KR20190056699A - Apparatus for sound recognition, and control method thereof - Google Patents

Abstract

The present invention relates to a voice recognition processing apparatus capable of increasing service satisfaction and security of an Internet protocol television (IPTV) and an operation method thereof. According to the present invention, the voice recognition processing apparatus comprises: a checking unit checking a predetermined member having the same reference voice pattern as a predetermined voice pattern; a determination unit determining whether a predetermined service requested through a voice signal can be processed based on a personal service policy defined for the predetermined member; and a generation unit generating a processing command for the predetermined service when it is determined that the predetermined service can be processed.

Description

[0001] APPARATUS FOR SOUND RECOGNITION, AND CONTROL METHOD THEREOF [0002]

The present invention relates to a method for providing a personalized service according to a home member through a method of recognizing a voice pattern by a home member based on a voice recognition processing apparatus associated with an IPTV service.

As digital-based digital television technology has been commercialized recently, various contents can be provided through a network such as the Internet connected to each home, and IPTV (Internet Protocol Television) service is a representative example.

The IPTV service refers to a service for providing a variety of service contents including broadcast contents, Internet contents, VoD (Video on Demand) contents to a subscriber through the Internet network.

However, in such an IPTV service, one specific member of the household members becomes an IPTV service subscriber and can receive the service.

Therefore, there is a limit in that existing IPTV service can not provide personalization service for each member of the home because it can not know any information about the home member other than the subscriber.

SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and it is an object of the present invention to provide a personalization service according to a home member through a method of recognizing a voice pattern by a home member based on a voice recognition processing device associated with an IPTV service .

According to an aspect of the present invention, there is provided an apparatus for recognizing a voice in association with an IPTV service, the apparatus comprising: A verification unit for verifying a specific member having the same reference speech pattern as the specific speech pattern; A determination unit for determining whether a specific service requested through the voice signal is a processable service based on a personal service policy defined for the specific member; And a generation unit generating a processing command for the specific service and processing the specific service according to the processing command when it is determined that the specific service is a processable service.

Specifically, the speech recognition processing apparatus includes a setting registration method for setting and registering a user-specific voice pattern identified for each of two or more wake-up words as the reference voice pattern for each household member, And an automatic registration method of registering a voice pattern for each terminal identified during a router access time, which is a time at which connection of each terminal is maintained to the router to which the processing apparatus is connected, with the reference voice pattern for each member, And a registration unit for registering the pattern.

Specifically, when registering the reference voice pattern according to the automatic registration method, the register registers a voice pattern that is confirmed in a single connection state in which only the router and the specific terminal are connected, from the specific terminal Can be registered in the reference voice pattern of FIG.

Specifically, the specific terminal may include a terminal having a connection history with the speech recognition processing device, or a terminal whose access period of the router is equal to or greater than the threshold time per set period.

Specifically, the personal service policy may be defined differently for each member of the household based on at least one of a processing time limit, which is a time period during which service processing is restricted, and a process restriction service, which is a type of service for which service processing is restricted.

Specifically, the specific service is a service related to the IPTV service requested by a set-top box in a wired connection with the router, and the specific service requested by the set-top box is related to a usage pattern of the specific member in the IPTV service And can be managed as log information.

Specifically, when it is determined that the voice signal is received by two or more and that all of the services requested through the two or more voice signals are services that can be processed, It is possible to generate the processing instruction for a voice signal of a specific member whose processing time limit is short or whose number of processing restriction services is determined to be less.

According to another aspect of the present invention, there is provided a method of operating a voice recognition processing apparatus interfaced with an IPTV service, comprising the steps of: when a voice signal is received, Comparing the specific speech patterns to identify specific members having the same reference speech pattern as the specific speech patterns; A determination step of determining whether a specific service requested through the voice signal is a processable service based on a personal service policy defined for the specific member; And a generation step of generating a processing command for the specific service and processing the specific service according to the processing command when it is determined that the specific service is a processable service.

Specifically, the method may include: a setting registration method of setting a voice pattern for each user, which is confirmed for each of two or more wake-up words, And an automatic registration method of registering the voice pattern for each terminal identified during the access time of the router, which is the time at which the connection of each terminal is maintained to the router to which the voice recognition processing apparatus is connected, And a registration step of registering the reference voice pattern.

Specifically, in the registering step, when registering the reference voice pattern according to the automatic registration method, the registering step registers a voice pattern, which is confirmed in a single connection state in which only the router and the specific terminal are connected, It can be registered in the reference voice pattern of the terminal.

Specifically, the specific terminal may include a terminal having a connection history with the speech recognition processing device, or a terminal whose access time of the router is equal to or greater than a threshold time for each setting period.

Specifically, the personal service policy may be defined differently for each member of the household based on at least one of a processing time limit, which is a time period during which service processing is restricted, and a process restriction service, which is a type of service for which service processing is restricted.

Specifically, the specific service is a service related to the IPTV service requested by a set-top box in a wired connection with the router, and the specific service requested by the set-top box is related to a usage pattern of the specific member in the IPTV service And can be managed as log information.

Specifically, in the case where it is determined that the voice signal is received by two or more, and that each of the services requested through the two or more voice signals is a processable service, It is possible to generate the processing command for a voice signal of a specific member whose shortage of the processing time limit is shorter or the number of the processing restriction services is less than the number of the home members.

According to the present invention, according to the voice recognition processing apparatus and the operation method thereof, it is possible to improve the satisfaction and security of the IPTV service by providing a personalization service for each member by means of a method of recognizing a voice pattern for each member in association with the IPTV service can do.

1 is a schematic configuration diagram of an IPTV service system according to an embodiment of the present invention;
2 is a schematic configuration diagram of a speech recognition processing apparatus according to an embodiment of the present invention;
FIG. 3 and FIG. 4 are flowcharts for explaining an operation method in a voice call processing apparatus according to an embodiment of the present invention;

Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings.

1 shows a schematic configuration of an IPTV service system according to an embodiment of the present invention.

1, an IPTV service system according to an embodiment of the present invention includes a set-top box 10, a router 20, a voice recognition processing device 30, and a service server 40 Lt; / RTI >

The set-top box 10 refers to a service relay device installed in a specific place (e.g., a home) to receive an IPTV service, and can receive an IPTV service through a connection with the router 20. [

The router 20 refers to a device for providing an Internet connection environment for the set-top box 10 and is connected to the set-top box 10 in a wired manner. In addition, a wireless terminal (e.g., a smart phone) It is possible to provide a connection-based Internet access environment.

The speech recognition processing device 30 refers to a kind of artificial intelligence device that recognizes a speech signal and processes a predetermined operation according to a speech signal recognition result.

The speech recognition processor 20 may be connected to the set-top box 10 through a router 20 or directly connected to the set-top box 10 via a local communication (e.g., Bluetooth) And may have the form of a lighting device that supports the function.

On the other hand, as a speech signal recognition technique used in the speech recognition processing device 20, a known technique based on, for example, a deep learning technique can be adopted.

The service server 40 refers to a service provider that provides service contents including, for example, broadcast contents, Internet contents, VoD (Video on Demand) contents and the like related to the IPTV service. For example, A VoD server, a metadata server, a subscriber management unit, and the like.

The service server 40 may be implemented in the form of, for example, a web server, a database server, a proxy server, and the like, and may include at least one of a network load balancing mechanism, various software for allowing the service device to operate on the Internet, And can be implemented as a computerized system. The network may also be an http network and may be a private line, an intranet, or any other network, and the connection between each of the configurations in a targeting ad system according to an embodiment of the present invention may be any data And may be connected to a secure network so as not to be attacked by a hacker or other third party.

The IPTV service system according to an embodiment of the present invention can provide an IPTV service based on the above-described configuration.

However, in the general IPTV service, in this IPTV service, one specific member of the household members becomes an IPTV service subscriber and can receive the service.

Therefore, there is a limit in that existing IPTV service can not provide personalization service for each member of the home because it can not know any information about the home member other than the subscriber.

According to an embodiment of the present invention, in order to solve such a problem, a method of providing a personalization service according to a home member through a method of recognizing a voice pattern according to a home member based on the configuration of the voice recognition processing device 30 Hereinafter, the configuration of the speech recognition processing device 30 for realizing this will be described in more detail.

FIG. 2 shows a schematic configuration of a speech recognition processor 30 according to an embodiment of the present invention.

2, the voice recognition processing apparatus 30 according to an embodiment of the present invention includes a registration unit 31 for registering a reference voice pattern for each member, a confirmation unit 32 for confirming the member of the home, A determination unit 33 for determining whether the service processing is possible, and a generation unit 34 for generating a processing instruction for service processing.

The entire configuration or at least a part of the speech recognition processing device 30 may be implemented in the form of a hardware module or a software module, or a combination of a hardware module and a software module.

Here, the software module may be understood as a command executed by a processor that processes an operation in the speech recognition processing device 30, and the command may be a form embedded in a memory in the speech recognition processing device 30 have.

The speech recognition processor 30 according to an embodiment of the present invention may further include a configuration of a communication unit 35 that is an RF module that performs an actual communication function with the set-top box 10 and the router 20 .

Here, the communication unit 35 includes, but is not limited to, an antenna system, an RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a CODEC chipset, But may include all known circuits to perform.

As a result, the speech recognition processing apparatus 30 according to the embodiment of the present invention can provide a personalization service by classifying the voice patterns according to the members of the house through the above-described configuration. Hereinafter, 30 will be described in more detail.

For reference, the speech pattern herein refers to a result of discriminating a speaker (household member) who uttered a speech signal through speech recognition. As a result of analyzing a sound wave, a transliteration region characterizing the vowel or a feature equivalent thereto is extracted and separated .

The registration unit 31 performs a function of registering a reference voice pattern for each member.

More specifically, the registration unit 31 compares the reference voice pattern of the voice signal received by the voice recognition processor 30 with the reference voice pattern to identify the member in the home, Registration.

At this time, the registering unit 31 can register the reference voice pattern for each member according to the setting registration method or the automatic registration method.

Here, the setting registration method is a method for setting and registering a reference voice pattern for each member in each of two or more wake-up words supported by the voice recognition processor 30, A method of registering a voice pattern per terminal identified during a router access time, which is a time at which connection of each terminal owned by a home member is maintained with the router 20 to which the recognition processing apparatus 30 is connected, .

On the other hand, when the reference voice pattern for each member is registered without the user's intervention according to the automatic registration method, the confirmed voice pattern must be verified as the voice pattern of the member of the home.

When registering the reference voice pattern according to the automatic registration method, the registering unit 31 registers the voice pattern, which is confirmed in the single connection state in which only the specific terminal is connected to the router 31, to the specific terminal Quot ;. < / RTI >

However, as a method for verifying that a terminal having a single connection state is a terminal owned by a home member, there is a connection history with the voice recognition processing device 30, A single connection state can be recognized only for a terminal whose router access time is equal to or longer than the threshold time.

Here, the information about the connection time for each terminal connected to the router 20 can be managed in the router 20 or the set-top box 10 in the form of log information mapped to the device identification information for each terminal, Of course, can be confirmed by the speech recognition processor 30 when necessary.

The confirming unit 32 compares the voice pattern of the voice signal and confirms the member.

More specifically, when the voice signal is received after the registration of the home-based reference voice signal pattern, the verifying unit 32 compares the previously registered reference voice pattern for each home member with the specific voice pattern of the received voice signal, As a result of comparison, when there is a reference speech pattern matching the specific speech pattern, the specific member corresponding to the reference speech pattern is confirmed as a speaker that has uttered the speech signal.

For reference, when there is no reference speech signal pattern that matches the speech pattern of the speech signal, service processing through speech recognition supported by the speech recognition processor 30 can not be used at all, or only limited services can be used.

The determination unit 33 performs a function of determining whether service processing is possible or not.

More specifically, when the specific member is identified from the voice pattern of the voice signal, the determination unit 33 determines whether the specific service requested through the voice signal is a service that can be processed based on the personal service policy defined for the specific member .

Here, the personal service policy refers to a policy for providing a personalized service for each member of the household. For example, the personal service policy includes at least one of a processing time limit, which is a time limit for service processing, and a processing restriction service, Can be defined differently for each member of the home based on

Such a personal service policy can be defined through the setting of a member designated as a master (representative subscriber) among the members of the household, for example, a child in our home is divided into voices so as not to see a specific time zone or designated harmful channel, It is for the purpose of providing a variety of personalized services such as chatting in English for personalized conversation ability or storing and confirming in a personalized schedule conversation format.

Accordingly, the determination unit 33 determines whether the requested time of the service belongs to the processing time limit zone according to the personal service policy defined for the identified specific member, or whether the requested service corresponds to the processing restriction service And determine whether the requested service is a service that can be processed through the voice signal according to the confirmation result.

In this case, the service requested through the voice signal may be an IPTV service requested to the service server 40 through the set-top box 10. In this case, the service requested by the service server 40 may be a service server 40 may be managed as log information related to an IPTV service use pattern for each member of the household. Such log information may be used as a personalization service, for example, Or providing targeted advertising for individual users.

The generation unit 34 performs a function of generating a processing command for service processing.

More specifically, when it is determined that the specific service requested by the voice signal is a service that can be processed, the generating unit 34 generates a processing command for the service, and according to the generated processing command, .

In this case, the process of a specific service may refer to a process of delivering the generated command to the set-top box 10 or transmitting the generated command to the function module in the voice recognition processing device 30. [

On the other hand, it can be assumed that a voice signal is received in two or more in the case where there are two or more speakers who uttered a voice signal, and it is determined that all of the services requested through the two or more voice signals are processable services.

In this case, by generating a processing command for a voice signal of a specific member whose processing time limit is short or the number of processing restriction services is determined to be smaller in the personal service policy among the in-house members corresponding to two or more voice signals, It is possible to prevent an erroneous operation due to the failure.

As described above, according to the configuration of the voice recognition processing device 30 according to the embodiment of the present invention, by providing a per-member personalization service through a method of recognizing a voice pattern for each member, You can improve your sex. For example, if the voice is not the voice of a member of the house such as a TV sound, it is prevented from malfunctioning, the service can be provided only for the members of the house, and security can be enhanced. It is possible to secure competitiveness relative to the company, and it is possible to provide various proposal services by grasping the pattern of use by members in the house. Thus, securing the data (log information) You can expect.

Hereinafter, an operation method of the speech recognition processing device 30 according to an embodiment of the present invention will be described with reference to FIGS. 3 and 4. FIG.

3 and 4 are schematic flowcharts for explaining a method of operating the speech recognition processor 30 according to an embodiment of the present invention.

Referring to FIG. 3, the registration unit 31 identifies a home member through a method of comparing a voice pattern of a voice signal received by the voice recognition processor 30 with a reference voice pattern, The reference voice pattern is registered (S10).

At this time, the registering unit 31 can register the reference voice pattern for each member according to the setting registration method or the automatic registration method.

Here, the setting registration method is a method for setting and registering a reference voice pattern for each member in each of two or more wake-up words supported by the voice recognition processor 30, A method of registering a voice pattern per terminal identified during a router access time, which is a time at which connection of each terminal owned by a home member is maintained with the router 20 to which the recognition processing apparatus 30 is connected, .

On the other hand, when the reference voice pattern for each member is registered without the user's intervention according to the automatic registration method, the confirmed voice pattern must be verified as the voice pattern of the member of the home.

When registering the reference voice pattern according to the automatic registration method, the registering unit 31 registers the voice pattern confirmed in the single connection state in which only one specific terminal is connected to the router 31 as shown in FIG. 4, (S11-S15). [0051] In step S15, the terminal recognizes the reference voice pattern of the specific terminal.

However, as a method for verifying that a terminal having a single connection state is a terminal owned by a home member, there is a connection history with the voice recognition processing device 30, A single connection state can be recognized only for a terminal whose router access time is equal to or longer than the threshold time.

Here, the information about the connection time for each terminal connected to the router 20 can be managed in the router 20 or the set-top box 10 in the form of log information mapped to the device identification information for each terminal, Of course, can be confirmed by the speech recognition processor 30 when necessary.

3, when the voice signal is received after the registration of the home-member-referred voice signal pattern, the confirmation unit 32 determines the voice pattern of the home member and the specific voice pattern of the received voice signal If there is a reference voice pattern that matches the specific voice pattern as a result of the comparison, the specific member corresponding to the reference voice pattern is confirmed as a speaker that has uttered the voice signal (S20-S50).

For reference, when there is no reference speech signal pattern that matches the speech pattern of the speech signal, service processing through speech recognition supported by the speech recognition processor 30 can not be used at all, or only limited services can be used.

In addition, when the specific member is identified from the voice pattern of the voice signal, the determination unit 33 determines whether the specific service requested through the voice signal is a service that can be processed based on the personal service policy defined for the specific member (S60-S70).

Here, the personal service policy refers to a policy for providing a personalized service for each member of the household. For example, the personal service policy includes at least one of a processing time limit, which is a time limit for service processing, and a processing restriction service, Can be defined differently for each member of the home based on

Such a personal service policy can be defined through the setting of a member designated as a master (representative subscriber) among the members of the household, for example, a child in our home is divided into voices so as not to see a specific time zone or designated harmful channel, It is for the purpose of providing a variety of personalized services such as chatting in English for personalized conversation ability or storing and confirming in a personalized schedule conversation format.

Accordingly, the determination unit 33 determines whether the requested time of the service belongs to the processing time limit zone according to the personal service policy defined for the identified specific member, or whether the requested service corresponds to the processing restriction service And determine whether the requested service is a service that can be processed through the voice signal according to the confirmation result.

In this case, the service requested through the voice signal may be an IPTV service requested to the service server 40 through the set-top box 10. In this case, the service requested by the service server 40 may be a service server 40 may be managed as log information related to an IPTV service use pattern for each member of the household. Such log information may be used as a personalization service, for example, Or providing targeted advertising for individual users.

Then, when it is determined that the specific service requested by the voice signal is a service that can be processed, the generating unit 34 generates a processing command for the service and causes the specific service requested to be processed according to the generated processing command (S80).

In this case, the process of a specific service may refer to a process of delivering the generated command to the set-top box 10 or transmitting the generated command to the function module in the voice recognition processing device 30. [

On the other hand, it can be assumed that a voice signal is received in two or more in the case where there are two or more speakers who uttered a voice signal, and it is determined that all of the services requested through the two or more voice signals are processable services.

In this case, by generating a processing command for a voice signal of a specific member whose processing time limit is short or the number of processing restriction services is determined to be smaller in the personal service policy among the in-house members corresponding to two or more voice signals, It is possible to prevent an erroneous operation due to the failure.

As described above, according to the operation method of the voice recognition processing device 30 according to the embodiment of the present invention, by providing the per-member personalization service through the method of recognizing the voice pattern according to the home member, Security can be improved. For example, if the voice is not the voice of a member of the house such as a TV sound, it is prevented from malfunctioning, the service can be provided only for the members of the house, and security can be enhanced. It is possible to secure competitiveness relative to the company, and it is possible to provide various proposal services by grasping the pattern of use by members in the house. Thus, securing the data (log information) You can expect.

It should be understood that the functional operations and subject matter implementations described herein may be implemented as digital electronic circuitry, or may be embodied in computer software, firmware, or hardware, including the structures disclosed herein, and structural equivalents thereof, . Implementations of the subject matter described herein may be implemented as one or more computer program products, i. E. As one or more modules for computer program instructions encoded on a program storage medium of the type for control of, or for execution by, the operation of the control system Can be implemented.

The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter that affects the machine readable propagation type signal, or a combination of one or more of the foregoing.

As used herein, the term " system " or " device " encompasses any apparatus, apparatus, and machine for controlling data, including, for example, a programmable processor, a computer or a multiprocessor or computer. The control system may, in addition to the hardware, comprise code that forms an execution environment for a computer program upon request, such as code comprising a processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of these .

A computer program (also known as a program, software, software application, script or code) may be written in any form of programming language, including compiled or interpreted language, a priori or procedural language, Components, subroutines, or other units suitable for use in a computer environment. A computer program does not necessarily correspond to a file in the file system. The program may be stored in a single file provided to the requested program, or in multiple interactive files (e.g., a file storing one or more modules, subprograms, or portions of code) (E.g., one or more scripts stored in a markup language document). A computer program may be deployed to run on multiple computers or on one computer, located on a single site or distributed across multiple sites and interconnected by a communications network.

On the other hand, computer readable media suitable for storing computer program instructions and data include semiconductor memory devices such as, for example, EPROM, EEPROM and flash memory devices, such as magnetic disks such as internal hard disks or external disks, Non-volatile memory, media and memory devices, including ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuits.

Implementations of the subject matter described herein may include, for example, a back-end component such as a data server, or may include a middleware component, such as an application server, or may be a web browser or a graphical user, for example a user, who may interact with an implementation of the subject- Front-end components such as client computers with interfaces, or any combination of one or more of such back-end, middleware, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication, such as, for example, a communications network.

While the specification contains a number of specific implementation details, it should be understood that they are not to be construed as limitations on the scope of any invention or claim, but rather on the description of features that may be specific to a particular embodiment of a particular invention Should be understood. Likewise, the specific features described herein in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments, either individually or in any suitable subcombination. Further, although the features may operate in a particular combination and may be initially described as so claimed, one or more features from the claimed combination may in some cases be excluded from the combination, Or a variant of a subcombination.

It is also to be understood that although the present invention is described herein with particular sequence of operations in the drawings, it is to be understood that it is to be understood that it is to be understood that all such illustrated acts have to be performed or that such acts must be performed in their particular order or sequential order, Can not be done. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and systems will generally be integrated together into a single software product or packaged into multiple software products It should be understood that

As such, the present specification is not intended to limit the invention to the specific terminology presented. Thus, while the present invention has been described in detail with reference to the above examples, those skilled in the art will be able to make adaptations, modifications, and variations on these examples without departing from the scope of the present invention. The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

According to an embodiment of the present invention, there is provided an apparatus for recognizing a speech and an operation method thereof, the system comprising: a voice recognition processing unit connected to an IPTV service; It is possible not only to use the related technology but also to be able to carry out the application or the operation of the applicable device as well as to be practically and practically possible, .

10: Set-top box
20: Router
30: Speech recognition processing device
31: registration unit 32: confirmation unit
33: Judgment section 34:
40: service server

Claims (14)

1. A voice recognition processing apparatus interfaced with an IPTV service,
A confirming unit for comparing a reference voice pattern of each registered member of the premises with a specific voice pattern of the voice signal to identify a specific member having the same reference voice pattern as the specific voice pattern when the voice signal is received;
A determination unit for determining whether a specific service requested through the voice signal is a processable service based on a personal service policy defined for the specific member; And
And a generation unit configured to generate a processing instruction for the specific service and to process the specific service according to the processing instruction when it is determined that the specific service is a processable service. The method according to claim 1,
The speech recognition processing apparatus includes:
A setting registration method of setting a voice pattern for each user identified for each of two or more wake-up words as a reference voice pattern for each household member and registering the same; Registering the reference voice pattern according to at least one of the automatic registration methods for registering the terminal-specific voice patterns identified during the router access time, which is the time during which the connection of the terminal is maintained, with the reference voice pattern for each member of the home And the speech recognition processing unit. 3. The method of claim 2,
Wherein the registration unit comprises:
When registering the reference voice pattern according to the automatic registration method, a voice pattern that is confirmed in a single connection state in which only the router and the specific terminal are connected is registered as the reference voice pattern of the specific terminal corresponding to one of the household members And the speech recognition processing unit. The method of claim 3,
The specific terminal,
And a terminal having a connection history with the speech recognition processing device or the router access time for each set period exceeding a threshold time. The method according to claim 1,
The personal service policy may include:
A processing time limit that is a time period during which service processing is restricted, and a processing restriction service that is a type of service for which service processing is restricted, is defined differently for each member of the household. The method according to claim 1,
The specific service includes:
A service related to the IPTV service requested by a set top box in a wired connection with the router,
Wherein the specific service requested by the set-
Wherein the IPTV service is managed as log information related to a usage pattern of the specific member in the IPTV service. 6. The method of claim 5,
Wherein the generation unit comprises:
When it is determined that the voice signal is received by two or more and that all of the services requested through the two or more voice signals are serviceable, the processing time limit of the home members corresponding to each of the two or more voice signals is Wherein the processing instruction is generated for a voice signal of a specific member that is short, or the number of the processing limiting services is determined to be less. A method of operating a voice recognition processing apparatus interlocked with an IPTV service,
Comparing the reference voice pattern of each of the pre-registered household members with the specific voice pattern of the voice signal to identify a specific member having the same reference voice pattern as the specific voice pattern when the voice signal is received;
A determination step of determining whether a specific service requested through the voice signal is a processable service based on a personal service policy defined for the specific member; And
And a generation step of generating a processing command for the specific service and processing the specific service according to the processing command when it is determined that the specific service is a processible service, How it works. 9. The method of claim 8,
The method comprises:
A setting registration method for registering and registering a user specific voice pattern for each of two or more wake-up words before the checking step in the reference voice pattern for each household member, Registering a voice pattern for each terminal identified during a router access time, which is a time during which connection of each terminal is maintained with a router in the home network, according to at least one method of registering the voice pattern according to each member in the home-based reference voice pattern Further comprising a registering step of registering the speech recognition result. 10. The method of claim 9,
Wherein the registering step comprises:
When registering the reference voice pattern according to the automatic registration method, a voice pattern that is confirmed in a single connection state in which only the router and the specific terminal are connected is registered as the reference voice pattern of the specific terminal corresponding to one of the household members Wherein the speech recognition processing apparatus is a speech recognition apparatus. 11. The method of claim 10,
The specific terminal,
And a terminal having a connection history with the speech recognition processing device or the router access time for each set period exceeding a threshold time. 9. The method of claim 8,
The personal service policy may include:
A processing time limit which is a time period during which service processing is restricted, and a processing restriction service which is a type of a service whose service processing is restricted, is defined differently for each member of the household. 9. The method of claim 8,
The specific service includes:
A service related to the IPTV service requested by a set top box in a wired connection with the router,
Wherein the specific service requested by the set-
Wherein the IPTV service is managed as log information related to a usage pattern of the specific member in the IPTV service. 13. The method of claim 12,
Wherein the generating comprises:
When it is determined that the voice signal is received by two or more and that all of the services requested through the two or more voice signals are serviceable, the processing time limit of the home members corresponding to each of the two or more voice signals is Wherein the processing instruction is generated for a voice signal of a specific member whose voice signal is short, or the number of the processing restricting services is determined to be smaller.

Images