Transliterated search method and electronic device supporting same

A method for transliterated search of an electronic device, the method comprising:

• extracting a first text in a first language included in data stored in a memory of the electronic device;
• determining whether a transliteration pair including the extracted first text and at least one second text in a second language corresponding to the extracted first text is included in a dictionary;
• in response to identifying the transliteration pair in the dictionary, indexing the first text and the at least one second text into the data to be stored in index information;
• and
• in response to the transliteration pair not being identified in the dictionary,
• inputting the first text into a machine learning model,
• obtaining, from the machine learning model, at least one third text in the second language based on the first text,
• indexing the first text and the at least one third text into the data so as to be stored in the index information,
• determining whether a frequency at which the first text is input into the electronic device by a user or searched for within the electronic device is greater than or equal to a predetermined frequency threshold,
• based on the determination that the frequency is greater than or equal to the predetermined frequency threshold, determining whether a probability value representing an output probability of the at least one third text obtained from the machine learning model is greater than or equal to a predetermined probability threshold, and
• based on the determination that the probability value is greater than or equal to the predetermined probability threshold, inserting a transliteration pair including the first text and the at least one third text into the dictionary.

A non-transitory computer-readable medium having recorded thereon computer-executable instructions, which when executed, cause an electronic device to execute a method for transliterated search, the method comprising:

• extracting a first text in a first language included in data stored in a memory of the electronic device;
• determining whether a transliteration pair including the extracted first text and at least one second text in a second language corresponding to the extracted first text is included in a dictionary;
• in response to identifying the transliteration pair in the dictionary, indexing the first text and the at least one second text into the data to be stored in index information;
• and
• in response to the transliteration pair not being identified in the dictionary,
• inputting the first text into a machine learning model,
• obtaining, from the machine learning model, at least one third text in the second language based on the first text,
• indexing the first text and the at least one third text into the data so as to be stored in the index information,
• determining whether a frequency at which the first text is input into the electronic device by a user or searched for within the electronic device is greater than or equal to a predetermined frequency threshold,
• based on the determination that the frequency is greater than or equal to the predetermined frequency threshold, determining whether a probability value representing an output probability of the at least one third text obtained from the machine learning model is greater than or equal to a predetermined probability threshold, and
• based on the determination that the probability value is greater than or equal to the predetermined probability threshold, inserting a transliteration pair including the first text and the at least one third text into the dictionary.