JP2019144884A - Information processing device, information processing method, and program - Google Patents

Abstract

To provide an information processing device, an information processing method, and a program capable of improving anonymity by changing a style.SOLUTION: An information processing device 10-1 includes: a style change unit 115 configured to receive a message based on a user input and generate a style change message in which the style has been changed; and a determination unit 113 configured to perform determination on the dissimilarity between the style of documents created by the user in the past and the style of the style change message, based on a user feature vector generated from a user-created document group that records documents created by the user in the past and an input sentence feature vector generated from the style change message.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program.

  In recent years, communication between a plurality of users is often performed via a network. On the other hand, there is a growing social demand for privacy protection, and there is a demand for smooth communication via a network while maintaining the ease of anonymous posting.

  In view of such a situation, the following Patent Document 1 includes at least information on the first terminal among messages received by the second terminal in accordance with a history of posting and reply between a plurality of users or an intimate relationship. A technique for processing and anonymizing is disclosed. In the following Patent Document 1, “anonymous” means that personal identification information such as a personal name and a user ID is not clearly indicated to other users.

JP 2009-20646 A

  However, the above-described technique may cause anonymization to be insufficient depending on users participating in communication. For example, each member in a relatively small group (for example, about 10 to 20 people) who knows each other well will usually talk to each other, exchange reports, etc. You will know the characteristics of the style. Even if only the personal identification information is anonymized by applying the above technique to communication within such a group, there is a risk that it may be estimated to some extent which message belongs to which user due to the characteristics of the style. is there.

  Therefore, the present invention has been made in view of the above problems, and the object of the present invention is a new and improved information processing that can improve anonymity by changing the style of writing. An apparatus, an information processing method, and a program are provided.

  In order to solve the above-described problem, according to an aspect of the present invention, a stylistic change unit that generates a stylistic change message in which a message based on a user input is input and changes the stylistic, and a document created by the user in the past Based on a user feature vector generated from a user-created document group in which the document is recorded, and an input sentence feature vector generated from the style change message, a style of a document created by the user in the past, and the style change message An information processing apparatus is provided that includes a determination unit that performs determination regarding the degree of dissimilarity between the text style and the style.

  When the determination unit determines that the dissimilarity is smaller than a predetermined threshold, the style change unit may receive the style change message as an input and further change the style to generate the style change message. Good.

  The information processing apparatus may further include a communication control unit that transmits the style change message when the determination unit determines that the dissimilarity is greater than or equal to a predetermined threshold.

  The information processing apparatus includes: a display control unit that displays the style change message when the determination unit determines that the dissimilarity is greater than or equal to a predetermined threshold; and the display style change message is displayed after the style change message is displayed. You may further provide the communication control part which transmits the said style change message according to a user's input.

  The style change unit may generate the style change message by changing an element characterizing the style.

  The element characterizing the sentence style may include at least one of the number of punctuation points per sentence, the number of reading points per sentence, the ratio of notation types, and the number of onomatopoeia per sentence.

  The information processing apparatus obtains a similar other sentence whose content is similar to a message based on an input of the user from a group of other persons created by recording a document created in the past by another person different from the user A personal sentence acquisition unit may be further included, and the style change unit may generate the style change message based on the similar others sentence.

  The style change unit may generate a style change message without changing the style of the quoted sentence when the message based on the user input includes a quoted sentence.

  The user feature vector may be generated using only a document that matches genre information corresponding to a message input by the user in the user-created document group.

  In order to solve the above-mentioned problem, according to another aspect of the present invention, a message based on a user input is used as an input, a style change message with a changed style is generated, and the user created in the past Based on a user feature vector generated from a user-created document group in which a document is recorded and an input sentence feature vector generated from the style change message, the style of the document created by the user in the past, and the style change An information processing method including determining a dissimilarity between a message style and a message style is provided.

  In order to solve the above-described problem, according to another aspect of the present invention, a computer receives a message based on a user's input and generates a style change message with a changed style, Based on the user feature vector generated from the user-created document group that records the document created in the above, and the input sentence feature vector generated from the style change message, the style of the document created by the user in the past, There is provided a program for realizing a function for making a determination regarding the degree of dissimilarity with the style of the style change message.

  As described above, according to the present invention, anonymity can be further improved by changing the style.

It is a figure which shows the schematic structure of the communication system 1 common to each embodiment. It is a block diagram showing an example of composition of information processor 10-1 concerning a 1st embodiment of the present invention. It is a flowchart figure which shows an example of operation | movement of the information processing apparatus 10-1 concerning the embodiment. It is a block diagram which shows an example of a structure of information processing apparatus 10-2 concerning the 2nd Embodiment of this invention. It is a flowchart figure which shows an example of operation | movement of the information processing apparatus 10-2 concerning the embodiment. It is explanatory drawing which shows the hardware structural example.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

<< 1. Basic configuration >>
First, the basic configuration of the communication system 1 common to the embodiments of the present invention will be described with reference to FIG. The communication system 1 is an information processing system that provides text communication among a plurality of users via a network while improving anonymity of users.

  FIG. 1 is a diagram showing a schematic configuration of a communication system 1 common to the embodiments. As illustrated in FIG. 1, the communication system 1 includes an information processing apparatus 10, a server 20, and a network 50.

  The information processing apparatus 10 is a terminal used by a user who participates in communication using the communication system 1. For example, the user uses the information processing apparatus 10 to input a text message that is text data (hereinafter sometimes simply referred to as a message), and the information processing apparatus 10 sends a message to the server 20 via the network 50. Send (post). In the present specification, the message may include a plurality of sentences.

  Further, the information processing apparatus 10 receives and displays messages (including messages posted by other users and / or messages transmitted from the information processing apparatus 10) from the server 20. Although only one information processing apparatus 10 is shown in FIG. 1, there are actually a plurality of information processing apparatuses 10, for example, as many information processing apparatuses 10 as there are users who use the communication system 1. Also good. Hereinafter, a user of the information processing apparatus 10 may be simply referred to as a user, and a user other than the user of the information processing apparatus 10 who participates in communication using the communication system 1 may be referred to as another user.

  In addition, the information processing apparatus 10 according to each embodiment of the present invention changes (processes) the style of the message input by the user before transmitting the message to the server 20, and changes the style of the message (hereinafter referred to as the style). May also be transmitted to the server 20. With this configuration, anonymity of a message transmitted to the server 20 is improved. For example, even if another user who knows the characteristics of the style of the user who has input the message participates in communication using the communication system 1, which user has posted the message whose style has been changed. It becomes difficult to grasp.

  The server 20 is an information processing apparatus that provides a text communication service for sharing a message posted by each user among the users. For example, the server 20 receives a message posted by each user from a terminal such as the information processing apparatus 10 via the network 50 and transmits the message posted by each user to each terminal.

  The network 50 is a wired or wireless transmission path for information transmitted from a device or system connected to the network 50. For example, the network 50 may include a public line network such as the Internet, a telephone line network, and a satellite communication network, various local area networks (LANs) including Ethernet (registered trademark), a wide area network (WAN), and the like. The network 50 may include a dedicated line network such as IP-VPN (Internet Protocol-Virtual Private Network).

  The basic configuration of the communication system 1 common to the embodiments of the present invention has been described above. Note that the communication system 1 described above may be a system used in a group such as a company that knows each other well. In such a case, since the users of the communication system 1 are members belonging to the same group, there are cases where the characteristics of the stylistic style such as each other's way of writing, writing, and wording are usually known through face-to-face conversations and report exchanges. . Therefore, the information processing apparatus 10 can more easily enjoy the effect of improving anonymity by changing the style of the message. However, it is not limited to such an example, and the communication system 1 can be used in various situations.

<< 2. Detailed description of each embodiment >>
<2-1. First Embodiment>
Next, the configuration and operation of the information processing apparatus according to the first embodiment of the present invention will be described. Hereinafter, the information processing apparatus 10 according to the first embodiment of the present invention is referred to as an information processing apparatus 10-1.
(Constitution)
FIG. 2 is a block diagram showing an example of the configuration of the information processing apparatus 10-1 according to the first embodiment of the present invention. As illustrated in FIG. 2, the information processing apparatus 10-1 according to the present embodiment includes a control unit 110, a communication unit 130, an input unit 140, a display unit 150, and a storage unit 160.

  The control unit 110 has a function of controlling each configuration of the information processing apparatus 10-1. In addition, the control unit 110 according to the present embodiment also functions as a feature acquisition unit 111, a determination unit 113, a style change unit 115, a display control unit 117, and a communication control unit 119, as illustrated in FIG.

  The feature acquisition unit 111 has a function of generating a feature vector composed of feature quantities of one document or the styles of a plurality of documents. Here, the index indicating the feature amount of the style is, for example, the number of readings per sentence, the number of reading characters per sentence, the number of characters, the number of phrases, the number of particles, the ratio of notation types such as Kanji, Hiragana and Katakana, and the reading between punctuation marks Number of characters, the number of parts of speech, the proportion of parts of speech before reading, the proportion of parts of speech before punctuation, the number of onomatopoeia per sentence, and the like. However, the present invention is not limited to this example, and the feature acquisition unit 111 may generate a feature vector using various indices.

  For example, the feature acquisition unit 111 generates a feature vector (hereinafter also referred to as a user feature vector) indicating a feature of the user's style from a user-created document group in which documents created by the user in the past are recorded (accumulated). The user-created document group may include, for example, a mail message log, a chat message log, a report, an in-house document, and the like created by the user. The user-created document group may be stored in advance in the storage unit 160, for example.

  More specifically, the feature acquisition unit 111 may calculate a feature vector of each document included in the user-created document group and generate a user feature vector based on each calculated feature vector. The user feature vector may be generated by averaging the feature vectors, or may be generated by extracting the most frequent feature vector.

  Further, the feature acquisition unit 111 generates a feature vector (hereinafter, also referred to as an input sentence feature vector) indicating a sentence style feature of the message based on the user input from the message based on the user input. The message based on the user input may be a message itself input by the user via the input unit 140 described later, or the style change unit 115 described later changes the style based on the message input by the user. The style change message generated in this way may be used.

  The feature acquisition unit 111 provides the generated user feature vector and input sentence feature vector to the determination unit 113.

  Based on the user feature vector and the input sentence feature vector generated by the feature acquisition unit 111, the determination unit 113 is used to generate the sentence style of the document created by the user in the past and the input sentence feature vector. A determination is made regarding the degree of dissimilarity between the message style. Hereinafter, the message used to generate the input sentence feature vector may be referred to as the current input message. The current input message is also a message based on the above-described user input.

  For example, the determination unit 113 uses the distance between two feature vectors (for example, Mahalanobis distance, etc.) as an index, and when the distance is greater than or equal to the i-th threshold and less than the i + 1-th threshold, “dissimilarity = i The dissimilarity may be calculated by setting “(dissimilarity = 1) is most similar”. However, the method of calculating the dissimilarity is not limited to such an example.

  For example, the determination unit 113 determines whether or not the calculated dissimilarity is greater than or equal to a predetermined threshold. If the determination unit 113 determines that the calculated dissimilarity is smaller than a predetermined threshold, the determination unit 113 provides the current input message to the style change unit 115. Further, when the determination unit 113 determines that the calculated dissimilarity is greater than or equal to a predetermined threshold, the determination unit 113 provides the current input message and the dissimilarity to the display control unit 117 and communicates the current input message. This is provided to the control unit 119.

  The style change unit 115 receives the current input message provided from the determination unit 113 as input, and generates a style change message in which the style is changed. Therefore, the current input message to be input to the style change unit 115 may be a message input by the user via the input unit 140 or a style change message generated by the style change unit 115. Good.

  As described above, the current input message is provided from the determination unit 113 to the style change unit 115 when the determination unit 113 determines that the dissimilarity is smaller than a predetermined threshold. Therefore, when the determination unit 113 determines that the dissimilarity is smaller than a predetermined threshold, the stylistic change unit 115 receives the provided current input message as input, changes the stylization, and outputs the stylistic change message. Generate.

  The style change unit 115 also provides the generated style change message to the feature acquisition unit 111. Here, as described above, the feature acquisition unit 111 generates an input sentence feature vector from the style change message provided from the style change unit 115 and provides the input sentence feature vector to the determination unit 113. Then, the determination unit 113 performs determination regarding the dissimilarity again based on the two feature vectors provided from the feature acquisition unit 111. If the dissimilarity is smaller than the threshold, the style change message is displayed as the current style change message. The input message is provided to the style change unit 115. Then, the style change unit 115 receives the style change message provided as the current input message from the determination unit 113, further changes the style, and generates the style change message again. In this way, the style change unit 115 continues to generate the style change message by changing the style with the current input message as input until the determination unit 113 determines that the dissimilarity is equal to or greater than the threshold. With this configuration, a message with a sufficiently high dissimilarity and higher anonymity can be provided to the display control unit 117 and the communication control unit 119.

  For example, the style change unit 115 may generate a style change message by changing an element that characterizes the style of the current input message to be input. The element characterizing the style used by the style change unit 115 is, for example, at least one of the number of punctuation points per sentence, the number of reading points per sentence, the ratio of notation types such as kanji, hiragana and katakana, and the number of onomatopoeia per sentence May be included.

  For example, the style change unit 115 increases or decreases the number of punctuation in the current input message to be input, increases or decreases the reading, changes (converts) the notation type such as kanji, hiragana or katakana, and inserts onomatopoeia. May be performed. An example of a message before the style change by the style change unit 115 and a message after the style change (style change message) are shown below.

Before changing style: “I found a very interesting article today.
After stylistic change: “Today I found a very interesting article, Masita! Zehi! Please look (excited)!”

  With this configuration, it is difficult to understand which user has posted the style change message even if it is seen by other users who know the characteristics of the user's usual style. Become.

  The display control unit 117 controls display on the display unit 150. For example, the display control unit 117 causes the display unit 150 to display a message input by the user via the input unit 140 or a message posted by another user received by the communication unit 130 from the server 20. In addition, when the determination unit 113 determines that the dissimilarity is equal to or greater than a predetermined threshold, the display control unit 117 displays the current input message and dissimilarity provided from the determination unit 113 on the display unit 150. It may be displayed. With this configuration, the user can check the posted (transmitted) message and the dissimilarity. The display control unit 117 may replace the message input by the user via the input unit 140 with the current input message provided from the determination unit 113 on the display unit 150 and display the message.

  The communication control unit 119 controls communication by the communication unit 130. For example, the communication control unit 119 controls the communication unit 130 to receive a message posted by another user from the server 20. Further, the communication control unit 119 controls the communication unit 130 when the determination unit 113 determines that the dissimilarity is equal to or greater than a predetermined threshold, and the current input message provided from the determination unit 113 is It is transmitted to the server 20 as a posted message by the user.

  The communication unit 130 is a communication interface that mediates communication between the information processing apparatus 10-1 and another apparatus. The communication unit 130 supports an arbitrary wireless communication protocol or wired communication protocol, and establishes a communication connection with another device, for example, via the network 50 described with reference to FIG. 1 or directly.

  As described above, the communication unit 130 transmits and receives information according to the control of the communication control unit 119. That is, when the determination unit 113 determines that the degree of dissimilarity is equal to or greater than a predetermined threshold, the communication unit 130 transmits the current input message provided from the determination unit 113 to the server 20 as a posted message by the user. May be.

  The input unit 140 receives a message input by the user. For example, the input unit 140 may include a keyboard, a touch panel, and the like.

  The display unit 150 displays various screens according to the control of the display control unit 117. That is, the display unit 150 may display the current input message and the dissimilarity provided from the determination unit 113 when the determination unit 113 determines that the dissimilarity is equal to or greater than a predetermined threshold.

  The storage unit 160 stores programs and data used for the operation of the information processing apparatus 10-1. For example, the storage unit 160 may store a user-created document group in advance as described above. The storage unit 160 may store the user feature vector generated by the feature acquisition unit 111 described above.

(Operation)
The configuration of the information processing apparatus 10-1 according to the first embodiment of the present invention has been described above. Next, the operation of the information processing apparatus 10-1 according to the present embodiment will be described with reference to FIG. FIG. 3 is a flowchart illustrating an example of the operation of the information processing apparatus 10-1 according to the present embodiment.

  As shown in FIG. 3, first, the feature acquisition unit 111 generates a user feature vector indicating the feature of the user's style from the user-created document group stored in advance in the storage unit 160 (S102). When a message is input by the user via the input unit 140 (S104), the feature acquisition unit 111 generates an input sentence feature vector indicating the style of the message from the message input by the user (S106). ). In the following, an example will be described in which a message “I found a very interesting article today.

  Subsequently, the determination unit 113 calculates a dissimilarity based on the user feature vector generated in step S102 and the input sentence feature vector generated in step S106 (S108), and the calculated dissimilarity Is determined to be greater than or equal to a predetermined threshold (S110).

  When it is determined that the dissimilarity is less than the predetermined threshold (YES in S110), the current input message is provided from the determination unit 113 to the style change unit 115, and the style change unit 115 stores the current input message. The style change message is generated by changing the style (S112). In step S112, as described above, the style change unit 115 increases or decreases the number of punctuation in the current input message to be input, increases or decreases the punctuation, changes (converts) the notation type such as kanji, hiragana, or katakana, or inserts onomatopoeia You may perform style change processing, such as doing.

  Here, the current input message input in step S112 is the message “Today I found a very interesting article. Please check it out” input in step S104. In step S112, the style change unit 115 changes the style of the message to generate, for example, a style change message such as “Let's find a very interesting article today! Zehi! Please look! Also good.

  The style change message generated in step S112 is provided as a current input message to the feature acquisition unit 111, and an input sentence feature vector is generated again from the style change message (S106). Then, the determination unit 113 calculates the dissimilarity again based on the user feature vector and the input sentence feature vector generated from the style change message (S108), and the calculated dissimilarity is equal to or greater than a predetermined threshold value. It is determined whether or not (S110). If the degree of dissimilarity is less than the predetermined threshold (YES in S110), the process proceeds to step S112 as described above, and “Today, find a very interesting article! Masashi! Zehi! Please see (excited)!” Is provided from the determination unit 113 to the style change unit 115 as the current input message.

  As described above, the processes in steps S106 to S112 are repeated until the determination unit 113 determines that the dissimilarity is equal to or greater than a predetermined threshold. If it is determined that the dissimilarity is equal to or higher than the predetermined threshold (NO in S110), the communication control unit 119 controls the communication unit 130 to send the current input message to the server 20 as a posted message by the user. Transmit (S116).

(effect)
The first embodiment of the present invention has been described above. According to this embodiment, a user who wants to improve anonymity in text communication can post a style change message in which the style has been changed with peace of mind.

<2-2. Second Embodiment>
Next, the configuration and operation of the information processing apparatus according to the second embodiment of the present invention will be described. Hereinafter, the information processing apparatus 10 according to the second exemplary embodiment of the present invention is referred to as an information processing apparatus 10-2.

(Constitution)
FIG. 4 is a block diagram showing an example of the configuration of the information processing apparatus 10-2 according to the second embodiment of the present invention. As illustrated in FIG. 4, the information processing apparatus 10-2 according to the present embodiment includes a control unit 120, a communication unit 130, an input unit 140, a display unit 150, and a storage unit 170. Among the components shown in FIG. 4, the components having substantially the same functional configuration as the components shown in FIG.

  The control unit 120 has a function of controlling each configuration of the information processing apparatus 10-2. As shown in FIG. 4, the control unit 120 according to the present embodiment includes a feature acquisition unit 111, a display control unit 117, a communication control unit 119, a determination unit 123, a similar others sentence acquisition unit 124, and a style change unit. 125 also functions. Among the functions of the control unit 120 shown in FIG. 4, the functions as the feature acquisition unit 111, the display control unit 117, and the communication control unit 119 have been described above with reference to FIG. .

  Similar to the determination unit 113 according to the first embodiment described with reference to FIG. 2, the determination unit 123 calculates the dissimilarity based on the user feature vector and the input sentence feature vector. Judgment on similarity is performed. However, when the determination unit 123 according to the present embodiment determines that the calculated dissimilarity is smaller than a predetermined threshold, the current input message is not only the stylistic change unit 125 but also the similar others sentence acquisition unit. It differs from the determination unit 113 according to the first embodiment in that it is also provided to 124.

  The similar other sentence acquisition unit 124 acquires a similar other sentence whose content is similar to that of the current input message from the other person created document group in which documents created by others different from the user are recorded in the past. The other person created document group may include, for example, a mail message log, a chat message log, a report, an in-house document, and the like created by another person. The other person created document group may be stored in advance in the storage unit 170, for example.

  The similar stranger sentence acquisition unit 124 has, for example, a function of acquiring the feature of the sentence content and a function of calculating the similarity of the feature characteristics of the two sentences, and the current input message and the other person-created document group The degree of similarity may be calculated between each document included in the document. Then, one or more sentences having a high degree of similarity may be acquired as a similar other person sentence from the other person created document group, and the acquired similar other person sentence may be provided to the style change unit 125.

  In addition, as a method of acquiring the feature of the content of a sentence, the method of acquiring a word vector etc. are mentioned, for example. Further, as a method for calculating the similarity between the features of the contents of two sentences, a method using the cosine similarity of the word vectors of each sentence as an index, and the like can be cited. When the cosine similarity is equal to or higher than the threshold value, it can be determined that “content features are similar”. However, the method of acquiring the feature of the content of the sentence performed by the similar others sentence acquisition unit 124 and the method of calculating the similarity of the feature of the contents of the two sentences are not limited to this example.

  The style change unit 125 receives the current input message provided from the determination unit 123 as an input, and changes the style according to the style change unit 115 according to the first embodiment described with reference to FIG. Generate a message. However, the style change unit 125 according to the present embodiment is based on the similar other person sentence provided from the similar other person sentence acquisition unit 124, and generates a style change message according to the first embodiment. Different from 125.

  For example, the style change unit 125 may change the style by replacing the current input message with the similar others sentence provided from the similar others sentence acquisition unit 124. Note that such replacement is not limited to replacing all of the current input message with the similar other sentence, but includes replacing at least a part of the current input message with at least a part of the similar other sentence.

  In addition, the style change unit 125 may generate a message in which the current input message is replaced with a similar other sentence as a style change message, or for a message in which the current input message is replaced with a similar other sentence, Further style change processing may be performed. For example, the style change unit 125 may generate a style change message by changing an element that characterizes the style of a message in which the current input message is replaced with a similar others sentence. In addition, since the change of the element characterizing the style is described in the first embodiment, the description thereof is omitted here.

  The storage unit 170 stores a program and data used for the operation of the information processing apparatus 10-2, similarly to the storage unit 160 according to the first embodiment described with reference to FIG. However, in addition to the data stored in the storage unit 160 according to the first embodiment, the storage unit 170 according to the present embodiment may store the above-described other person-created document group in advance.

(Operation)
The configuration of the information processing apparatus 10-2 according to the second embodiment of the present invention has been described above. Next, the operation of the information processing apparatus 10-2 according to the present embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing an example of the operation of the information processing apparatus 10-2 according to the present embodiment.

  As shown in FIG. 5, first, the feature acquisition unit 111 generates a user feature vector indicating the feature of the user's style from the user-created document group stored in advance in the storage unit 160 (S202). When a message is input by the user via the input unit 140 (S204), the feature acquisition unit 111 generates an input sentence feature vector indicating the style of the message from the message input by the user (S206). ). In the following, an example will be described in which a message “Please read because I found an interesting article just before” is input in step S204.

  Subsequently, the determination unit 123 calculates the dissimilarity based on the user feature vector generated in step S202 and the input sentence feature vector generated in step S206 (S208), and the calculated dissimilarity Is determined to be greater than or equal to a predetermined threshold (S210).

  When it is determined that the dissimilarity is less than the predetermined threshold (YES in S210), the current input message is provided from the determination unit 123 to the similar other sentence acquisition unit 124, and the similar other sentence acquisition unit 124 A similar others sentence similar to the current input message is acquired from the others created document group (S212). In step S212, the similar others sentence acquisition unit 124 acquires the characteristics of the contents of the current input message and the characteristics of the contents of each sentence acquired from the other person-created document group, and determines the similarity of these characteristics. One or more sentences with high similarity may be calculated and acquired as similar others sentences.

  Here, the current input message input in step S212 is the message “please read because I found an interesting article a while ago” input in step S204. In step S212, the similar other sentence acquisition unit 124 may acquire, for example, a sentence “I found a very interesting article today. Good.

  Subsequently, the style change unit 125 changes the style of the current input message provided from the determination unit 123 based on the similar others sentence acquired in step S212, and generates a style change message (S214).

  In step S214, the style change unit 125 may generate the style change message by changing the element characterizing the style after replacing the current input message with a similar others sentence. For example, in step S214, the style change unit 125 changes the style of the message replaced with the above-mentioned similar others sentence, and “Today, find a very interesting article! Masashi! Zehi! Please see (excited)!” May be generated.

  The style change message generated in step S214 is provided as a current input message to the feature acquisition unit 111, and an input sentence feature vector is generated again from the style change message (S206). Then, the determination unit 123 calculates the dissimilarity again based on the user feature vector and the input sentence feature vector generated from the style change message (S208), and the calculated dissimilarity is equal to or greater than a predetermined threshold value. It is determined whether or not (S210). If the degree of dissimilarity is less than the predetermined threshold (YES in S210), the process proceeds to step S212 as described above, and “Today, find a very interesting article! Masita! Zehi! Please see (excited!)!” Is provided from the determination unit 113 to the similar others sentence acquisition unit 124 as the current input message.

  As described above, the processes in steps S206 to S214 are repeated until the determination unit 123 determines that the dissimilarity is equal to or greater than the predetermined threshold. In the second and subsequent iterations, step S212 may be skipped, and only the style change processing that does not use the similar others sentence may be performed.

  When it is determined that the dissimilarity is equal to or higher than the predetermined threshold (NO in S210), the communication control unit 119 controls the communication unit 130 to transmit the current input message to the server 20 as a posted message by the user. (S216).

(effect)
The second embodiment of the present invention has been described above. According to the present embodiment, the style of the message can be changed based on a similar other sentence whose content is similar to the input message, so that the impression of the style can be further greatly changed. As a result, a user who wants to improve anonymity in text communication can post a style change message whose style has been changed with more peace of mind.

<< 3. Modification >>
The embodiments of the present invention have been described above. Below, some modifications of each embodiment of the present invention are explained. Each modification described below may be applied to each embodiment of the present invention alone, or may be applied to each embodiment of the present invention in combination. Each modification may be applied instead of the configuration described in each embodiment of the present invention, or may be additionally applied to the configuration described in each embodiment of the present invention.

<3-1. Modification 1>
In the above-described embodiment, when the dissimilarity is determined to be equal to or greater than the predetermined threshold, the example in which the current input message related to the dissimilarity is automatically transmitted has been described. It is not limited. For example, the user may be asked for confirmation before sending the current input message.

  In such a case, for example, after the current input message is displayed on the display unit 150 under the control of the display control unit 117, the communication control unit 119 responds to the user input via the input unit 140 and the current input message. May be transmitted.

  For example, when the user performs an input to approve replacement of the message input by the user with the current input message, the communication control unit 119 may cause the current input message to be transmitted. Also, if the user makes an input that refuses to replace the message entered by the user with the current input message, for example, the current input message is used as an input to change the style (for example, FIG. 3). Steps S106 to S112) may be performed again.

  According to such a configuration, even when the style of the message is changed, the user can check the message after the style change and check whether or not the message can be transmitted as his / her own posted message. .

<3-2. Modification 2>
In each of the above embodiments, an example has been described in which the feature acquisition unit 111 calculates the feature vector of each document included in the user-created document group and generates the user feature vector based on the calculated feature vector. However, if one user feature vector is generated using all the documents included in the user-created document group, the user feature vector may not appropriately indicate the feature of the user's style.

  For example, if a user-created document group includes documents of various genres (for example, emails, reports, patent proposals, chat logs, etc.), even if these documents are all created by the same user, Depending on the user's style, the characteristics of the user's style may be different. Therefore, the feature acquisition unit 111 may generate a user feature vector using only a document that matches the genre information specified so as to correspond to the message input by the user in the user-created document group.

  In such a case, genre information indicating a genre may be added to each document included in the user-created document group. Then, the feature acquisition unit 111 extracts a document that matches the genre information specified to correspond to the message input by the user from the user-created document group, calculates a feature vector of each extracted document, and calculates A user feature vector may be generated based on each feature vector that has been set.

  According to such a configuration, since the determination process is performed using the user feature vector corresponding to the genre information corresponding to the input message, the anonymity of the finally transmitted message can be further improved.

<3-3. Modification 3>
In each of the above-described embodiments, the example has been described in which the style change unit (the style change unit 115 or the style change unit 125) generates the style change message by changing the style of the current input message. However, for example, when a quoted sentence is included in the message before the style change, if the style change is applied to the quoted sentence, the difference in style from the quote source may cause confusion. Therefore, in the following, a modified example in which a quoted sentence is excluded from the style change target will be described.

  The style change unit according to this modification generates the style change message without changing the style of the quoted text included in the current input message provided from the determination unit 113. For example, for the part of the current input message that has been determined to be a quoted sentence, the elements that characterize the sentence style are not changed or replaced by similar others sentences. A style change message may be generated.

  The method for determining a quote from the current input message is not particularly limited. For example, as in the second embodiment described above, another person-created document group is prepared in advance, and among the sentences included in the current input message, a sentence whose number of characters is equal to or greater than a predetermined threshold is included in the other-person-created document group. If so, the sentence may be determined to be a quoted sentence. Or, when the sentences included in the current input message are compared with the sentences whose number of characters is above the threshold, and the sentences included in the other person's created document group, both the style and content are similar The sentence may be determined to be a quoted sentence. In addition, by acquiring the words and phrases that are used in the sentences included in the current input message, and by obtaining documents with a high degree of duplication of such words and phrases, it is possible to efficiently locate the sentences including the quoted sentences. You may get it.

  According to this modification, it is possible to avoid the confusion of the user who posts the message and other users by excluding the quoted sentence from the subject of the style change.

<3-4. Modification 4>
Further, the present invention is not limited to the configuration described in the above embodiment, and the functions of the plurality of devices described above may be provided in one device, or one device among the devices described above. These functions may be divided into a plurality of devices.

  For example, the information such as the user-created document group and the other company-created document group described above is not limited to the example stored in the storage unit included in the information processing apparatus 10, but is stored in advance in another apparatus, and the information is stored as necessary. The information may be transmitted from another device to the information processing device 10.

  Further, the server 20 may be provided with some functions of the information processing apparatus 10 described above. For example, the information processing apparatus 10 has a function as an interface for inputting and displaying a message by the user, and the server 20 has the above-described feature acquisition unit 111, determination units 113 and 123, stylistic change units 115 and 125, and the like. It may have a function of the person sentence acquisition unit 124 and the like.

<3-5. Modification 5>
Moreover, although the said embodiment demonstrated the example to which embodiment of this invention is applied to the system which performs communication by a text, this invention is not limited to this example. Input and output are not limited to text data as long as a message that is at least text data can be processed. For example, the input may be voice, and in such a case, the style may be changed as described above for a message obtained by converting the input voice into text data by voice recognition. Further, the output may be voice, and in such a case, the message whose style has been changed may be converted into voice data by a voice synthesis technique or the like and then output as voice.

<< 4. Hardware configuration >>
The embodiments of the present invention have been described above. Information processing such as the above-described feature acquisition processing, determination processing, style change processing, display control processing, communication control processing, and the like is realized by cooperation between software and the hardware of the information processing apparatus 10 and the server 20. Hereinafter, a hardware configuration of the information processing apparatus 1000 will be described as an example of a hardware configuration of the information processing apparatus 10 and the server 20 that are information processing apparatuses according to the embodiment of the present invention.

  FIG. 6 is an explanatory diagram showing a hardware configuration of the information processing apparatus 1000 according to the embodiment of the present invention. As shown in FIG. 6, the information processing apparatus 1000 includes a CPU (Central Processing Unit) 1001, a ROM (Read Only Memory) 1002, a RAM (Random Access Memory) 1003, an input device 1004, and an output device 1005. A storage apparatus 1006 and a communication apparatus 1007.

  The CPU 1001 functions as an arithmetic processing unit and a control unit, and controls the overall operation in the information processing apparatus 1000 according to various programs. Further, the CPU 1001 may be a microprocessor. The ROM 1002 stores programs used by the CPU 1001 and calculation parameters. The RAM 1003 temporarily stores programs used in the execution of the CPU 1001, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus including a CPU bus. Mainly, the functions of the control units 110 and 120, for example, are realized by the cooperation of the CPU 1001, the ROM 1002, the RAM 1003, and the software.

  The input device 1004 includes input means for a user to input information, such as a mouse, keyboard, touch panel, button, microphone, switch, and lever, and an input control circuit that generates an input signal based on the input by the user and outputs the input signal to the CPU 1001 Etc. A user of the information processing apparatus 1000 can input various data and instruct a processing operation to the information processing apparatus 1000 by operating the input device 1004. Note that the input device 1004 corresponds to the input unit 140.

  The output device 1005 includes a display device such as a liquid crystal display (LCD) device, an OLED device, and a lamp. Furthermore, the output device 1005 includes an audio output device such as a speaker and headphones. For example, the display device displays a captured image or a generated image. On the other hand, the audio output device converts audio data or the like into audio and outputs it. Note that the output device 1005 corresponds to the display unit 150.

  The storage device 1006 is a device for storing data. The storage device 1006 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded on the storage medium, and the like. The storage device 1006 stores programs executed by the CPU 1001 and various data. The storage device 1006 corresponds to the storage units 160 and 170.

  The communication device 1007 is a communication interface configured with, for example, a communication device for connecting to a communication network. Further, the communication device 1007 may include a wireless LAN (Local Area Network) compatible communication device, an LTE (Long Term Evolution) compatible communication device, a wire communication device that performs wired communication, or a Bluetooth (registered trademark) communication device. Note that the communication device 1007 corresponds to the communication unit 130.

<< 5. Conclusion >>
As described above, according to the embodiment of the present invention, it is possible to improve anonymity by changing the style.

  The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention pertains can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that these also belong to the technical scope of the present invention.

  For example, each step in the above embodiment does not necessarily have to be processed in time series in the order described as a flowchart. For example, each step in the processing of the above embodiment may be processed in an order different from the order described as the flowchart diagram or may be processed in parallel.

  Further, according to the embodiment, it is possible to provide a computer program for causing hardware such as the CPU 1001, the ROM 1002, and the RAM 1003 to perform the same functions as the components of the information processing apparatus 10 described above. A recording medium on which the computer program is recorded is also provided.

DESCRIPTION OF SYMBOLS 1 Communication system 10 Information processing apparatus 20 Server 50 Network 110 Control part 111 Feature acquisition part 113 Judgment part 115 Stylistic change part 117 Display control part 119 Communication control part 124 Similar others sentence acquisition part 130 Communication part 140 Input part 150 Display part 160 Memory

Claims (11)

A stylistic change unit that generates a stylistic change message in which a message based on a user input is input,
A document created by the user in the past based on a user feature vector generated from a user-created document group recording documents created by the user in the past and an input sentence feature vector generated from the style change message A determination unit that performs a determination on the dissimilarity between the style of the text and the style of the style change message;
An information processing apparatus comprising:   When the determination unit determines that the dissimilarity is smaller than a predetermined threshold, the style change unit receives the style change message as an input, and further changes the style to generate the style change message. Item 4. The information processing apparatus according to Item 1.   The information processing apparatus according to claim 1, further comprising a communication control unit configured to transmit the style change message when the determination unit determines that the dissimilarity is equal to or greater than a predetermined threshold. A display control unit that displays the style change message when the determination unit determines that the dissimilarity is greater than or equal to a predetermined threshold;
The information processing apparatus according to claim 1, further comprising: a communication control unit configured to transmit the style change message in response to an input of the user after the style change message is displayed.   The information processing apparatus according to claim 1, wherein the style change unit generates the style change message by changing an element characterizing the style.   The information processing apparatus according to claim 5, wherein the elements characterizing the sentence style include at least one of the number of punctuation points per sentence, the number of reading points per sentence, the ratio of notation types, and the number of onomatopoeia per sentence. . A similar other sentence acquisition unit that acquires a similar other sentence whose content is similar to a message based on the user's input from a group of other persons created by recording documents previously created by another person different from the user; Prepared,
The information processing apparatus according to claim 1, wherein the style change unit generates the style change message based on the similar others sentence.   The style change unit generates a style change message without changing the style of the quoted sentence when a quoted text is included in the message based on the user's input. The information processing apparatus described in 1.   The said user feature vector is produced | generated only using the document suitable for the genre information corresponding to the message input by the said user among the said user created document groups. Information processing device. Taking a message based on the user's input as input, generating a style change message with a changed style,
A document created by the user in the past based on a user feature vector generated from a user-created document group recording documents created by the user in the past and an input sentence feature vector generated from the style change message Determining the dissimilarity between the style of the text and the style of the style change message,
An information processing method including: On the computer,
A function for generating a stylistic change message that takes a message based on the user's input as input and changed the style,
A document created by the user in the past based on a user feature vector generated from a user-created document group recording documents created by the user in the past and an input sentence feature vector generated from the style change message A function for determining the dissimilarity between the style of the text and the style of the style change message;
A program to realize

Images