KR20190107351A - System and method for minimizing service delays for user voice based on terminal - Google Patents

Abstract

According to the present invention, disclosed are a voice conversation system centered on a terminal for minimizing service delay for a user voice and a method thereof. According to one aspect of the present invention, the system has fast response speed since a series of processing steps are made to provide a voice conversation service centered on a terminal.

Description

TECHNICAL AND METHOD FOR MINIMIZING SERVICE DELAYS FOR USER VOICE BASED ON TERMINAL}

The present invention relates to a voice conversation system, and more particularly, a terminal-centered voice conversation system that minimizes service delay for a user voice that provides a voice conversation service centered on a terminal by receiving only resources necessary for providing a conversation service from a server. And to a method.

As communication equipment and network technology have developed, users are using a voice conversation service for obtaining desired information through voice input using a terminal such as a mobile phone.

However, in the voice conversation service according to the related art, when a user inputs a voice using a terminal, the conversation service related information corresponding to the voice is obtained by performing a series of processes in a server where resources exist. As such, when the processing of the voice conversation service is made centered on the server, there is an advantage that the function can be easily updated and the service can be provided even if the terminal is changed, but there is a disadvantage that the response speed is slowed. In addition, when the server does not operate, the voice conversation system is paralyzed, and thus the voice conversation service is not provided smoothly. When the load is applied to the server, the quality of the voice conversation service provided by the users of the terminal is degraded. Occurs.

Korean Patent Publication No. 2017-0043955 (published Apr. 24, 2017)

The present invention has been proposed to solve the above problems, and receives only a resource necessary for providing a chat service from a server, and a process delay for providing a voice chat service is performed by a terminal. It is an object of the present invention to provide a terminal-oriented voice conversation system and method for minimizing.

Other objects and advantages of the present invention can be understood by the following description, and will be more clearly understood by one embodiment of the present invention. It will also be appreciated that the objects and advantages of the present invention may be realized by the means and combinations thereof indicated in the claims.

According to an aspect of the present invention, a user terminal for providing a voice conversation service for a voice spoken by a user and a resource request for providing the voice conversation service from the user terminal are provided. In a voice dialogue system including a resource server for providing a resource to a terminal, the user terminal comprises: a voice recognition unit for recognizing a user's voice to the voice spoken by the user received from the input unit; A voice conversation processing unit which analyzes the recognized user's voice and requests and receives a required resource from the resource server to process a voice conversation; A voice conversation delay processor configured to provide a delay scenario to a user when the voice conversation is not performed for a predetermined time set by the voice conversation processor; And a voice generator configured to generate a voice for providing a voice dialogue processed by the voice dialogue processor and a delay scenario provided by the voice dialogue delay processor.

The speech conversation processing unit may understand a natural language necessary for speech conversation based on a context management database composed of unstructured text data collected in advance from the recognized user's speech, and extract a key word necessary for speech conversation from the understood natural language. The voice dialogue is processed by requesting and receiving a resource for the key word from the resource server and generating a natural language corresponding to the voice spoken by the user based on the resource.

The voice conversation delay processing unit may request another voice conversation from the user or provide a list of voice conversation services that can be immediately provided to the user when the voice conversation is not processed by the voice conversation processing unit for a predetermined time. do.

According to another aspect of the present invention for achieving the above object, a user terminal for providing a voice conversation service for the voice spoken by the user and a resource request for providing the voice conversation service from the user terminal, the user A voice conversation method in a voice conversation system including a resource server for providing a resource to a terminal may include: recognizing, by the user terminal, a user's voice with respect to a voice spoken by the user; Analyzing, by the user terminal, a voice of the recognized user, requesting and receiving a required resource from the resource server to process a voice conversation; Providing, by the user terminal, a delay scenario to the user when the voice conversation is not performed for a predetermined time; And generating, by the user terminal, voice for providing the processed voice conversation and delay scenario.

Analyzing the recognized user's voice, requesting and receiving a required resource from the resource server, and processing a voice conversation, based on a context management database composed of pre-collected unstructured text data. Understanding the natural language required for speech conversation; Extracting a key word required for voice conversation from the understood natural language and requesting and receiving a resource for the key word from the resource server; And generating a natural language corresponding to the voice spoken by the user based on the received resource and processing the voice conversation.

When the voice conversation is not performed for the predetermined time period, the step of providing a delay scenario to the user may include: When the voice conversation is not processed by the voice conversation processing unit for a predetermined time, another voice conversation is performed to the user. Requesting or providing a list of voice chat services that can be immediately provided to the user.

According to an aspect of the present invention, since a series of processes for providing a voice conversation service centered on the terminal is made, the response speed is high.

In addition, since the user terminal performs a series of processes for providing the voice conversation service by requesting and receiving only the resources necessary for providing the voice conversation service from the server, the quality of the voice conversation service provided by the user is minimized by minimizing the load on the server. There is an effect to improve.

The effect obtained in the present invention is not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description. .

The following drawings attached to this specification are illustrative of the preferred embodiments of the present invention, and together with the specific details for carrying out the invention serve to further understand the technical spirit of the present invention, the present invention in such drawings It should not be construed as limited to the matters described.
1 is a diagram showing the configuration of a voice conversation system according to an embodiment of the present invention;
2 is a diagram illustrating a flow of a voice conversation method according to an embodiment of the present invention.

The above objects, features, and advantages will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, whereby those skilled in the art may easily implement the technical idea of the present invention. There will be. In addition, in describing the present invention, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Throughout the specification, when a part is said to "include" a certain component, it means that it can further include other components, without excluding other components unless otherwise stated. In addition, the “…” described in the specification. “Unit” refers to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software.

1 is a diagram illustrating a configuration of a voice conversation system according to an embodiment of the present invention.

Referring to FIG. 1, the voice conversation system according to the present embodiment includes a user terminal 100 and a resource server 200.

The user terminal 100 provides a voice conversation service for the voice spoken by the user, and the resource server 200 sends a request for a resource for providing a voice conversation service from the user terminal 100 to the user terminal 100. Provide the appropriate resources. In this case, the resource may be information for providing a voice conversation service. For example, if the voice spoken by the user is “what is the weather of today?”, The resource may be information about the weather. Meanwhile, the user terminal 100 and the resource server 200 may be connected through a network to perform communication. In this case, the network may mean a network capable of transmitting and receiving data through an internet protocol using various wired and wireless communication technologies such as an internet network, an intranet network, a mobile communication network, and a satellite communication network. Meanwhile, the network is not only a closed network such as a local area network (LAN), a wide area network (WAN), and an open network such as the Internet, but also code division multiple access (CDMA) and wide band code division multiple access (WCDMA). , Networks such as Global System for Mobile Communication (GSM), Long Term Evolution (LTE), and Evolved Packet Core (EPC), as well as future generations of networks and computing networks.

In the present embodiment, the user terminal 100 outputs an output unit 160 for receiving a voice from the user and an output unit 160 for outputting an answer thereof (for example, a chat service corresponding to the input voice). A device capable of voice communication, for example, may be a smart phone, a mobile phone, a personal digital assistant (PDA) or a portable multimedia player (PMP). It may also be a robot that can communicate.

The user terminal 100 includes an input unit 110, a voice recognition unit 120, a voice conversation processing unit 130, a voice conversation delay processing unit 140, a voice generation unit 150, and an output unit 160.

The input unit 110 may receive a spoken voice from a user and may be a device such as a microphone.

The voice recognition unit 120 recognizes the user's voice with respect to the voice spoken by the user received from the input unit 110. That is, the voice recognition unit 120 may convert the voice spoken by the user into a text form.

The voice conversation processing unit 130 analyzes the voice of the user recognized by the voice recognition unit 120 to check the necessary resources, and requests and receives the identified resources from the resource server 200 to process the voice conversation.

The voice conversation processor 130 understands the natural language necessary for the voice conversation based on a context management database composed of unstructured text data collected in advance from the recognized user's voice. Thereafter, the voice conversation processing unit 130 extracts a key word necessary for the voice conversation from the understood natural language and requests and receives a resource for the key word from the resource server 200. In more detail, the speech conversation processor 130 analyzes the speech spoken by the user, which is converted into a text form, through syntax analysis, to find the structure of the sentence and the syntactic components of each word, and to analyze the correlation between adjacent words. Key words can be extracted by identifying the collective dependencies between them. Thereafter, the voice conversation processor 130 processes the voice conversation by generating a natural language corresponding to the voice spoken by the user based on the received resource.

The natural language may be a sentence provided by an operation such as a search, a query response, or a chat of the user terminal 100. In the case of a search or a query response, the natural language may be performed through voice recognition. In this case, it is preferable that the text-based recognition result is provided as an input sentence. However, when a voice signal is simply input, the text-based recognition result may be provided to the conversation processor to generate a text-based recognition result.

In addition, the voice conversation processing unit 130 may, in particular, understand the natural language required for the voice conversation based on a context management database consisting of unstructured text data collected in advance from the recognized user's voice. After converting to, decomposing the converted text into morphological units, dummy morphemes may be added after the last morpheme, and parts of speech information and relation information between morphemes may be generated.

The voice conversation delay processing unit 140 may request another voice from the user when the voice conversation processing is not performed by the voice conversation processing unit 130. The voice conversation delay processor 140 may provide a delay scenario to the user when the voice conversation processing is not performed for a predetermined time in the voice conversation processor 130. In this case, the delay scenario is to prevent the user from being bored when the voice conversation service for the voice spoken by the user is not provided by the voice conversation processing unit 130, and requests another voice conversation to the user or to the user. This may include providing a list of voice chat services that can be provided immediately. That is, when the voice conversation is not processed by the voice conversation processor 130 for a predetermined time, the voice conversation delay processing unit 140 determines that a delay has occurred in the voice conversation service, and requests another voice conversation from the user. Alternatively, the user may provide a list of voice chat services that can be immediately provided to the user.

The voice generator 150 may generate a voice for providing a delay scenario provided by the voice conversation and the voice conversation delay processor 140 processed by the voice conversation processor 130.

The output unit 160 may output the voice generated by the voice generator 150 and provide the same to the user. The output unit 160 may be a device such as a speaker.

Meanwhile, the user terminal 100 may further include a preprocessor (not shown) for removing noise included in the voice spoken by the user. The voice may include ambient noise in addition to the voice message of the user, and accurate voice recognition may not be performed when such noise is included. Therefore, in order to solve this problem, the user terminal 100 may remove noise included in the voice spoken by the user using a preprocessor (not shown). Specifically, the preprocessor (not shown) may include any one of LowPassFilter, HighPassFilter, BandPassFilter, and set the natural frequency based on the user's voice, and apply the filter around the frequency to filter out unnecessary signals. Can be.

In addition, the user terminal 100 may further include a storage unit (not shown), the storage unit (not shown) is a program (application) for performing a voice conversation processing method (natural language understanding, context management and natural language generation, etc.) This may be stored.

In the present embodiment, the above-described components are described as operating individually, but the present invention is not limited thereto and may be controlled by a controller (not shown) to operate organically.

The resource server 200 may store information related to a resource requested by the user terminal 100.

2 is a diagram illustrating a flow of a voice conversation method according to an embodiment of the present invention.

Referring to FIG. 2, first, the user terminal 100 recognizes a user's voice with respect to a voice spoken by the user (S210).

Next, the user terminal 100 analyzes the voice of the recognized user to request and receive the necessary resources to the resource server 200 to process the voice conversation (S220).

Next, the user terminal 100 provides a delay scenario to the user when the voice conversation is not performed for a predetermined time (S230). For example, the user terminal 100 may provide a delay scenario as follows.

Delay Scenario 1

User: Please let me know your schedule for Team A this week.

System: We will let you know as soon as you find the match information. Do you have anything else you need?

User: Please tell me the weather of the day.

System: Today's weather is 19 degrees chilly, with a 60% chance of snow.

System: This is your schedule for Team A this week. This Wednesday, at 19:00 K Stadium and Friday 19:00, we will play at the X Stadium.

Delay scenario 2

User: Please let me know your schedule for Team A this week.

System: We will let you know as soon as you find the match information. Do you have anything else you need?

User: Please tell me the weather of the day.

System: Today's weather is 19 degrees chilly, with a 60% chance of snow.

System: We could not find the team A schedule you requested this week. There seems to be something wrong with the server.

As such, since the user terminal 100 provides the user voice conversation service centered on the user terminal 100 instead of the server 200, a series of processes may be performed in the terminal, thereby speeding up the response speed for the voice conversation service. . In addition, since the user terminal performs a series of processes for providing a voice conversation service by receiving and requesting only the resources necessary for providing the voice conversation service to the server 200, the user minimizes the load on the server 200 and provides the user. There is an effect that can improve the quality of the received voice chat service. In addition, by applying a delay scenario, the user may not be bored when receiving the voice conversation service.

Thereafter, the user terminal 100 generates a voice for providing the processed voice dialogue and delay scenario (S240).

Methods according to an embodiment of the present invention may be implemented in the form of program instructions that may be implemented as an application or executed through various computer components, and may be recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the computer-readable recording medium may be those specially designed and constructed for the present invention, and may be known and available to those skilled in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs, DVDs, and magneto-optical media such as floptical disks. media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform the process according to the invention, and vice versa.

While this specification includes many features, such features should not be construed as limiting the scope of the invention or the claims. In addition, the features described in the individual embodiments herein can be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment of the present specification can be implemented individually in various embodiments or in combination as appropriate.

Although the operations have been described in a particular order in the drawings, they should not be understood as being performed in a particular order as shown or in a sequence of successive orders, or all of the described actions being performed to obtain a desired result. Multitasking and parallel processing may be advantageous in certain circumstances. In addition, it should be understood that the division of various system components in the above-described embodiments does not require such division in all embodiments. The app components and systems described above may generally be packaged in a single software product or multiple software products.

The present invention described above is capable of various substitutions, modifications, and changes without departing from the technical spirit of the present invention for those skilled in the art to which the present invention pertains. It is not limited by the drawing.

1

Claims (6)

In a voice conversation system including a user terminal for providing a voice conversation service for the voice spoken by the user and a resource server for providing a resource to the user terminal when the resource request for the voice conversation service is provided from the user terminal. In
The user terminal,
A voice recognition unit for recognizing the user's voice with respect to the voice spoken by the user received from the input unit;
A voice conversation processing unit which analyzes the recognized user's voice and requests and receives a required resource from the resource server to process a voice conversation;
A voice conversation delay processor configured to provide a delay scenario to a user when the voice conversation is not performed for a predetermined time set by the voice conversation processor; And
A voice center system for minimizing service delay for a user voice including a voice generator configured to generate a voice for providing a voice conversation processed by the voice conversation processor and a delay scenario provided by the voice conversation delay processor. . The method of claim 1,
The voice conversation processing unit,
Based on the context management database consisting of the unstructured text data collected in advance from the recognized user's voice, understand the natural language required for the voice conversation, and extract the key words required for the voice conversation from the understood natural language to obtain resources for the key word. Requesting and receiving a request from the resource server to generate a natural language corresponding to the voice spoken by the user based on the resource, thereby processing the voice conversation. . The method of claim 1,
The voice conversation delay processing unit,
When the voice conversation is not processed by the voice conversation processing unit for a predetermined time,
A terminal-oriented voice conversation system for minimizing service delay for a user's voice, which requests a user for another voice conversation or provides a list of voice conversation services that can be immediately provided to the user. In a voice conversation system including a user terminal for providing a voice conversation service for a voice spoken by a user, and a resource server for providing a resource to the user terminal when a resource request for providing the voice conversation service is received from the user terminal. In the voice conversation method of,
Recognizing, by the user terminal, the user's voice with respect to the voice spoken by the user;
Analyzing, by the user terminal, a voice of the recognized user, requesting and receiving a required resource from the resource server to process a voice conversation;
Providing, by the user terminal, a delay scenario to the user when the voice conversation is not performed for a predetermined time; And
Generating, by the user terminal, a voice for providing a processed voice conversation and a delay scenario. The method of claim 4, wherein
Analyzing the recognized user's voice to request and receive the necessary resources to the resource server to process the voice conversation,
Understanding a natural language required for speech conversation based on a context management database consisting of the pre-collected unstructured text data of the recognized user's speech;
Extracting a key word required for voice conversation from the understood natural language and requesting and receiving a resource for the key word from the resource server; And
And generating a natural language corresponding to the voice spoken by the user based on the received resource to process a voice dialogue. The method of claim 4, wherein
If the voice conversation is not performed for the predetermined time period, the step of providing a delay scenario to the user may include:
If the voice conversation is not processed by the voice conversation processing unit for a predetermined time, requesting another voice conversation to the user or providing a list of voice chat services that can be immediately provided to the user. Way.

Images