Samsung electronics co., ltd. (20240161744). ELECTRONIC DEVICES AND METHODS OF HANDLING USER UTTERANCES simplified abstract

From WikiPatents
Jump to navigation Jump to search

ELECTRONIC DEVICES AND METHODS OF HANDLING USER UTTERANCES

Organization Name

samsung electronics co., ltd.

Inventor(s)

Sangmin Park of Suwon-si (KR)

Gajin Song of Suwon-si (KR)

Kyungtae Kim of Suwon-si (KR)

ELECTRONIC DEVICES AND METHODS OF HANDLING USER UTTERANCES - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240161744 titled 'ELECTRONIC DEVICES AND METHODS OF HANDLING USER UTTERANCES

Simplified Explanation

The abstract describes an electronic device that can receive user utterance data, generate transformed utterance data based on a language model and candidate utterance data, and provide a response corresponding to the user utterance data.

  • The electronic device includes a memory storing instructions and a processor executing the instructions.
  • The processor obtains an utterance-domain data set with candidate utterance data based on the user utterance data.
  • Transformed utterance data is generated using a language model and the utterance-domain data set.
  • The response provided is based on the transformed utterance data.

Potential Applications

This technology could be applied in voice recognition systems, virtual assistants, customer service chatbots, and language translation tools.

Problems Solved

This technology helps improve the accuracy and efficiency of natural language processing systems by generating responses based on user utterances and language models.

Benefits

The benefits of this technology include enhanced user experience, faster response times, and more accurate communication in various applications.

Potential Commercial Applications

The potential commercial applications of this technology include customer service automation, language translation services, and voice-controlled devices.

Possible Prior Art

One possible prior art for this technology could be existing natural language processing systems that use language models to generate responses based on user input.

Unanswered Questions

How does this technology handle multi-language support?

This technology could potentially support multiple languages by incorporating language models for each supported language and mapping candidate utterance data accordingly.

What is the impact of user accents or speech variations on the accuracy of the transformed utterance data?

The technology may need to account for user accents or speech variations by training the language model with diverse data sets to improve accuracy in understanding and generating responses.


Original Abstract Submitted

an electronic device includes a memory storing instructions; and a processor electrically connected to the memory and configured to execute the instructions to: receive user utterance data; obtain an utterance-domain data set including candidate utterance data that is based on the user utterance data; generate transformed utterance data associated with the user utterance data based on a language model and the utterance-domain data set; and provide a response corresponding to the user utterance data, based on the transformed utterance data. the utterance-domain data set may include at least one candidate utterance data paired with each of a plurality of domains. each domain of the plurality of domains corresponds to a different operation or function.