stored in the memory 11 of the electronic device is a combination of multiple computer programs. When running in the processor 10, it is possible to implement:
receiving an interactive object name and an interactive action text sent by the interactive voice sending end;
screening all preset intelligent household equipment according to the interactive object names to obtain target equipment;
constructing an equipment interaction instruction according to the interaction action text and a pre-constructed command template data table;
acquiring the equipment address of the target equipment, and constructing a target channel according to the equipment address;
and sending the device interaction instruction to the target device by using the target channel so as to enable the target device to execute the device interaction instruction.
Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, and is not described herein again.
Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. The computer readable medium may be non-volatile or volatile. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
Embodiments of the present invention may also provide a computer-readable storage medium, which stores a computer program.
Optionally, when the electronic device is an interactive voice sender, the computer program, when executed by a processor of the electronic device, may implement:
acquiring interactive voice of a user, performing digital sampling on the interactive voice to obtain a standard digital voice signal, and framing the standard digital voice signal to obtain a plurality of voice frames;
constructing a conversion function to convert the time domain characteristics of the voice frame into frequency domain characteristics to obtain a voice frame frequency spectrum, wherein the conversion function is as follows:
Figure 993588DEST_PATH_IMAGE010
wherein N is the number of all the speech frames, N is the sequence of the speech frames in the standard digital speech signal, j is a preset transformation weight value,
Figure 829826DEST_PATH_IMAGE012
the speech frequency of the speech frame with the sequence of n in the standard digital speech signal is obtained, and D is the speech frame frequency spectrum of the speech frame with the sequence of m in the standard digital speech signal.
Performing power cepstrum on the voice frame frequency spectrum to obtain a voice frequency spectrogram, and identifying all the voice frequency spectrograms by using a trained deep learning model to obtain an interactive text;
performing entity extraction on the interactive text to obtain an interactive object name, and performing intention identification on the interactive text to obtain an interactive action text;
and sending the interactive object name and the interactive action text to an Internet of things equipment control server.
Optionally, when the electronic device is an internet of things device control server, the computer program is executed by a processor of the electronic device, and may implement:
receiving an interactive object name and an interactive action text sent by the interactive voice sending end;
screening all preset intelligent household equipment according to the interactive object name to obtain target equipment;
constructing an equipment interaction instruction according to the interaction action text and a pre-constructed command template data table;
acquiring the equipment address of the target equipment, and constructing a target channel according to the equipment address;
and sending the device interaction instruction to the target device by using the target channel so as to enable the target device to execute the device interaction instruction.
Further, the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. An intelligent home interaction method based on the Internet of things is applied to an interactive voice sending end and comprises the following steps:
the method comprises the steps of obtaining interactive voice of a user, carrying out digital sampling on the interactive voice to obtain a standard digital voice signal, and framing the standard digital voice signal to obtain a plurality of voice frames;
constructing a conversion function to convert the time domain characteristics of the voice frame into frequency domain characteristics to obtain a voice frame frequency spectrum, wherein the conversion function is as follows:
Figure 121416DEST_PATH_IMAGE002
wherein N is the number of all the speech frames, N is the sequence of the speech frames in the standard digital speech signal, j is a preset transformation weight value,
Figure 324865DEST_PATH_IMAGE004
the voice frequency of the voice frame with the sequence of n in the standard digital voice signal is set as D, and the voice frame frequency spectrum of the voice frame with the sequence of m in the standard digital voice signal is set as D;
performing power cepstrum on the voice frame frequency spectrum to obtain a voice frequency spectrogram, and identifying all the voice frequency spectrogram by using a trained deep learning model to obtain an interactive text;
performing entity extraction on the interactive text to obtain an interactive object name, and performing intention identification on the interactive text to obtain an interactive action text;
and sending the interactive object name and the interactive action text to an Internet of things equipment control server.
2. The Internet of things-based smart home interaction method according to claim 1, wherein the step of recognizing all the voice frequency spectrograms by using the trained deep learning model to obtain an interaction text comprises the steps of:
recognizing the voice frequency spectrogram by using the deep learning model to obtain recognized characters;
and combining all the recognition characters according to the sequence of the voice frame corresponding to the voice spectrogram in the standard digital voice signal to obtain the interactive text.
3. The Internet of things-based smart home interaction method according to claim 1, wherein the recognizing the voice spectrogram by using the trained deep learning model to obtain recognized characters comprises the following steps:
performing feature extraction on the voice frequency spectrogram by using a convolutional neural network in the deep learning model to obtain a first frequency spectrum feature;
performing feature conversion on the first spectrum feature by using a multilayer recurrent neural network in the deep learning model to obtain a second spectrum feature;
calculating a probability value of the second spectrum feature mapping to each character in a preset voice recognition dictionary by utilizing a softmax activation function of a full connection layer in the deep learning model;
and determining the character with the maximum probability value as the identification character.
4. The intelligent home interaction method based on the internet of things according to claim 1, wherein the extracting the entity of the interaction text to obtain the name of the interaction object comprises:
segmenting the interactive text to obtain a plurality of segmented words;
converting the word segmentation words into vectors to obtain word segmentation word vectors;
performing feature extraction on the word segmentation word vectors by using a BilSTM model to obtain corresponding entity probability;
determining the participle words corresponding to the participle word vector with the entity probability being greater than a preset entity threshold value as entity words;
and calculating the sequence coefficient of each entity word by using a sequence labeling algorithm, and combining the entity words according to the sequence coefficient to obtain the interactive object name.
5. An intelligent home interaction method based on the Internet of things is characterized in that the method is applied to an Internet of things equipment control server side and comprises the following steps:
receiving an interactive object name and an interactive action text sent by the interactive voice sending end;
screening all preset intelligent household equipment according to the interactive object names to obtain target equipment;
constructing an equipment interaction instruction according to the interaction action text and a pre-constructed command template data table;
acquiring the equipment address of the target equipment, and constructing a target channel according to the equipment address;
and sending the device interaction instruction to the target device by utilizing the target channel so as to enable the target device to execute the device interaction instruction.
6. The Internet of things-based smart home interaction method according to claim 5, wherein the step of screening all preset smart home devices according to the interaction object names to obtain target devices comprises the steps of:
converting the name of the interactive object into a vector to obtain an interactive object vector;
converting the equipment name of the intelligent household equipment into a vector to obtain a household equipment vector;
calculating the similarity between the interactive object vector and the household equipment vector to obtain equipment similarity;
determining the household equipment vector corresponding to the maximum equipment similarity as a target household equipment vector;
determining the device name corresponding to the target household device vector as a target device name;
and determining the intelligent household equipment to which the target equipment name belongs as the target equipment.
7. The Internet of things-based smart home interaction method according to claim 5, wherein the constructing a target channel according to the device address comprises:
judging whether the instruction size of the equipment interaction instruction is larger than a preset capacity threshold value or not, and screening transmission protocols in a preset transmission protocol set according to a judgment result to obtain a target transmission protocol;
and replacing the transmission object address in the target transmission protocol with the equipment address to obtain the target channel.
8. The intelligent home interaction method based on the internet of things according to claim 7, wherein the step of judging whether the instruction size of the device interaction instruction is larger than a preset capacity threshold value and screening transmission protocols in a preset transmission protocol set according to the judgment result to obtain a target transmission protocol comprises the steps of:
when the instruction size is larger than the capacity threshold value, determining a TCP transmission protocol in the transmission protocol set as the target transmission protocol;
when the instruction size is not larger than the capacity threshold value, determining a UDP transmission protocol in the transmission protocols as the target transmission protocol.
9. The Internet of things-based smart home interaction method according to claim 5, wherein the constructing of the device interaction instruction according to the interaction action text and the pre-constructed command template data table comprises:
acquiring the data type of the command template in the command template data table to obtain a target data type;
and converting the interactive action text into the target data type to obtain the equipment interactive instruction.
10. An intelligent home interaction device based on the internet of things is characterized in that the device comprises various modules, and when any processor executes the functional modules, the intelligent home interaction method based on the internet of things according to any one of claims 1 to 9 can be executed.
CN202210647573.8A 2022-06-09 2022-06-09 Intelligent household interaction method and device based on Internet of things Pending CN114743554A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210647573.8A CN114743554A (en) 2022-06-09 2022-06-09 Intelligent household interaction method and device based on Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210647573.8A CN114743554A (en) 2022-06-09 2022-06-09 Intelligent household interaction method and device based on Internet of things

Publications (1)

Publication Number Publication Date
CN114743554A true CN114743554A (en) 2022-07-12

Family

ID=82287140

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210647573.8A Pending CN114743554A (en) 2022-06-09 2022-06-09 Intelligent household interaction method and device based on Internet of things

Country Status (1)

Country Link
CN (1) CN114743554A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117198290A (en) * 2023-11-06 2023-12-08 深圳市金鼎胜照明有限公司 Acoustic control-based multi-mode LED intelligent control method and apparatus
WO2024061155A1 (en) * 2022-09-20 2024-03-28 中国联合网络通信集团有限公司 Device control method and apparatus, and storage medium

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101409819A (en) * 2008-11-27 2009-04-15 杭州电子科技大学 Method for encrypting and deciphering digital camera picture based on voiceprint
CN107408111A (en) * 2015-11-25 2017-11-28 百度（美国）有限责任公司 End-to-end speech recognition
CN107515674A (en) * 2017-08-08 2017-12-26 山东科技大学 It is a kind of that implementation method is interacted based on virtual reality more with the mining processes of augmented reality
CN109003601A (en) * 2018-08-31 2018-12-14 北京工商大学 A kind of across language end-to-end speech recognition methods for low-resource Tujia language
CN110120224A (en) * 2019-05-10 2019-08-13 平安科技（深圳）有限公司 Construction method, device, computer equipment and the storage medium of bird sound identification model
CN110189749A (en) * 2019-06-06 2019-08-30 四川大学 Voice keyword automatic identifying method
CN110600018A (en) * 2019-09-05 2019-12-20 腾讯科技（深圳）有限公司 Voice recognition method and device and neural network training method and device
CN110738984A (en) * 2019-05-13 2020-01-31 苏州闪驰数控系统集成有限公司 Artificial intelligence CNN, LSTM neural network speech recognition system
CN111538753A (en) * 2020-06-04 2020-08-14 南京金鼎嘉崎信息科技有限公司 Research and judgment platform based on big data analysis
CN111785257A (en) * 2020-07-10 2020-10-16 四川大学 Empty pipe voice recognition method and device for small amount of labeled samples
CN112632292A (en) * 2020-12-23 2021-04-09 深圳壹账通智能科技有限公司 Method, device and equipment for extracting service keywords and storage medium
CN112951233A (en) * 2021-03-30 2021-06-11 平安科技（深圳）有限公司 Voice question and answer method and device, electronic equipment and readable storage medium
CN113327586A (en) * 2021-06-01 2021-08-31 深圳市北科瑞声科技股份有限公司 Voice recognition method and device, electronic equipment and storage medium
CN113470642A (en) * 2021-06-11 2021-10-01 广东好太太智能家居有限公司 Method and system for realizing voice control scene based on intelligent household APP
CN114067783A (en) * 2021-11-10 2022-02-18 杭州网易智企科技有限公司 Speech recognition method, speech recognition device, storage medium, and electronic apparatus
CN114155834A (en) * 2021-11-29 2022-03-08 科大讯飞股份有限公司 Voice recognition method, device, equipment and storage medium

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101409819A (en) * 2008-11-27 2009-04-15 杭州电子科技大学 Method for encrypting and deciphering digital camera picture based on voiceprint
CN107408111A (en) * 2015-11-25 2017-11-28 百度（美国）有限责任公司 End-to-end speech recognition
CN107515674A (en) * 2017-08-08 2017-12-26 山东科技大学 It is a kind of that implementation method is interacted based on virtual reality more with the mining processes of augmented reality
CN109003601A (en) * 2018-08-31 2018-12-14 北京工商大学 A kind of across language end-to-end speech recognition methods for low-resource Tujia language
CN110120224A (en) * 2019-05-10 2019-08-13 平安科技（深圳）有限公司 Construction method, device, computer equipment and the storage medium of bird sound identification model
CN110738984A (en) * 2019-05-13 2020-01-31 苏州闪驰数控系统集成有限公司 Artificial intelligence CNN, LSTM neural network speech recognition system
CN110189749A (en) * 2019-06-06 2019-08-30 四川大学 Voice keyword automatic identifying method
CN110600018A (en) * 2019-09-05 2019-12-20 腾讯科技（深圳）有限公司 Voice recognition method and device and neural network training method and device
CN111538753A (en) * 2020-06-04 2020-08-14 南京金鼎嘉崎信息科技有限公司 Research and judgment platform based on big data analysis
CN111785257A (en) * 2020-07-10 2020-10-16 四川大学 Empty pipe voice recognition method and device for small amount of labeled samples
CN112632292A (en) * 2020-12-23 2021-04-09 深圳壹账通智能科技有限公司 Method, device and equipment for extracting service keywords and storage medium
CN112951233A (en) * 2021-03-30 2021-06-11 平安科技（深圳）有限公司 Voice question and answer method and device, electronic equipment and readable storage medium
CN113327586A (en) * 2021-06-01 2021-08-31 深圳市北科瑞声科技股份有限公司 Voice recognition method and device, electronic equipment and storage medium
CN113470642A (en) * 2021-06-11 2021-10-01 广东好太太智能家居有限公司 Method and system for realizing voice control scene based on intelligent household APP
CN114067783A (en) * 2021-11-10 2022-02-18 杭州网易智企科技有限公司 Speech recognition method, speech recognition device, storage medium, and electronic apparatus
CN114155834A (en) * 2021-11-29 2022-03-08 科大讯飞股份有限公司 Voice recognition method, device, equipment and storage medium

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
何泽奇 等: "《人工智能》", 31 March 2021, 航空工业出版社 *
孟子厚 等: "《汉语语音区别特征分析》", 30 June 2016, 国防工业出版社 *
曾向阳 等: "《声信号处理基础》", 30 September 2015, 西北工业大学出版社 *
胡盼盼编著: "《自然语言处理从入门到实战》", 30 June 2020, 中国铁道出版社 *
齐力: "《公共安全大数据技术与应用》", 31 December 2017, 上海科学技术出版社 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024061155A1 (en) * 2022-09-20 2024-03-28 中国联合网络通信集团有限公司 Device control method and apparatus, and storage medium
CN117198290A (en) * 2023-11-06 2023-12-08 深圳市金鼎胜照明有限公司 Acoustic control-based multi-mode LED intelligent control method and apparatus

Similar Documents

Publication Publication Date Title
CN114743554A (en) Intelligent household interaction method and device based on Internet of things
CN108304846B (en) Image recognition method, device and storage medium
US11257493B2 (en) Vision-assisted speech processing
US11138903B2 (en) Method, apparatus, device and system for sign language translation
US11412574B2 (en) Split predictions for IoT devices
CN110992937B (en) Language off-line identification method, terminal and readable storage medium
WO2021254411A1 (en) Intent recognigion method and electronic device
CN113095434A (en) Target detection method and device, electronic equipment and storage medium
JP2017192091A (en) IOT system with voice control function and information processing method thereof
CN112149637A (en) Method and apparatus for generating an object re-recognition model and for object re-recognition
CN113611306A (en) Intelligent household voice control method and system based on user habits and storage medium
CN109584864B (en) Image processing apparatus and method
CN114925163A (en) Intelligent equipment and intention recognition model training method
Devi et al. Smart home system using voice command with integration of esp8266
CN109976169B (en) Internet television intelligent control method and system based on self-learning technology
CN107180629B (en) Voice acquisition and recognition method and system
CN114511424A (en) Classroom quality management method based on big data and intelligent education
CN114638308A (en) Method and device for acquiring object relationship, electronic equipment and storage medium
CN113611332A (en) Intelligent control switching power supply method and device based on neural network
CN112242140A (en) Intelligent device control method and device, electronic device and storage medium
KR20110117449A (en) Voice recognition system using data collecting terminal
CN110362837A (en) A kind of artificial intelligence translation integrated system
CN205247684U (en) Speech recognition system based on keyword
US20240096063A1 (en) Integrating model reuse with model retraining for video analytics
WO2023065854A1 (en) Distributed speech control method and electronic device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20220712

RJ01 Rejection of invention patent application after publication