Electronic device and device function search method thereof

Patent metadata

Field	Value
Publication number	US-12554729-B2
Application number	US-202418928198-A
Country	US
Kind code	B2
Filing date	Oct 28, 2024
Priority date	Nov 15, 2023
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

An electronic device and a device function search method thereof are provided. The method is adapted for the electronic device having a plurality of functions and includes the following steps. A search query is obtained through an input device. A first semantic feature vector of the search query is generated by using a natural language model. Semantic similarity between the first semantic feature vector of the search query and at least one second semantic feature vector of each function is determined. A search result corresponding to the search query is determined according to the semantic similarity between the first semantic feature vector of the search query and the at least one second semantic feature vector of each of the functions. The search result includes at least one of the functions.

First claim

What is claimed is:

1 . A device function search method, adapted for an electronic device having a plurality of functions, the method comprising:
obtaining a search query through an input device; generating a first semantic feature vector of the search query by using a natural language model; generating at least one second semantic feature vector of each of the plurality of functions according to at least one function description of each of the plurality of functions by using the natural language model, wherein the plurality of functions are provided by the electronic device for a user to set or operate; determining semantic similarity between the first semantic feature vector of the search query and at least one second semantic feature vector of each of the plurality of functions; and determining a search result corresponding to the search query according to the semantic similarity between the first semantic feature vector of the search query and the at least one second semantic feature vector of each of the plurality of functions, wherein the search result comprises at least one of the plurality of functions, wherein the plurality of functions comprises a first function, and the step of generating the at least one second semantic feature vector of each of the plurality of functions according to the at least one function description of each of the plurality of functions by using the natural language model comprises:
inputting a first function name of the first function into the natural language model to generate one of the at least one second semantic feature vector of the first function; and
inputting a second function name of the first function into the natural language model to generate another one of the at least one second semantic feature vector of the first function, wherein the first function name is a first language, and the second function name is a second language.

2 . The device function search method according to claim 1 , further comprising:
recording the at least one second semantic feature vector of each of the plurality of functions into a database.

3 . The device function search method according to claim 1 , wherein the step of generating the at least one second semantic feature vector of each of the plurality of functions according to the at least one function description of each of the plurality of functions by using the natural language model further comprises:
inputting a function feature string of the first function into the natural language model to generate another one of the at least one second semantic feature vector of the first function.

4 . The device function search method according to claim 3 , wherein the function feature string of the first function is a first language, and the search query is the first language or a second language, and the first language is different from the second language.

5 . The device function search method according to claim 1 , wherein the plurality of functions comprises the first function, and the step of determining the search result corresponding to the search query according to the semantic similarity between the first semantic feature vector of the search query and the at least one second semantic feature vector of each of the plurality of functions comprises:
determining to contain the search result of the first function when the semantic similarity between the first semantic feature vector and the at least one second semantic feature vector of the first function is greater than a preset threshold; and determining not to contain the search result of the first function when the semantic similarity between the first semantic feature vector and the at least one second semantic feature vector of the first function is not greater than the preset threshold.

6 . The device function search method according to claim 1 , wherein the step of determining the search result corresponding to the search query according to the semantic similarity between the first semantic feature vector of the search query and the at least one second semantic feature vector of each of the plurality of functions comprises:
sorting the semantic similarity corresponding to each of the at least one second semantic feature vector to obtain a similarity ranking of each of the plurality of functions; and determining at least one first function in the search result from the plurality of functions according to the similarity ranking of each of the plurality of functions.

7 . The device function search method according to claim 1 , further comprising:
establishing an initial natural language model, wherein each of a plurality of weight parameters of the initial natural language model is a floating-point number; and quantizing the plurality of weight parameters of the initial natural language model into corresponding integers to obtain the natural language model.

8 . The device function search method according to claim 1 , before the step of generating a first semantic feature vector of the search query by using the natural language model, the method further comprising:
translating the search query from the second language to the first language.

9 . An electronic device, comprising:
an input device; a storage device, recording a plurality of instructions; and a processor, connected to the input device and the storage device, and configured to execute the instructions to:
obtain a search query through the input device;
generate a first semantic feature vector of the search query by using a natural language model;
generate at least one second semantic feature vector of each of a plurality of functions according to at least one function description of each of the plurality of functions by using the natural language model, wherein the plurality of functions are provided by the electronic device for a user to set or operate;
determine semantic similarity between the first semantic feature vector of the search query and at least one second semantic feature vector of each of a plurality of functions; and
determine a search result corresponding to the search query according to the semantic similarity between the first semantic feature vector of the search query and the at least one second semantic feature vector of each of the plurality of functions, wherein the search result comprises at least one of the plurality of functions,
wherein the plurality of functions comprises a first function, the processor is configured to execute the instructions to:
input a first function name of the first function into the natural language model to generate one of the at least one second semantic feature vector of the first function; and
input a second function name of the first function into the natural language model to generate another one of the at least one second semantic feature vector of the first function, wherein the first function name is a first language, and the second function name is a second language.

Assignees

• Asustek Comp Inc

Inventors

• Lee Yi-Nan
• Liao Shih-Chieh
• Chang Chin-Hao
• Chiu Shih-Chuan
• Chuang Tzu-Hung
• Kang Chia-Hao
• Chen Wei-Cheng
• Huang Shin-Yi
• Mou Tsung Huai
• Lu Wen-Tsong

Classifications

• G06F16/243

  Natural language query formulation · CPC title

• G06F16/24578 Primary

  using ranking · CPC title