CN110570855A - system, method and device for controlling intelligent household equipment through conversation mechanism - Google Patents
system, method and device for controlling intelligent household equipment through conversation mechanism Download PDFInfo
- Publication number
- CN110570855A CN110570855A CN201910803974.6A CN201910803974A CN110570855A CN 110570855 A CN110570855 A CN 110570855A CN 201910803974 A CN201910803974 A CN 201910803974A CN 110570855 A CN110570855 A CN 110570855A
- Authority
- CN
- China
- Prior art keywords
- control instruction
- cloud server
- voice data
- target control
- text file
- 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
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
- 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
- G10L15/26—Speech to text systems
-
- 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
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- 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
- H04L12/2818—Controlling appliance services of a home automation network by calling their functionalities from a device located outside both the home and the home network
-
- 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
Abstract
the application discloses a system, a method and a device for controlling intelligent household equipment through a dialogue mechanism, which realize the effect of controlling the intelligent household equipment through voice dialogue, and the method comprises the following steps: according to the method, voice dialogue is carried out between the control equipment and a user, voice data are generated and sent to the cloud server, the cloud server carries out voice analysis on the voice data, the voice data are converted into corresponding text files, then word segmentation vector division is carried out on the text files, the similarity between the text files and preset control instructions is calculated, and after the target control instructions are confirmed, the control equipment is triggered to send the target control instructions to the intelligent home equipment. According to the method and the system, the cloud server divides the text file into word segments and vectors, calculates the similarity between the text file and the preset control instruction, and can improve the processing efficiency of the system and the hit rate of the control instruction, so that the user experience is improved.
Description
Technical Field
the application relates to the technical field of smart home, in particular to a system, a method and a device for controlling smart home equipment through a conversation mechanism.
Background
With the development of smart home devices, the control of smart home devices has been performed by conventional key operations and remote controllers, and gradually developed to the present through Application (APP) and applet terminals.
Using APP as an example, under the prior art, when a user sends a control instruction to an intelligent home device through APP, the APP needs to operate, the control instruction is selected through APP, the intelligent terminal sends the control instruction to a server on a network side, and the server forwards the control instruction to the corresponding intelligent home device.
However, in some special cases, the smart terminal may not be connected to the network, and at this time, the smart terminal cannot issue the control instruction, so that the user is affected to operate the smart home device. In addition, if the user cannot use the intelligent terminal at present, the operation on the intelligent household equipment cannot be completed. Therefore, the intelligent terminal sends the control instruction to the server on the network side, so that the method has certain limitation, sometimes possibly influences the operation of the user, and is very inconvenient for the user.
it follows that a new solution needs to be devised to overcome the above drawbacks.
disclosure of Invention
the application provides a system, a method and a device for controlling intelligent household equipment through a dialogue mechanism, which are used for solving the limitation that the intelligent household equipment is controlled through an intelligent terminal in the prior art.
The technical scheme provided by the embodiment of the application is as follows:
A system for controlling smart home devices through a dialog mechanism, comprising:
The control equipment is used for carrying out voice conversation with a user, generating voice data and sending the voice data to the cloud server; receiving a target control instruction returned by the cloud server, and sending the target control instruction to the intelligent home equipment;
the cloud server is used for receiving the voice data sent by the control equipment, carrying out voice analysis on the voice data, converting the voice data into a corresponding text file, carrying out word segmentation vector division on the text file, calculating the similarity between the text file and a preset control instruction based on a division result, confirming a target control instruction, and sending the target control instruction to the control equipment.
Optionally, the cloud server performs voice parsing on the voice data, converts the voice data into a corresponding text file, and specifically includes:
The cloud server performs voice recognition on the voice data, converts the voice data into dialogue text information, performs semantic analysis based on the dialogue text information to obtain user intentions, and converts the user intentions into corresponding text files.
Optionally, the cloud server performs word segmentation and vector division on the text file, and specifically includes:
The cloud server performs word segmentation processing on the text file and stores a word segmentation processing result to a training corpus;
the cloud server acquires the word segmentation processing result from the training corpus and converts the word segmentation processing result into a word vector;
And the cloud server converts the word vector into a rear vector to obtain the division result.
Optionally, the cloud server calculates similarity between the text file and a preset control instruction based on the division result to determine a target control instruction, and specifically includes:
the cloud server calculates the similarity between the division result and a preset control instruction according to a cosine similarity algorithm based on the division result to obtain a corresponding group of similarity values;
And the cloud server compares the group of similarity values with numerical values of a preset threshold, and when the similarity values larger than the preset threshold exist in the group of similarity values, the control instruction corresponding to the similarity value with the largest numerical value is used as the target control instruction.
optionally, the sending, by the control device, the target control instruction to the smart home device includes:
the control equipment directly sends the target control instruction to the intelligent household equipment; or the control equipment informs the user terminal of the target control instruction, and sends the target control instruction to the intelligent household equipment when receiving a confirmation instruction.
a method for controlling intelligent household equipment through a conversation mechanism comprises the following steps:
The control device carries out voice conversation with a user, generates voice data, sends the voice data to a cloud server, and triggers the cloud server to execute the following operations: performing voice analysis on the voice data, converting the voice data into a corresponding text file, performing word segmentation vector division on the text file, calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction, and sending the target control instruction to the control equipment;
and the control equipment receives a target control instruction returned by the cloud server and sends the target control instruction to the intelligent household equipment.
Optionally, the sending, by the control device, the target control instruction to the smart home device includes:
the control equipment directly sends the target control instruction to the intelligent household equipment; or the control equipment informs the user terminal of the target control instruction, and sends the target control instruction to the intelligent household equipment when receiving a confirmation instruction.
A method for controlling intelligent household equipment through a conversation mechanism comprises the following steps:
The cloud server receives voice data sent by the control equipment, carries out voice analysis on the voice data and converts the voice data into a corresponding text file;
The cloud server divides the text file into word segmentation vectors, and calculates the similarity between the text file and a preset control instruction based on the division result so as to confirm a target control instruction;
the cloud server sends the target control instruction to the control equipment, and triggers the control equipment to send the target control instruction to the corresponding intelligent home equipment.
optionally, the server receives voice data sent by the control device, performs voice analysis on the voice data, and converts the voice data into a corresponding text file, which specifically includes:
the cloud server performs voice recognition on the voice data, converts the voice data into dialogue text information, performs semantic analysis based on the dialogue text information to obtain user intentions, and converts the user intentions into corresponding text files.
optionally, the cloud server performs word segmentation and vector division on the text file, and specifically includes:
The cloud server performs word segmentation processing on the text file and stores a word segmentation processing result to a training corpus;
the cloud server acquires the word segmentation processing result from the training corpus and converts the word segmentation processing result into a word vector;
And the cloud server converts the word vector into a rear vector to obtain a corresponding division result.
Optionally, the cloud server calculates similarity between the text file and a preset control instruction based on the division result to determine a target control instruction, and specifically includes:
the cloud server calculates the similarity between the division result and a preset control instruction according to a cosine similarity algorithm based on the division result to obtain a corresponding group of similarity values;
and the cloud server compares the group of similarity values with numerical values of a preset threshold, and when the similarity values larger than the preset threshold exist in the group of similarity values, the control instruction corresponding to the similarity value with the largest numerical value is used as the target control instruction.
an apparatus for controlling smart home devices through a dialog mechanism, comprising:
The dialogue module is used for carrying out voice dialogue with a user, generating voice data, sending the voice data to the cloud server, and triggering the cloud server to execute the following operations: performing voice analysis on the voice data, converting the voice data into a corresponding text file, performing word segmentation vector division on the text file, calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction, and sending the target control instruction to the control equipment;
And the receiving module is used for receiving the target control instruction returned by the cloud server and sending the target control instruction to the intelligent household equipment.
an apparatus for controlling smart home devices through a dialog mechanism, comprising:
The analysis module is used for receiving voice data sent by the control equipment, carrying out voice analysis on the voice data and converting the voice data into a corresponding text file;
the confirming module is used for carrying out word segmentation vector division on the text file and calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction;
And the sending module is used for sending the target control instruction to the control equipment and triggering the control equipment to send the target control instruction to the corresponding intelligent household equipment.
a control device, comprising:
A memory for storing executable instructions;
And the processor is used for reading and executing the executable instructions stored in the memory so as to realize the method for controlling the intelligent household equipment through the conversation mechanism.
A storage medium, wherein instructions when executed by a processor enable the processor to perform a method for controlling a smart home device through a dialogue mechanism as in any one of the above.
A server, comprising:
A memory for storing executable instructions;
And the processor is used for reading and executing the executable instructions stored in the memory so as to realize the method for controlling the intelligent household equipment through the conversation mechanism.
a storage medium, wherein instructions when executed by a processor enable the processor to perform a method for controlling a smart home device through a dialogue mechanism as in any one of the above.
In the embodiment of the application, the control device sends voice data generated by voice conversation with a user to the cloud server, the cloud server performs voice analysis on the voice data, converts the voice data into a corresponding text file, then performs word segmentation vector division on the text file, calculates the similarity between the text file and a preset control instruction, and triggers the control device to send the target control instruction to the smart home device after confirming the target control instruction. Therefore, the user can send the control instruction through voice conversation without performing key operation, so that the user can conveniently control the intelligent household equipment; furthermore, the cloud server obtains the really expressed intention of the user by performing voice analysis on the voice data, so that the hit rate of the control instruction can be improved; furthermore, the cloud server divides the text file into word segments and vectors, calculates the similarity between the text file and a preset control instruction, and confirms the target control instruction, so that the processing efficiency of the system and the hit rate of the control instruction can be further improved, the quick response of the intelligent household equipment to the control instruction is guaranteed, and the user experience is improved.
Drawings
in order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a system for controlling smart home devices through a dialogue mechanism in an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating control of smart home devices by a dialog mechanism in an embodiment of the present application;
Fig. 3 is a schematic structural diagram of an apparatus for controlling smart home devices through a dialog mechanism in an embodiment of the present application;
Fig. 4 is a schematic structural diagram of an apparatus for controlling smart home devices through a dialog mechanism in an embodiment of the present application;
FIG. 5 is a schematic structural diagram of a control device in an embodiment of the present application;
Fig. 6 is a schematic structural diagram of a server in an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
Referring to fig. 1, in the embodiment of the present application, a system for controlling smart home devices through a dialog mechanism at least includes:
Control device, high in the clouds server and intelligent house equipment.
the control equipment is used for carrying out voice conversation with a user, generating voice data and sending the voice data to the cloud server; and receiving a target control instruction returned by the cloud server, and sending the target control instruction to the intelligent household equipment. In this embodiment of the application, the control device may be a functional module in a smart home device, or may be a separate device, for example, including but not limited to a smart phone, a notebook computer, a personal digital assistant, a mobile internet device, a smart wearable device (e.g., a smart watch, a smart bracelet), and the like.
And the intelligent household equipment is used for receiving the target control instruction sent by the control equipment and executing corresponding operation according to the received target control instruction. In the embodiment of the application, the smart home devices include but are not limited to various smart homes such as air conditioners, washing machines, refrigerators, water heaters, electric cookers, lamps and the like.
And the cloud server is used for receiving the voice data of the control equipment, carrying out voice analysis on the voice data, carrying out similarity comparison, and sending the target control instruction to the control equipment after confirming the target control instruction.
Based on the system architecture, referring to fig. 2, in the embodiment of the present application, a detailed process for controlling the smart home device through the dialog mechanism is as follows:
step S201: the control equipment carries out voice conversation with a user, generates voice data and sends the voice data to the cloud server.
Specifically, in this application embodiment, the user can send control instruction through carrying out voice conversation with controlgear to realize controlling intelligent household equipment, controlgear generates corresponding speech data according to the speech conversation content of user input, and sends speech data to the high in the clouds server, makes the high in the clouds server carry out speech analysis to speech data.
Taking an intelligent air conditioner as an example, a user can say that the air conditioner is turned off to the control equipment, the control equipment turns the voice conversation content input by the user off the air conditioner, the voice conversation content is converted into corresponding voice data, and the corresponding voice data are sent to the cloud server.
step S202: the cloud server receives the voice data sent by the control equipment, carries out voice analysis on the voice data and converts the voice data into a corresponding text file.
specifically, in the embodiment of the application, after receiving the voice data sent by the control device, the cloud server performs voice recognition on the voice data, converts the voice data into the dialog text information, performs semantic analysis based on the dialog text information, obtains the user intention through the semantic analysis, and converts the user intention into a corresponding text file.
specifically, the Speech data is converted into the dialog text information by performing Speech Recognition through an Automatic Speech Recognition (ASR) technology.
Specifically, the dialog text information is understood in a Natural Language by a Natural Language Processing (NLP) technique/engine, and the meaning intended by the user is analyzed.
Taking an intelligent air conditioner as an example, assuming that voice data sent by control equipment is 'tuned to 28 ℃', after receiving the voice data sent by the control equipment, a cloud server performs voice recognition and semantic analysis on the 'tuned to 28 ℃', so as to obtain a user intention representing 'temperature is adjusted to 28 ℃', and the user intention is converted into a text file.
Step S203: the cloud server divides the text file into word segments and vectors, and calculates the similarity between the text file and a preset control instruction based on the division result so as to confirm the target control instruction.
specifically, in the embodiment of the present application, when step S203 is executed, the following manners may be adopted, but are not limited to: the cloud server divides the text file into word segments and vectors, and calculates the similarity between the text file and a preset control instruction based on the division result so as to confirm the target control instruction.
the method specifically comprises the following steps:
A1, the cloud server processes word segmentation to the text file, and stores the word segmentation result to the training corpus.
specifically, the cloud server can use the CIPP _ JSsetup tool to perform word segmentation processing on the text file, and the CIPP _ JSsetup tool can automatically segment words of the text file and label the part of speech of each word or phrase in the text file.
For example, the content of the text file is "i leave", the cloud server performs word segmentation processing on the text file, the word segmentation processing result is "i, leave, and yes", wherein "i" is a pronoun, "leave" is a verb, and "yes" is an assistant, and then the cloud server stores the word segmentation processing result to the training corpus.
b1, the cloud server obtains the word segmentation processing result from the training corpus and converts the word segmentation processing result into a word vector.
specifically, the cloud server may convert the word segmentation processing result into a word vector using a word2vec tool. Through conversion, processing on the text file is simplified into vector operation in a vector space, so that the semantic similarity of the text file is represented by calculating the similarity in the vector space.
for example, the word segmentation processing result is "i, leave, and done", the cloud server obtains the word segmentation processing result from the training corpus, that is, the cloud server obtains "i, leave, and done" from the training corpus, and then converts "i, leave, and done" into a word vector, that is, the word vector is me (a)1，a2，…，ai) Away (b)1，b2，…，bi) Is shown by (c)1，c2，…，ci)。
c1, the cloud server converts the word vectors into rear vectors to obtain the division results.
For example, the word vector is me (a)1，a2，…，ai) Away (b)1，b2，…，bi) Is shown by (c)1，c2，…，ci) Cloud server to make word vector I (a)1，a2，…，ai) Away (b)1，b2，…，bi) Is shown by (c)1，c2，…，ci) Convert to back vector I left (A)1，A2，…，Ai) I.e. dividing the result into I's leave (A)1，A2，…，Ai)。
D1, the cloud server calculates the similarity between the text file and the preset control instruction based on the division result to confirm the target control instruction.
Specifically, the cloud server calculates the similarity between the division result and a preset control instruction according to a cosine similarity algorithm based on the division result to obtain a corresponding group of similarity values, then compares the group of similarity values with a preset threshold value, and takes the control instruction corresponding to the similarity value with the largest value as the target control instruction when the similarity value larger than the preset threshold value exists in the group of similarity values.
The cosine similarity is to evaluate the similarity of two vectors by calculating the cosine value of the included angle of the two vectors. In the embodiment of the application, the cosine similarity algorithm has the calculation formulaWherein L is the similarity value, Mi，NiRespectively, a division result and a preset control instruction.
for example, the preset threshold is 0.5, and the division result is that I leaves (A)1，A2，…，Ai) And the cloud server calculates the similarity between the division result and a preset control instruction according to a cosine similarity algorithm, and if the similarity between the division result and the preset control instruction 1, the similarity between the division result and the preset control instruction 2 and the similarity between the division result and the preset control instruction 3 in a group of calculated similarity values is 0.6, 0.7 and 0.4, the preset control instruction 2 is taken as a target control instruction.
Step S204: and the cloud server sends the target control instruction to the control equipment.
Step S205: and the control equipment sends the received target control instruction to the intelligent household equipment.
Specifically, when step S205 is executed, the following two ways are included, but not limited to:
the first mode is as follows: the control equipment directly sends the target control instruction to the intelligent household equipment.
Taking the intelligent sound as an example, assuming that the target control instruction represents and switches to the next song, after the cloud server confirms the target control instruction, the cloud server sends the target control instruction to the control device, the control device directly sends the target control instruction to the intelligent sound, and after receiving the target control instruction, the intelligent sound switches to the next song according to the target control instruction.
The second mode is as follows: and the control equipment informs the user terminal of the target control instruction, and sends the target control instruction to the intelligent household equipment when receiving the confirmation instruction.
still taking the intelligent sound as an example, assuming that the target control instruction represents that the song is stopped to be played, after the cloud server confirms the target control instruction, the target control instruction is sent to the control device, the control device notifies the user terminal of the target control instruction representing that the song is stopped to be played, when the confirmation instruction is received, the target control instruction representing that the song is stopped to be played is sent to the intelligent sound, and after the intelligent sound receives the target control instruction, the song is stopped to be played according to the target control instruction.
based on the same inventive concept, in the embodiment of the present application, an apparatus for controlling smart home devices through a dialog mechanism is provided, as shown in fig. 3, which includes at least a dialog module 301 and a receiving module 302, wherein,
The dialogue module 301 is configured to perform voice dialogue with a user, generate voice data, send the voice data to a cloud server, and trigger the cloud server to perform the following operations: performing voice analysis on the voice data, converting the voice data into a corresponding text file, performing word segmentation vector division on the text file, calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction, and sending the target control instruction to the control equipment;
The receiving module 302 is configured to receive a target control instruction returned by the cloud server, and send the target control instruction to the smart home device.
based on the same inventive concept, in the embodiment of the present application, an apparatus for controlling smart home devices through a dialog mechanism is provided, as shown in fig. 4, the apparatus at least includes a parsing module 401, a confirming module 402, and a sending module 403, where,
The analysis module 401 is configured to receive voice data sent by the control device, perform voice analysis on the voice data, and convert the voice data into a corresponding text file;
A confirming module 402, configured to perform word segmentation vector division on the text file, and based on a division result, calculate a similarity between the text file and a preset control instruction to confirm a target control instruction;
A sending module 403, configured to send the target control instruction to the control device, and trigger the control device to send the target control instruction to a corresponding smart home device.
based on the same inventive concept, in the embodiment of the present application, a control device is provided, as shown in fig. 5, the entity apparatus may include: a processor 501, a memory 502, a transceiver 503, and a bus interface 504;
the processor 501 is configured to read the computer instructions in the memory 502, and execute the following steps:
carrying out voice conversation with a user, generating voice data, sending the voice data to a cloud server, and triggering the cloud server to execute the following operations: performing voice analysis on the voice data, converting the voice data into a corresponding text file, performing word segmentation vector division on the text file, calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction, and sending the target control instruction to the control equipment;
And receiving a target control instruction returned by the cloud server, and sending the target control instruction to the intelligent household equipment.
Optionally, the target control instruction is sent to the smart home device, and the processor 501 is configured to:
Directly sending the target control instruction to the intelligent household equipment; alternatively, the first and second electrodes may be,
and informing the user terminal of the target control instruction, and sending the target control instruction to the intelligent household equipment when receiving a confirmation instruction.
The processor 501 is responsible for managing the bus architecture and general processing, and the memory 502 may store data used by the processor 501 in performing operations. The transceiver 503 is used to receive and transmit data under the control of the processor 501.
The bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by processor 501, and various circuits, represented by memory 502, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The processor 501 is responsible for managing the bus architecture and general processing, and the memory 502 may store data used by the processor 501 in performing operations.
Based on the same inventive concept, in the embodiment of the present application, a server is provided, as shown in fig. 6, where the entity apparatus may include: a processor 601, a memory 602, a transceiver 603, and a bus interface 604;
The processor 601 is configured to read the computer instructions in the memory 602, and execute the following steps:
receiving voice data sent by control equipment, carrying out voice analysis on the voice data, and converting the voice data into a corresponding text file;
performing word segmentation vector division on the text file, and calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction;
and sending the target control instruction to the control equipment, and triggering the control equipment to send the target control instruction to the corresponding intelligent household equipment.
optionally, the processor 601 is specifically configured to receive voice data sent by the control device, perform voice analysis on the voice data, and convert the voice data into a corresponding text file, where:
and carrying out voice recognition on the voice data, converting the voice data into dialogue text information, carrying out semantic analysis based on the dialogue text information to obtain user intention, and converting the user intention into a corresponding text file.
optionally, the word segmentation vector division is performed on the text file, and the processor 601 is specifically configured to:
performing word segmentation processing on the text file, and storing a word segmentation processing result to a training corpus;
acquiring the word segmentation processing result from the training corpus, and converting the word segmentation processing result into a word vector;
and converting the word vector into a post vector to obtain a corresponding division result.
Optionally, based on the division result, a similarity between the text file and a preset control instruction is calculated to confirm the target control instruction, and the processor 601 is specifically configured to:
Based on the division result, calculating the similarity between the division result and a preset control instruction according to a cosine similarity algorithm to obtain a corresponding group of similarity values;
and comparing the group of similarity values with a preset threshold value, and taking the control instruction corresponding to the similarity value with the maximum value as the target control instruction when the similarity value larger than the preset threshold value exists in the group of similarity values.
The processor 601 is responsible for managing the bus architecture and general processing, and the memory 602 may store data used by the processor 601 in performing operations. The transceiver 603 is used for receiving and transmitting data under the control of the processor 601.
The bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by processor 601, and various circuits of memory, represented by memory 602, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The processor 601 is responsible for managing the bus architecture and general processing, and the memory 602 may store data used by the processor 601 in performing operations.
Based on the same inventive concept, the present application provides a storage medium, where the storage medium stores computer-executable instructions, where the computer-executable instructions are configured to enable a computer to execute the method performed by the apparatus (i.e., the control device) for controlling smart home devices through a dialog mechanism in the foregoing embodiments.
Based on the same inventive concept, the present application provides a storage medium, where the storage medium stores computer-executable instructions, where the computer-executable instructions are configured to enable a computer to execute the method performed by the apparatus (i.e., the server) for controlling the smart home devices through the dialog mechanism in the foregoing embodiments.
In the embodiment of the application, the control device sends voice data generated by voice conversation with a user to the cloud server, the cloud server performs voice analysis on the voice data, converts the voice data into a corresponding text file, then performs word segmentation vector division on the text file, calculates the similarity between the text file and a preset control instruction, and triggers the control device to send the target control instruction to the smart home device after confirming the target control instruction. Therefore, after the control equipment has voice conversation with the user, the generated voice data is sent to the cloud server, and the user does not need to perform key operation, so that the user can conveniently control the intelligent household equipment; furthermore, the cloud server obtains the true expression intention of the user by performing voice analysis on the voice data, so that the hit rate of the control instruction is improved; furthermore, the cloud server divides the text file into word segments and vectors, calculates the similarity between the text file and a preset control instruction, and confirms the target control instruction, so that the processing efficiency of the system and the hit rate of the control instruction can be further improved, the quick response of the intelligent household equipment to the control instruction is guaranteed, and the user experience is improved.
for the system/apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
It is to be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or operation from another entity or operation without necessarily requiring or implying any actual such relationship or order between such entities or operations.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
these computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
it will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (17)
1. a system for controlling intelligent household equipment through a conversation mechanism is characterized by comprising:
The control equipment is used for carrying out voice conversation with a user, generating voice data and sending the voice data to the cloud server; receiving a target control instruction returned by the cloud server, and sending the target control instruction to the intelligent home equipment;
the cloud server is used for receiving the voice data sent by the control equipment, carrying out voice analysis on the voice data, converting the voice data into a corresponding text file, carrying out word segmentation vector division on the text file, calculating the similarity between the text file and a preset control instruction based on a division result, confirming a target control instruction, and sending the target control instruction to the control equipment.
2. the system of claim 1, wherein the cloud server performs voice parsing on the voice data and converts the voice data into a corresponding text file, and specifically comprises:
The cloud server performs voice recognition on the voice data, converts the voice data into dialogue text information, performs semantic analysis based on the dialogue text information to obtain user intentions, and converts the user intentions into corresponding text files.
3. the system of claim 1 or 2, wherein the cloud server performs word segmentation vector division on the text file, specifically comprising:
the cloud server performs word segmentation processing on the text file and stores a word segmentation processing result to a training corpus;
The cloud server acquires the word segmentation processing result from the training corpus and converts the word segmentation processing result into a word vector;
and the cloud server converts the word vector into a rear vector to obtain the division result.
4. The system of claim 3, wherein the cloud server calculates a similarity between the text file and a preset control command based on the division result to determine a target control command, and specifically comprises:
the cloud server calculates the similarity between the division result and a preset control instruction according to a cosine similarity algorithm based on the division result to obtain a corresponding group of similarity values;
and the cloud server compares the group of similarity values with numerical values of a preset threshold, and when the similarity values larger than the preset threshold exist in the group of similarity values, the control instruction corresponding to the similarity value with the largest numerical value is used as the target control instruction.
5. the system according to claim 1 or 2, wherein the control device sends the target control instruction to the smart home device, including:
The control equipment directly sends the target control instruction to the intelligent household equipment; alternatively, the first and second electrodes may be,
And the control equipment informs the user terminal of the target control instruction, and sends the target control instruction to the intelligent household equipment when receiving a confirmation instruction.
6. A method for controlling intelligent household equipment through a conversation mechanism is characterized by comprising the following steps:
the control device carries out voice conversation with a user, generates voice data, sends the voice data to a cloud server, and triggers the cloud server to execute the following operations: performing voice analysis on the voice data, converting the voice data into a corresponding text file, performing word segmentation vector division on the text file, calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction, and sending the target control instruction to the control equipment;
and the control equipment receives a target control instruction returned by the cloud server and sends the target control instruction to the intelligent household equipment.
7. The method of claim 6, wherein the control device sending the target control instruction to a smart home device comprises:
the control equipment directly sends the target control instruction to the intelligent household equipment; alternatively, the first and second electrodes may be,
and the control equipment informs the user terminal of the target control instruction, and sends the target control instruction to the intelligent household equipment when receiving a confirmation instruction.
8. A method for controlling intelligent household equipment through a conversation mechanism is characterized by comprising the following steps:
the cloud server receives voice data sent by the control equipment, carries out voice analysis on the voice data and converts the voice data into a corresponding text file;
The cloud server divides the text file into word segmentation vectors, and calculates the similarity between the text file and a preset control instruction based on the division result so as to confirm a target control instruction;
The cloud server sends the target control instruction to the control equipment, and triggers the control equipment to send the target control instruction to the corresponding intelligent home equipment.
9. the method of claim 8, wherein the cloud server receives voice data sent by the control device, performs voice parsing on the voice data, and converts the voice data into a corresponding text file, and specifically comprises:
The cloud server performs voice recognition on the voice data, converts the voice data into dialogue text information, performs semantic analysis based on the dialogue text information to obtain user intentions, and converts the user intentions into corresponding text files.
10. The method according to claim 8 or 9, wherein the cloud server performs word segmentation vector division on the text file, specifically comprising:
the cloud server performs word segmentation processing on the text file and stores a word segmentation processing result to a training corpus;
the cloud server acquires the word segmentation processing result from the training corpus and converts the word segmentation processing result into a word vector;
And the cloud server converts the word vector into a rear vector to obtain a corresponding division result.
11. The method of claim 10, wherein the cloud server calculates a similarity between the text file and a preset control command based on the division result to determine a target control command, and specifically comprises:
The cloud server calculates the similarity between the division result and a preset control instruction according to a cosine similarity algorithm based on the division result to obtain a corresponding group of similarity values;
And the cloud server compares the group of similarity values with numerical values of a preset threshold, and when the similarity values larger than the preset threshold exist in the group of similarity values, the control instruction corresponding to the similarity value with the largest numerical value is used as the target control instruction.
12. an apparatus for controlling smart home devices through a dialog mechanism, comprising:
The dialogue module is used for carrying out voice dialogue with a user, generating voice data, sending the voice data to the cloud server, and triggering the cloud server to execute the following operations: performing voice analysis on the voice data, converting the voice data into a corresponding text file, performing word segmentation vector division on the text file, calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction, and sending the target control instruction to the control equipment;
and the receiving module is used for receiving the target control instruction returned by the cloud server and sending the target control instruction to the intelligent household equipment.
13. An apparatus for controlling smart home devices through a dialog mechanism, comprising:
The analysis module is used for receiving voice data sent by the control equipment, carrying out voice analysis on the voice data and converting the voice data into a corresponding text file;
the confirming module is used for carrying out word segmentation vector division on the text file and calculating the similarity between the text file and a preset control instruction based on a division result so as to confirm a target control instruction;
And the sending module is used for sending the target control instruction to the control equipment and triggering the control equipment to send the target control instruction to the corresponding intelligent household equipment.
14. A control apparatus, characterized by comprising:
A memory for storing executable instructions;
a processor configured to read and execute the executable instructions stored in the memory to implement the method for controlling the smart home device through the dialogue mechanism according to any one of claims 6 to 7.
15. A storage medium, wherein instructions in the storage medium, when executed by a processor, enable the processor to perform the method for controlling a smart home device through a dialogue mechanism according to any one of claims 6 to 7.
16. A server, comprising:
A memory for storing executable instructions;
a processor configured to read and execute the executable instructions stored in the memory to implement the method for controlling the smart home device through the dialogue mechanism according to any one of claims 8 to 11.
17. a storage medium, wherein instructions in the storage medium, when executed by a processor, enable the processor to perform the method for controlling a smart home device through a dialogue mechanism according to any one of claims 8 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910803974.6A CN110570855A (en) | 2019-08-28 | 2019-08-28 | system, method and device for controlling intelligent household equipment through conversation mechanism |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910803974.6A CN110570855A (en) | 2019-08-28 | 2019-08-28 | system, method and device for controlling intelligent household equipment through conversation mechanism |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110570855A true CN110570855A (en) | 2019-12-13 |
Family
ID=68776596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910803974.6A Pending CN110570855A (en) | 2019-08-28 | 2019-08-28 | system, method and device for controlling intelligent household equipment through conversation mechanism |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110570855A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675870A (en) * | 2019-08-30 | 2020-01-10 | 深圳绿米联创科技有限公司 | Voice recognition method and device, electronic equipment and storage medium |
| CN111681652A (en) * | 2020-04-28 | 2020-09-18 | 海信（山东）空调有限公司 | Voice control method, system and storage medium of intelligent household appliance |
| CN111881263A (en) * | 2020-08-12 | 2020-11-03 | 福州大学 | Service recommendation online optimization method for intelligent home scene |
| CN115086099A (en) * | 2022-06-07 | 2022-09-20 | 浙江浩瀚能源科技有限公司 | Data processing method, device, storage medium and system |
| CN115240668A (en) * | 2022-07-06 | 2022-10-25 | 广东开放大学（广东理工职业学院） | Voice interaction household control method and robot |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106571140A (en) * | 2016-11-14 | 2017-04-19 | Tcl集团股份有限公司 | Electrical appliance intelligent control method based on voice meaning and electrical appliance intelligent control system thereof |
| CN107622652A (en) * | 2016-07-15 | 2018-01-23 | 青岛海尔智能技术研发有限公司 | The sound control method and appliance control system of appliance system |
| US20180102144A1 (en) * | 2015-09-09 | 2018-04-12 | A9.Com, Inc. | Section identification in video content |
| CN108595696A (en) * | 2018-05-09 | 2018-09-28 | 长沙学院 | A kind of human-computer interaction intelligent answering method and system based on cloud platform |
| EP3301896B1 (en) * | 2016-09-28 | 2019-07-24 | British Telecommunications public limited company | Streamed communication |
| CN110085219A (en) * | 2018-01-26 | 2019-08-02 | 博西华电器（江苏）有限公司 | Household electrical appliance and method and system by the voice control household electrical appliance |
-
2019
- 2019-08-28 CN CN201910803974.6A patent/CN110570855A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180102144A1 (en) * | 2015-09-09 | 2018-04-12 | A9.Com, Inc. | Section identification in video content |
| CN107622652A (en) * | 2016-07-15 | 2018-01-23 | 青岛海尔智能技术研发有限公司 | The sound control method and appliance control system of appliance system |
| EP3301896B1 (en) * | 2016-09-28 | 2019-07-24 | British Telecommunications public limited company | Streamed communication |
| CN106571140A (en) * | 2016-11-14 | 2017-04-19 | Tcl集团股份有限公司 | Electrical appliance intelligent control method based on voice meaning and electrical appliance intelligent control system thereof |
| CN110085219A (en) * | 2018-01-26 | 2019-08-02 | 博西华电器（江苏）有限公司 | Household electrical appliance and method and system by the voice control household electrical appliance |
| CN108595696A (en) * | 2018-05-09 | 2018-09-28 | 长沙学院 | A kind of human-computer interaction intelligent answering method and system based on cloud platform |
Non-Patent Citations (1)
| Title |
|---|
| 李德毅等: "《中国科协新一代信息技术系列丛书 人工智能导论》", 30 August 2018 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675870A (en) * | 2019-08-30 | 2020-01-10 | 深圳绿米联创科技有限公司 | Voice recognition method and device, electronic equipment and storage medium |
| CN111681652A (en) * | 2020-04-28 | 2020-09-18 | 海信（山东）空调有限公司 | Voice control method, system and storage medium of intelligent household appliance |
| CN111881263A (en) * | 2020-08-12 | 2020-11-03 | 福州大学 | Service recommendation online optimization method for intelligent home scene |
| CN115086099A (en) * | 2022-06-07 | 2022-09-20 | 浙江浩瀚能源科技有限公司 | Data processing method, device, storage medium and system |
| CN115086099B (en) * | 2022-06-07 | 2023-12-29 | 浙江浩瀚能源科技有限公司 | Data processing method, device, storage medium and system |
| CN115240668A (en) * | 2022-07-06 | 2022-10-25 | 广东开放大学（广东理工职业学院） | Voice interaction household control method and robot |
| CN115240668B (en) * | 2022-07-06 | 2023-06-02 | 广东开放大学（广东理工职业学院） | Voice interaction home control method and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110570855A (en) | system, method and device for controlling intelligent household equipment through conversation mechanism | |
| JP6828001B2 (en) | Voice wakeup method and equipment | |
| CN108694940B (en) | Voice recognition method and device and electronic equipment | |
| JP6677419B2 (en) | Voice interaction method and apparatus | |
| CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN106098063B (en) | Voice control method, terminal device and server | |
| JP2022552662A (en) | Speech recognition error correction method, related device and readable storage medium | |
| CN112802459A (en) | Consultation service processing method and device based on voice recognition | |
| JP2019091418A (en) | Method and device for controlling page | |
| CN109767758B (en) | Vehicle-mounted voice analysis method, system, storage medium and device | |
| CN111161726B (en) | Intelligent voice interaction method, device, medium and system | |
| CN109766422A (en) | Information processing method, apparatus and system, storage medium, terminal | |
| CN115132209B (en) | Speech recognition method, apparatus, device and medium | |
| CN112825114A (en) | Semantic recognition method and device, electronic equipment and storage medium | |
| CN112669842A (en) | Man-machine conversation control method, device, computer equipment and storage medium | |
| US20120053937A1 (en) | Generalizing text content summary from speech content | |
| CN111126084B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN113220828B (en) | Method, device, computer equipment and storage medium for processing intention recognition model | |
| CN111402864A (en) | Voice processing method and electronic equipment | |
| CN110827799A (en) | Method, apparatus, device and medium for processing voice signal | |
| US20220399013A1 (en) | Response method, terminal, and storage medium | |
| CN116705018A (en) | Voice control method, voice control device, electronic equipment and readable storage medium | |
| US20230005466A1 (en) | Speech synthesis method, and electronic device | |
| CN114299955B (en) | Voice interaction method and device, electronic equipment and storage medium | |
| CN112489644B (en) | Voice recognition method and device for electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191213 |