KR20120019011A - Interaction service providing apparatus based on combination of users' information - Google Patents

Abstract

PURPOSE: An interaction service providing device using user information combination is provided to enable a user to analyze a state and to improve the quality of a service. CONSTITUTION: A condition determining unit(130) combines inputted personal information of a user and received personal information of the other user. The condition determining unit analyzes a condition o the user and the other user based on the combined information. A service adjusting unit(140) adjusts support service information.

Description

Interaction service providing device using user information combinations {Interaction Service Providing Apparatus Based On Combination of Users' Information}

The present invention relates to a device for improving the performance of a service provided when at least two users connect and interact with their respective devices, and more specifically, by using a combination of user information of users interacting through their own devices. It relates to a device for providing a service.

The present invention is derived from a study conducted as part of the IT growth engine technology development project of the Ministry of Knowledge Economy [Task management number: 2008-S-019-02, Title: Development of portable Korean / English automatic interpretation technology].

The services provided to users by devices such as software and portable electronic devices are mostly limited to the relationship between one device and one user, but two users having their own devices interact with each other by using each device. There are also services provided.

For example, two people connect each other's devices to transfer data stored on one user's device to another user's device, and two people who speak different languages communicate with each other using their automatic interpreter. This is the case when two users with their own devices interact with each other.

The above-described automatic interpreter is a device for allowing people who speak different languages to communicate in their native language, which receives speech signals, performs speech recognition, and automatically translates the results into a second language. After that, the result is synthesized again by voice and output. In other words, by connecting two devices, the user's automatic interpreter recognizes the speech spoken by the other person's language, automatically translates the result into a second language, and translates the result into the screen of the user's automatic interpreter. It can be shown or output through speech synthesis.

On the other hand, in the case of a service limited to the relationship between the user and the device alone, the service may be provided using information of the user previously stored in the device. For example, a device that plays and outputs music may select and present music that the user may like based on the information of the user. However, in this case, the information available is limited to the general characteristics of the user, such as gender, age, interests, etc., and this information does not reflect the moment in which the user is trying to use the device, so the services provided through it are quite limited. It must be

However, when two people interact with their own devices, they can combine their information, which gives them more specific information about what they want to do and what problems they want to solve. have. And through this, the service at the time of interaction can be improved and provided more effectively.

For example, people use a variety of information when meeting and interacting directly with others. It uses the place of interaction, the appearance of the other party, and the job, status, origin, and time of the interaction and the situation before and after the interaction. For example, when a person recognizes a voice spoken by another person, he or she has various background information such as who the other person is, where the conversation takes place, when the current time is, and what they want from each other. In fact, even if you do not hear every word of the sentence spoken by the other party can use this information to determine the other person's intention.

Similarly, when two people interact with their own devices, each device combines the information of two people together, like a person, to grasp the situation, providing a service that can better assist the interaction of two users. Can provide.

However, existing service providing devices only follow the user's instructions when at least two users attempt to interact through their own devices, without understanding the situation in which the users belong, which causes inconvenience to users by providing more instructions than necessary. If the user's instructions are less specific or the device does not understand the user's instructions, there is a problem that the user cannot provide the level of service required.

The present invention was created in view of the above-mentioned problems, and connects the devices of at least two users who interact with each other using a service providing device to exchange personal information of users, and analyzes the current user's situation by combining them. Therefore, the object of the present invention is to provide an interactive service providing apparatus using a combination of user information that can improve the quality of service to be provided when users interact with each other.

In order to achieve the above object, a service providing device for interaction according to an aspect of the present invention is a device for providing a support service to the interaction using the electronic device between at least two users, the user's personal information and A situation determination unit for combining the received personal information of the counterpart user and analyzing surrounding conditions of the user and the counterpart user based on the combined information; A service adjustment unit for adjusting information and resources of the support service based on the analyzed surrounding situation; And a service provider for providing a support service suitable for the surrounding situation according to the adjusted information and resources.

According to the present invention, the personal information of at least two users attempting to interact using their respective service providing devices is combined to extract information on the current situation of users, and based on this, it is suitable for the situation in which the interaction is made. There is an effect that can provide a service.

In particular, there is an advantage that can improve the performance of the service providing apparatus can provide a service suitable for the situation in which the interaction occurs.

1 is a block diagram illustrating an interaction service providing apparatus according to an embodiment of the present invention.
FIG. 2 is a block diagram of an automatic interpreter for outputting an interpretation result for an input voice to specifically describe FIG. 1.
3 is a flowchart illustrating a process of outputting an interpretation result for an input voice according to an embodiment of the present invention.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. And is intended to enable a person skilled in the art to readily understand the scope of the invention, and the invention is defined by the claims. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. It is noted that " comprises, " or "comprising," as used herein, means the presence or absence of one or more other components, steps, operations, and / Do not exclude the addition.

When two people from different languages speak using the automatic interpreter, it is assumed that both have electronic devices equipped with the automatic interpreter. Currently, mobile electronic devices such as smart phones and netbooks are becoming popular, and automatic interpretation devices installed in PCs can be used in an environment where users can communicate through the messenger program of PCs. Is a general assumption enough

Hereinafter, an interaction service providing apparatus using a combination of user information according to an embodiment of the present invention will be described with reference to FIGS. 1 and 2. FIG. 1 is a block diagram illustrating an interaction service providing apparatus according to an embodiment of the present invention, and FIG. 2 is a block diagram of an automatic interpretation apparatus outputting an interpretation result for an input voice to specifically describe FIG. 1. It is also.

As shown in FIG. 1, the interactive service providing apparatus 100 of the present invention includes a personal information managing unit 110, a counterpart information receiving unit 120, a situation determining unit 130, a service adjusting unit 140, and a service providing unit. And 150.

The personal information manager 110 stores personal information including a job, a place of origin, a native language, an age, a gender, and an interest of the user input by the main user. For example, the personal information management unit 110 may request to input personal information when the main user first purchases and installs the interactive service providing apparatus 100, and may store personal information input by the user in response to the request.

The personal information manager 110 transmits the personal information to the situation determination unit 130 and transmits the personal information to the counterpart device 20. For example, the personal information management unit 110 may include any one of an infrared unit, a radio frequency unit, a Bluetooth unit, and a wireless LAN unit for exchanging information with the counterpart device 20 to be interacted with. The personal information of the main user is transmitted to the counterpart device 20 by using any one of communication, a radio frequency, a Bluetooth, and a wireless LAN.

The other party information receiving unit 120 receives the personal information of the other party to communicate with from the personal information manager of the person device. For example, the counterpart information receiver 120 may be equipped with devices such as infrared, radio frequency, Bluetooth, and wireless LAN to exchange information with the counterpart device 20. The counterpart information received by the counterpart information receiver 120 includes a job, a place of origin, a native language, an age, a gender, an interest, and the like, as the personal information. The other party information receiving unit 120 outputs the other party information to the situation determination unit 130.

The situation determination unit 130 determines a situation in which a current interaction is performed by combining the input personal information and the counterpart information of the main user. How the two people's personal information is combined determines the usefulness of the information combination. The situation determination unit 130 outputs the combined information to the service adjustment unit 140.

The service coordination unit 140 determines appropriate coordination information based on the input of the personal information of the two persons and the resources necessary for coordinating the service for each situation, and outputs the coordination information to the service provider 150.

The service provider 150 determines and outputs a suitable service in a situation based on the information input by the user and the adjustment information output from the service adjustment unit 140.

Hereinafter, in order to describe the interaction service providing apparatus using the user information combination in detail, the situation is determined by combining the personal information of the two users with reference to FIG. 2 and used for voice recognition and automatic translation. Explain the automatic interpreter that improves quality.

As shown in FIG. 2, the automatic interpreter 200 includes a personal information manager 210, a counterpart information receiver 220, a situation determiner 230, a language model adjuster 240, a translation resource adjuster 250, The voice recognition unit 260, an automatic translation unit 270, and a speech synthesis unit 280 are included.

The personal information manager 210 may receive personal information including a job, a place of origin, a native language, an age, a gender, a concern, and role information in a situation where the automatic interpreter 200 is used by the main user. . For example, when the automatic interpreter 200 is used for travel, the automatic interpreter 200 may play a role in a situation where the user needs an automatic interpreter such as a role of a traveler, a role of a local, or a clerk of a shop that a lot of travelers find. Information about whether to perform may be input from the user. Alternatively, when the automatic interpreter 200 is used for medical purposes, the automatic interpreter 200 may receive role information such as a role of a patient, a role of a doctor or a pharmacist. Since the role information may or may not match the user's job, the role information may be variously input by the user according to the purpose of the automatic interpretation device 200.

The personal information manager 210 outputs the personal information of the main user to the situation determiner 230. In addition, the personal information manager 210 transmits the personal information of the main user to the counterpart interpreter 30 to communicate with.

The counterpart information receiver 220 receives personal information on the counterpart to be communicated with from the personal information manager of the counterpart automatic interpreter 30. For example, the counterpart information receiving unit 220 may provide job information, a place of origin, a native language, an age, a gender, a concern, and role information in a situation in which the automatic interpreter 200 is used in the same manner as the personal information from the counterpart interpreter 30. Receives the other party information to be included, and outputs the received other party information to the situation determination unit 230.

The situation determination unit 230 determines a situation where a current conversation is made by combining the input personal information and the counterpart information of the main user. The situation determination unit 230 outputs the combined information to the language model adjusting unit 240 and the translation resource adjusting unit 250.

The language model adjusting unit 240 determines the appropriate language model based on the input combination of the two persons' personal information and the resources required for the contextual language model extraction and outputs the appropriate language model to the speech recognition unit 260.

The translation resource adjustment unit 250 determines an appropriate translation resource based on the input personal information combination and contextual translation resources of the two persons and outputs the appropriate translation resource to the automatic translation unit 270.

The speech recognizer 260 determines the most probable sentence in a given situation based on the input voice and the language model output from the language model adjuster 240 and outputs the sentence to the automatic translation unit 270.

The automatic translation unit 270 determines the most appropriate translation result in a given situation based on the input sentence and the translation resource output from the translation resource adjusting unit 250 and outputs the result to the speech synthesis unit 280.

The speech synthesizer 280 synthesizes the input sentence into speech and outputs the synthesized speech. In this case, the voice synthesizer 280 may use the voice synthesizer in the counterpart interpreter 30. In this case, a communication process of transmitting and receiving a translation result is required, and the communication device may utilize any one of communication devices belonging to the personal information management unit, such as an infrared unit, a radio frequency unit, a Bluetooth unit, and a wireless LNA unit. When speech synthesis is performed by the user's automatic interpretation device 200, the voice synthesis unit 280 for various foreign languages should be provided. However, when the other person's speech synthesis unit is used, each user has a voice corresponding to his or her language. The conversation is possible by installing only the synthesis unit.

The interaction service providing apparatus using a user information combination according to an embodiment of the present invention and an automatic interpretation apparatus for outputting an interpretation result for an input voice as a specific example thereof have been described below. The process of combining the user's information using an interpreter and converting the input voice into an interpretation result suitable for the situation will be described. 3 is a flowchart illustrating a process of outputting an interpretation result for an input voice according to an embodiment of the present invention.

Suppose a first user is a Korean, a traveler in his early twenties, and a second user is an American and a shoe store manager in his mid-fifties.

As shown in FIG. 3, when a user purchases or installs the automatic interpretation device 200 for the first time, a user is required to input personal information. The personal information manager 210 stores the input personal information (S300). By this process, the personal information is generally input once when the user first executes the automatic interpretation device 200, but may be re-entered when the user's situation changes. Personal information consists of [the language, age group, role in travel situation], the first user's personal information [Korean, early 20s, traveler], the second user's personal information [English, mid 50's, Shoe store manager].

When two people attempt a conversation with their respective automatic interpretation devices 200 and 30, they first connect the two automatic interpretation devices 200 and 30 by communication (S310). For example, two devices 200 and 30 are connected to each other through a process of searching for each other to identify a counterpart device through Bluetooth communication. Alternatively, when the acceleration sensors are installed in the two devices 200 and 30, the two devices 200 and 30 are bumped, and the two devices 200 and 30 are bumped by comparing the recorded acceleration change information. You can also use the "Bump" function to connect the two devices (200, 30).

When the two automatic interpretation devices 200 and 30 are wirelessly connected, the user information of the two devices 200 and 30 may be transferred from the personal information management unit 210 of each device 200 or 30 to the counterpart information receiving unit of the counterpart device ( 220) (S320).

Each of the automatic interpretation devices 200 and 30 transmits the personal information of the counterpart received by the counterpart information receiver 220 and the personal information of the user already stored in the personal information manager 210 to the situation determination unit 230 (S330). .

The situation determination unit 230 combines the information to extract information useful for speech recognition and automatic translation (S340), and outputs the extracted information to the language model adjusting unit 240 and the translation resource adjusting unit 250.

The language model adjusting unit 240 creates a language model that expresses sentences that may be uttered in a given situation through the input information.

The translation resource adjustment unit 250 extracts a translation resource suitable for a given situation through the input information (S350). Here, the context presentation information may be a combination of age groups of the first user and the second user and a role in the travel situation.

That is, in the situation determination unit 230, age group combination information such as [early 20s and late 50s] and role combination information of [traveler, shoe store manager] are provided to the language model adjusting unit 240 and the translation resource adjusting unit 250. can send. This process is performed at the same time in each of the two automatic interpreter (200,30).

The language model adjusting unit 240 of the automatic interpretation apparatus 200 of the first user anticipates that the first user will utter great words in the dialogue with the second user through the information [the early 20s and the late 50s], You can create a language model for that. In addition, the information "Traveler, Shoe Store Manager" can be used to predict where a particular shoe is, what size it is, and so on, so you can create a language model that fits it.

The language model adjustment unit of the automatic interpretation device 30 of the second user may expect that the second user will make a utterance explaining the store arrangement, the type of shoes, and guide the payment method through the information [traveler, shoe store manager]. You can create a language model that fits your needs. In addition, the translation resource coordination unit of the second user may retrieve a translation resource suitable for a conversation in the shoe store through the information [traveler, shoe store manager].

In the case of "Air Force," it is usually translated as "air force." But in a shoe store, it is a specific brand name. When a second user speaks "This doesn't go that small." Translation resources such as 'This doesn't go that small' but 'It doesn't come out that small' can be called.

The language model generated by the language model adjusting unit 240 is sent to the speech recognition unit 260, and the speech recognition unit 260 recognizes the voice spoken by the user based on the input language model and the voice signal and automatically converts the text into a text sentence. Output to the translation unit 270 (S360).

The translation resource extracted from the translation resource adjusting unit 250 is sent to the automatic translation unit 270, and the automatic translation unit 270 utters the user based on the input translation resource and the sentence output from the voice recognition unit 260. The voice is translated into the second language and output as a text sentence to the voice synthesizer 280 (S370).

The speech synthesizer 280 synthesizes the text sentences output from the automatic translation unit 270 into speech and outputs the speech (S380).

As described above, when each user attempts to interact using his or her own service providing device, the service providing device of each user extracts the surrounding information by combining the user's personal information and the other's personal information for interaction. And, based on this, it is possible to provide a service suitable for the situation where the interaction between each user is made.

In the above embodiment, it is assumed that all the processes of FIG. 2 are performed by the user's automatic interpreter 200, but since the speech synthesizer 280 is a device that outputs the voice to be heard by the other party, the automatic interpreter 200 automatically Translating the translation result output from the translator 270 to the other party's automatic interpreter 30, receiving the translation result from the other party's automatic interpreter 30 to display on the screen and outputs the speech synthesis results through the speech synthesizer Of course you can. In this way, when the user is configured to deliver the result of speech synthesis to the other party using his or her automatic interpreter 200, by installing a different speech synthesizer 280 according to the language used by the other party in the automatic interpreter Unlike, the user only needs to install the speech synthesizer 280 corresponding to the language of the automatic interpretation device 200 of each user.

In addition, the automatic translator 270 may be installed in the user's automatic translator 200 or by using the automatic translator of the counterpart's automatic translator 30. An automatic translation unit may be installed in a server-class computing device that can use a large amount of computation and memory at a place, and may be configured to transmit and receive voice recognition results and automatic translation results through communication.

Although the configuration of the present invention has been described in detail with reference to the preferred embodiments and the accompanying drawings, this is only an example, and various modifications are possible within the scope without departing from the spirit of the present invention. Therefore, the scope of the present invention should not be limited by the illustrated embodiments, but should be determined by the scope of the appended claims and equivalents thereof.

20: counterpart device 30: counterpart automatic interpretation device
100: interaction service providing apparatus 110: personal information management unit
120: counterpart information receiver 130: situation determination unit
140: service adjustment unit 150: service provider
160: service coordination support 200: automatic interpretation device
210: personal information manager 220: counterpart information receiver
230: situation determination unit 240: language model adjustment unit
250: translation resource adjustment unit 260: speech recognition unit
270: automatic translation unit 280: speech synthesis unit
290: Contextual Translation Resources 291: Contextual Language Model Extraction Resources

Claims (1)

An apparatus for providing a support service for interaction between at least two users using their own electronic devices,
A situation determination unit which combines input personal information of the user and personal information of the received counterpart user, and analyzes the surrounding conditions of the user and the counterpart user based on the combined information;
A service adjustment unit for adjusting information and resources of the support service based on the analyzed surrounding situation; And
A service provider for providing a support service suitable for the surrounding situation according to the adjusted information and resources
Device for providing a service for interaction comprising a.

Images