ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE

    公开(公告)号:US20210097242A1

    公开(公告)日:2021-04-01

    申请号:US17030934

    申请日:2020-09-24

    Abstract: An electronic device is provided. The electronic device includes a memory and a processor. The processor is configured to, based on acquiring a first sentence in a first language, determine whether to correct the first sentence to another sentence in the first language by using a second language model trained based on a learning corpus, and based on determining to correct the first sentence to another sentence in the first language, input the first sentence into a conversion model trained to acquire another sentence having a similarity greater than or equal to a threshold value to an input sentence and acquire a second sentence in the first language which is a corrected form of the first sentence, and based on acquiring the second sentence, input the second sentence into a translation model trained based on the learning corpus and acquire a third sentence in a second language.

    METHOD FOR PROVIDING INFORMATION MAPPED BETWEEN A PLURALITY OF INPUTS AND ELECTRONIC DEVICE FOR SUPPORTING THE SAME

    公开(公告)号:US20190294408A1

    公开(公告)日:2019-09-26

    申请号:US16360175

    申请日:2019-03-21

    Abstract: An electronic device is provided. The electronic device includes a microphone, a touch screen display, a processor, and memory. The memory stores instructions, when executed, causing the at least one processor to: output a screen where a specified application is executed, the screen including a first interface configured to support recording a voice input through the at least one microphone and a second interface configured to receive content input of a user, on the touch screen display; pairing and storing in the memory each one of a plurality of recorded voice inputs to the first interface with a corresponding one of a plurality of content inputs to the second interface, thereby forming a voice-content pair, wherein the voice input and content input of each voice-content pair are contemporaneously recorded and received; receive a user input based on a keyword for specified content; select at least one recorded voice-content pair in response to the user input; convert recorded voice inputs of the at least one voice-content pair into text data; and output the converted text data on the touch screen display.

Patent Agency Ranking