A method, device and electronic device for generating voice control instructions
A technology for voice control and command generation, applied in voice analysis, voice recognition, instruments, etc., can solve the problems of low accuracy of voice control commands and wrong digital form recognition, and achieve the effect of accurate text recognition results and guaranteed accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0040] figure 1 It is a schematic flowchart of a method for generating voice control instructions provided by an embodiment of the present invention, the method includes the following steps:
[0041] S101: Obtain text to be output according to received voice information, and identify numbers in the text to be output and positions of the numbers in the text.
[0042] In order to facilitate the user to control the smart device, the user may input voice information for control by voice. After receiving the voice information, the device controlling the smart device acquires text to be output according to the voice information. Specifically, the text to be output can be acquired through semantic recognition of the speech information.
[0043] The correct output of the digital form in the voice text will directly affect the accuracy of the overall semantic understanding of the voice text and the accuracy of the output voice control instructions. In order to correctly output each ...
Embodiment 2
[0056] In order to more accurately determine the number and the position of the number in the text to be output, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, the identification of the number in the text to be output and the number in the text The locations include:
[0057] Using the first character in the text to be output as the character to be detected;
[0058] Using the sliding window of the current length to slide to the character to be detected, and judging whether the character string in the sliding window is a character string satisfying the digital rule;
[0059] If so, update the position of the character string corresponding to the character to be detected recorded in the text, and increase the sliding window to a set length, continue according to the character to be detected and the length after the change Sliding window to judge the corresponding string;
[0060] If not, according to the recorded position of the c...
Embodiment 3
[0083] In order to further improve the accuracy of speech understanding, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, converting the numbers in the positions in the text to be output into Chinese numbers and Arabic numbers respectively includes :
[0084] Simultaneously convert the numbers belonging to the same character string in the text to be output to Chinese numbers or Arabic numbers.
[0085] Numbers belonging to the same string refer to adjacent numbers, such as the two numbers zero and one in the nine days and one early morning in the above example, the two numbers are adjacent, so the two numbers can be regarded as belonging to the same string of numbers. And when we speak, generally if a string of numbers is spoken, then the possibility of the string of numbers being both Arabic numerals or Chinese numerals is relatively high. Therefore, in the embodiment of the present invention, numbers belonging to the same charact...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More