Artificial intelligence voice interaction method, computer program product, and near-end electronic device thereof

1. An artificial intelligence voice interaction method for a user to employ a near-end electronic device and can be fulfilled by a remote artificial intelligence server, the method comprising the following steps:

receiving a voice input by the user;

when a sound energy comparison value is greater than a start threshold, recording the voice first, then transmitting the voice to the remote artificial intelligence server;

determining whether the voice has ended by the near-end electronic device;

calculating a sound energy value and a previous sound energy;

comparing the sound energy value with the previous sound energy value to obtain the sound energy comparison value;

determining whether the sound energy comparison value is less than an end threshold;

if the sound energy comparison value is less than the end threshold, determining whether the sound energy comparison value is not greater than the start threshold and is not less than the end threshold within a time interval;

if the sound energy comparison value is not greater than the start threshold and not less than the end threshold within the time interval, it is determined that the voice has ended;

when the voice is determined to be ended by the near-end electronic device or a stop recording signal is transmitted by the remote artificial intelligence server, the voice is stopped recording, then stopped transmitting to the remote artificial intelligence server; and

receiving a response signal sent back from the remote artificial intelligence server.

2. The artificial intelligence voice interaction method as claimed in claim 1 , wherein the step of determining whether the voice has ended includes determining whether the voice is a complete sentence.

3. The artificial intelligence voice interaction method as claimed in claim 1 , wherein the sound energy value is calculated every 0.2 sec.

4. The artificial intelligence voice interaction method as claimed in claim 1 , wherein the time interval is 0.6 sec.

5. The artificial intelligence voice interaction method as claimed in claim 1 , stops recording the voice after recording for more than 10 sec.

6. A non-transitory computer-readable storage medium used in a near-end electronic device for implementing the method as claimed in claim 1 .

7. A near-end electronic device, used by a user and connected to a remote artificial intelligence server via a network, the near-end electronic device comprising:

a microphone, which is used for receiving a voice input by the user; a transmission module, which is electrically connected to the microphone for transmitting the voice to the remote artificial intelligence server; a near-end processing module, which is electrically connected to the transmission module;

a sound energy calculation module, which is used for calculating a sound energy and a previous sound energy to obtain a sound energy comparison value, the near-end processing module determining whether the sound energy comparison value is greater than a start threshold or less than an end threshold; if the sound energy comparison value is greater than the start threshold, the near-end processing module records the voice, then transmits the voice to the remote artificial intelligence server; if the sound energy comparison value is less than the end threshold, the near-end processing module determining whether the sound energy comparison value is not greater than the start threshold and is not less than the end threshold within a time interval; if the sound energy comparison value is not greater than the start threshold and not less than the end threshold within the time interval, then the near-end processing module determining that the voice has ended; wherein when the near-end processing module determining that the voice has ended or a stop recording signal is transmitted by the remote artificial intelligence server, it stops recording the voice, then stops transmitting the voice to the remote artificial intelligence; and

a voice module, which is electrically connected to the near-end processing module for emitting a response signal sent back from the remote artificial intelligence server.

8. The near-end electronic device as claimed in claim 7 , wherein the near-end processing module determines whether the voice is a complete sentence to know if the voice has ended.

9. The near-end electronic device as claimed in claim 7 , wherein the sound energy calculation module calculates the sound energy comparison value every 0.2 sec.

10. The near-end electronic device as claimed in claim 7 , wherein the time interval is 0.6 sec.

11. The near-end electronic device as claimed in claim 7 , wherein the near-end processing module stops recording the voice after the recording time exceeds 10 sec.

12. An artificial intelligence voice interaction method for a user to employ a near-end electronic device and can be fulfilled by a remote artificial intelligence server, the method comprising the following steps:

receiving a voice input by the user;

transmitting the voice to the remote artificial intelligence server;

calculating a sound energy value and a previous sound energy by the near-end electronic device;

comparing the sound energy value with the previous sound energy value to obtain the sound energy comparison value;

determining whether the sound energy comparison value is less than an end threshold;

if the sound energy comparison value is less than the end threshold, determining whether the sound energy comparison value is not greater than a start threshold and is not less than the end threshold within a time interval;

if the sound energy comparison value is not greater than the start threshold and not less than the end threshold within the time interval, it is determined that the voice has ended;

when determining that the voice has ended and has not received a stop recording signal transmitted by the remote artificial intelligence server, it stops transmitting the voice to the remote artificial intelligence server;

before determining that the voice has ended, and has received the stop recording signal from the remote artificial intelligence server, it stops transmitting the voice to the remote artificial intelligence server; and

receiving a response signal sent back from the remote artificial intelligence server.

13. The artificial intelligence voice interaction method as claimed in claim 12 , wherein when the sound energy comparison value is greater than the start threshold, the step of recording the voice is performed.

14. The artificial intelligence voice interaction method as claimed in claim 13 , further comprising the following steps:

recording the voice first before transmitting the voice to the remote artificial intelligence server; and

stopping recording the voice before stopping transmitting the voice to the remote artificial intelligence server.

15. The artificial intelligence voice interaction method as claimed in claim 14 , wherein the step of determining whether the voice has ended includes determining whether the voice is a complete sentence.