METHOD AND APPARATUS FOR PROVIDING SERVICES USING VOICE RECOGNITION IN POS SYSTEM

• US 20130246066A1
• Filed: 10/30/2012
• Published: 09/19/2013
• Est. Priority Date: 03/14/2012
• Status: Abandoned Application

• Current Assignee: Posbank Co., Ltd.
• Original Assignee: Posbank Co., Ltd.
• Inventors: Choi, Jae Seob
• Application Number:
  US13/664,310
• Publication Number:
  US 20130246066A1
• Time in Patent Office: Days
• US Class Current: 704/246
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06Q 20/20 Point-of-sale [POS] network systems
• CPC Class Codes: G06Q 20/204 comprising interface for record bearing medium or carrier for electronic funds transfer or payment credit
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A method of providing services using voice recognition in a POS system includes loading an execution command set for each service subject provided by the POS system for each group; registering item-based voice pattern information on the execution command for each group; detecting operation mode of the POS system and activating a microphone by driving voice recognition mode in response to the detected operation mode; converting the received signal of the activated microphone into digital data, detecting properties of a sound wave from the digital data, and extracting sound wave analysis data from the detecting properties; checking whether the sound wave analysis data has been registered and assigning a service use right to the received signal according to a result of the check; and performing voice recognition conversion on the received signal, searching for an execution command having a maximum likelihood for the resulting data, and performing services corresponding to the retrieved execution command.

Claims

1. A method of providing services using voice recognition in a Point Of Sales (POS) system, the method comprising the steps of:

loading an execution command, set for each service subject that is provided by the POS system, for each group;

registering information on a voice pattern corresponding to the execution command for each item for each of the loaded groups with a voice recognition engine registration unit;

detecting operation mode of the POS system and activating a microphone by driving voice recognition mode in response to the detected operation mode;

converting a signal, received through the activated microphone, into digital data, detecting properties of a sound wave from the converted digital data, and extracting sound wave analysis data for authenticating the received signal from the detecting properties;

checking whether the extracted sound wave analysis data has been previously registered or not and assigning a service use right to the received signal according to a result of the check; and

performing voice recognition conversion on the received signal, searching for an execution command having a maximum likelihood for the resulting data, and performing one or more services corresponding to the retrieved execution command.

2. The method of claim 1, wherein the step of performing the voice recognition conversion comprises the steps of:

matching symbols and letters formed by the voice recognition and converting a result of the voice recognition into a character string based on a predetermined table; and

extracting a predetermined key value from the converted character string, loading a previously stored execution command corresponding to the extracted key value, and outputting the loaded execution command.

3. The method of claim 1, wherein the sound wave analysis data is previously obtained and registered in a form of a voice waveform consecutively interrupted and modulated from a waveform of voice in a cycle similar to a pitch cycle of the voice except a resonant component of the voice in order to modulate the specialized properties of voice for each authenticated user in the POS system.

4. The method of claim 1, wherein the received signal is obtained by eliminating interference noise from the converted digital data and amplifying the data from which the noise has been eliminated.

5. The method of claim 1, wherein the one or more services are provided in such a way as to analyze the sound wave analysis data extracted from the received signal, compare the analyzed sound wave analysis data with previously registered sound wave analysis data, assign a service use right to the received signal if, as a result of the comparison, the extracted sound wave analysis data is identical with the previously registered sound wave analysis data, and then provide the one or more services in association with an object provided for each service server in response to the execution command corresponding to the voice recognition of the received signal.

6. The method of claim 5, wherein the object comprises information on a specific product, product search service, an order, a member search, mileage accumulation, and settlement service corresponding to the execution command.

7. The method of claim 1, wherein:

the execution command set for each service subject is a default menu previously set when the POS system is initially driven, and

the execution command is set again in response to a signal of a user received through the microphone.

13. The method of claim 1, wherein the execution command comprises a product name, a service name, and a member name.

8. An apparatus for providing services using voice recognition in a Point Of Sales (POS) system, the apparatus comprising:

a microphone;

an Analog-to-Digital (A/D) converter unit configured to convert a signal, received from the microphone, into digital data;

a voice recognition engine registration unit specialized to the POS system;

a sound wave conversion unit configured to detect properties of a sound wave from the converted digital data and extract sound wave analysis data from the detected properties of the sound wave; and

a control unit configured to detect operation mode of the POS system, activate the microphone by driving voice recognition mode in response to the detected operation mode, and perform control so that the A/D converter unit converts the signal, received through the activated microphone, into the digital data, the sound wave conversion unit detects the properties of the sound wave from the converted digital data and extracts the sound wave analysis data for authenticating the received signal from the detected properties of the sound wave, whether the extracted sound wave analysis data has been previously registered or not is checked, a service use right according to a result of the check is assigned to the received signal, and voice recognition conversion is performed on the received analog voice signal.

9. The apparatus of claim 8, wherein the control unit performs control so that the voice recognition engine registration unit searches for an execution command having a maximum likelihood for the resulting data of the voice recognition conversion and provides one or more services corresponding to the retrieved execution command.

10. The apparatus of claim 8, wherein the control unit matches symbols and letters formed by the voice recognition when the voice recognition conversion is performed on the received signal, converts a result of the voice recognition into a character string based on a predetermined table, extracts a predetermined key value from the converted character string, and outputs a previously stored execution command through the voice recognition engine registration unit based on the extracted key value.

11. The apparatus of claim 8, wherein the sound wave analysis data is previously obtained and registered in a form of a voice waveform consecutively interrupted and modulated from a waveform of voice in a cycle similar to a pitch cycle of the voice except a resonant component of the voice in order to modulate the specialized properties of voice for each authenticated user in the POS system.

12. The apparatus of claim 8, wherein the voice recognition engine registration unit loads an execution command, set for each service subject provided by the POS system, for each group under the control of the control unit and registers information on a pattern of the execution command for each item for each of the loaded groups.