TW201947359A - Method and system for terminal device accessing different cloud servers - Google Patents

Abstract

The present invention provides a method and a system for a terminal device accessing different cloud servers. The terminal device receives a voice message, and converts the voice message into a text, and then checks the text. The terminal device sends the voice to a first cloud server through internet when the text includes a first wake command, and the terminal device sends the voice to a second cloud server through internet when the text includes a second wake command.

Description

Voice control method and system for connecting different cloud servers

The present invention relates to voice control technology, and more particularly to a method for voice control to connect to different cloud servers.

At the end of 2016, the Market Intelligence & Consulting Institute (MIC) proposed nine major development trends for the 2017 network communications industry, namely the 5G growth wind, the car networking wind, the cross-domain merger and acquisition wind, The precision wind of film and television, the wind of action of the Internet of things, the wind of the Internet, the wind of human-machine dialogue, the wearing of wind and wind, and the cold wind at first glance. The human-machine dialogue mentioned in the nine major trends is the current discussion in the market. The rising artificial intelligence voice assistant service can be seen from the Google Trends chart. Setting the timeline to 2012 to April 2017, the voice assistant has maintained a certain amount of discussion on the Internet, but in recent years There is a clear upward trend in the future, representing that the voice assistant market is gradually taking shape, and various manufacturers are actively expanding overseas markets in order to eat the global huge voice assistant market and seize the global market share.

At present, the application and development of artificial intelligence technology are mainly based on "speech recognition" and "image recognition". According to international data information IDC (hereinafter referred to as IDC) research forecasts, the size of the artificial intelligence market in 2016 will grow rapidly from USD 8 billion in 2016 to USD 47 billion in 2020, with a compound annual growth rate of 55.1%. IEK of ITRI pointed out that the artificial intelligence industry has entered an accelerated phase in 2017, such as machine vision, voice assistants, image recognition, medical diagnosis, etc., and then has prompted the relevant industrial chain to begin to change. Smart terminal device products will begin to explode.

IDC said that almost all industries are expected to inject a living water through the profit brought by the ability of artificial intelligence to process data, and once again drive the industry's growth. At this stage, the main industries that have adopted artificial intelligence systems are mainly financial, retail, medical and discrete manufacturing. The total output value of these four industries has accounted for 50% of the 2016 market size. Field development.

IDC research shows that if differentiated by regional market, North America accounts for 78% of the global market's output value with a market size of 6.2 billion US dollars. Europe, the Middle East, and Africa occupy the second place. Although the Asia-Pacific region currently has a slower development than other regions, the rapid growth rate is expected to win the second place in the market size by 2020. Looking at the growth rate, it is predicted that the Japanese market will have a compound annual growth rate of 114.9% from 2015 to 2020, followed by 63.9% in Asia Pacific except Japan, 36.2% in South America, 54.5% in the United States, and Western Europe. 50.1%. If you want to seize the huge market brought by voice assistants, it will depend on whether the system provides multi-language recognition capabilities.

Voice devices are a market that major brands are vying for, and they are also regarded as the next computing platform behind computers and smartphones. The vendors that currently provide speech recognition services on the market include: Amazon.com's Alexa, Apple's Siri, Facebook's Facebook M, Google's Google Assistant, and Samsung's Bixby. Each manufacturer's voice assistant has its strengths and weaknesses. However, most of the terminal devices appearing on the market can only use the voice assistant of a certain manufacturer, and cannot be used across platforms. This is not an optimal use environment.

The main purpose of the present invention is to provide a method and system for voice control to connect to different cloud servers, which can use voice control to connect to different network servers on a single terminal device.

In order to achieve the above-mentioned object and effect, the method for voice control connecting to different cloud servers disclosed in the present invention is a method for voice control connecting to different cloud servers, for a user to use a terminal device and connect to a first by voice control The cloud server or a second cloud server includes the following steps:

1. Provide a voice message to a terminal device;

2. Convert the voice message into a text in the terminal device;

3. Check whether the text contains a first wake-up instruction or a second wake-up instruction;

4. If the text contains a first wake-up instruction, send the voice message to a first cloud server; if the text contains a second wake-up instruction, send the voice message to a second cloud server; If the text does not include the first wake-up instruction and the second wake-up instruction, repeat step 1 to step 4.

In one embodiment, after receiving the voice message, the terminal device temporarily stores the voice message in a buffer unit.

In one embodiment, after the voice message is converted into the text, the text is temporarily stored in the buffer unit.

In one embodiment, the voice message is transmitted to the first cloud server or the second cloud server through a network.

The present invention further provides a system for voice-controlled connection to different cloud servers, including: a terminal device, a network, a first cloud server, and a second cloud server.

The terminal device includes: an audio receiving unit that receives a voice message; an audio conversion unit that converts the voice message into a text; and a comparison unit that checks whether the text contains a first wakeup instruction or a second wakeup Instruction; a network connection unit, if the text contains the first wake-up instruction, the voice message is transmitted to a first cloud server through the network; if the text contains the second wake-up instruction, the voice The message is sent to a second cloud server through the network.

In one embodiment, the terminal device further includes a buffer unit for storing the voice message and the text.

In one embodiment, the terminal device further includes a sleep wakeup unit and a central processing unit. When the comparison unit finds that the text contains the first wakeup instruction or the second wakeup instruction, the sleep wakeup unit wakes up at The central processing unit in the sleep mode, the central processing unit will capture the voice message in the buffer unit, connect to the network through the network connection unit, and send the voice message to the first cloud server or Is the second cloud server.

The above-mentioned objects and advantages of the present invention can be obtained from the detailed description and accompanying drawings of selected embodiments described below.

FIG. 1 shows a schematic diagram of a voice control system provided by a preferred embodiment of the present invention, which includes a terminal device 10, a network 12, and a plurality of cloud servers 14, 16, 18. The terminal device 10 may be an electronic device, such as a smart phone, a tablet computer, a laptop computer, a desktop computer, and a personal digital assistant. digital assistant (PDA), or other specific electronic products. Please refer to FIG. 2. In this embodiment, the terminal device 10 is a smart phone and has at least: an audio receiving unit 20, a buffer unit 22, an audio conversion unit 24, a comparison unit 26, A sleep wake-up unit 28, a central processing unit 30, and a network connection unit 32. In addition, an application (APP) (not shown) is installed in the terminal device 10 to perform various actions described below.

In this embodiment, the audio receiving unit 20 may be a microphone or other equivalent device for receiving voice messages. The voice message received by the audio receiving unit 20 includes environmental sounds and sounds emitted by users. The voice message received by the audio receiving unit 20 may be temporarily stored in the buffer unit 22 or directly transmitted to the audio converting unit 24 for related processing.

The main function of the audio conversion unit 24 is to convert the voice message received by the audio receiving unit 20 into text. The audio message received by the audio receiving unit 20 is an analog signal, so when the audio conversion unit 24 receives the audio message from the audio receiving unit 20, it first converts the analog voice message to digital The voice message, and then a digital filter filters out the ambient sound in the digital voice message, leaving the voice emitted by the user. Finally, the audio conversion unit 24 converts the filtered digital voice message into text, and temporarily stores the text in the buffer unit 22. The content described above is a commonly known speech recognition technique, which is a technique well-known to those having ordinary knowledge in the technical field, and its content is not described in detail herein.

The function of the comparison unit 26 is to check whether a specific wake-up instruction exists in the text. A normal executable voice message usually consists of two parts, beginning with the "wake command" and then followed by the "executing command". For example: "Siri, call Wang Datou." Among them, "Siri" is a wake-up command, which wakes up the terminal device 10 from a sleep state to work state; "calls Wang Datou" is an execution command, instructing the terminal device 10 to be raised by the contact person's telephone number of Wang Datou And make a dialing action.

In this embodiment, we set three connectable cloud servers, which are defined as: a first cloud server 14, a second cloud server 16, and a third cloud server 18. The audio conversion unit 24 stores three wake-up commands in advance, which are a first wake-up command, a second wake-up command, and a third wake-up command. The comparison unit 26 first checks whether the first wake-up instruction exists in the text. If the result of the check is that the first wake-up instruction is present in the text, the sleep wake-up unit 28 is commanded to wake up the central processing in the sleep mode. Unit 30. The central processing unit 30 converted from the sleep mode to the working mode will capture the voice message in the buffer unit 22, connect to the network 12 through the network connection unit 32, and transmit the voice message to the first cloud server器 14。 14. If the result of the check is that the text does not have the first wake-up instruction, the comparison unit 26 then checks whether the text has the second wake-up instruction.

As before, if the result of the check is that the text has the second wake-up instruction, the sleep wake-up unit 28 is commanded to wake up the central processing unit 30 in the sleep mode. The central processing unit 30 converted from the sleep mode to the working mode will capture the voice message in the buffer unit 22, connect to the network 12 through the network connection unit 32, and transmit the voice message to the second cloud server器 16。 16. If the result of the check is that the text does not have the second wake-up instruction, the comparison unit 26 then checks whether the text has the second wake-up instruction. If the result of the check is that the text does not have the second wake-up instruction, the comparison unit 26 then checks whether the text has the third wake-up instruction. If the result of the check is that the third wake-up instruction is included in the text, the sleep wake-up unit 28 is commanded to wake up the central processing unit 30 in the sleep mode. The central processing unit 30 converted from the sleep mode to the working mode will capture the voice message in the buffer unit 22, connect to the network 12 through the network connection unit 32, and transmit the voice message to the third cloud server器 18。 18.

If the checking result of the comparison unit 26 is that the first, the second and the third wake-up instructions are not included in the text, no action is taken, the system remains in the sleep mode, and the audio receiving unit 20 then Receive voice messages continuously and repeat the steps previously described.

It should be particularly mentioned here that the first, the second and the third wake-up instructions can be user-defined content, such as: "Hello, smart speaker!" Or content specified by the cloud server For example, if the first cloud server 14 is a cloud server of Apple Inc., the first wake-up command may be "Siri".

In an embodiment, we set the first cloud server 14 as a cloud server of Amazon.com, and the first wake-up command is "Alexa". When a user says "Alexa, Yesterday Once More by The Carpenters". After receiving the audio message, the audio receiving unit 20 converts the audio message into a text through the audio converting unit 24. Then, the comparison unit 26 inspects the content of the text and finds that the first wake-up instruction (Alexa) is included. Therefore, the wake-up unit 28 wakes up the central processing unit 30 to change from the sleep mode to the working mode. The central processing unit 30 then extracts the voice message from the buffer unit 22 and uploads the voice message to the Amazon company's cloud server through the network connection unit 32. After the server executes the execution instruction (plays "Yesterday Once More" of The Carpenters), obtains the audio file of the song and returns it to the terminal device 10, and starts the player program of the terminal device 10 to play the song.

In one embodiment, we set the second cloud server 16 as a cloud server of Apple Inc., and the second wake-up command is "Siri". When a user says "Hi Siri, navigate to No. 185, Section 2, Xinhai Road, Daan District, Taipei City". After receiving the audio message, the audio receiving unit 20 converts the audio message into a text through the audio converting unit 24. Then, the comparison unit 26 inspects the content of the text and finds that the second wake-up instruction (Siri) is included. Therefore, the wake-up unit 28 wakes up the central processing unit 30 to change from the sleep mode to the working mode. The central processing unit 30 then extracts the voice message from the buffer unit 22 and uploads the voice message to the Apple cloud server through the network connection unit 32. After the server executes the execution instruction (navigation to No. 185, Section 2, Xinhai Road, Da'an District, Taipei City), the corresponding map is called back to the terminal device 10, and then the GPS signal of the terminal device 10 is used to display the The superscript is the location of the terminal device 10 for navigation.

In one embodiment, we set the third cloud server 18 as a server for remotely controlling electrical appliances, which can control the electrical appliances in the user's home through the network 12, and the third wakeup command is "Skill platform ". When a user says "Skill platform, turn on the air conditioner and adjust the temperature to 25 ° C". After receiving the audio message, the audio receiving unit 20 converts the audio message into a text through the audio converting unit 24. Then, the comparison unit 26 inspects the content of the text and finds that the third wake-up instruction (Skill platform) is included. Therefore, the wake-up unit 28 wakes up the central processing unit 30 to change from the sleep mode to the working mode. The central processing unit 30 then extracts the voice message from the buffer unit 22 and uploads the voice message to the remote control server through the network connection unit 32. After the server executes the execution instruction (turn on the air conditioner and adjust the temperature to 25 ° C), it is connected to the air conditioner 34 through the network 12, and the power of the air conditioner 34 is turned on to start operation, and the temperature is adjusted to 25 ° C.

The above description is only an illustration to illustrate the present invention, and does not limit the present invention in any form. The scope of the claimed rights of the present invention shall be based on the scope of the patent application, rather than being limited to the above embodiments. Any person with ordinary knowledge in the technical field can make use of the disclosed technical content to make some changes or modifications to equivalent embodiments without departing from the scope of the technical solution of the present invention. The contents of the technical solutions are still within the scope of the technical solutions of the present invention.

10‧‧‧Terminal device

12‧‧‧Internet

14‧‧‧First Cloud Server

16‧‧‧Second Cloud Server

18‧‧‧ Third Cloud Server

20‧‧‧Audio receiving unit

22‧‧‧ buffer unit

24‧‧‧ Audio Conversion Unit

26‧‧‧ Matching Unit

28‧‧‧sleep wake unit

30‧‧‧ Central Processing Unit

32‧‧‧Network Connection Unit

34‧‧‧Air conditioner

FIG. 1 is a schematic diagram of a preferred embodiment of the present invention. FIG. 2 is a block diagram of a Chinese speech recognition system according to a preferred embodiment of the present invention. FIG. 3 is a flowchart of a preferred embodiment of the present invention. FIG. 4 is a schematic diagram of a preferred embodiment of the present invention, showing the state of the first cloud server operated by voice. FIG. 5 is a schematic diagram of a preferred embodiment of the present invention, which shows the state of voice-operated second cloud server. FIG. 6 is a schematic diagram of a preferred embodiment of the present invention, showing the status of the third cloud server operated by voice.

Claims (7)

A method for voice-controlled connection to different cloud servers, for a user to use a terminal device to connect to a first cloud server or a second cloud server using voice control, including the following steps: 1. Provide a voice Message to a terminal device; 2. converting the voice message into a text in the terminal device; 3. checking whether the text contains a first wakeup instruction or a second wakeup instruction; 4. if the text contains a first wakeup instruction A wake-up command to send the voice message to a first cloud server; if the text includes a second wake-up command, send the voice message to a second cloud server; if the text does not include the first The wake-up instruction and the second wake-up instruction are repeated from step 1 to step 4. According to the method for voice control connection to different cloud servers described in the first patent application scope, in step 1, after receiving the voice message, the terminal device temporarily stores the voice message in a buffer unit. The method for connecting voice control to different cloud servers according to item 2 of the patent application scope, wherein in step 1, after the voice message is converted into the text, the text is temporarily stored in the buffer unit. The voice control method for connecting different cloud servers according to the first patent application scope, wherein in step four, the voice message is transmitted to the first cloud server or the second cloud server through a network. A system for voice-controlled connection to different cloud servers includes: a terminal device, a network, a first cloud server, and a second cloud server. The terminal device includes: an audio receiving unit for receiving Voice message; an audio conversion unit that converts the voice message into a text; a comparison unit that checks whether the text contains a first wake-up command or a second wake-up command; a network connection unit, as in the text Including the first wake-up command to transmit the voice message to a first cloud server through the network; if the text includes the second wake-up command to transmit the voice message to a second cloud server through the network Device. For example, the voice control system described in claim 5 of the patent application connects to different cloud servers, wherein the terminal device further includes a buffer unit for storing the voice message and the text. For example, the system for voice control connecting to different cloud servers as described in the scope of patent application 5, wherein the terminal device further includes a sleep wakeup unit and a central processing unit. When the comparison unit finds that the text contains the first wakeup instruction Or the second wake-up command, the sleep wake-up unit wakes up the central processing unit in the sleep mode, the central processing unit captures the voice message in the buffer unit, and connects to the network through the network connection unit , Sending the voice message to the first cloud server or the second cloud server.