CN109192205B - Intelligent voice interaction system and control method thereof - Google Patents
Intelligent voice interaction system and control method thereof Download PDFInfo
- Publication number
- CN109192205B CN109192205B CN201811060107.XA CN201811060107A CN109192205B CN 109192205 B CN109192205 B CN 109192205B CN 201811060107 A CN201811060107 A CN 201811060107A CN 109192205 B CN109192205 B CN 109192205B
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- voice acquisition
- gateway module
- acquisition module
- 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.)
- Active
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
- 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
-
- 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
- G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
-
- 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
-
- 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
- G10L2015/225—Feedback of the input speech
Abstract
The invention provides an intelligent voice interaction system and a control method thereof, the intelligent voice interaction system comprises a plurality of voice acquisition modules, a gateway module and a cloud server, the gateway module selects the nearest voice acquisition module for connection by judging whether the data of an original broadcast data packet is modified and comparing the distance value between each voice acquisition module and a sound source, the voice acquisition module is selected by the two modes, finally the connection of the voice acquisition module is determined, a stable connection data transmission channel is established, the above mode can lead the gateway module to select the voice acquisition module for connection, avoid the same voice instruction from being transmitted by a plurality of voice acquisition modules, lead a plurality of voice acquisition modules to be connected with the gateway module, influence the data transmission efficiency, and the gateway module can be simultaneously connected with a plurality of voice acquisition modules, so that the concurrent voice instruction transmission capability of the intelligent voice interaction system is realized.
Description
Technical Field
The invention relates to a voice control system, in particular to an intelligent voice interaction system and a control method thereof.
Background
With the development of science and technology, the living standard of people is gradually improved, the popularization of an intelligent home service platform realizes the purpose of providing a low-carbon, healthy, intelligent and comfortable home life mode for people, human-computer voice interaction becomes a common interaction means, and various internet companies launch sound boxes with voice interaction functions. The sound box of the type can not only identify human languages, but also respond according to human requirements, including playing music, reserving air tickets, even controlling household appliances and the like, and the mature wireless technical schemes in the market at present comprise WiFi, 4G, ZigBee, LoRa, NB-Iot and the like. However, it is necessary to make sure that what we need to transmit is voice data, that is, a wireless scheme with a relatively stable and high transmission rate is needed, in the prior art, some nodes adopt a single node device to collect voice, when a user is far away from the node device, the user cannot collect a voice instruction, the user must use the system in a designated area, when an intelligent voice interaction system has a plurality of voice collection modules, there is a problem that the voice collection modules and a control system are many-to-one, how to optimize the connection between the voice collection modules and the control system, establish a stable data transmission channel, and make the system respond to the voice instruction of the user most quickly, which is a place where the prior art needs to be improved.
Disclosure of Invention
The invention aims to provide an intelligent voice interaction system and a control method thereof, wherein the intelligent voice interaction system enables the connection between a gateway module and a voice acquisition module to be more stable through the verification and selection of multiple data, and simultaneously enables the connection relation between the voice acquisition module and the control system to be optimized, so that the intelligent voice interaction system can respond to a voice instruction of a user in an optimal and fastest mode, the overall coordination of the intelligent voice interaction system is improved, and the user experience is improved.
The first objective of the present invention is to provide an intelligent voice interaction system, which includes:
the system comprises a plurality of voice acquisition modules, a distance measuring device is arranged in each voice acquisition module, each voice acquisition module can send an original broadcast data packet, each voice acquisition module has a standby state and a connection state, when the voice acquisition modules are in the standby state, the voice acquisition modules can acquire voice commands in a preset range, when the voice acquisition modules acquire the voice commands, the distance measuring device measures a distance value between a sound source and the voice acquisition modules, the voice acquisition modules modify data of the original broadcast data packets and generate marked broadcast data packets, and the voice acquisition modules send the generated marked broadcast data packets;
the gateway module is provided with a scanning state and a connection state, when the gateway module is in the scanning state, the gateway module can identify a marked broadcast data packet and is connected to the voice acquisition module which contains the marked broadcast data packet and has the minimum distance value, at the moment, the voice acquisition module enters the connection state, the gateway module starts the connection state, and the gateway module receives a voice instruction sent by the voice acquisition module and packages the voice instruction into an instruction audio file to be sent; and
and the cloud server can receive and identify the instruction audio file sent by the gateway module, and feeds back the operation instruction and the voice reply instruction according to the instruction audio file.
Furthermore, the voice acquisition module comprises a data packet processing device, when the voice acquisition module acquires a voice instruction, the data packet processing device modifies part of data of the original broadcast data packet to obtain marked data, the marked broadcast data packet comprises the marked data and a distance value, the gateway module detects whether the marked broadcast data packet contains the marked data in a scanning state, compares the distance values between the plurality of voice acquisition modules and the sound source, and selects the voice acquisition module which contains the marked data and has the smallest distance value in the marked broadcast data packet to establish bidirectional connection.
Further, when the voice acquisition module is in bidirectional connection with the gateway module, the voice acquisition module is connected with the gateway module through a low-power Bluetooth technology and transmits a voice command, the voice reply command is transmitted to the gateway module through the cloud server and then transmitted to the voice acquisition module through the gateway module, and the voice reply command is played by the voice acquisition module.
Furthermore, after the data packet processing device modifies part of data of the original broadcast data packet to obtain marked data, the voice acquisition module sets a waiting time, and when the waiting time is exceeded, the voice acquisition module resets the marked broadcast data packet to the original broadcast data packet.
Furthermore, the voice acquisition module and/or the gateway module are/is provided with a voice data cache queue, and if the gateway module is in an overload connection state at the moment, the voice acquisition module stores the voice instruction into the voice data cache queue; and if the gateway module is not in an overload connection state, the gateway module establishes bidirectional connection with the voice acquisition module.
Furthermore, the intelligent voice interaction system comprises household appliances and furniture, and the voice acquisition module is arranged on the household appliances, the furniture and a wall body.
The first objective of the present invention is to provide a control method for an intelligent voice interaction system, the control method comprising the following steps:
s1, the voice acquisition module acquires a voice command in a preset range, modifies partial data of an original broadcast data packet to obtain marked data, and measures a distance value between a sound source and the voice acquisition module;
s2, the gateway module scans the label broadcast data packet in the voice acquisition module, wherein the label broadcast data packet comprises the label data and the distance value;
s3, the gateway module judges whether the voice acquisition module meets a first condition, the first condition is that the tag broadcast data packet broadcast by the voice acquisition module contains tag data, if only one voice acquisition module meets the first condition, the gateway module establishes bidirectional connection with the voice acquisition module;
s4, if a plurality of voice acquisition modules meet the first condition, the gateway module judges whether the voice acquisition modules meet a second condition, the gateway module selects the voice acquisition modules meeting the second condition to establish bidirectional connection, and the second condition is that the distance value between the sound source and the voice acquisition modules is minimum;
the step S4 includes S41, if the voice collecting module satisfies the second condition, determining whether the gateway module is in an overload connection state at this time, and if the gateway module is in the overload connection state at this time, storing the voice command in a voice data cache queue of the voice collecting module; if the gateway module is not in an overload connection state at the moment, the gateway module establishes bidirectional connection with the voice acquisition module;
s5, after the gateway module and the voice acquisition module are connected in a two-way mode, the cloud server can receive and recognize the voice command sent by the gateway module and feed back an operation command and a voice reply command, the voice reply command is transmitted to the gateway module by the cloud server and then transmitted to the voice acquisition module by the gateway module, the voice reply command is played by the voice acquisition module and is disconnected with the connection between the voice acquisition module and the gateway module, and finally the marked broadcast data packet is reset into an original broadcast data packet by the voice acquisition module.
Further, the step S1 includes a step S11, when the voice collecting module collects a nearby voice command, the data packet processing device of the voice collecting module modifies part of the data of the original broadcast data packet to obtain the tag data.
Further, the step S4 includes a step S42, when the voice collecting module does not satisfy the second condition, the voice collecting module sets a waiting time, when the time exceeds the waiting time, the voice collecting module is disconnected from the gateway module, and finally the voice collecting module resets the marked broadcast data packet to the original broadcast data packet.
Further, the step S5 includes a step S51, where after the gateway module establishes a bidirectional connection with the voice collecting module, the voice collecting module performs identity verification on the gateway module; if the identity authentication fails, the voice data transmission is not carried out, and the connection between the voice acquisition module and the gateway module is disconnected; and
furthermore, the step S5 further includes a step S52, after the gateway module passes the authentication, the gateway module and the voice collecting module transmit voice data to each other, where the voice data includes a voice command and a voice reply command.
Has the advantages that: the invention provides an intelligent voice interaction system which comprises a plurality of voice acquisition modules, wherein when the voice acquisition modules are in a standby state, the voice acquisition modules can acquire voice commands within a preset range, and when the voice acquisition modules acquire the voice commands, a distance value between a sound source and the voice acquisition modules is measured by a distance measuring device, the voice acquisition modules modify data of original broadcast data packets and generate marked broadcast data packets, and the voice acquisition modules send the generated marked broadcast data packets;
when the gateway module is in a scanning state, the gateway module can identify a marked broadcast data packet and is connected to the voice acquisition module which contains the marked broadcast data packet and has the minimum distance value, at the moment, the voice acquisition module enters a connection state, the gateway module is in a connection state, and the gateway module receives a voice command sent by the voice acquisition module and packages the voice command into a command audio file to be sent;
and the cloud server can receive and identify the instruction audio file sent by the gateway module, and feeds back the operation instruction and the voice reply instruction according to the instruction audio file.
The gateway module selects the nearest voice acquisition module to connect by judging whether the data of the original broadcast data packet is modified and comparing the distance value between each voice acquisition module and the sound source, the voice acquisition modules are selected by the two modes, finally the voice acquisition modules are determined to be connected, and a stable connection data transmission channel is established.
Drawings
Fig. 1 is a schematic diagram of an intelligent voice interaction system according to an embodiment of the present invention.
Fig. 2 is a logic flow diagram of a control method determination of an intelligent voice interaction system according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the description of the present invention, it is to be understood that the terms "lateral," "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "clockwise," "counterclockwise," and the like are used in the orientation or positional relationship indicated in the drawings for convenience in describing the invention and for simplicity in description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
The present invention is proposed based on the following knowledge: at present, man-machine voice interaction becomes a common interaction means, and various large internet companies launch sound boxes with voice interaction functions. The sound box of the type can not only identify human language, but also respond according to human requirements, including playing music, reserving air tickets, even controlling household appliances and the like, and realizes a distributed voice acquisition scheme, a voice acquisition node can be hidden in a switch as an independent module, a socket, even integrated on some household appliances, so that a user can issue voice commands in each corner of a home, but when the design is carried out, the situation that a plurality of acquisition nodes receive voice commands simultaneously exists, and how to connect a gateway module is carried out at the moment, the inventor researches the whole scheme, provides the technical scheme of the invention, selects the nearest voice acquisition module to connect by detecting whether data is modified and comparing the distance value between each voice acquisition module and a sound source, namely selects the voice acquisition module by the two modes, finally, a proper voice acquisition module is determined to be connected, and a stable data transmission channel is established.
The invention is further described with reference to the following figures and examples.
As shown in fig. 1 to fig. 2, an objective of the present invention is to provide an intelligent voice interaction system, which includes:
the system comprises a plurality of voice acquisition modules, a distance measuring device is arranged in each voice acquisition module, each voice acquisition module can send an original broadcast data packet, each voice acquisition module has a standby state and a connection state, when the voice acquisition modules are in the standby state, the voice acquisition modules can acquire voice commands in a preset range, when the voice acquisition modules acquire the voice commands, the distance measuring device measures a distance value between a sound source and the voice acquisition modules, the voice acquisition modules modify data of the original broadcast data packets and generate marked broadcast data packets, and the voice acquisition modules send the generated marked broadcast data packets;
the gateway module is provided with a scanning state and a connection state, when the gateway module is in the scanning state, the gateway module can identify a marked broadcast data packet and is connected to the voice acquisition module which contains the marked broadcast data packet and has the minimum distance value, at the moment, the voice acquisition module enters the connection state, the gateway module starts the connection state, and the gateway module receives a voice instruction sent by the voice acquisition module and packages the voice instruction into an instruction audio file to be sent; and
and the cloud server can receive and identify the instruction audio file sent by the gateway module, and feeds back the operation instruction and the voice reply instruction according to the instruction audio file. The operation instruction refers to the control of the intelligent voice interaction system on household electrical equipment, such as the control of turning on or off a television, an air conditioner and a lamp.
The voice acquisition modules are distributed at a plurality of positions of the intelligent voice interaction system so as to acquire voice instructions of users at different positions; specifically, a singlechip, a chip or a processor is arranged in the voice acquisition module, so that data of the voice instruction is modified to obtain marked data.
The gateway module has two states, namely a scanning state and a connection state, and specifically, the gateway module can detect a tag broadcast packet containing tag data in the scanning state. The marked data enables the gateway module to accurately identify the voice acquisition module corresponding to the marked data, avoids other voice acquisition modules from participating in connection, improves the reliability of connection, optimizes an intelligent voice interaction system, and improves user experience. The scanning state of the gateway module refers to that the gateway module can scan surrounding radio electromagnetic wave signals after being powered on.
The distance measuring device is used for measuring the distance value between the sound source and the voice acquisition module and adding the distance value into the marked broadcast data packet, so that the voice acquisition module can feed the distance value back to the gateway module. Specifically, the distance measuring device comprises a timer, the position resolution precision of the timer is D, and the distance value D is determined by measuring the time t from the user sending an instruction to the voice acquisition module to collect the instruction, wherein D is equal to the product of D and t.
During specific implementation, a plurality of voice acquisition modules are arranged in a distributed mode in an indoor environment, if a user issues a voice command, a plurality of voice acquisition modules are awakened and connected with a gateway module to transmit data, the mode that the voice command occupies a plurality of connecting channels to transmit is not economical, the operating speed of the whole system is influenced, only one voice acquisition module can respond, and the voice acquisition module is the nearest equipment to the user.
The gateway module determines whether the voice acquisition module is connected by judging whether the broadcast tag broadcast data packet is the minimum or not and judging whether the distance value measured in the tag broadcast data packet is the minimum or not, and a stable connection data transmission channel is established. And the gateway module can be simultaneously connected with a plurality of voice acquisition modules, so that the concurrent voice instruction transmission capability of the intelligent voice interaction system is realized.
Furthermore, the voice acquisition module comprises a data packet processing device, when the voice acquisition module acquires a voice instruction, the data packet processing device modifies part of data of the original broadcast data packet to obtain marked data, the marked broadcast data packet comprises the marked data and a distance value, the gateway module detects whether the marked broadcast data packet contains the marked data in a scanning state, compares the distance values between the plurality of voice acquisition modules and the sound source, and selects the voice acquisition module which contains the marked data and has the smallest distance value in the marked broadcast data packet to establish bidirectional connection.
When the voice acquisition module and the gateway module are connected in a two-way mode, the voice acquisition module and the gateway module are connected through a low-power Bluetooth technology and transmit a voice command, the voice reply command is transmitted to the gateway module through the cloud server and then transmitted to the voice acquisition module through the gateway module, and the voice reply command is played through the voice acquisition module. The voice acquisition module is connected with the gateway module through a low-power Bluetooth technology. The BLE5.0 technology is preferentially adopted in the low-power-consumption Bluetooth technology, the scanning state and the connection state of the gateway module can exist at the same time, and namely voice can be played by the voice acquisition module and the gateway module in the connection state. The voice data transmission mode in the invention is wireless transmission, preferably low power consumption Bluetooth technology, and other wireless transmission modes are also within the protection scope of the invention.
Furthermore, after the data packet processing device modifies part of data of the original broadcast data packet to obtain marked data, the voice acquisition module sets a waiting time, and when the waiting time is exceeded, the voice acquisition module resets the marked broadcast data packet to the original broadcast data packet.
Further, when the voice acquisition module establishes bidirectional connection with the gateway module, the voice acquisition module is connected with the gateway module through a low-power Bluetooth technology and transmits a voice instruction. At the moment, the transmission rate of the voice instruction is greatly improved, specifically, the transmission rate can reach 2Mbps, after the voice data transmission is completed, the connection is disconnected, and the marked broadcast data packet is reset to be the original broadcast data packet.
The voice acquisition module and/or the gateway module are/is provided with a voice data cache queue, if the gateway module is in an overload connection state at the moment, the voice acquisition module stores a voice instruction into the voice data cache queue, and after the gateway module breaks the existing bidirectional connection, the voice acquisition module and the gateway module establish bidirectional connection; and at the moment, if the gateway module is not in an overload connection state, the gateway module establishes bidirectional connection with the voice acquisition module. The gateway module can be connected with a plurality of devices at the same time, the number of the connected devices has a maximum value due to the limitation of hardware conditions, and when the maximum value is exceeded, the gateway module is in an overload connection state.
The design of the voice data buffer queue is proposed based on the following considerations:
in the first case, when the gateway module is already in an overloaded connection state, the system will lose this data if the user issues a valid voice command during this time. In order to solve the problem, a technician develops a voice data buffer queue in the voice acquisition module, and the voice data buffer queue temporarily stores the voice instruction in the period of time.
In the second situation, when the voice acquisition module meets the first condition and the second condition and before the voice acquisition module establishes the bidirectional connection with the network management module, if a user sends a voice instruction, and the situation that the voice instruction is lost or the voice instruction is incomplete necessarily occurs at the moment, the voice instruction can be stored by using the voice data cache queue, so that the loss of the effective data or the failure of acquisition of the new voice instruction is avoided. When a plurality of new voice instructions exist in the voice data cache queue, the new voice instructions are stored in order according to the time sent by the voice instructions until the gateway module is disconnected from the voice acquisition module, and the voice instructions stored in the voice data cache queue are executed one by one and are executed according to the first-in first-out sequence.
Furthermore, the intelligent voice interaction system comprises household appliances and furniture, and the voice acquisition module is arranged on the household appliances, the furniture and a wall body. Particularly, the voice acquisition module can be arranged on a switch, a socket and household appliances in an integrated mode, and can also adopt a conventional design scheme, such as the conventional design scheme arranged on an indoor wall body, so that voice instructions sent by a user can be acquired at any time, and the user experience is improved.
The second objective of the present invention is a control method of an intelligent voice interaction system, comprising the following steps:
s1, the voice acquisition module acquires a voice command in a preset range, modifies partial data of an original broadcast data packet to obtain marked data, and measures a distance value between a sound source and the voice acquisition module;
s2, the gateway module scans the label broadcast data packet in the voice acquisition module, wherein the label broadcast data packet comprises the label data and the distance value;
s3, the gateway module judges whether the voice acquisition module meets a first condition, the first condition is that the tag broadcast data packet broadcast by the voice acquisition module contains tag data, if only one voice acquisition module meets the first condition, the gateway module establishes bidirectional connection with the voice acquisition module;
s4, if a plurality of voice acquisition modules meet the first condition, the gateway module judges whether the voice acquisition modules meet a second condition, the gateway module selects the voice acquisition modules meeting the second condition to establish bidirectional connection, and the second condition is that the distance value between the sound source and the voice acquisition modules is minimum;
the step S4 includes S41, if the voice collecting module satisfies the second condition, determining whether the gateway module is in an overload connection state at this time, and if the gateway module is in the overload connection state at this time, storing the voice command in a voice data cache queue of the voice collecting module; if the gateway module is not in an overload connection state at the moment, the gateway module establishes bidirectional connection with the voice acquisition module;
s5, after the gateway module and the voice acquisition module are connected in a two-way mode, the cloud server can receive and recognize the voice command sent by the gateway module and feed back an operation command and a voice reply command, the voice reply command is transmitted to the gateway module by the cloud server and then transmitted to the voice acquisition module by the gateway module, the voice reply command is played by the voice acquisition module and is disconnected with the connection between the voice acquisition module and the gateway module, and finally the marked broadcast data packet is reset into an original broadcast data packet by the voice acquisition module.
Further, the step S1 includes a step S11, when the voice collecting module collects a nearby voice command, the data packet processing device of the voice collecting module modifies part of the data of the original broadcast data packet to obtain the tag data.
Further, the step S4 includes a step S42, when the voice collecting module does not satisfy the second condition, the voice collecting module sets a waiting time, when the time exceeds the waiting time, the voice collecting module is disconnected from the gateway module, and finally the voice collecting module resets the marked broadcast data packet to the original broadcast data packet.
Further, the step S5 includes a step S51, where after the gateway module establishes a bidirectional connection with the voice collecting module, the voice collecting module performs identity verification on the gateway module; if the identity authentication fails, the voice data transmission is not carried out, and the connection between the voice acquisition module and the gateway module is disconnected; the step S51 is used to determine whether the connection object is a gateway module in the intelligent voice interaction system, so as to prevent the voice acquisition module from being maliciously connected to cause abnormal data transmission or leaking to the outside, thereby improving the security and stability of the system.
Furthermore, the step S5 further includes a step S52, after the gateway module passes the authentication, the gateway module and the voice collecting module transmit voice data to each other, where the voice data includes a voice command and a voice reply command.
The intelligent voice interaction system numbers the voice acquisition modules in sequence to obtain V1, V2.. times Vn, the connection priority of the N voice acquisition modules is reduced from V1 to Vn in sequence, and if two or even more than two voice acquisition modules simultaneously meet a first condition and a second condition, the gateway module of the intelligent voice interaction system can select the connection with higher priority through the priority of the voice acquisition modules.
The detailed working process of the intelligent voice interaction system is described as follows:
as shown in fig. 1 and fig. 2, the voice collecting module is in a standby state, a user sends a voice command at a certain indoor place, when the voice collecting module collects the voice command, the distance measuring device measures a distance value between a sound source and the voice collecting module, the voice collecting module modifies data of an original broadcast data packet and generates a marked broadcast data packet, the voice collecting module sends the generated marked broadcast data packet, and the marked broadcast data packet sends a signal containing the distance value and the marked data;
the gateway module can identify nearby wireless broadcast signals in a scanning state, detect whether the received marked broadcast data has marked data, and further judge whether a distance value fed back by the voice acquisition module is minimum if the marked data exists;
if the gateway module is in an overload connection state, the voice acquisition module stores the voice instruction into the voice data cache queue, and after the gateway module breaks the existing bidirectional connection, the voice acquisition module establishes bidirectional connection with the gateway module; and at the moment, if the gateway module is not in an overload connection state, the gateway module establishes bidirectional connection with the voice acquisition module.
The cloud server receives the voice instruction generated by the gateway module and then makes an operation instruction and a voice reply instruction, specifically, on one hand, the cloud server unscrambles the voice instruction of the user, if the voice instruction of the user is 'turn on the air conditioner', the cloud server unscrambles the voice instruction of the user through an algorithm and then sends a control instruction to the gateway module, and the gateway module turns on the air conditioner through controlling electrical equipment, such as the on-off of a loop where a relay is located; on the other hand, the cloud server reads the voice command and then feeds back the voice reply command to the gateway module, the gateway module transmits the voice reply command to the corresponding voice acquisition module which establishes the bidirectional connection and plays the voice reply command, so that the user knows that the voice command of the user starts to be executed, after the above process is completed, the gateway module is disconnected from the voice acquisition module, and finally the voice acquisition module resets the original broadcast data packet with the marked broadcast data packet.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. An intelligent voice interaction system, comprising:
the voice acquisition module can acquire a voice command in a preset range when the voice acquisition module is in a standby state, and the distance measuring device measures a distance value between a sound source and the voice acquisition module when the voice acquisition module acquires the voice command;
the gateway module is provided with a scanning state and a connection state, when the gateway module is in the scanning state, the gateway module can identify a marked broadcast data packet and is connected to the voice acquisition module which contains the marked broadcast data packet and has the minimum distance value, at the moment, the voice acquisition module enters the connection state, the gateway module starts the connection state, and the gateway module receives a voice instruction sent by the voice acquisition module and packages the voice instruction into an instruction audio file to be sent; and
the cloud server can receive and identify the instruction audio file sent by the gateway module, and feeds back an operation instruction and a voice reply instruction according to the instruction audio file;
the voice acquisition module comprises a data packet processing device, when the voice acquisition module acquires a voice instruction, the data packet processing device modifies partial data of an original broadcast data packet to obtain marked data, the marked broadcast data packet comprises the marked data and a distance value, the gateway module detects whether the marked broadcast data packet contains the marked data in a scanning state, the distance values between the voice acquisition modules and a sound source are compared, and the voice acquisition module which contains the marked data and has the smallest distance value in the marked broadcast data packet is selected to establish bidirectional connection.
2. The intelligent voice interaction system of claim 1, wherein when the voice collection module and the gateway module establish a bidirectional connection, the voice collection module and the gateway module are connected by a low power consumption bluetooth technology and transmit a voice command, the voice reply command is transmitted to the gateway module by the cloud server, then transmitted to the voice collection module by the gateway module, and the voice reply command is played by the voice collection module.
3. The intelligent voice interaction system of claim 1, wherein after the data packet processing device modifies a part of data of the original broadcast data packet to obtain the tagged data, the voice capture module sets a waiting time, and when the waiting time is exceeded, the voice capture module resets the tagged broadcast data packet to the original broadcast data packet.
4. The intelligent voice interaction system according to any one of claims 1 to 3, wherein the voice acquisition module and/or the gateway module is provided with a voice data cache queue, and if the gateway module is in an overload connection state at the moment, the voice acquisition module stores a voice instruction into the voice data cache queue; and if the gateway module is not in an overload connection state, the gateway module establishes bidirectional connection with the voice acquisition module.
5. The intelligent voice interaction system according to any one of claims 1 to 3, wherein the intelligent voice interaction system comprises household appliances and furniture, and the voice acquisition module is arranged on the household appliances, the furniture and a wall body.
6. A control method of an intelligent voice interaction system is characterized by comprising the following steps:
s1, the voice acquisition module acquires a voice command in a preset range, modifies partial data of an original broadcast data packet to obtain marked data, and measures a distance value between a sound source and the voice acquisition module;
s2, the gateway module scans the label broadcast data packet in the voice acquisition module, wherein the label broadcast data packet comprises the label data and the distance value;
s3, the gateway module judges whether the voice acquisition module meets a first condition, the first condition is that the tag broadcast data packet broadcast by the voice acquisition module contains tag data, if only one voice acquisition module meets the first condition, the gateway module establishes bidirectional connection with the voice acquisition module;
s4, if a plurality of voice acquisition modules meet the first condition, the gateway module judges whether the voice acquisition modules meet a second condition, the gateway module selects the voice acquisition modules meeting the second condition to establish bidirectional connection, and the second condition is that the distance value between the sound source and the voice acquisition modules is minimum;
the step S4 includes S41, if the voice collecting module satisfies the second condition, determining whether the gateway module is in an overload connection state at this time, and if the gateway module is in the overload connection state at this time, storing the voice command in a voice data cache queue of the voice collecting module; if the gateway module is not in an overload connection state at the moment, the gateway module establishes bidirectional connection with the voice acquisition module; the voice acquisition modules are distributed at a plurality of positions of the intelligent voice interaction system so as to acquire voice instructions of users at different positions;
s5, after the gateway module and the voice acquisition module are in bidirectional connection, the cloud server can receive and recognize a voice instruction sent by the gateway module, feed back an operation instruction and a voice reply instruction, the voice reply instruction is transmitted to the gateway module by the cloud server, then is transmitted to the voice acquisition module by the gateway module, the voice reply instruction is played by the voice acquisition module, the connection between the voice acquisition module and the gateway module is disconnected, and finally the voice acquisition module resets the marked broadcast data packet into an original broadcast data packet;
the step S1 includes a step S11, where the voice collecting module collects nearby voice commands, and the data packet processing device of the voice collecting module modifies partial data of the original broadcast data packet to obtain the tag data.
7. The method of claim 6, wherein the step S4 includes a step S42, when the voice capture module does not satisfy the second condition, the voice capture module sets a waiting time, when the time exceeds the waiting time, the voice capture module disconnects from the gateway module, and finally the voice capture module resets the marked broadcasting data packet to the original broadcasting data packet.
8. The method for controlling an intelligent voice interaction system according to claim 6, wherein the step S5 includes a step S51, when the gateway module establishes a bidirectional connection with the voice capture module, the voice capture module performs authentication on the gateway module; if the identity authentication fails, the voice data transmission is not carried out, and the connection between the voice acquisition module and the gateway module is disconnected; and
the step S5 further includes a step S52, after the gateway module passes the identity authentication, the gateway module and the voice collecting module transmit voice data to each other, and the voice data includes a voice instruction and a voice reply instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811060107.XA CN109192205B (en) | 2018-09-12 | 2018-09-12 | Intelligent voice interaction system and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811060107.XA CN109192205B (en) | 2018-09-12 | 2018-09-12 | Intelligent voice interaction system and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109192205A CN109192205A (en) | 2019-01-11 |
| CN109192205B true CN109192205B (en) | 2021-05-04 |
Family
ID=64910275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811060107.XA Active CN109192205B (en) | 2018-09-12 | 2018-09-12 | Intelligent voice interaction system and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109192205B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110085233B (en) * | 2019-04-08 | 2021-02-09 | 广东美的制冷设备有限公司 | Voice control method and device, electronic equipment and computer readable storage medium |
| CN110635976B (en) * | 2019-09-02 | 2022-04-01 | 深圳市酷开网络科技股份有限公司 | Accompanying equipment control method, accompanying equipment control system and storage medium |
| CN111210826B (en) * | 2019-12-26 | 2022-08-05 | 深圳市优必选科技股份有限公司 | Voice information processing method and device, storage medium and intelligent terminal |
| CN113674738A (en) * | 2020-05-14 | 2021-11-19 | 青岛鼎信通讯股份有限公司 | Whole-house distributed voice system and method |
| CN113658592B (en) * | 2021-07-29 | 2024-04-02 | 浙江亿秒数字科技有限公司 | Data visualization system capable of supporting voice recognition function |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106448658A (en) * | 2016-11-17 | 2017-02-22 | 海信集团有限公司 | Voice control method of intelligent home equipment, as well as intelligent home gateway |
| CN106878923A (en) * | 2017-01-09 | 2017-06-20 | 云丁网络技术(北京)有限公司 | The quick method of network entry of ultra-low power consumption intelligent equipment and intelligent domestic system |
| CN107579883A (en) * | 2017-08-25 | 2018-01-12 | 上海肖克利信息科技股份有限公司 | Distributed pickup intelligent home furnishing control method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160023089A (en) * | 2014-08-21 | 2016-03-03 | 엘지전자 주식회사 | Digital device and method for controlling the same |
-
2018
- 2018-09-12 CN CN201811060107.XA patent/CN109192205B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106448658A (en) * | 2016-11-17 | 2017-02-22 | 海信集团有限公司 | Voice control method of intelligent home equipment, as well as intelligent home gateway |
| CN106878923A (en) * | 2017-01-09 | 2017-06-20 | 云丁网络技术(北京)有限公司 | The quick method of network entry of ultra-low power consumption intelligent equipment and intelligent domestic system |
| CN107579883A (en) * | 2017-08-25 | 2018-01-12 | 上海肖克利信息科技股份有限公司 | Distributed pickup intelligent home furnishing control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109192205A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109192205B (en) | Intelligent voice interaction system and control method thereof | |
| CN104126326B (en) | System and method for the sectorized transmission of wireless network | |
| CN108933671A (en) | Power supply management method, equipment and system | |
| US20130223423A1 (en) | Terminal and method for determining priority of connection with a wireless network access point | |
| US20120116724A1 (en) | Sensor data transmission frequency controller using sensor situation information | |
| CN105072670A (en) | Sharing method for WiFi hotspot and electronic equipment | |
| KR101310968B1 (en) | Standby power control device and control method thereof | |
| CN110568771B (en) | System and method for intelligently and cooperatively controlling intelligent household equipment | |
| US20190124590A1 (en) | Wireless sensing network communication method | |
| US9609591B2 (en) | Communication device, power management system having communication device and control method of communication device | |
| CN111161522B (en) | Method for processing remote control data, storage medium, computer device and remote control system | |
| CN107171905A (en) | Home appliance distribution method and apparatus | |
| CN103249166A (en) | Method and device and system for starting RTS/CTS mechanism | |
| CN112902294A (en) | Capacity-increase-free electric heating control method and system | |
| CN112910744A (en) | Intelligent device control method and device, storage medium and electronic device | |
| CN107979641B (en) | A kind of intelligent domestic system based on cloud computing | |
| CN109831756B (en) | Operating system based on human intelligent recognition and wireless sensor network | |
| CN106412999A (en) | Load balancing method and load balancing system | |
| KR102320027B1 (en) | Voice transmission method, voice transmission apparatus implementing the same, and system including the same | |
| CN106162475A (en) | Identification of sound source system based on mike and intelligent appliance equipment | |
| CN105101347A (en) | Communication method and device of wireless local network | |
| CN116600359A (en) | Data transmission method, device, system and readable storage medium | |
| CN115019793A (en) | Awakening method, device, system, medium and equipment based on cooperative error correction | |
| KR101971170B1 (en) | System and method for socializing distributed machines based on web server | |
| JP2001108284A (en) | Transmission converting method and transmission converter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |