KR102466725B1 - Electronic apparatus that provides the chat function based on sentiment analysis and operating method thereof - Google Patents

Abstract

Disclosed are an electronic device providing a chatting function based on emotion analysis and an operating method thereof. An electronic device and method of operation thereof according to the present invention, when a plurality of chatting messages are received from a chatting party's terminal, perform emotion analysis on the plurality of chatting messages, and based on this, determine the current emotional state of the chatting party. This relates to a technology for supporting a user of an electronic device to continue smooth communication with a chatting partner by guiding the chatter.

Description

Electronic device providing a chat function based on emotion analysis and its operation method

The present invention relates to an electronic device providing a chatting function based on emotion analysis and an operating method thereof.

BACKGROUND OF THE INVENTION [0002] Recently, as a chat application is widely spread, communication between people is being actively performed.

In relation to this, in existing chat applications, communication between people has been performed through text composed of general characters. However, there was a limit to understanding the emotions of others or conveying one's own emotions only with the text composed of general characters.

In order to overcome these limitations, recently, symbol combinations consisting of a combination of general characters and special characters have been used in chatting, so that emotions can be conveyed effectively.

In this way, as symbol combinations are used in chatting, although emotions can be conveyed effectively, it is not easy for a user to grasp the emotional state of a chatting partner by only looking at chatting messages received from the chatting counterpart.

In this regard, if the chatting counterpart's current emotional state can be analyzed based on the chatting messages received from the chatting counterpart, the user will be able to continue smooth communication with the chatting counterpart.

Therefore, it is necessary to study a chatting service technology that can provide a chatting function based on emotion analysis.

The present invention relates to an electronic device that, when a plurality of chatting messages are received from a terminal of a chatting partner, performs emotion analysis on the plurality of chatting messages, and guides the current emotional state of the chatting party based on this, and its operation By presenting a method, it is intended to support a user of an electronic device to continue smooth communication with a chatting partner.

An electronic device providing a chatting function based on emotion analysis according to an embodiment of the present invention stores and maintains an emotion item table in which information on k (k is a natural number of 2 or more) preset emotion items are recorded. An emotion item table holding unit that stores a plurality of different symbol combinations composed of combinations of one or more symbols and a symbol combination table in which preset scores for each of the k emotion items of each of the plurality of symbol combinations are recorded. When a chatting function is executed as the user of the electronic device runs a chatting application installed in the electronic device, the chatting message received from the terminal of the chatting party is n (n is a natural number equal to or greater than 2), an emotion analysis event generating unit generating an emotion analysis event for analyzing emotions of n chatting messages received from the chatting party's terminal, when the emotion analysis event occurs, the A symbol combination extraction unit extracting a symbol combination included in the plurality of symbol combinations from the n chatting messages with reference to a symbol combination table, and a symbol included in the plurality of symbol combinations from the n chatting messages. When t (t is a natural number of 2 or more) number combinations are extracted as a combination, a confirmation unit for checking scores for each of the k emotion items of the t symbol combinations from the symbol combination table; An emotional index calculating unit that calculates an emotional index for each of the k emotional items based on scores for each of the k emotional items, and selects a first emotional item having the largest emotional index among the k emotional items. Then, an emotional state information unit displaying on a screen a guide message informing that the current emotional state of the chatting partner is an emotional state according to the first emotional item.

In addition, a method of operating an electronic device providing a chatting function based on emotion analysis according to an embodiment of the present invention includes emotion items in which information on different k (k is a natural number equal to or greater than 2) number of preset emotion items is recorded. Storing and maintaining a table, a symbol combination table in which a plurality of different symbol combinations composed of combinations of one or more symbols and preset scores for each of the k emotion items of each of the plurality of symbol combinations are recorded Storing and maintaining, when a chatting function is executed as a chatting application installed in the electronic device is executed by the user of the electronic device, the chatting message received from the terminal of the chatting party is n (n is 2 or more Generating an emotion analysis event for analyzing emotions of n chatting messages received from the chatting party's terminal whenever the number is a natural number), when the emotion analysis event occurs, referring to the symbol combination table, Extracting a symbol combination included in the plurality of symbol combinations from the n chatting messages, t (t is a natural number of 2 or more) as a symbol combination included in the plurality of symbol combinations from the n chatting messages When the number of symbol combinations are extracted, checking scores for each of the k emotion items of the t symbol combinations from the symbol combination table, calculating the score for each of the k emotion items of the t symbol combinations After calculating an emotional index for each of the k emotional items based on the above and selecting a first emotional item having the largest emotional index among the k emotional items, the current emotional state of the chatting partner is determined by the first emotional index. and displaying on a screen a guide message informing that the emotional state is in accordance with the emotional item.

The present invention relates to an electronic device that, when a plurality of chatting messages are received from a terminal of a chatting partner, performs emotion analysis on the plurality of chatting messages, and guides the current emotional state of the chatting party based on this, and its operation By suggesting a method, it is possible to support a user of an electronic device to continue smooth communication with a chatting partner.

1 is a diagram showing the structure of an electronic device providing a chatting function based on emotion analysis according to an embodiment of the present invention.
2 is a diagram for explaining an operating method of an electronic device that provides a chatting function based on emotion analysis according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. This description is not intended to limit the present invention to specific embodiments, but should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. While describing each drawing, similar reference numerals have been used for similar components, and unless otherwise defined, all terms used in this specification, including technical or scientific terms, are common knowledge in the art to which the present invention belongs. has the same meaning as commonly understood by the person who has it.

In this document, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated. In addition, in various embodiments of the present invention, each component, functional block, or means may be composed of one or more sub-components, and the electrical, electronic, and mechanical functions performed by each component are electronic It may be implemented with various known elements or mechanical elements such as circuits, integrated circuits, ASICs (Application Specific Integrated Circuits), and may be implemented separately or two or more may be integrated into one.

On the other hand, the blocks of the accompanying block diagram or the steps of the flowchart are computer program instructions that perform designated functions by being loaded into a processor or memory of a device capable of data processing, such as a general-purpose computer, a special purpose computer, a portable notebook computer, and a network computer. can be interpreted as meaning Since these computer program instructions may be stored in a memory included in a computer device or in a computer readable memory, the functions described in blocks of a block diagram or steps of a flowchart are produced as a product containing instruction means for performing them. It could be. Further, each block or each step may represent a module, segment or portion of code that includes one or more executable instructions for executing specified logical function(s). Also, it should be noted that in some alternative embodiments, functions mentioned in blocks or steps may be executed out of a predetermined order. For example, two blocks or steps shown in succession may be performed substantially simultaneously or in reverse order, and in some cases, some blocks or steps may be omitted.

1 is a diagram showing the structure of an electronic device providing a chatting function based on emotion analysis according to an embodiment of the present invention.

Referring to FIG. 1 , an electronic device 110 according to an embodiment of the present invention includes an emotion item table maintainer 111, a symbol combination table maintainer 112, an emotion analysis event generator 113, and a symbol combination extraction unit. It includes a unit 114, a confirmation unit 115, an emotional index calculation unit 116, and an emotional state information unit 117.

The emotion item table holding unit 111 stores and maintains an emotion item table in which information on different k (k is a natural number equal to or greater than 2) previously set emotion items are recorded.

For example, when it is assumed that 'k=4' and four emotion items exist, the emotion item table maintaining unit 111 may store and maintain the emotion item table as shown in Table 1 below.

Information on the 4 emotion items Embarrassment sadness pleasure aggro

The symbol combination table holding unit 112 stores a plurality of different symbol combinations composed of combinations of one or more symbols and a symbol combination in which preset scores for each of the k emotion items of each of the plurality of symbol combinations are recorded. Save and maintain the table.

For example, the symbol combination table holding unit 112 may store and maintain a symbol combination table as shown in Table 2 below.

multiple symbol combinations Scores for each of the four emotion items Embarrassment sadness pleasure aggro ^^; 40 points 10 points 75 points 15 points ^0^ 5 points 15 points 85 points 15 points *^^* 5 points 45 points 65 points 10 points ㅠㅠ 5 points 70 points 35 points 15 points (>_<) 80 points 10 points 30 points 50 points ... ... ... ... ...

The emotion analysis event generating unit 113 generates information received from the terminal 130 of a chatting partner when a chatting function is executed as a chatting application installed in the electronic device 110 is executed by the user of the electronic device 110. Whenever the number of chatting messages is n (n is a natural number equal to or greater than 2), an emotion analysis event is generated to analyze the emotions of the n number of chatting messages received from the chatting partner's terminal 130 .

When the emotion analysis event occurs, the preference combination extractor 114 refers to the preference combination table and extracts a symbol combination included in the plurality of symbol combinations from the n chatting messages.

When t (t is a natural number equal to or greater than 2) number of symbol combinations among the plurality of symbol combinations is extracted from the n chatting messages, the checker 115 extracts the t number of symbol combinations from the symbol combination table. Scores for each of the k emotion items of .

For example, assume that 'n=13' and 't=4'. At this time, when a chatting function is executed as a chatting application installed in the electronic device 110 is executed by the user of the electronic device 110, the emotion analysis event generating unit 113 receives information from the chatting partner's terminal 130. Whenever the number of received chatting messages reaches 13, an emotion analysis event for analyzing the emotions of the 13 chatting messages received from the chatting partner's terminal 130 may be generated.

In this way, when the emotion analysis event is generated by the emotion analysis event generating unit 113, the preference combination extraction unit 114 refers to the preference combination table as shown in Table 2, and selects the plurality of the plurality of chatting messages from the 13 chatting messages. Symbol combinations included in symbol combinations '^^;, ^0^, *^^*, ㅠㅠ, (>_<), ...' can be extracted.

If, by the symbol combination extraction unit 114, the plurality of symbol combinations '^^;, ^0^, *^^*, ㅠㅠ, (>_<), ...' from the 13 chat messages When it is said that four symbol combinations '^^;, ^0^, *^^*, ㅠㅠ' are extracted as symbol combinations included in Scores for each of the four emotion items 'embarrassment, sadness, joy, anger' of '^^;, ^0^, *^^*, ㅠㅠ', which are combinations of dogs, can be checked.

That is, the confirmation unit 115 may confirm '40 points, 10 points, 75 points, and 15 points' as the scores for each of 'embarrassment, sadness, joy, and anger' for '^^;', and '^0 For ^', you can check '5 points, 15 points, 85 points, 15 points' as the score for each of 'embarrassment, sadness, joy, anger', and 'Embarrassment, sadness, joy' for '*^^*' , Angry' can be checked as '5 points, 45 points, 65 points, and 10 points' as the scores for each, and for 'ㅠ_ㅠ', 'Embarrassed, sad, happy, angry' can be scored as '5 points, 70 points' respectively. points, 35 points, and 15 points.

The emotion index calculation unit 116 calculates an emotion index for each of the k emotion items based on scores for each of the k emotion items of the t symbol combinations.

In this case, according to an embodiment of the present invention, the emotion index calculator 116 may include an emotion vector generator 118 and a calculator 119 .

For each of the k emotion items, the emotion vector generator 118 constructs a t-dimensional vector having a score for each emotion item of the t symbol combinations as a component, thereby generating a value corresponding to each of the k emotion items. Create a t-dimensional emotion vector.

The operation unit 119 calculates a Euclidean norm of an emotion vector corresponding to each of the k emotion items as an emotion index corresponding to each of the k emotion items.

Here, the Euclidean norm is an L2 norm for representing the size of a vector or matrix, and can be calculated according to Equation 1 below.

는 유클리드 노름을 의미하고, x_i는 벡터나 행렬에 포함되어 있는 i번째 성분을 의미한다.In Equation 1 above

denotes the Euclidean norm, and x _i denotes the i-th element included in a vector or matrix.

For example, as in the above example, the four emotion items of the four symbol combinations '^^;, ^0^, *^^*, ㅠㅠ' are 'embarrassment, sadness, joy' by the confirmation unit 115. , Angry', each score is '40 points, 10 points, 75 points, 15 points', '5 points, 15 points, 85 points, 15 points', '5 points, 45 points, 65 points, 10 points', Let's assume that it is confirmed as '5 points, 70 points, 35 points, 15 points'.

At this time, the emotion vector generator 118 has a 4-dimensional score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' for each of 'embarrassment, sadness, joy, anger' By configuring the vector of , it is possible to generate a 4-dimensional emotion vector corresponding to each of 'embarrassment, sadness, joy, and anger'.

In this regard, for 'embarrassment', the score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' was '40 (points), 5 (points), 5 (points), 5 (points) )', the emotion vector generator 118 may generate '[40 5 5 5]' as a 4-dimensional emotion vector for 'embarrassment'. And, for 'sadness', the score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' is '10 (points), 15 (points), 45 (points), 70 (points)' Therefore, the emotion vector generator 118 may generate '[10 15 45 70]' as a 4-dimensional emotion vector for 'sadness'. And, for 'joy', the score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' is '75 (points), 85 (points), 65 (points), 35 (points)' , '[75 85 65 35]' can be generated as a 4-dimensional emotion vector for 'joy'. Lastly, for 'angry man', the score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' was 15 (points), 15 (points), 10 (points), 15 (points) ', it is possible to generate '[15 15 10 15]' as a 4-dimensional emotion vector for 'angry man'.

In this way, when the emotion vectors corresponding to each of 'embarrassment, sadness, joy, and anger' are generated, the operation unit 119 determines the emotion vectors corresponding to each of 'embarrassment, sadness, joy, and anger' '[40 5 5 5], The Euclidean norms of [10 15 45 70], [75 85 65 35], and [15 15 10 15] can be calculated as '40.92, 85.14, 135.27, 27.83' according to Equation 1 above.

After that, the operation unit 119 converts '40.92, 85.14, 135.27, 27.83', which are Euclidean norms corresponding to each of 'embarrassment, sadness, joy, and anger', into an emotional index corresponding to each of 'embarrassment, sadness, joy, and anger'. can be computed.

After selecting a first emotion item having the largest emotional index among the k emotion items, the emotional state information unit 117 informs that the current emotional state of the chatting partner is an emotional state according to the first emotion item. message is displayed on the screen.

In relation to this, the operation of the emotional state information unit 117 according to the above-described embodiment will be described. Since the emotion item having the largest emotional index among 'embarrassment, sadness, joy, and anger' is 'joy', the emotional state information unit (117) may select the emotion item 'joy' as the first emotion item.

Then, the emotional state information unit 117 may display on the screen a guide message informing that the current emotional state of the chatting partner is an emotional state according to the first emotional item, 'joy'.

Through this, the user of the electronic device 110 checks a guide message for guiding the chatting partner's current emotional state, and then conducts an appropriate chat according to the chatting partner's current emotional state confirmed through the guide message, thereby enabling the chatting party to chat. You can continue to communicate smoothly with the other party.

According to an embodiment of the present invention, the electronic device 110 includes an average score value generator 120, an average score vector generator 121, a score vector generator 122, a Euclidean distance calculator 123, and a display unit ( 124) may be further included.

After the guidance message is displayed on the screen by the emotional state information unit 117, the average score value generator 120 averages the scores for each emotion item of the t taste combinations for each of the k emotion items. By calculating , an average score value corresponding to each of the k emotion items is generated.

The average score vector generator 121 generates a k-dimensional average score vector having average score values corresponding to each of the k emotion items as components.

The score vector generator 122 refers to the symbol combination table, and constructs a k-dimensional vector having as components a score for each of the k emotion items of each symbol combination, for each of the plurality of symbol combinations. By doing so, a k-dimensional score vector corresponding to each of the plurality of symbol combinations is generated.

The Euclidean distance calculator 123 calculates a Euclidean distance between the average score vector and score vectors corresponding to each of the plurality of symbol combinations.

Here, the Euclidean distance means the distance between two vectors when it is assumed that two vectors exist, and can be calculated according to Equation 2 below.

In Equation 2, D is the Euclidean distance, and A _i and B _i denote i-th components included in the two vectors. In general, the smaller the Euclidean distance between two vectors, the more similar the two vectors are, and the larger the Euclidean distance between the two vectors, the more dissimilar vectors they are.

The display unit 124 selects p (p is a natural number equal to or greater than 2) number of symbol combinations in order of decreasing Euclidean distance among the plurality of symbol combinations, configures the p number of symbol combinations into a list, and sends the list to a chat message. Information on recommended symbol combinations to be input is displayed on the screen.

For example, as in the above example, when it is assumed that the guidance message is displayed on the screen by the emotional state guide unit 117, the average score value generator 120 calculates 'embarrassment, sadness, joy, and anger' respectively. , '^^;, ^0^, *^^*, ㅠㅠ' average score values corresponding to each of 'embarrassment, sadness, joy, anger' can be generated by calculating the average of the scores for each emotion item.

In this regard, for 'embarrassment', the score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' was '40 (points), 5 (points), 5 (points), 5 (points) )', the average score generator 120 may generate '13.75' as the average score for 'embarrassment'. And, for 'sadness', the score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' is '10 (points), 15 (points), 45 (points), 70 (points)' Therefore, the average score value generating unit 120 may generate '35' as the average score value for 'sadness'. And, for 'joy', the score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' is '75 (points), 85 (points), 65 (points), 35 (points)' Therefore, '65' can be generated as the average score for 'joy'. Lastly, for 'angry man', the score for each emotion item of '^^;, ^0^, *^^*, ㅠㅠ' was 15 (points), 15 (points), 10 (points), 15 (points) ', it is possible to generate '13.75' as the average score for 'Angry Man'.

In this way, when the average score value corresponding to each of 'embarrassment, sadness, joy, and anger' is generated, the average score vector generator 121 calculates the average score value '13.75, '[13.75 35 65 13.75]' can be created as a 4-dimensional average score vector having 35, 65, 13.75' as components.

After that, the score vector generator 122 refers to the symbol combination table as shown in Table 2 above, and the plurality of symbol combinations '^^;, ^0^, *^^*, ㅠㅠ, (>_<) , ...', by constructing a 4-dimensional vector having a score for each of 'embarrassment, sadness, joy, anger' of each symbol combination as a component, '^^;, ^0^, *^^ A 4-dimensional score vector corresponding to each of *, ㅠㅠ, (>_<), ...' can be created.

In this regard, for '^^;', the scores for each of 'embarrassment, sadness, joy, and anger' are '40 (points), 10 (points), 75 (points), and 15 (points)', so the score vector The generation unit 122 may generate '[40 10 75 15]' as a 4-dimensional score vector for '^^;'. In this way, the score vector generator 122 converts '[ 40 10 75 15], [5 15 85 15], [5 45 65 10], [5 70 35 15], [80 10 30 50], ...'.

Then, the Euclidean distance calculation unit 123 uses the mean score vector '[13.75 35 65 13.75]' and the plurality of symbol combinations '^^;, ^0^, *^^*, ㅠㅠ, (>_ <), ...' corresponding score vectors '[40 10 75 15], [5 15 85 15], [5 45 65 10], [5 70 35 15], [80 10 30 50], The Euclidean distance between ...' can be calculated as 'D ₁ , D ₂ , D ₃ , D ₄ , D ₅ , ...' according to Equation 2 above.

In this way, the average score vector '[13.75 35 65 13.75]' and the plurality of symbol combinations '^^;, ^0^, *^^*, ㅠㅠ, (>_ <), ...' corresponding score vectors '[40 10 75 15], [5 15 85 15], [5 45 65 10], [5 70 35 15], [80 10 30 50], If the Euclidean distance between ...' is calculated as 'D ₁ , D ₂ , D ₃ , D ₄ , D ₅ , ...', the display unit 124 displays the plurality of symbol combinations '^^;, ^ Among 0^, *^^*, ㅠㅠ, (>_<), ...', p symbol combinations may be selected in order of the smallest Euclidean distance.

If p is '3' and it is assumed that among the Euclidean distances, the Euclidean distances are small in the order of 'D ₃ , D ₂ , D ₁ , D ₄ , D ₅ , ...', the display unit 124 Among the plurality of symbol combinations '^^;, ^0^, *^^*, ㅠㅠ, (>_<), ...', three symbol combinations '*^^*, ^0^, ^^ You can choose ;'.

After that, the display unit 124 organizes the three symbol combinations '*^^*, ^0^, ^^;' into a list, and displays the list as information on recommended symbol combinations to be input in the chatting message on the screen. can be displayed on

Through this, the user inserts any one of the recommended symbol combinations displayed in the list into a chatting message and transmits it to the chatting partner, thereby expressing emotion corresponding to the chatting partner's current emotional state.

At this time, according to an embodiment of the present invention, when the list is configured, the display unit 124 selects a first symbol combination having the maximum score for the first emotion item among the p symbol combinations included in the list. After selection, the font format of the first symbol combination in the list is applied as a preset emphasis format to indicate that it is a preferred symbol combination, and the font format of the remaining symbol combinations is applied as a preset basic format. The application-completed list may be displayed on the screen.

For example, as in the above example, the first emotional item identified as the current emotional state of the chatting party by the emotional state information unit 117 is 'joy', and the display unit 124 sets the list to the three When it is assumed that it is composed of the symbol combinations '*^^*, ^0^, ^^;', the display unit 124 displays the three symbol combinations '*^^*, ^0^, ^ included in the list. ^;' Among them, a first symbol combination having a maximum score for 'joy', which is the first emotion item, may be selected.

Regarding '*^^*', the score for 'joy' is '65 points', for '^0^', the score for 'joy' is '85 points', and for '^^; Since the score for 'joy' is '75 points', the display unit 124 displays '*^^*, ^0^, ^^;' Among them, '^0^' may be selected as the first symbol combination having the maximum score for 'joy'.

After that, the display unit 124 may apply the font style of '^0^', which is the first symbol combination in the list, as a preset emphasis style to indicate that it is a symbol combination that is a priority recommendation target.

At this time, assuming that the emphasis style is 'bold', the display unit 124 may apply the font style of '^0^', which is the first symbol combination in the list, to the emphasis style 'bold'.

Then, the display unit 124 may apply the font styles of '*^^*, ^^;', which are the remaining symbol combinations, as a preset basic style, and then display the list to which the font style has been applied on the screen.

That is, when the electronic device 110 according to the present invention configures the list including p symbol combinations to be recommended to the user, the score for the first emotion item among the p symbol combinations included in the list is A predetermined emphasis format is applied to the first maximum symbol combination, and a predetermined basic format is applied to the remaining symbol combinations, and the list to which the font format is applied is displayed on the screen, thereby displaying the list on the screen. In step 110, the user can quickly check a symbol combination having the highest score for the first emotion item from the list of recommended symbol combinations.

2 is a flowchart illustrating an operating method of an electronic device providing a chatting function based on emotion analysis according to an embodiment of the present invention.

In step S210, an emotion item table in which information on different k (k is a natural number equal to or greater than 2) previously set emotion items is recorded is stored and maintained.

In step S220, a symbol combination table in which a plurality of different symbol combinations composed of combinations of one or more symbols and preset scores for each of the k emotion items of each of the plurality of symbol combinations are recorded is stored. keep

In step S230, when the chatting function is executed as the chatting application installed in the electronic device is executed by the user of the electronic device, the chatting message received from the chatting party's terminal is n (n is a natural number greater than or equal to 2). An emotion analysis event is generated to analyze the emotions of the n number of chatting messages received from the chatting counterpart's terminal whenever number of times becomes the number.

In step S240, when the emotion analysis event occurs, a symbol combination included in the plurality of symbol combinations is extracted from the n chatting messages with reference to the symbol combination table.

In step S250, when t (t is a natural number equal to or greater than 2) number of symbol combinations among the plurality of symbol combinations is extracted from the n chatting messages, the t number of symbol combinations are obtained from the symbol combination table. A score for each of the k emotion items is checked.

In step S260, an emotional index for each of the k emotion items is calculated based on a score for each of the k emotion items of the t symbol combinations.

In step S270, after selecting a first emotion item having the largest emotional index among the k emotion items, a guide message notifying that the chatting partner's current emotional state is based on the first emotion item is displayed on the screen. displayed on the

At this time, according to an embodiment of the present invention, in step S260, for each of the k emotion items, a t-dimensional vector having as components the scores for each emotion item of the t symbol combinations is constructed, so that the k generating a t-dimensional emotion vector corresponding to each of the k emotion items, and calculating a Euclidean norm of the emotion vector corresponding to each of the k emotion items as an emotion index corresponding to each of the k emotion items. can include

In addition, according to an embodiment of the present invention, after the guide message is displayed on the screen, the average score for each emotion item of the t symbol combinations for each of the k emotion items generating an average score value corresponding to each of the k emotion items by calculating , generating a k-dimensional average score vector having an average score value corresponding to each of the k emotion items as a component; With reference to the symbol combination table, for each of the plurality of symbol combinations, a k-dimensional vector having a score for each of the k emotion items of each symbol combination as a component is constructed, thereby determining the plurality of symbol combinations. Generating a k-dimensional score vector corresponding to each, calculating a Euclidean distance between the average score vector and a score vector corresponding to each of the plurality of symbol combinations, and the Euclidean distance among the plurality of symbol combinations Selecting p (p is a natural number of 2 or more) number of symbol combinations in the order of small number to form a list of the number of symbol combinations, and then displaying the list on the screen as information on recommended symbol combinations to be input in a chatting message. may further include.

At this time, according to one embodiment of the present invention, the step of displaying the list on the screen is, when the list is configured, the score for the first emotion item among the p symbol combinations included in the list is the maximum. After selecting the first symbol combination, the font format of the first symbol combination in the list is applied as a preset emphasis format to indicate that it is a preferred symbol combination, and the font format of the remaining symbol combinations is applied as a preset basic format Then, the list to which the font format is applied can be displayed on the screen.

In the above, the operating method of the electronic device according to an embodiment of the present invention has been described with reference to FIG. 2 . Here, since the operating method of the electronic device according to an embodiment of the present invention may correspond to the configuration of the operation of the electronic device 110 described with reference to FIG. 1 , a detailed description thereof will be omitted.

An operating method of an electronic device providing a chatting function based on emotion analysis according to an embodiment of the present invention may be implemented as a computer program stored in a storage medium for execution through combination with a computer.

In addition, the operating method of an electronic device providing a chatting function based on emotion analysis according to an embodiment of the present invention may be implemented in the form of computer program instructions for execution through combination with a computer and recorded on a computer readable medium. . The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be those specially designed and configured for the present invention or those known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler.

As described above, the present invention has been described by specific details such as specific components and limited embodiments and drawings, but these are provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , Those skilled in the art in the field to which the present invention belongs can make various modifications and variations from these descriptions.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and it will be said that not only the claims to be described later, but also all modifications equivalent or equivalent to these claims belong to the scope of the present invention. .

110: Electronic device providing a chat function based on sentiment analysis
111: Emotion item table holding unit 112: Symbol combination table holding unit
113: emotion analysis event generating unit 114: symbol combination extraction unit
115: confirmation unit 116: emotional index calculation unit
117: Emotion state information unit 118: Emotion vector generation unit
119: calculation unit 120: average score value generation unit
121: average score vector generator 122: score vector generator
123: Euclidean distance calculation unit 124: display unit
130: chatting party's terminal

Claims (10)

An electronic device providing a chat function based on emotion analysis,
an emotion item table holding unit which stores and maintains an emotion item table in which information on k (k is a natural number equal to or greater than 2) number of different preset emotion items is recorded;
A symbol combination table for storing and maintaining a plurality of different symbol combinations composed of combinations of one or more symbols and a symbol combination table in which preset scores for each of the k emotion items of each of the plurality of symbol combinations are recorded. maintenance part;
When the chatting function is executed as the chatting application installed in the electronic device is executed by the user of the electronic device, the number of chatting messages received from the chatting party's terminal reaches n (n is a natural number equal to or greater than 2). an emotion analysis event generator configured to generate an emotion analysis event for analyzing emotions of n number of chatting messages received from a chatting counterpart's terminal;
a symbol combination extraction unit extracting a symbol combination included in the plurality of symbol combinations from the n chatting messages by referring to the symbol combination table when the emotion analysis event occurs;
When t (t is a natural number of 2 or more) number of symbol combinations are extracted from the n chatting messages as symbol combinations included among the plurality of symbol combinations, the k emotion items of the t symbol combinations from the symbol combination table Confirmation unit for checking the score for each of them;
an emotional index calculator calculating an emotional index for each of the k emotional items of the t symbol combinations based on a score for each of the k emotional items;
After selecting a first emotion item having the largest emotional index among the k emotion items, a guide message notifying that the current emotional state of the chatting partner is based on the first emotion item is displayed on the screen. status guide;
After the guide message is displayed on the screen by the emotional state information unit, for each of the k emotion items, by calculating an average of scores for each emotion item of the t taste combinations, each of the k emotion items an average point value generation unit for generating an average point value corresponding to;
an average score vector generator generating a k-dimensional average score vector having average score values corresponding to each of the k emotion items as components;
With reference to the symbol combination table, for each of the plurality of symbol combinations, a k-dimensional vector having a score for each of the k emotion items of each symbol combination as a component is constructed, thereby determining the plurality of symbol combinations. a score vector generator for generating a k-dimensional score vector corresponding to each score;
a Euclidean distance calculating unit calculating a Euclidean distance between the average score vector and score vectors corresponding to each of the plurality of symbol combinations; and
Among the plurality of symbol combinations, p (p is a natural number of 2 or more) number of symbol combinations are selected in order of small Euclidean distance to form a list of the p number of symbol combinations, and then the list is recommended symbol combinations to be input to a chatting message. Display unit displayed on the screen as information about
An electronic device comprising a. According to claim 1,
The emotional index calculation unit
Generating a t-dimensional emotion vector corresponding to each of the k emotion items by constructing a t-dimensional vector having as components a score for each emotion item of the t symbol combinations for each of the k emotion items. an emotion vector generating unit; and
A calculator that calculates a Euclidean norm of an emotion vector corresponding to each of the k emotion items as an emotion index corresponding to each of the k emotion items.
An electronic device comprising a. delete According to claim 1,
the display part
When the list is configured, after selecting the first symbol combination having the maximum score for the first emotion item among the p symbol combinations included in the list, the font format of the first symbol combination is given priority in the list. An electronic device that applies a preset emphasis format to indicate a symbol combination that is a recommended target, applies a font format of the remaining symbol combinations as a preset basic format, and then displays the list to which the font format has been applied on the screen. In the operating method of an electronic device providing a chat function based on emotion analysis,
storing and maintaining an emotion item table in which information on k different (k is a natural number equal to or greater than 2) number of preset emotion items is recorded;
storing and maintaining a symbol combination table in which a plurality of different symbol combinations composed of combinations of one or more symbols and preset scores for each of the k emotion items of each of the plurality of symbol combinations are recorded;
When the chatting function is executed as the chatting application installed in the electronic device is executed by the user of the electronic device, the number of chatting messages received from the chatting party's terminal reaches n (n is a natural number equal to or greater than 2). generating an emotion analysis event for analyzing emotions of n number of chatting messages received from a chatting counterpart's terminal;
extracting a symbol combination included in the plurality of symbol combinations from the n chatting messages by referring to the symbol combination table when the emotion analysis event occurs;
When t (t is a natural number of 2 or more) number of symbol combinations are extracted from the n chatting messages as symbol combinations included among the plurality of symbol combinations, the k emotion items of the t symbol combinations from the symbol combination table Checking the score for each of them;
calculating an emotional index for each of the k emotion items based on a score for each of the k emotion items of the t symbol combinations;
After selecting a first emotion item having the largest emotional index among the k emotion items, displaying a guide message on the screen informing that the chatting partner's current emotional state is based on the first emotion item. ;
After the guide message is displayed on the screen, for each of the k emotion items, an average score value corresponding to each of the k emotion items is calculated by calculating an average of scores for each emotion item of the t symbol combinations. generating;
generating a k-dimensional mean score vector having mean score values corresponding to each of the k emotion items as components;
With reference to the symbol combination table, for each of the plurality of symbol combinations, a k-dimensional vector having a score for each of the k emotion items of each symbol combination as a component is constructed, thereby determining the plurality of symbol combinations. generating k-dimensional score vectors corresponding to each;
calculating a Euclidean distance between the average score vector and score vectors corresponding to each of the plurality of symbol combinations; and
Information on recommended symbol combinations to be input to a chatting message after p (p is a natural number of 2 or more) number of symbol combinations are selected from among the plurality of symbol combinations in order of small Euclidean distance to form a list of the p number of symbol combinations. displaying the list on the screen with
A method of operating an electronic device comprising a. According to claim 5,
Calculating the emotion index
Generating a t-dimensional emotion vector corresponding to each of the k emotion items by constructing a t-dimensional vector having as components a score for each emotion item of the t symbol combinations for each of the k emotion items. step; and
calculating a Euclidean norm of an emotion vector corresponding to each of the k emotion items as an emotion index corresponding to each of the k emotion items;
A method of operating an electronic device comprising a. delete According to claim 5,
The step of displaying the list on the screen is
When the list is configured, after selecting the first symbol combination having the maximum score for the first emotion item among the p symbol combinations included in the list, the font format of the first symbol combination is given priority in the list. A method of operating an electronic device that applies a preset emphasis format to indicate that it is a recommended symbol combination, applies the font format of the remaining symbol combinations as a preset basic format, and then displays the list to which the font format has been applied on the screen. . A computer-readable recording medium recording a computer program for executing the method of any one of claims 5, 6 or 8 through a combination with a computer. A computer program stored in a storage medium for executing the method of any one of claims 5, 6 or 8 through a combination with a computer.

Images