CN107004020B

CN107004020B - Terminal device and data processing method thereof

Info

Publication number: CN107004020B
Application number: CN201580066773.2A
Authority: CN
Inventors: 赵相旭; 金瑜娜
Original assignee: Samsung Electronics Co Ltd
Current assignee: Samsung Electronics Co Ltd
Priority date: 2014-12-08
Filing date: 2015-12-03
Publication date: 2021-06-01
Anticipated expiration: 2035-12-03
Also published as: KR102386739B1; KR20160069456A; EP3230902A2; EP3230902A4; CN107004020A

Abstract

A terminal device is provided. The terminal device includes: a communication interface configured to perform communication with an external device at the start of a chat; a display configured to display a chat message transmitted and received through the communication interface; a memory; and a processor configured to classify the chat message into a plurality of conversation sessions, store keywords defining the respective classified conversation sessions on the memory, and provide, through the display, a conversation session matching at least one keyword among the plurality of keywords stored on the memory when an event associated with the at least one keyword occurs.

Description

Terminal device and data processing method thereof

Technical Field

The present disclosure relates to a terminal device and a data processing method thereof. More particularly, the present disclosure relates to a terminal device configured to provide analysis and search based on a dialogue unit by classifying chat messages transmitted and received in the past as the dialogue unit, and a data processing method thereof.

Background

The development of electronic technology has made it possible to provide various services through personal terminal devices. A user can easily talk to another user of another terminal device through the terminal device such as a smartphone. For example, a user may send and receive chat messages to and from other users by using a terminal device.

The user's chat messages that have been transmitted to and received from another user may be stored in a terminal device or a server providing a chat service, and the user may read past chat messages.

However, the user must read the conversation one by one starting from a plurality of chat messages currently to the messages stored in the past in order to read a specific part of the conversation made in the past. In this process, it may be difficult for the user to correctly find the portion of the conversation he needs to read, and sometimes it takes a significant amount of time to do so.

Recent terminal devices are providing a message search function to solve the above-described problems. However, the message search function simply searches for and finds chat messages that include text that matches the text entered by the user.

A user who searches for (search through) past chats may want to read how a conversation is conducted, or with whom or on which subject, but cannot easily do so with the message search function of the existing terminal device unless the user checks past chat messages one by one.

The foregoing is presented merely as background information to assist in understanding the present disclosure. No determination is made as to whether any of the above is applicable as prior art to the present disclosure, nor is it asserted.

Disclosure of Invention

Technical scheme

Aspects of the present disclosure are directed to solving at least the above problems and/or disadvantages and to providing at least the advantages described below. Accordingly, an aspect of the present disclosure is to provide a terminal device that provides analysis and search based on a dialogue unit by classifying chat messages transmitted and received in the past as the dialogue unit, and a data processing method thereof.

According to one aspect of the present disclosure, a terminal device is provided. The terminal device includes: a communication interface configured to perform communication with an external device at the start of a chat; a display configured to display chat messages sent and received through the communication interface; a memory; and a processor configured to classify the chat message into a plurality of conversation sessions and to store on the memory keywords defining respective classified conversation sessions.

The processor may provide a dialog session matching at least one keyword through a display when an event associated with at least one keyword of a plurality of keywords stored on the memory occurs.

The processor may check transmission time or reception time of each chat message and classify the chat messages transmitted and received for a duration exceeding a certain time interval as conversation sessions different from each other.

The processor may classify the conversation session into different conversation sessions based on a time point of sending or receiving a chat message including a specific word.

The processor integrates the plurality of dialog sessions into one dialog session when the plurality of dialog sessions are stored on the memory and keywords on the plurality of dialog sessions are associated with each other.

In response to an input of a user manipulation selecting at least a portion of the plurality of chat messages displayed on the display, the processor may determine chat messages within a range corresponding to the input user manipulation as one conversation session.

When a conversation session is completed during a chat, the processor may provide a graphic effect to notify an end of the conversation session by display, and determine a chat message within a range corresponding to the graphic effect as a conversation session in response to a user-manipulated input agreeing to the end of the conversation session.

The processor may control the display to display a User Interface (UI) screen for editing a previously defined keyword with respect to a particular dialog session in response to a user-manipulated input for editing the keyword.

When an event for inputting a keyword for searching the dialog session occurs, the processor may display a list of dialog sessions corresponding to the input keyword on the display.

The processor displays a chat region and an associated conversation region on a screen of the display, respectively, displays chat messages transmitted and received through the communication interface on the chat region, and displays a conversation matching the displayed keyword on the associated conversation region when an event that one of the plurality of keywords stored in the memory is displayed on the chat region occurs.

The processor may display a chat region and an associated conversation session region on a screen of the display, respectively, display chat messages transmitted and received through the communication interface on the chat region, and display a conversation session matching a previous keyword on the associated conversation session region when an event occurs in which the keyword of the conversation session including the chat messages displayed on the chat region matches the previous keyword stored on the memory.

In response to a user-manipulated input selecting the conversation session, the processor may display a new chat screen on the display that includes the chat messages within the selected conversation session.

The processor may control the display to display a background image associated with the keyword for defining a particular conversation session on the chat screen while displaying a chat message within the particular conversation session on the chat screen.

The processor may determine the keywords for each conversation session based on at least one of conversation participants, conversation topics, conversation intents, and conversation times for each conversation session.

The terminal device may additionally include a sensor configured to sense at least one state regarding a location of the terminal device, a movement of the terminal device, an ambient temperature of the terminal device, and an ambient humidity of the terminal device. The processor may determine a keyword for defining the conversation session including the input chat message based on information sensed by the sensor at a time when the chat message is input.

The processor may receive a keyword stored in another terminal device through the communication interface, and determine a popular keyword based on the received keyword and the keyword stored on the memory.

The processor may display the auto-suggested words on the display while inputting text, and may select the displayed auto-suggested words from the popular keywords.

According to another aspect of the present disclosure, a data processing method of a terminal device is provided. The data processing method comprises the following steps: the method includes classifying previously stored chat messages into a plurality of conversation sessions, storing keywords on a storage of the terminal device for defining the respective classified conversation sessions, and providing a conversation session matching at least one keyword through a display of the terminal device when an event associated with the at least one keyword among the plurality of keywords stored on the storage occurs.

The classification may include checking time points at which respective chat messages are transmitted or received, and classifying the chat messages transmitted and received for a duration exceeding a certain time interval into conversation sessions different from each other.

The classifying may include classifying the chat messages including the specific word into different conversation sessions with each other based on the transmission time or the reception time.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable recording medium including a program for executing the data processing method. The data processing method comprises the following steps: the method includes classifying previously stored chat messages into a plurality of conversation sessions, storing keywords defining respective classified conversation sessions at the terminal device on a memory of the terminal device, and providing a conversation session matching at least one keyword through a display of the terminal device when an event associated with the at least one keyword among the plurality of keywords stored in the memory occurs.

Other aspects, advantages, and salient features of the disclosure will become apparent to those skilled in the art from the following detailed description, which, taken in conjunction with the annexed drawings, discloses various embodiments of the disclosure.

Drawings

The above and other aspects, features and advantages of certain embodiments of the present disclosure will become more apparent from the following description when taken in conjunction with the accompanying drawings, in which:

fig. 1 is a block diagram provided to illustrate a terminal device according to an embodiment of the present disclosure;

fig. 2, 3, and 4 are diagrams provided to illustrate methods for classifying dialog sessions according to various embodiments of the present disclosure;

fig. 5 and 6 are diagrams provided to illustrate methods for determining a dialog session according to various embodiments of the present disclosure;

FIG. 7 is a block diagram provided to illustrate a method for determining keywords for defining a conversation session in accordance with an embodiment of the present disclosure;

fig. 8 is a diagram provided to explain a method for providing a keyword of a terminal device according to an embodiment of the present disclosure;

fig. 9, 10, 11, 12 and 13 are diagrams provided to illustrate methods for providing dialog sessions according to various embodiments of the present disclosure;

FIG. 14 is a diagram provided to illustrate a method for sharing keywords according to an embodiment of the present disclosure;

FIG. 15 is a diagram provided to illustrate a method of using keywords, according to various embodiments of the present disclosure;

fig. 16 is a diagram provided to explain an operation between a terminal device and an external server according to an embodiment of the present disclosure;

FIG. 17 is a block diagram provided to illustrate a terminal device according to an embodiment of the present disclosure; and

fig. 18 is a flowchart provided to explain a data processing method of a terminal device according to an embodiment of the present disclosure.

It should be noted that throughout the drawings, like reference numerals are used to depict the same or similar elements, features and structures.

Detailed Description

The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of various embodiments of the disclosure as defined by the claims and their equivalents. It includes various specific details to aid understanding, but these specific details should be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the various embodiments described herein can be made without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and constructions may be omitted for clarity and conciseness.

The terms and words used in the following description and claims are not limited to bibliographic meanings, but are used only by the inventors to enable a clear and consistent understanding of the disclosure. Accordingly, it will be apparent to those skilled in the art that the following descriptions of the various embodiments of the present disclosure are provided for illustration only and not for the purpose of limiting the disclosure as defined by the appended claims and their equivalents.

It is to be understood that the singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a component surface" includes reference to one or more such surfaces.

Although expressions such as "first" or "second" may be used to describe various constituent elements, these expressions should not limit the constituent elements in any way. These terms are only used to distinguish one constituent element from another.

The expressions used throughout the present disclosure are used for the purpose of explaining specific embodiments and are not to be construed as limiting. Expressions such as "comprises" or "comprising" used in the present disclosure are used to indicate the presence of the features, numbers, steps, operations, constituent elements, components or combinations thereof described herein, but are not to be understood as excluding the possibility of the presence or addition of one or more other features, numbers, steps, operations, constituent elements, components or combinations thereof.

In describing certain embodiments of the present disclosure, the term "module" or "portion" may be provided to perform at least one or more functions of an operation, and may be implemented as hardware or software, or a combination of hardware and software. Furthermore, a plurality of "modules" or "portions" may be implemented as at least one processor (not shown) integrated into at least one module, except for "modules" or "portions" that must be implemented as specific hardware.

Fig. 1 is a block diagram provided to illustrate a terminal device according to an embodiment of the present disclosure.

Referring to fig. 1, the terminal device 100 includes a memory 110, a display 120, a processor 130, and a communication interface 140.

The terminal device 100 may be implemented as a device that can transmit and receive chat messages to and from another terminal device. For example, the terminal device 100 may be implemented as any of a variety of electronic devices, such as a desktop computer, a smart phone, a tablet Personal Computer (PC), a laptop computer, a Portable Media Player (PMP), a Moving Picture Experts Group phase1or phase 2 (MPEG-1 or MPEG-2) audio layer 3(MP3) player, a Television (TV), and a wearable device (e.g., a smart watch). As used herein, a "chat message" refers to any of various forms of data, such as text, sound, or images, that a user sends to and receives from another user by using an electronic device. For text, these may be referred to as "text messages", for example, or for voice, as voice messages, for example.

The memory 110 is configured to store a plurality of programs and data necessary for driving of the terminal device 100. The memory 110 may be implemented as a nonvolatile memory, a volatile memory, a flash memory, a Hard Disk Drive (HDD), or a Solid State Drive (SSD). The memory 110 may be accessed by the processor 130, and the processor 130 may perform reading, recording, modifying, deleting, and updating with respect to data in the memory 110. According to embodiments of the present disclosure, the term "memory" as used herein may encompass the memory 110, a Read Only Memory (ROM) (not shown) and a Random Access Memory (RAM) (not shown) within the processor 130, or a memory card (not shown) mounted to a server (e.g., a micro secure digital (micro-SD) card or memory stick).

The memory 110 may store chat messages transmitted to and received from another terminal device and also store various pieces of information on the chat messages. For example, the memory 110 may store information about the chat message such as transmission and reception times of the chat message or a transmitter or receiver of the chat message.

In addition, the memory 110 may store various pieces of information stored by the user. For example, the memory 110 may store various pieces of information such as schedule information (calendar information) or yellow pages (address book) input by the user. For example, the address book may include relationship information set by the user. For example, a user may store phone numbers under categories such as "family" and "friends". According to an embodiment of the present disclosure, which will be described below, schedule information and relationship information may be used to determine keywords regarding a conversation session.

Further, the memory 110 may store data indicating a result of classifying the chat messages transmitted and received with other users into a plurality of conversation sessions. In addition, the memory 110 may also store index information regarding the location of each dialog session. The index information about the location may be used to move from the current chat screen to the chat screen of the past conversation session. In addition, the memory 110 may store keywords for defining respective dialog sessions, and the keywords may be mapped with the dialog sessions and stored, respectively.

Further, the memory 110 may store an image to be used as a background image of the chat screen that has been classified by category. The background image on the chat screen may be changed according to user settings or contents of the chat conversation. As will be described below, the processor 130 may generate a background image on the chat screen by selecting an image suitable for a keyword defining a conversation session.

Further, the memory 110 may store connection information necessary to connect communication with other terminal devices. In this case, the connection information may be information on encryption for directly connecting between the terminal devices.

The display 120 may display various images under the control of the processor 130. According to an embodiment of the present disclosure, the display 120 may be implemented as a touch screen in combination with a touch sensor. The touch sensor may be implemented in a capacitive or resistive manner. The capacitive manner refers to the use of a dielectric material coated on a surface and senses the micro electricity excited by the user's body and calculates touch coordinates when a portion of the user's body touches on the surface of the display 120. The resistive type refers to the use of two electrode plates, and senses current flow when a user touches the screen causing the upper and lower plates on a touch point to contact each other, and calculates a contact coordinate. Accordingly, various types of touch sensors may be implemented as described above.

Display 120 may display chat messages sent and received through communication interface 140. According to an embodiment of the present disclosure, the display 120 may display chat messages classified according to conversation sessions under the control of the processor 130. In addition, the display 130 may arrange and display the keywords stored in the memory 110.

The communication interface 140 is configured to transmit and receive various data to and from an external device. A communication interface 140 may be provided to connect the terminal device 100 with an external device. The external device may be connected through a Local Area Network (LAN) and the internet. Further, the wireless communication method (e.g., such as Z-wave, Internet protocol version 4(Internet protocol version 4over low power wireless personal area network, 4LoWPAN), Radio Frequency Identification (RFID), long term evolution device to device (LTE D2D), Bluetooth low energy (Bluetooth low energy, BLE), General Packet Radio Service (GPRS), Bluetooth, edge ZigBee, ANT +, Near Field Communication (NFC), infrared data association (infrared data association, IrDA), digital enhanced telecommunication (digital enhanced telecommunication, wireless LAN, a Universal Mobile Telecommunications System (UMTS), LTE, wireless broadband (WiBRO), and the like) performs connection.

For example, terminal device 100 may be connected to a chat service provider server, or also to other terminal devices, through communication interface 140.

The processor 130 is configured to control the overall operation of the terminal device 100. For example, the processor 130 may control the overall operation of the terminal device 100 using various programs stored in the memory 110. For example, the processor 130 may include a Central Processing Unit (CPU), a RAM, a ROM, or a system bus. As described herein, ROM is configured to store a set of commands for system startup. The CPU may copy an operating system (O/S) stored in the memory 110 onto the RAM according to a command stored in the ROM and start the system by implementing the O/S. When the startup is completed, the CPU may copy various applications stored on the memory 110 onto the RAM and perform various operations by implementing the copied applications. Although it is described herein that the processor 130 includes only one CPU, in practical implementations, the processor 130 may be implemented as multiple CPUs (digital signal processors (DSPs) or system on chips (socs)).

For example, processor 130 may classify chat messages sent and received over communication interface 140 into a plurality of conversation sessions. As used herein, a "conversation session" refers to a unit of a conversation that includes a plurality of chat messages entered by a particular user within a certain time. Thus, a conversation session may include at least two or more chat messages.

Processor 130 may classify chat messages sent and received over communication interface 140 into a plurality of conversation sessions according to various criteria. For example, processor 130 may automatically classify conversation sessions based on data obtained through chat messages or classify conversation sessions according to user manipulations that specify conversation sessions. A method for classifying the dialog sessions will be described below with reference to fig. 2 to 4.

Fig. 2-4 are diagrams provided to illustrate methods used by a terminal device to automatically classify dialog sessions according to various embodiments of the present disclosure.

Referring to fig. 2, the processor 130 may check transmission or reception times of respective chat messages and classify the transmitted and received chat messages exceeding a certain time interval into conversation sessions different from each other. For example, processor 130 may determine that a new conversation session begins when the sending and receiving time intervals of successive chat messages match or exceed a preset time. For example, as shown in fig. 2, processor 130 may determine that conversation session 1 is complete and conversation session 2 is beginning when the interval between the time of transmission (PM 2:00) of first chat message 10 and the time of receipt (PM 7:00) of second chat message 12 is equal to or greater than one hour.

Further, referring to fig. 3, the processor 130 may classify the conversation sessions to be different from each other based on a time point of transmitting or receiving a chat message including a specific word. For example, the memory of the terminal device 100 may previously store data on a topic replacement word or a topic replacement sentence, and the processor 130 may determine that a new conversation session starts when the chat message includes the topic replacement word or the topic replacement sentence. For example, the topic replacement word may be "hi", "what? "or" hello ". As shown in fig. 3, when the chat message 14 includes the word "hi", the processor 130 may determine that conversation session 1 is complete and conversation session 2 begins.

Meanwhile, data on topic replacement words or sentences may be manually input and stored one by one, or may be collected through machine learning. As used herein, "machine learning" refers to a field of artificial intelligence that involves developing algorithms and techniques for computer learning. For example, when the user directly specifies a conversation session, the processor 130 may statistically analyze a word included in the first chat message of the conversation session specified by the user and know that the word is a topic replacement word.

According to an embodiment of the present disclosure, when a plurality of dialog sessions are stored on the memory 110, and when keywords related to the plurality of dialog sessions are associated with each other, the processor 130 may integrate the plurality of dialog sessions into one dialog session.

For example, referring to fig. 4, processor 130 may determine dialogs 1-3 as an overall dialog session based on keyword correlations that define dialog sessions 1-3, respectively. For example, as shown in fig. 4, the processor 130 may determine a preset number of (e.g., two) chat messages as one conversation session and keywords for respectively defining the conversation sessions (a method for determining the keywords for defining the conversation sessions will be described below). When the keywords defining dialog sessions 1 through 3 are determined to be the same or associated, processor 130 may determine dialog sessions 1 through 3 as one overall dialog session.

Meanwhile, in this case, even when the keyword for defining the dialog session 2 of fig. 4 is not associated with the dialog sessions 1 and 3, the processor 130 may determine the dialog sessions 1 to 3 as one overall dialog session. This would allow the conversation session to continue uninterrupted even if the user briefly talks about another topic during the chat.

For example, when a conversation session is determined to start (e.g., in response to an input of a chat message after one hour, or when a topic replacement word is included in the chat message), processor 130 may determine a preset number of chat messages after the conversation session starts as conversation session 1, and determine a first keyword for defining conversation session 1. Further, the processor may determine a preset number of chat messages input thereafter as the conversation session 2, determine a second keyword for defining the conversation session 2, and compare the second keyword with the first keyword. When it is determined that the first keyword and the second keyword are not associated with each other, the processor 130 may recognize the dialog session 1 and the dialog session 2 as being different from each other. Further, the processor 130 may determine a preset number of chat messages input after the dialog session 2 as dialog session 3, and determine a third keyword for defining the dialog session 3. When it is determined that the third keyword is associated with the second keyword as a result of the comparison, the processor 130 may recognize the dialog session 2 and the dialog session 3 as one session. Conversely, when the third keyword and the second keyword are determined to be unassociated with each other, the processor 130 may compare the first keyword and the third keyword. When it is determined that the first keyword and the third keyword are associated with each other, the processor 130 may recognize the dialog sessions 1 to 3 as one overall dialog session. According to the embodiments of the present disclosure, there is provided an effect in which all dialogs exchanged between users can be treated as one dialog session based on the entire context of the dialogs even when the users briefly talk about different subjects during chatting.

As described above, the dialog sessions may be automatically classified by operation of the processor 130. An embodiment of the present disclosure in which a dialog session is classified by a user will be explained below with reference to fig. 5 to 6.

Fig. 5 is a diagram provided to explain a method of classifying a dialog session by a user according to an embodiment of the present disclosure.

Referring to fig. 5, the terminal device 100 includes an inputter for receiving a user manipulation. The inputter may be implemented in the form of a touch screen combined with the display 120. In response to an input of a user manipulation for selecting at least a portion of the plurality of chat messages displayed on the display 120, the processor 130 may determine a chat message within a range corresponding to the input user manipulation as one conversation session.

For example, as shown in fig. 5, according to drag manipulation 3 on the touch screen, the processor 130 may determine a chat message within a range corresponding to the drag manipulation 3 as one dialog session. Drag manipulation 3 is only one of the various embodiments of the present disclosure, and thus, any manipulation for specifying the scope of the chat message may be applied. According to the embodiments of the present disclosure, since a dialog session can be manually determined by a user, an effect can be obtained that management of a dialog session can be performed by considering user opinions.

Fig. 6 is a diagram provided to explain a method of classifying a dialog session by a user according to an embodiment of the present disclosure.

Referring to fig. 6, when a conversation session is completed during a chat, the processor 130 may provide a graphic effect 60 through the display 120 to inform the end of the conversation session. Accordingly, the processor 130 may sense the end of the conversation session (e.g., sense the occurrence of a topic replacement word) and display the graphical effect 60 according to the description above. For example, the graphical effect 60 may be a flashing dashed box 60 surrounding chat messages included in a conversation session, as shown in FIG. 6. In response to user-manipulated input agreeing to the end of the conversation session, the processor 130 may determine a chat message within a range corresponding to the graphical effect 60 as one conversation session. In this case, as shown in fig. 6, the processor 130 may display a User Interface (UI)62 to the user on the display 120 to ask whether he or she agrees with the end of the dialog session. In response to the user-manipulated input selecting OK in menu 62a, processor 130 may determine the chat message within the box as graphical effect 60 as a conversation session.

When determining a conversation session, processor 130 may determine keywords defining the conversation session by analyzing chat messages within the conversation session. A method for determining a keyword for defining a dialog session will be explained below.

As used herein, "keyword for defining a dialog session" refers to index information for searching the dialog session. In accordance with embodiments of the present disclosure, the term "keyword" as used herein may be used to indicate two or more words or sentences and a combination of words. The determined keyword may be shared with another user of the other terminal device, which may be described further below.

There may be one or more keywords that define a dialog session. For example, the keyword may be determined based on at least one of a conversation participant, a conversation time, a conversation topic, a word associated with the conversation, and a conversation intent regarding the conversation session. "conversation participant" can refer to either the sender or the recipient of a chat message, and "conversation time" can refer to the time it takes to send and receive chat messages within a conversation session, or the time periods mentioned in chat messages. The "conversation related word" may refer to a word/sentence included in a chat message of a conversation session, or a superordinate word or related word with respect to the word/sentence. For example, when words such as "Galaxy S5" and "Galaxy Note" are mentioned in the conversation session, the upper-level word may be determined as a keyword such as "smartphone". Further, "dialog intent" may refer to a user intent of a target word, which may be classified mainly by analyzing verbs of sentences. For example, when the conversation topic is "travel" and the intent is "go," the user intent may be determined as a travel itinerary across the entire context of the conversation.

For example, the processor 130 may analyze a chat message included in the conversation session and extract an entity and an intention of a chat message sentence by using Natural Language Understanding (NLU), data mining, or the like. NLU is a field of artificial intelligence that deals with machine-reading understanding. NLUs and data mining are readily understood in the art and are not described further herein.

During the extraction, semantics may be used, social relationship information (e.g., a phone book or a Social Network Service (SNS)) previously stored in the memory 110 may be used with respect to a person to enhance clarity of extraction, and schedule information previously stored in the memory 110 may be used with respect to a schedule. The process of determining the keyword will be described below with reference to fig. 7.

Fig. 7 is a diagram provided to explain a method of determining a keyword for defining a dialog session according to an embodiment of the present disclosure.

Referring to fig. 7, the processor 130 may extract and analyze words/sentences such as "las vegas", "your milk", "our travel", "this weekend", "victory", "rainy", "my meeting here", "weekend" or "coming here" from a certain conversation session, and determine the following keywords by analyzing the extracted words/sentences. For example, "Lory" and "Jessica" may be determined as participant keywords, "June travel" may be determined as topic keywords, and "Las Vegas", "Lory's milk", "places of goodness", and "weekends" may be determined as related words. In this case, the milk of Lory can be determined based on the word "your". Thus, the keyword may be determined by considering the sender or recipient of the chat message. In addition, schedule changes and a schedule check may be determined as the dialog intention keywords.

Meanwhile, when the memory 110 of the terminal device 100 stores the schedule of travel on the weekend in the previously stored schedule information, the processor 130 may extract the keyword "travel" from the word "this weekend". Further, when a person is mentioned in the conversation session, the processor 130 may determine a relationship between the person mentioned in the conversation session and the user who inputs the chat message as a keyword by using a phone book (address book) previously stored in the memory 110. For example, when the chat message includes "James", and when "James" is designated as a brother based on the relationship information of the phonebook, keywords "brother" and "family" may be extracted. In addition to the phone book, information about social relationships registered on the SNS may be used to determine keywords.

Further, relationship information regarding whether a conversation participant is recently known, or how long the conversation participant has been known, may be categorized based on the frequency with which chat messages are sent and received by the user. Thus, the processor 130 may determine the keyword based on the above information.

Meanwhile, the range of the extension keyword may depend on user settings. For example, the user may set whether to extend the keyword by using social relationship information on a phone book or SNS, or to extend the keyword into a higher-level concept of the extracted keyword.

Meanwhile, according to an embodiment of the present disclosure, the terminal device 100 may further include a sensor (not shown) to sense at least one state of a position of the terminal device 100, movement of the terminal device 100, an ambient temperature of the terminal device 100, and an ambient humidity of the terminal device 100.

For example, the terminal device 100 may include a Global Positioning System (GPS) receiver. The GPS receiver may receive GPS signals from GPS satellites and calculate the current position of the terminal device 100.

Further, the processor 130 may determine the movement of the terminal device 100 through a motion recognition sensor provided on the terminal device 100. The motion recognition sensor may sense a posture change based on at least one axis of the three-dimensional axes. For example, the motion recognition sensor may be implemented as various sensors such as a gyro sensor, a geomagnetic sensor, or an acceleration sensor. The acceleration sensor may output a sensing value corresponding to a gravitational acceleration that varies according to an inclination of the device in which the sensor is installed. While performing the rotation, the gyro sensor may measure a coriolis force applied toward the velocity direction and calculate an angular velocity. The geomagnetic sensor may sense an azimuth angle.

Further, the processor 130 may determine the ambient temperature and the ambient humidity of the terminal device 100 through temperature and/or humidity sensors provided on the terminal device 100.

The terminal device 100 can determine the state of the terminal device 100 using the various units described above, and use the state information for determining the keyword of the dialogue session.

For example, based on information sensed by the sensor at a time when the chat message is input, the processor 130 may determine a keyword for defining a conversation session including the input chat message. For example, when the user inputs a chat message "i see my friends here" in a south area, which is a south area of korea, by using the terminal device 100, the processor 130 may recognize that the location of the terminal device 100 is the south area when the chat message is input through the GPS receiver. Therefore, at a point of time when a chat message is input, keywords for defining a conversation session may include a south of the river region.

For another example, at a time when a chat message is input, the processor 130 may analyze movement information of the terminal device 100 by using a gyro sensor or a gravity sensor and determine whether the user is exercising. Therefore, even when there is no information about exercise in the chat message, the keyword for defining the dialog session at the time point when the chat message is input may include "exercise".

For another example, the processor 130 may obtain the ambient environment information of the terminal device 100 at a time point when the chat message is input through a temperature and/or humidity sensor. Based on the above, even if there is no information on weather in the chat message at the point of time when the chat message is input, "rainy" or "hot" can be selected as a keyword for defining a conversation session.

According to various embodiments of the present disclosure including the above description, the entire context of a conversation generated by a chat message can be understood because the chat message can be comprehensively analyzed based on various pieces of information, rather than simply analyzing text to analyze the chat message.

The processor 130 may store keywords for the dialog sessions that respectively define the classifications on the memory. Further, the processor 130 may provide the determined keyword to the user or update the keyword according to a user manipulation for editing the determined keyword. The above may be further described below with reference to fig. 8.

Fig. 8 is a diagram provided to explain a method for providing a keyword of a terminal device according to an embodiment of the present disclosure.

Referring to fig. 8, the processor 130 may display a keyword with respect to the determined dialog session in response to a preset user-manipulated input after the dialog session is determined. For example, as shown in fig. 8, in response to a user-manipulated input double-clicking on a region displaying chat messages within a conversation session, the processor 130 may display a UI 80 including a list of keywords used to define the conversation session corresponding to the clicked region. The user can confirm at least one keyword used to define the dialog session, delete the keyword or add a new keyword through the UI 80. For example, when the edit menu 82 is selected, the keywords within the UI 70 may be changed to an editable form.

When an event associated with at least one keyword of the plurality of keywords stored in the memory 110 occurs, the processor 130 may provide a dialog session matching the at least one keyword through the display 120.

For example, when an event occurs in which a keyword is input to search for a dialog session, the processor 130 may display a dialog session list corresponding to the input keyword on the display 120. The above may be further described below by referring to fig. 9.

Fig. 9 is a diagram provided to explain a method for providing a dialog session according to an embodiment of the present disclosure.

Referring to fig. 9, the processor 130 may display a UI 90 on the display 120 to search for a dialog session, and the user may search for a dialog session through the UI 90. One or more keywords for searching the conversation session may be entered, and these keywords may be associated with participants, topics, time, or intent of the conversation session.

The processor 130 may control the display 120 to display a list UI 92 of dialog sessions corresponding to the entered keywords. The list UI 92 may include an image representing the conversation session, the date the conversation was conducted, or information about the participants of the conversation.

The processor 130 may use the relationship data stored on the memory 110 in a keyword search. For example, in response to input of the keyword "friend," the processor 130 may search for and provide a conversation session of a person in which a person designated as a friend of the user is mentioned, based on relationship information included in the phonebook stored on the memory 110. Further, the processor 130 may provide search results based on information about the frequency of conversations. For example, in response to input of the search term "stranger," the processor 130 may search for and provide a dialog session of: where people who communicate little conversation are mentioned, or where people who communicate little conversation are the conversation participants themselves. For another example, in response to an input of the keyword "smartphone", a dialog session including lower words such as "Galaxy S5" or "Galaxy Note" may be searched for and provided.

Fig. 10 is a diagram provided to explain a method for providing a dialog session according to an embodiment of the present disclosure.

Referring to fig. 10, the processor 130 may display a chat area 30 and an associated conversation session area 32 on the screen of the display 120, respectively, and display chat messages transmitted and received through the communication interface 140 on the chat area 30, and in response to an occurrence of an event that displays one of keywords stored on the memory 110 on the chat area 30, the processor 130 may display a conversation session matching the displayed keyword on the associated conversation session area 32. For example, while the user is entering a chat message that includes "the study," processor 130 may display a list of conversation sessions that match "the study" on the associated conversation session region 32.

Further, processor 130 may display a chat region and an associated conversation session region on a screen of display 120, respectively, and display chat messages transmitted and received through communication interface 140 on chat region 30, and in response to an occurrence of an event in which a keyword of a conversation session including a chat message displayed on chat region 30 corresponds to a previous keyword stored on memory 110, processor 130 may display a conversation session matching the previous keyword in associated conversation session region 32. According to an embodiment of the present disclosure, a past conversation session suitable for a conversation topic about which a chat is currently being performed can be provided.

According to the embodiments of the present disclosure described above, when the inputter 140 is implemented as a touch panel, the associated dialog session region 32 may be displayed on the screen in response to the swipe manipulation 1. Further, the associated dialog session region may be displayed in a blooming shape.

When the user selects one from the list of dialog sessions displayed on the associated dialog session region 32, the processor 130 may display the selected dialog session over the entire region of the associated dialog session region 32. Otherwise, the processor 130 may display the selected dialog session over the entire area of the screen.

Meanwhile, in response to a user-manipulated input for selecting a conversation session, the processor 130 may display a new chat screen including chat messages within the selected conversation session on the display 120, according to an embodiment of the present disclosure. Hereinafter, the above is described by referring to fig. 11.

Fig. 11 is a diagram provided to explain a method for generating a new chat screen with a conversation session according to an embodiment of the present disclosure.

Referring to fig. 11, the user may designate a dialog session by direct drag as shown in fig. 5. Further, processor 130 may generate and display a new chat screen with a user-specified conversation session on display 120. Thus, as shown in FIG. 11, a new two-person chat room 22 can be created by replicating chat messages shared in group chat room 20. According to an embodiment of the present disclosure, a user can generate a new chat screen by selecting a necessary portion on a current chat screen. Thus, when a first and second conversation participant is sending and receiving chat messages in the chat dimension for a group conversation, and when a third participant is not interested in the conversation, the first and second conversation participants can replicate the conversation and generate a new chat screen, enabling the conversation to continue in the dimension for both.

Further, a new chat screen may be generated according to the method described below. For example, as described with reference to fig. 9, the user may be provided with a list of dialog sessions corresponding to the search term by inputting the search term. Further, as described with reference to fig. 10, a list of conversation sessions may be provided to the user on one area of the screen while the current chat is being performed. Thereafter, by selecting one of the conversation sessions on the provided list, the user can generate a new chat screen with the selected conversation session.

According to the above-described embodiment of the present disclosure, the user can acquire a dialog from a past dialog session, in addition to simply reading the past dialog session.

Fig. 12 is a diagram provided to explain a method for providing a dialog session according to an embodiment of the present disclosure.

Referring to fig. 12, each time a new chat message is input on the chat screen, the past chat message moves upward and disappears. In response to input of user manipulation 2 for selecting a particular conversation session on the chat screen 34 in which the current chat is performed, the processor 130 may control the display 120 to automatically scroll the current chat screen toward the selected conversation session.

For example, the memory 120 may store location information of a conversation session on a chat screen and keywords for defining the conversation session. Thus, the processor 130 may automatically scroll towards past dialog sessions based on the location information. According to the embodiments of the present disclosure, in addition to a quick movement toward a past dialog session, a user can easily confirm dialogs before and after the dialog session.

Meanwhile, according to the above-described various embodiments of the present disclosure, various operations may be performed by using a keyword defining a dialog session. For example, while displaying chat messages within a particular conversation session on a chat screen, processor 130 may control display 120 to display keywords and associated background images defining the particular conversation session on the chat screen. Hereinafter, the above will be described by referring to fig. 13.

Fig. 13 is a diagram provided to explain a process of converting a background image on a chat screen according to an embodiment of the present disclosure.

Referring to fig. 13, when a dialog session is determined (e.g., in response to the occurrence of a topic replacement word/sentence), the processor 130 may determine a keyword for defining the determined dialog session and search the memory 110 for an image corresponding to the determined keyword. In addition, the processor 130 may display the searched image as a background image on the chat screen. In this case, when there are a plurality of keywords for defining a conversation session, a keyword regarding the subject of the conversation session may be selected as a keyword used in searching for an image. Accordingly, when the topic keyword for defining the current dialog session is "travel", the current background image 1300-1 may be changed to the background image 1300-2 suitable for travel. Meanwhile, according to an embodiment of the present disclosure, a smaller image associated with a keyword may be displayed on a portion of a screen (such as an upper portion of the screen) instead of displaying a background image on the entire area of the screen. According to an embodiment of the present disclosure, a user may be provided with a chat background screen suitable for chatting an image of a currently shared conversation topic.

Meanwhile, the processor 130 may arrange and display the keywords stored on the memory 110 on the display 120 according to an embodiment of the present disclosure. In this case, the processor 130 may display the keywords on the display 120 according to the order of the keywords most frequently used when defining the dialog session (i.e., according to the popularity order). In addition, the processor 130 may display popular keywords by expanding the size of characters on the display 120. Otherwise, the keywords may be organized and displayed according to a statistical order. For example, under the upper category of travel, business travel, family travel, and vacations may be organized and displayed into lower categories.

According to the above-described embodiments of the present disclosure, the user can recognize the conversation subject of his or her previous conversation at a glance through the keyword, and can also know the subject he or she mainly discusses in the conversation.

Further, in response to a user-manipulated input selecting any one of the arranged and displayed keywords, the processor 130 may search for and display a dialog session corresponding to the selected keyword on the display 120.

Meanwhile, according to an embodiment of the present disclosure, the keyword may be shared with other terminal devices. The shared keyword may be used for various operations of the terminal device 100. For example, the terminal device 100 may transmit and receive keywords with other terminal devices through the communication interface 140. Here, the terminal device 100 can directly perform communication with other terminal devices, which can thereby prevent inadvertent keyword leakage to the outside.

According to an embodiment of the present disclosure, the processor 130 may receive a keyword stored in another terminal device through the communication interface 140, and determine a popular keyword based on the received keyword and the keyword stored on the memory. Here, the other terminal device may also classify the conversation session and determine a keyword of the classified conversation session. Further, the terminal device 100 may share the keyword with a plurality of other terminal devices. The popular keywords may refer to keywords frequently used when a dialog session is defined in the terminal device 100 and another terminal device. Thus, popular keywords may refer to common interests of a user and another user.

Popular keywords may be arranged and displayed on the display 120, which may be described below with reference to fig. 14.

Fig. 14 is a diagram provided to explain a method for sharing keywords according to an embodiment of the present disclosure.

Referring to fig. 14, the terminal device 100 may be connected to the terminal device 100-1 of "John" and the terminal device 100-2 of "Mark" and may share a keyword. Meanwhile, the user may set a limit on sharing of keywords that the user does not want to share. The processor 130 may analyze the shared keywords, recognize the words "baseball" and "dodge team" as common keywords, and determine these words as popular keywords. The processor 130 may arrange and display the shared keywords on the display 120 or mark the words "baseball" and "dodge team" as being popular keywords as priority. Further, when displaying keywords, the processor 130 may consider the user who is sending the keywords. Thus, when keywords are sent from friends, the processor 130 may tag these with "common interests of my friends". When a keyword is sent from a local neighbor, the processor 130 may tag the keyword with "common interests of my neighbor". In identifying a user who transmits a keyword, a phone book or SNS social relationship information may be used.

According to an embodiment of the present disclosure, a user can confirm a conversation topic that friends send and receive during a chat. More specifically, using the previously stored social relationship information, the processor 130 may determine popular keywords for each age or each local area. In this case, the social relationship information may be the relationship information or SNS information of the phone book stored on the storage device 110.

Meanwhile, according to an embodiment of the present disclosure, the processor 130 may display automatically suggested words on the display while inputting text through the inputter 140, and may select the displayed automatically suggested words from the popular keywords. The automatic word suggestion function may refer to a function of suggesting words to the user while text is input on the terminal device 100. Thereby, the user can input text by selecting a suggested word even before the desired text is completely input. According to an embodiment of the present disclosure, the popular keywords described above may be suggested as auto-suggested words.

For example, the processor 130 may weight words corresponding to popular keywords among the auto-suggested words such that the processor 130 displays the words on a higher rank of the suggested words. Hereinafter, the above may be described by referring to fig. 15.

Fig. 15 is a diagram provided to illustrate a method of utilizing keywords according to various embodiments of the present disclosure.

Referring to fig. 15(a), when the user inputs text, the processor 130 may control the display 120 to display various auto-suggested words and display a keyword determined to be a popular keyword in front of the shared keyword. For example, in a normal use environment, entry of the partial word "Bas" may first result in "Base" being suggested as the auto-suggested word. However, according to embodiments of the present disclosure, "basecall" determined to be a popular keyword may be suggested first.

In addition to text input, the above described functionality may also be applied to speech recognition.

Referring to fig. 15(b), if the speech input matches multiple of the corresponding words in the speech recognition, the processor 130 may give more weight to the words corresponding to the popular keywords. For example, the user may say the word "basecall" and the terminal device 100 may determine the voice input as any one of "basecall" and "basic". In this case, since the popular word "basecall" has a larger voice recognition weight, the terminal device 100 can recognize the voice input as "basecall".

According to the above-described embodiments of the present disclosure, when a text or voice command is input, words corresponding to subjects in which the user and friends thereof are interested may be suggested or classified first. Thus, words representing the user's interests may be suggested first.

Although the above describes that the processes of classifying the conversation session and determining the keyword for defining the conversation session may be performed in the terminal device 100, these processes may also be performed by an external server. In this case, the external server may notify the processing result of the terminal device 100. Hereinafter, this embodiment of the present disclosure may be explained by referring to fig. 16.

Fig. 16 is a diagram provided to explain an operation between a terminal device and an external server according to an embodiment of the present disclosure.

Referring to fig. 16, the terminal device 100 may receive a chat message input from another terminal device 100-1 communicating with the external server 200. In addition, the chat message input from the terminal device 100 may be transmitted to another terminal device 100-1 through the external server 200. The external server 200 may be implemented as a server providing a chat service.

The external server 200 may classify the chat messages received from the terminal device 100 and the other terminal device 100-1 into a plurality of conversation sessions. In addition, the external server 200 may store keywords for defining the respective classified conversation sessions on an internal storage unit. Accordingly, the above-described operation of the terminal device 100 may be performed by the external server 200. The external server 200 may include a memory, a communication interface, and a processor performing a unified operation on the terminal device 100 described above. For the sake of brevity, the description of this operation will not be repeated below.

Meanwhile, the terminal device 100 and the other terminal device 100-1 may transmit a keyword for defining a dialog session to the external server 200. The external server 200 may analyze interest areas of the terminal device 100 and the users of the other terminal devices 100-1 and extract popular keywords by analyzing the transmitted keywords. The extracted popular keywords may be provided to the terminal device 100 and the other terminal device 100-1 and used in various ways. For example, popular keywords may be used in the automatic word suggestion functionality described above.

Fig. 17 is a block diagram provided to illustrate a terminal device according to an embodiment of the present disclosure.

Referring to fig. 17, the processor 130 may be implemented as a CPU or a microcomputer (micom). Further, the storage 133 may include a CPU, a RAM, or a ROM. Here, the ROM is configured to store a command set for system startup. The processor 130 may copy the stored O/S on the memory 110 into RAM according to the stored command and start the system by implementing the O/S. When the booting is completed, the processor 130 may copy various applications stored on the memory 110 to the RAM and perform various operations by implementing the copied applications. Although the processor 130 is described herein as one CPU, when actually implemented, the processor 130 may be implemented as a plurality of CPUs (DSPs or socs).

The memory 110 may include various programs and modules necessary to drive the system. For example, the memory 110 may store a chat application, a conversation session classification module, a keyword extraction module, an event determination module, a communication module, a display control module, or a UI management module.

A chat application is a program that allows sending and receiving chat messages with other terminal devices. A conversation session classification module is provided to classify transmitted and received chat messages into a plurality of conversation sessions. In addition, a keyword extraction module is provided to extract keywords within the chat message. For example, the keyword extraction module may extract associated keywords that can be inferred from words included in the chat message, as well as words included in the chat message. An event determination module is provided to determine whether a preset event has occurred. For example, an event that inputs a keyword stored on the memory 110 may be determined by the event determination module. A communication module is provided to connect the terminal device 100 to an external device. For example, the communication module may be used to recognize other terminal devices or an external server as an external device and to connect the external device to the terminal device 100. Through the communication module, other terminal devices and the terminal device 100 can transmit and receive data through point-to-point (P2P). The display control module is a module for generating a screen displayed on the display 120. Further, the UI management module is a module for managing UIs displayed on the display 120 and storing various UI templates.

With the terminal device 100 and the external server 200 according to the above-described embodiments of the present disclosure, it is possible to perform analysis based on a conversation session unit including a plurality of chat messages, instead of analyzing a single chat message transmitted and received by a user. Thus, the entire dialog context can be classified by using NLU techniques. Further, according to the above-described embodiments of the present disclosure, since the dialog classification time point can be determined similarly to the user dialog, the dialog context can be classified more correctly.

A data processing method of a terminal device according to an embodiment of the present disclosure will be explained below by referring to fig. 18.

Referring to fig. 18, the terminal device 100 may classify the chat message into a plurality of conversation sessions in operation S1810. The chat messages may be sent and received directly with other terminal devices or from a server providing a chat service. Chat messages of users of the terminal device and other terminal devices may proceed without classification. However, according to embodiments of the present disclosure, chat messages may be classified into a plurality of conversation sessions based on conversation units. The criteria for classifying chat messages may be: whether a particular word is included in a chat message, or a time interval when sending and receiving a continued chat message.

In operation S1820, the terminal device 100 may store keywords respectively defining the classified conversation sessions on a memory of the terminal device 100. In this case, the keyword for defining the dialog session may be selected from words included in the dialog session or may be a new word according to a combination of words included in the dialog session. For example, keywords may be determined from participants, topics, intentions, and times regarding the conversation session.

When an event associated with at least one keyword among a plurality of keywords stored on the memory of the terminal device 100 occurs, the terminal device 100 may provide a dialog session matched with the at least one keyword in operation S1830. The event associated with the keyword may be an event of a search conversation session, may be an event of corresponding a keyword included in a chat message transmitted and received in real time to a keyword stored on a memory, or an event of determining a keyword for defining a conversation session after the conversation session including a plurality of chat messages is determined. Further, the terminal device 100 may provide a conversation session by displaying a list on a display with respect to a plurality of conversation sessions or by displaying a chat message within one conversation session on a display.

Further, the terminal device 100 may use a keyword defining a conversation session in various functions. As described above, the terminal device 100 may provide the user with the keywords through the display or provide the user's interest areas of the terminal device and other terminal devices by sharing the keywords with the other terminal devices. Further, the terminal device 100 may extract popular keywords from the shared keywords and use them in the automatic word suggestion function. These embodiments of the disclosure have been described above and may not be further described below within the scope of the overlap.

Meanwhile, although it is described herein that the data processing is performed by the terminal device 100, the operation may be uniformly performed by a server providing a chat service. In this case, the server may be implemented as a device capable of classifying chat messages into a plurality of conversation sessions. Further, the server may receive information about an event occurring in the terminal device and provide a dialog session corresponding to the event to the terminal device.

With the data processing method according to the above-described various embodiments of the present disclosure, a user can easily find chat conversations with other users in the past according to subject matter, time, conversation participants, and conversation intentions.

The data processing method according to the above-described various embodiments of the present disclosure may be implemented as a program including an algorithm that can be executed on a computer, and the program may be stored and provided in a non-transitory computer-readable recording medium. The non-transitory computer readable recording medium may be loaded on various devices.

The non-transitory computer-readable recording medium refers to a medium that can store data semi-permanently and can be read by a device, and not a medium that temporarily stores data, such as a register, a cache, or a storage. For example, the various application programs or programs described above may be stored and provided in a non-transitory computer-readable recording medium such as a Compact Disc (CD), a Digital Versatile Disc (DVD), a hard disk, a blu-ray disc, a Universal Serial Bus (USB), a memory card, or a ROM.

Accordingly, the above-described program can be installed on the related device, and a terminal device or a server that can classify and manage chat messages through a conversation session can be implemented.

While the disclosure has been shown and described with reference to various embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the disclosure as defined by the appended claims and their equivalents.

Claims

1. A terminal device, comprising:

a communication interface configured to perform communication with an external device at the start of a chat;

a display configured to display chat messages sent and received through the communication interface;

a memory; and

a processor configured to:

classifying the chat message into a plurality of conversation sessions based on a time point of transmitting or receiving the chat message including at least one of a topic exchange word or a topic exchange sentence,

in response to the chat message being classified into the plurality of conversation sessions, identifying a plurality of keywords respectively corresponding to the plurality of conversation sessions,

storing the plurality of keywords respectively mapped to the plurality of dialog sessions on the memory, an

In response to an event that a keyword among the plurality of keywords is input to search for a dialog session or an event that a keyword among the plurality of keywords is displayed, controlling a display to display a dialog session mapped to the input keyword or the displayed keyword.

2. The terminal device of claim 1, wherein the processor is further configured to:

checking the transmission time or reception time of each chat message, an

Chat messages transmitted and received for a duration exceeding a certain time interval are classified into conversation sessions different from each other.

3. The terminal device of claim 1, wherein the processor is further configured to: when the plurality of dialog sessions are stored on the memory and keywords on the plurality of dialog sessions are associated with each other, the plurality of dialog sessions are integrated into one dialog session.

4. The terminal device of claim 1, wherein in response to input of a user manipulation selecting at least a portion of a plurality of chat messages displayed on the display, the processor is further configured to determine chat messages within a range corresponding to the input user manipulation as one conversation session.

5. The terminal device of claim 1, wherein the processor is further configured to:

providing a graphic effect through the display to inform of the end of the conversation session when a conversation session is completed during the chat, and

in response to user-manipulated input agreeing to the end of the conversation session, chat messages within a range corresponding to the graphical effect are determined as one conversation session.

6. The terminal device of claim 1, wherein the processor is further configured to control the display to display a User Interface (UI) screen for editing a previously defined keyword for a particular dialog session in response to a user-manipulated input for editing the keyword.

7. The terminal device of claim 1, wherein when an event occurs in which a keyword for searching the conversation session is input, the processor is further configured to display a list of conversation sessions corresponding to the input keyword on the display.

8. The terminal device of claim 1, wherein the processor is further configured to:

a chat area and an associated conversation session area are respectively displayed on a screen of the display,

displaying chat messages sent and received through the communication interface on the chat area, an

When an event occurs in which one of the keywords stored in the memory is displayed on the chat area, a dialog session matching the displayed keyword is displayed on the associated dialog session area.

9. The terminal device of claim 1, wherein the processor is further configured to:

chat regions and associated conversation session regions are respectively displayed on a screen of the display,

displaying chat messages sent and received through a communication interface on the chat area, an

When an event occurs in which a keyword of a conversation session including the chat message displayed on the chat area matches a previous keyword stored on the memory, the conversation session matching the previous keyword is displayed on the associated conversation session area.

10. The terminal device of claim 1, wherein in response to a user-manipulated input selecting the conversation session, the processor is further configured to display a new chat screen on the display that includes chat messages within the selected conversation session.

11. The terminal device of claim 1, wherein the processor is further configured to control the display to display a background image associated with a keyword for defining a particular conversation session on a chat screen while chat messages within the particular conversation session are displayed on the chat screen.

12. The terminal device of claim 1, wherein the processor is further configured to determine a keyword for each conversation session based on at least one of conversation participants, conversation topic, conversation intent, and conversation time for each conversation session.

13. The terminal device of claim 1, further comprising:

a sensor configured to sense at least one state regarding a location of the terminal device, a movement of the terminal device, an ambient temperature of the terminal device, and an ambient humidity of the terminal device,

wherein the processor is further configured to determine a keyword for defining a conversation session including the input chat message based on information sensed by the sensor at a time when the chat message is input.

14. A method of processing data in a terminal device, the method comprising:

classifying previously stored chat messages into a plurality of conversation sessions based on a point in time at which a chat message including at least one of a topic exchange word or a topic exchange sentence is transmitted or received;

in response to the chat message being classified as the plurality of conversation sessions, identifying a plurality of keywords respectively corresponding to the plurality of conversation sessions;

storing the plurality of keywords respectively mapped to the plurality of dialog sessions on a memory of the terminal device; and

displaying the dialog session mapped to the input keyword or the displayed keyword in response to an event of an occurrence of inputting a keyword among the plurality of keywords to search for the dialog session or an event of displaying a keyword among the plurality of keywords.