KR20070021414A - An Information providing method using telephone - Google Patents

Abstract

The present invention relates to a technology for providing information using a procedure of generating a word by combining a phoneme-based speech recognition and a recognized phoneme, confirming the information of the generated word, and providing the same to a customer. To this end, the present invention provides a first step of receiving a voice in a phoneme unit, a second step of recognizing the voice of the input phoneme unit and combining them into words, and searching for and obtaining information on the words combined in the second step. And a third step of providing the customer, a fourth step of searching for information using the combined word, and a fifth step of providing the customer with the information retrieved in the fourth step.

Description

An information providing method using telephone

1 is a block diagram of an information providing system according to the present invention.

2 is a flow chart of an information providing method according to the present invention.

The present invention relates to a method of providing information using a telephone, and more particularly, to increase a voice recognition rate by inputting a voice in a phoneme unit and using the voice input system, a telephone dictionary service, a telephone mail checking service, music and radio broadcasting to a customer. It is to provide services such as services.

A general web based information providing service enables a variety of information to be provided using the Internet. While the information providing service using the Internet can be provided with various and vast amounts of information, the customer can be provided with information only while connected to the Internet at all times in order to provide the service. Therefore, this service cannot be provided when the customer cannot access the Internet.

In order to solve this disadvantage, an information providing service using a telephone is provided. There is an information providing service that enables dial-up to collect and acquire necessary information through a web-based network such as the Internet, and to easily obtain various information desired by customers through a telephone connection. These services are based on the speech recognition technology to check the information desired by the customer and to search for and provide the corresponding information.

However, this speech recognition has a problem that the recognition rate is low. People's voices are different from person to person, and they may differ depending on their speaking habits. Basically, voices are not the same because the structure of the vocal cords varies from person to person. Also, in Korean, words are made by combining consonants and vowels. These combinations can produce about 100,000 combinations. Such a wide range of the voice recognition target area is a big problem to improve the voice recognition rate.

An object of the present invention to solve the above problems is to increase the speech recognition rate by using the process of recognizing speech in the minimum phoneme unit, generating a word through the analysis and combination process of the input voice, and verifying the generated word.

The information providing method using the telephone of the present invention for achieving the above object, the first step of receiving a voice in a phoneme unit; A second step of recognizing the voice of the input phoneme unit and combining the voice into words; A third step of searching for, acquiring and providing information on the words of the words combined in the second step; A fourth step of searching for information using the combined words; And a fifth step of providing the customer with the information retrieved in the fourth step.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of an information providing service system according to the present invention.

The information providing service system 100 includes an interworking function unit 110, a voice recognition unit 120, a word combining unit 130, a web dictionary unit 140, and a service providing unit 150.

The interworking function unit 110 is a function unit that is connected to the outside and connected to a communication network such as a telephone network or a mobile communication network and requests a customer to request information. The input method of the customer input through the interworking function is the main method, but the message transmission using various communication networks capable of short message service such as a mobile communication network may also be input. In this case, the message skips the speech recognition process and is transferred to the next step to be processed by a predetermined procedure.

The voice recognition unit 120 is a block for recognizing the voice input from the interworking function unit 110. The speech recognition unit 120 receives an input in a minimum phoneme unit, unlike the conventional speech recognition that recognizes all words. The voice input to the voice recognition unit 120 is input in consonants and vowels or alphabetically. For example, if the user wants to enter the word "patent", the customer using the information providing service reads 'ㅌ', 'ㅡ', 'ㄱ', 'ㅎ' and 'ㅎ' instead of reading "patent". In the case of the alphabet, it is not inputted by the pronunciation of the whole word, but is inputted by reading each letter of the alphabet. When using the existing speech recognition method, it is necessary to recognize more than 100,000 letter combinations. However, since the input pattern is limited to only 13 consonants, 10 vowels, and 26 letters, the speech recognition range is reduced and the recognition rate is increased.

The word combiner 130 is a block for combining and generating words using consonants and vowels or alphabets generated by the voice recognized by the voice recognizer 120. There may be several ways of this combination. For example, as in the case of a computer keyboard, the voice recognized by the voice recognition unit 120 may be used. Computer keyboards are not entered character by character. Each vowel or consonant is input according to the composition of the letters. In other words, when inputting a "patent" using the keyboard, the keys of the keyboard are input in the order of 'ㅌ', 'ㅡ', 'ㄱ', 'ㅎ', 'ㅓ'. This order is almost similar to the order of letters recognized by the speech recognition unit 120. Using this method, the word combination unit 130 combines words.

The web dictionary unit 140 is a block for detecting an error or the like that may occur in the word combination unit 130. Since the words combined in the word combination unit 130 are simply combined words by the input order of consonants and vowels, there may be an error in the combination process. For example, when two letters are input, two last consonants of the first letter are used and the same as the first consonant of the second letter. The web dictionary unit 140 detects such an error. In addition, the web dictionary unit 140 also performs an error check on the input in the form of a character input through a short message. The web dictionary unit 140 interlocks with the interworking function unit 110 to provide the customer with information of a corresponding word when such an input word occurs so that the customer checks whether the input word is a word for which the customer seeks information. . In this case, in the case of a word input through a short service, the word information may be provided to the short service. This can be implemented in various forms according to the intention of the person skilled in the art as a method for increasing the accuracy and reliability of the service.

The service provider 150 is a system for providing a corresponding service in the information providing service. It collects and provides the information requested by the customer by using the information request input of the customer who has passed through the web dictionary unit 140. The service provider 150 may be replaced with various service systems according to service purposes.

The dictionary service using a telephone is a service that searches a dictionary for input words that have passed through the web dictionary unit 140 and provides information on the corresponding words, and uses a voice recognition technology to voice a customer's ID and password. It is also possible to check the customer's e-mail and provide it. In order to provide such a service, a system for converting collected and acquired information into voice is required. It is to provide the requested information in the form of extracting the text of the information collected and obtained by the service system, converting it to voice, and delivering it to a customer using a communication network. Music and broadcast services can also be provided. It searches for broadcasting or music such as internet broadcasting that customers want and converts it to the telephone voice on the wire and delivers it. The implementation of such a service may be provided by using a short service, and may be provided by receiving input as a short service and providing a service requested by the user as a short service, which may be provided in various forms according to an implementation intention of those skilled in the art. Implementation is possible.

2 is a flowchart illustrating a method of providing information according to the present invention.

When a customer calls a specific telephone number providing a service to receive the information providing service and the call is connected (S2), the service desired by the customer is input to the information providing service system 100 (S4). Services provided through the information providing service system 100 may include a telephone dictionary service, an information retrieval service, a telephone mail confirmation service, and the like.

When the service is requested, the customer receives a desired query and is recognized by the information providing service system 100 (S6). The query is input in phoneme units and recognized by the information providing service system 100.

The information providing service system 100 combines words based on the recognized phonemes (S8). Search for the combined word to obtain information of the word (S10). Information of the acquired word is provided to the customer (S12), and it is checked whether the customer wants to search (S14). If the word recognized by the information providing service system 100 does not match the query word of the customer, the query word is input again by bypassing the step S6.

When the query word and the recognized word match in step S14, the recognized word is transmitted to the service provider 150 (S16). The service provider 150 searches for information using the recognized word to obtain information required by the customer (S18). The information providing service system 100 provides the searched information to the customer by using the voice guidance device (not shown) or the interworking function unit 110 (S20).

As described above, in the information providing service using a telephone according to the present invention, in a service providing information required by a customer using a telephone, a voice input is recognized by receiving a voice as a minimum syllable of a phoneme unit. The speech recognition target area is reduced, and a word is generated by combining the recognized phonemes, and the generated word information is provided to the customer, thereby improving the recognition rate and reliability of the speech recognition.

In addition, a preferred embodiment of the present invention is for the purpose of illustration, those skilled in the art will be able to various modifications, changes, substitutions and additions through the spirit and scope of the appended claims, such modifications, changes are as follows It should be regarded as belonging to the claims.

Claims (3)

Receiving a voice in a phoneme unit; A second step of recognizing the voice of the input phoneme unit and combining the voice into words; A third step of searching for, acquiring and providing information on the words of the words combined in the second step; A fourth step of searching for information using the combined words; And And a fifth step of providing the customer with the information retrieved in the fourth step. The method of claim 1, The third step is a method for providing information using a telephone, characterized in that for searching for information including the definition of the combined words using a dictionary. The method of claim 1, The fourth step is a method of providing information using a telephone, characterized in that for providing a dictionary search service using a telephone, an Internet information search service, an electronic mail confirmation using a telephone and a music or radio broadcasting providing service according to a service purpose.

Images