Samsung electronics co., ltd. (20240160860). ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE simplified abstract

From WikiPatents
Revision as of 02:53, 23 May 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE

Organization Name

samsung electronics co., ltd.

Inventor(s)

Sungjun Lim of Suwon-si (KR)

ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240160860 titled 'ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE

Simplified Explanation

The patent application describes an electronic device and a controlling method that involve using an encoder and learning data to process information on an original text of a first language and generate encoding vectors indicating semantic information. The device can then determine the probability of the encoding vector corresponding to a normal translation and transmit the vector to an external device for translation. If the probability is low, the device identifies a similar encoding vector from the learning data and transmits it instead.

  • The electronic device includes a communicator, a memory for storing information on an encoder and learning data, and a processor for processing information on original text and generating encoding vectors.
  • The device can determine the probability of an encoding vector corresponding to a normal translation and transmit it to an external device for translation.
  • If the probability is low, the device can identify a similar encoding vector from the learning data and transmit it instead.

Potential Applications

This technology could be applied in language translation devices, machine learning systems, and communication tools.

Problems Solved

This technology helps improve the accuracy and efficiency of language translation by using encoding vectors to convey semantic information.

Benefits

The benefits of this technology include more accurate translations, faster processing of language data, and improved communication across different languages.

Potential Commercial Applications

Potential commercial applications of this technology include language translation devices, AI-powered communication tools, and machine learning systems for language processing.

Possible Prior Art

One possible prior art for this technology could be existing machine translation systems that use neural networks and encoding techniques for language processing.

Unanswered Questions

How does this technology handle complex or ambiguous language structures during translation?

The patent application does not provide specific details on how the device handles complex or ambiguous language structures during translation.

What are the limitations of this technology in terms of language pairs and translation accuracy?

The patent application does not address the limitations of this technology in terms of language pairs and translation accuracy.


Original Abstract Submitted

an electronic device and a controlling method of the electronic device are disclosed. in particular, the electronic device according to the disclosure includes a communicator, a memory configured to store information on an encoder and learning data for learning of the encoder, and a processor configured to, based on acquiring information on an original text of a first language, input the information on the original text into the encoder, and acquire a first encoding vector indicating semantic information included in the original text, input the first encoding vector into a discriminator, and acquire a probability value indicating a probability that the first encoding vector would correspond to a normal translation, based on the probability value being greater than or equal to a predetermined first threshold value, control the communicator to transmit the first encoding vector to an external device including a decoder for acquiring a translation text of a second language corresponding to the original text, and based on the probability value being smaller than the first threshold value, identify a second encoding vector having the highest similarity value indicating similarity to the first encoding vector among encoding vectors included in the learning data, and control the communicator to transmit the identified second encoding vector to the external device.