WO2023017690A1

WO2023017690A1 - Information processing device, information processing method, and information processing program

Info

Publication number: WO2023017690A1
Application number: PCT/JP2022/025966
Authority: WO
Inventors: 勇也西村
Original assignee: 株式会社エッセンス
Priority date: 2021-08-10
Filing date: 2022-06-29
Publication date: 2023-02-16
Also published as: JP7373213B2; JP2023025470A

Abstract

The present invention provides an information processing device, an information processing method, and an information processing program that can group users to be used to recommend a document. The information processing device comprises: a storage unit that stores a document, specific positions of indicators attached by a user to prescribed units obtained by dividing the document, and association information associating the document with a user classification estimated on the basis of the specific positions; a first acquisition unit that acquires user information pertaining to the specific positions of the indicators added by a first user when the first user read the document; an estimation unit that estimates, on the basis of the user information acquired by the first acquisition unit and the association information stored in the storage unit, a classification according to the specific positions designated by the first user; and a group setting unit that groups a plurality of first users for each classification estimated by the estimation unit.

Description

Information processing device, information processing method and information processing program

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

2. Description of the Related Art Conventionally, there is a device (document retrieval device) for retrieving documents. As described in Japanese Patent Laid-Open No. 2002-200012, there is a document search device specialized for searching patent documents.
The document search device described in Patent Literature 1 searches for patent documents that match a search keyword, and when the search result is browsed, associates the browse with the document and stores it as a search history. Furthermore, the document search device calculates the similarity based on the search history of other users and the search history of the current user, and among the patent documents viewed by other users with the highest calculated similarity, the current recommend patent documents that have not been viewed by users of

JP 2014-186607 A

As described above, the document search device described in Patent Document 1 recommends patent documents depending on whether or not the search result based on the search keyword has been viewed. However, in general, literature includes not only patent literature but also various other literature. In this case, the user may wish to read a document that suits his or her taste, and the document retrieval device described in Patent Document 1 cannot set the search keyword according to the user's preference. There is a possibility that recommendations according to the user's preferences cannot be made.

The present invention provides an information processing device, an information processing method, and an information processing program capable of grouping users to be used for recommending sentences.

An information processing apparatus according to one aspect includes a text, a specific position where a user attaches an index to a predetermined unit when the text is divided into predetermined units, and a user classification estimated based on the text and the specific position. a first acquisition unit for acquiring user information about a specific position marked by the first user when the first user reads a sentence; an estimation unit for estimating a classification corresponding to a specific position of the first user based on the acquired user information and the corresponding information stored in the storage unit; and a plurality of first users for each classification estimated by the estimation unit. and a group setting unit that performs grouping.

According to one aspect, when the first user reads a text, user information about a specific position marked by the first user is acquired, and based on the user information and the corresponding information, the specific position of the first user is displayed. Since the corresponding classification is estimated and a plurality of first users are grouped for each classification, it is possible to group users to be used for recommending sentences.

1 is a diagram for explaining an information processing device according to an embodiment; FIG. 1 is a block diagram for explaining an information processing device according to an embodiment; FIG. FIG. 4 is a diagram showing the relationship between visible variable vectors and hidden variable vectors; 4 is a first flowchart for explaining an information processing method according to one embodiment; 7 is a second flowchart for explaining the information processing method according to one embodiment; 9 is a third flowchart for explaining the information processing method according to one embodiment;

An embodiment will be described below.

[Overview of information processing device]
First, an outline of an information processing device 1 according to an embodiment will be described.
FIG. 1 is a diagram for explaining an information processing device 1 according to one embodiment.

For example, the information processing device 1 may be configured as a group forming device for grouping users to be used for recommending texts, or may be configured as a text recommendation device for recommending texts to users in a group.
The information processing device 1 may be, for example, a computer such as a server, laptop, desktop, tablet, and smart phone.

The information processing apparatus 1, for example, classifies users into one of a plurality of groups, and recommends sentences read by users in one group to other users in the group. In this case, the information processing device 1 first classifies the users into groups based on the correspondence information.
Here, the correspondence information is estimated based on, for example, the text 201, the specific position where the user attaches an index to the predetermined unit when the text 201 is divided into predetermined units, and the text 201 and the specific position. It may also be information that associates a user classification (for example, a classification for grouping users). As an example, the corresponding information is a sentence 201 and a sentence 201 divided into clauses (predetermined units) for each punctuation mark. It may be information that associates (specific position) with a group classification when users having the same (substantially the same or similar) tendency are grouped based on the positions of the text 201 and the bookmark 202 . As a more specific example, as illustrated in FIG. 1, the correspondence information may be information about groups A and B classified according to the sentence 201 and the position of the bookmark 202 . Correspondence information may be stored in the storage unit 21 .

For example, when a first user as a new user reads a text 101 and attaches a bookmark 102 (index) to a clause (predetermined unit) of the text 101 that the first user is interested in, the User information about the position (specific position) of the bookmark 102 is acquired.
The information processing device 1 classifies the first users into groups, for example, based on the correspondence information and the user information. That is, based on the correspondence information and the user information, the information processing apparatus 1 groups a plurality of first users who have the same (substantially the same or similar) tendency with respect to the portion of the text 101 that interests them. A plurality of first users are classified into the same group.
As a more specific example, as illustrated in FIG. 1, the information processing apparatus 1 acquires user information bookmarked 102 by first users C, D, and E after reading sentences 101 . In the information processing apparatus 1, for example, the text 101 and the specific position of the bookmark 102 as the user information of the first users C, D, and E correspond to the text 101 and the bookmark 102 in any of the groups A and B as the correspondence information. It is determined whether the specific position of corresponds. That is, for example, the information processing apparatus 1 determines whether the specific positions of the text 101 and the bookmark 102 of the user information are the same (substantially the same or similar) as the specific positions of the text 201 and the bookmark 202 of the corresponding information. Classify C, D and E into either group A or B. In the case illustrated in FIG. 1, the information processing device 1 estimates that the first users C and D belong to the same group, and the first user E belongs to another group.
In the case illustrated in FIG. 1, the information processing apparatus 1 detects, for example, a text read by the first user C who belongs to the same group, and if there is a text not read by the first user D, the text read by the first user C is recommended to the first user D.

[Details of information processing device 1]
Next, details of the information processing apparatus 1 according to one embodiment will be described.
FIG. 2 is a block diagram for explaining the information processing device 1 according to one embodiment.

The information processing device 1 includes, for example, a storage unit 21, a communication unit 22, a display unit 23, a control unit 10, and the like. The control unit 10 includes, for example, a first acquisition unit 11, an estimation unit 12, a group setting unit 13, a second acquisition unit 14, a specification unit 15, a recommendation unit 16, and the like. The control unit 10 may be configured by, for example, an arithmetic processing unit of the information processing device 1 or the like. For example, by appropriately reading and executing various programs stored in the storage unit 21 or the like, the control unit 10 controls each unit (for example, the first acquisition unit 11, the estimation unit 12, the group setting unit 13, the second acquisition unit 14). , the identifying unit 15, the recommending unit 16, etc.).

The storage unit 21 may store various information and programs, for example. Examples of the storage unit 21 may be a memory, a solid state drive, a hard disk drive, and the like. The storage unit 21 may be, for example, inside the information processing device 1 or outside the information processing device 1 .

The storage unit 21 associates a text with a specific position where the user marks a predetermined unit when the text is divided into predetermined units, and a user classification estimated based on the text and the specific position. Store the attached correspondence information. As described above, the corresponding information is, for example, a sentence, and when the sentence is divided into clauses (predetermined units) for each punctuation mark and bookmarks (indicators) are added to sentences (clauses) that the user is interested in. and a group classification when users having the same (substantially the same or similar) tendency are grouped based on the position of the text and the bookmark. .

Here, the text may be, for example, an interview article created when the researcher is interviewed, or may be an article other than the interview article. The specific position may be, for example, the position of a clause when a sentence (interview article) is divided into clauses as a predetermined unit.
Further, as an example, the control unit 10 and the like may divide sentences by punctuation when dividing sentences into clauses as predetermined units. As a specific example, the control unit 10 and the like may divide sentences into clauses based on a learning model in which punctuation is learned in advance and sentences. The control unit 10 and the like may divide sentences into clauses by various processing methods, not limited to the specific example described above. In addition, the control unit 10 or the like divides the text into specific units, and is not limited to the example of dividing the sentences into specific units as described above. Each page, etc.) may be used to separate sentences.

The corresponding information may be further associated with one or more recommended sentences recommended for each user classification. The recommended sentence may be, for example, a sentence recommended to the first user in the group classified by the specifying unit 15, which will be described later. The recommendation text may be, for example, an interview article created when the researcher is interviewed.

The communication unit 22 is capable of transmitting and receiving various information with, for example, a device outside the information processing device 1 (external device). The external device may be, for example, an external server (not shown), the user terminal 100 (see FIG. 1), or the like. The user terminal 100 may be, for example, a terminal or the like used by a user (for example, a first user or the like). User terminal 100 may be, for example, a desktop, a laptop, a tablet, a smart phone, and the like.

The display unit 23 can display, for example, various characters, symbols and images.

The first acquisition unit 11 acquires user information about a specific position marked by the first user when the first user reads a sentence.
As an example, when displaying text stored in a storage area on a display, if the first user finds a part of the text that interests him or the like, he operates an input unit (not shown) or the like, An index (for example, a bookmark or the like) is attached to an interesting part (specific position) in the text. Here, the storage area may be various storage areas such as the storage unit 21, an external server (not shown), and a terminal storage unit (not shown) of the user terminal 100, for example. The display may be, for example, the display unit 23, a terminal display unit (not shown) of the user terminal 100, or the like. The input unit may be, for example, a keyboard (eg, hard keys, soft keys, etc.), a mouse, and the like.
For example, when an index is attached to a sentence in the user terminal 100 , the first acquisition unit 11 acquires information about the specific position to which the index is attached from the user terminal 100 via the communication unit 22 . Alternatively, for example, when an index is attached to a predetermined unit in the information processing device 1, the first acquisition unit 11 acquires information about the specific position to which the index is attached.

Here, the text may be, for example, an interview article created when interviewing a researcher, as described above. Also, the specific position may be, for example, the position of a clause when a sentence (interview article) is segmented into clauses as a predetermined unit, as described above. Therefore, when the first user reads the interview article, the first acquisition unit 11 obtains user information about the specific position of one or more indicators attached to the specific clause of the interview article as a reference for the first user. may be obtained.

Based on the user information acquired by the first acquisition unit 11 and the correspondence information stored in the storage unit 21, the estimation unit 12 estimates the classification according to the specific position of the first user. If the specific position of the text recorded in the user information is the same (or substantially the same) or similar to the specific position of the text recorded in the corresponding information, the estimating unit 12 detects the specific position of the text recorded in the user information. is relatively close to the specific position of the sentence recorded in the corresponding information, the first user is presumed to belong to the category recorded in the corresponding information. Here, the text recorded in the user information and the text recorded in the correspondence information may be the same, for example.

When estimating the classification corresponding to the specific position of the first user, the estimation unit 12 may perform the following processing as an example.
FIG. 3 is a diagram showing the relationship between visible variable vectors and hidden variable vectors.

As an example, the estimating unit 12 uses the contrastive divergence method or the like to perform mutual sampling of the visible variable vector and the hidden variable vector as illustrated in FIG. 3, thereby classifying the first user. can be estimated.

That is, as an example, the estimating unit 12 constructs a model (relationship illustrated in FIG. 3) for estimating hidden human characteristics "h" based on correspondence information using visible data "V" based on user information. may
The visible data V is data indicating a specific position (clause) with an index (bookmark) attached to a sentence based on user information. Vectorizing the visible data V results in the following visible variable vector. Here, N indicates the number of clauses in the entire sentence. In the visible variable vector, there are N for each first user.

　Hidden personal characteristics h indicate the assumed personal characteristics of each user based on the corresponding information. That is, the hidden person characteristic h is a person characteristic hypothesis when it is assumed that a person exists. Vectorizing the hidden person characteristic h results in the following hidden variable vector.

　The following probability distribution is provided between the visible data V and the hidden human characteristics h, and is governed by the following formula. Here, T indicates the transposition of the vector, and b, c, and w indicate the parameters.

The group setting unit 13 groups a plurality of first users for each classification estimated by the estimation unit 12 . When the estimation unit 12 estimates the classification of a plurality of first users, the group setting unit 13 groups the plurality of first users for each classification.

Here, as exemplified in FIG. 1, when the control unit 10 acquires user information corresponding to each of the first users C, D, and E reading the text and adding the index, the user information and , and the correspondence information, the classification of the first users C, D, and E is estimated. Here, in the case of FIG. 1, the control unit 10 presumes that the first users C and D belong to the same classification and the first user E belongs to another classification. , and the first user E is grouped.

The second acquisition unit 14 acquires sentence information related to sentences read by the plurality of first users based on the user information of each of the plurality of first users grouped by the group setting unit 13 .
In the case of FIG. 1, the second acquisition unit 14 obtains the first user C's , D acquire text information about the text read. The text information may be, for example, information that can identify the text read by the first users C and D. By way of example, textual information may be information that can identify various texts, including text content, author, title, researcher interviewed, publisher and publication date, and the like.
In the same manner as described above, in the case illustrated in FIG. 1, the second acquisition unit 14, based on the user information when each of the first users E in the same group puts an index (for example, a bookmark) in a sentence, Sentence information related to the sentence read by the first user E is acquired.

The specifying unit 15 is a second user and a third user among the plurality of first users grouped by the group setting unit 13, and the text information of the second user acquired by the second acquiring unit 14; Based on the third user's sentence information, the second user identifies sentences that the third user has not read among the sentences read by the second user.
In the case of FIG. 1, as an example, the identification unit 15 determines, based on the text information of the first users C and D in the same group, that although the first user C is reading the text, the first user D Identify sentences you haven't read. That is, the identifying unit 15 identifies sentences that the first user D (third user) has not read among the sentences read by the first user C (second user).

The identifying unit 15 selects a fourth user among the plurality of first users grouped by the group setting unit 13 and selects a fourth user among the recommended sentences associated in the correspondence information stored in the storage unit 21 . 2 Based on the text information of the fourth user acquired by the acquisition unit 14, recommended texts that the fourth user has not read may be specified.
In the case illustrated in FIG. 1, as an example, the specifying unit 15 selects the first users C, D ( A recommended sentence that the fourth user) has not read is specified.
Similarly, in the case of FIG. 1, the identification unit 15 selects the first user E (fourth user) among the recommended sentences recorded in the correspondence information based on the sentence information of the first user E in the same group. Identify recommended texts that have not read.

The recommendation unit 16 recommends the text identified by the identification unit 15 to the third user.
In the case illustrated in FIG. 1, as an example, the recommendation unit 16 determines that, among the sentences F, G, and H read by the first user C (second user) by the identification unit 15, the first user D (third user) When sentence H is identified as a sentence that has not been read, sentence H is recommended to first user D (third user) (here, symbols F, G, and H are not shown in FIG. 1). Here, as an example, the recommendation unit 16 may control the communication unit 22 to transmit the text information of the text H to the user terminal 100 used by the first user D (third user). As another example, the recommendation unit 16 may control the display unit 23 to display the text information of the text H.

The recommendation unit 16 may recommend the recommended text identified by the identification unit 15 to the fourth user.
In the case illustrated in FIG. 1, as an example, the recommendation unit 16 causes the specification unit 15 to specify the recommended text K as the recommended text that the first user D (fourth user) has not read among the recommended texts (I, J, K). If identified, recommended sentence K is recommended to first user D (fourth user) (where symbols I, J, and K are not shown in FIG. 1). As an example, the recommendation unit 16 may control the communication unit 22 to transmit the recommended sentence information of the recommended sentence K to the user terminal 100 used by the first user D (fourth user). As another example, the recommendation unit 16 may control the display unit 23 to display the text information of the recommended text K. FIG. The recommendation unit 16, for example, similarly recommends a recommendation sentence for the first user C (fourth user).
Similarly, in the case of FIG. 1, as an example, the recommendation unit 16 selects a recommended text from among the recommended texts (I, J, K) that the first user E (fourth user) has not read, by the specifying unit 15. When J is identified, recommended sentence J is recommended to first user E (fourth user). As an example, the recommendation unit 16 may control the communication unit 22 to transmit the recommended sentence information of the recommended sentence J to the user terminal 100 used by the first user E (fourth user). As another example, the recommendation unit 16 may control the display unit 23 to display the recommended sentence information of the recommended sentence J. FIG.
As an example, the recommended text information may be associated with the recommended text of the corresponding information, and includes various recommendations including recommended text content, author, title, interviewed researcher, publisher, publication date, and the like. Information that can specify a sentence may be used.

[Information processing method]
Next, an information processing method according to one embodiment will be described.

First, an overview of the information processing method will be described.
As step ST1, the control unit 10 learns parameters b, c, and w based on output results of visible data V as user information and hidden person characteristics h as corresponding information. As an example, the control unit 10 may perform learning based on the gradient method for the parameters b, c, and w. In this case, the control unit 10 may stop learning when the range of change is small and falls below a predetermined standard. The predetermined criterion may be determined based on learning data and actual learning conditions. The estimation unit 12 may learn the parameters b, c, and w at predetermined timings.

As step ST2, the control unit 10 uses the past visible data V of the first user to output the person characteristic h (classification of the first user) for the first user (sampling). Furthermore, the control unit 10 outputs (sampling) the visible data V again from the person characteristics h (classification of the first user), and predicts the reaction of the first user to the unread text. In this case, the control unit 10 excludes read sentences from the recommendation and recommends only unread sentences.

At step ST3, the control unit 10 recommends, to the first user, sentences that are expected to respond favorably to the first user among the unread sentences.

Next, the information processing method according to one embodiment will be specifically described with reference to FIGS.

First, processing for estimating the classification of the first user will be described as an information processing method according to an embodiment.
FIG. 4 is a first flowchart for explaining an information processing method according to one embodiment.

In step ST101, the first acquisition unit 11 acquires user information. The user information may be information about a specific position to which the first user marks (bookmarks) when the first user reads the text. The specific position may be, for example, the position of the indexed clause in the sentence, ie information that characterizes the indexed clause.
In this case, for example, when the first user reads the interview article, the first acquisition unit 11 obtains information about specific positions of one or more indices attached to a specific phrase of the interview article as a reference for the first user. User information may be obtained.

In step ST102, the estimation unit 12 estimates the classification corresponding to the specific position of the first user based on the user information acquired in step ST101 and the correspondence information stored in the storage unit 21.

In step ST103, the group setting unit 13 groups a plurality of first users for each classification estimated in step ST102. That is, for example, when the classification of a plurality of first users is estimated in step ST102, the group setting unit 13 groups the plurality of first users for each classification.

Next, processing for recommending text to the first user (third user) will be described as an information processing method according to an embodiment.
FIG. 5 is a second flowchart for explaining the information processing method according to one embodiment.

In step ST201, the second acquisition unit 14 collects sentence information related to sentences read by the plurality of first users based on the user information of each of the plurality of first users grouped in step ST103 shown in FIG. to get

In step ST202, the identifying unit 15 identifies, for example, the second user C and the third user D among the plurality of first users C and D in the same group grouped in step ST103, Based on the sentence information of the second user C and the sentence information of the third user D acquired by the acquisition unit 14, the sentences read by the second user C but not read by the third user D are specified.

In step ST203, the recommendation unit 16 recommends the text identified in step ST202 to the third user D. That is, the recommendation unit 16 controls the output unit so that the third user D can browse the text information related to the text specified in step ST202. The recommendation unit 16 may control, for example, at least one of the communication unit 22 and the display unit 23, in other words, at least one selected from the group of the communication unit 22 and the display unit 23, as the output unit. Note that the recommendation unit 16 may control the storage unit 21 as an embodiment of the output unit so as to store sentence information related to the sentence specified in step ST202.

Next, as an information processing method according to an embodiment, processing for recommending a recommended sentence to the first user (fourth user) will be described.
FIG. 6 is a third flowchart for explaining the information processing method according to one embodiment.

In step ST301, the second acquisition unit 14 collects sentence information related to sentences read by the plurality of first users based on the user information of each of the plurality of first users grouped in step ST103 shown in FIG. to get

In step ST302, the identification unit 15 is, for example, the fourth user E among one or more first users E in the same group grouped in step ST103, and is stored in the storage unit 21. Of the recommended sentences associated in the correspondence information, recommended sentences that the fourth user E has not read are specified based on the sentence information of the fourth user E acquired in step ST301.

In step ST303, the recommendation unit 16 recommends the recommended text identified in step ST302 to the fourth user E. That is, the recommendation unit 16 controls the output unit so that the fourth user E can browse the recommended sentence information related to the recommended sentence specified in step ST302. The recommendation unit 16 may control, for example, at least one of the communication unit 22 and the display unit 23, in other words, at least one selected from the group of the communication unit 22 and the display unit 23, as the output unit. Note that the recommendation unit 16 may control the storage unit 21 as an embodiment of the output unit so as to store recommended text information related to the recommended text specified in step ST302.

Each unit of the information processing apparatus 1 described above may be implemented as a function of an arithmetic processing unit of a computer or the like. That is, the first acquiring unit 11, the estimating unit 12, the group setting unit 13, the second acquiring unit 14, the identifying unit 15, and the recommending unit 16 (control unit 10) of the information processing device 1 are configured by an arithmetic processing unit of a computer or the like. It may be implemented as a first acquisition function, an estimation function, a group setting function, a second acquisition function, a specific function, and a recommendation function (control function).
The information processing program can cause the computer to implement each function described above. The information processing program may be recorded in a non-temporary computer-readable recording medium such as a memory, solid state drive, hard disk drive, or optical disc.
Further, as described above, each part of the information processing device 1 may be realized by an arithmetic processing device of a computer or the like. The arithmetic processing unit or the like is configured by an integrated circuit or the like, for example. Therefore, each part of the information processing device 1 may be implemented as a circuit that constitutes an arithmetic processing device or the like. That is, the first acquisition unit 11, the estimation unit 12, the group setting unit 13, the second acquisition unit 14, the identification unit 15, and the recommendation unit 16 (control unit 10) of the information processing device 1 constitute an arithmetic processing unit of a computer. may be implemented as a first acquisition circuit, an estimation circuit, a group setting circuit, a second acquisition circuit, a specification circuit, and a recommendation circuit (control circuit).
Further, the storage unit 21, the communication unit 22, and the display unit 23 (output unit) of the information processing device 1 may be implemented as, for example, a storage function including functions of an arithmetic processing unit, a communication function, and a display function (output function). good. Further, the storage unit 21, the communication unit 22, and the display unit 23 (output unit) of the information processing device 1 are realized as a storage circuit, a communication circuit, and a display circuit (output circuit) by being configured by an integrated circuit or the like, for example. may The storage unit 21, the communication unit 22, and the display unit 23 (output unit) of the information processing device 1 are configured as a storage device, a communication device, and a display device (output device), for example, by being configured by a plurality of devices. may

The information processing apparatus 1 can combine any one of the plurality of units described above or an arbitrary plurality thereof.
Although the term "information" is used in this disclosure, the term "information" can be interchanged with "data" and the term "data" can be interchanged with "information."

[Aspects and effects of the present embodiment]
Next, one aspect of the present embodiment and effects produced by each aspect will be described. Note that the effects described below are merely examples, and the effects of each aspect are not limited to those described below.

(Aspect 1)
An information processing apparatus according to one aspect includes a text, a specific position where a user attaches an index to a predetermined unit when the text is divided into predetermined units, and a user classification estimated based on the text and the specific position. a first acquisition unit for acquiring user information about a specific position marked by the first user when the first user reads a sentence; an estimation unit for estimating a classification corresponding to a specific position of the first user based on the acquired user information and the corresponding information stored in the storage unit; and a plurality of first users for each classification estimated by the estimation unit. and a group setting unit that performs grouping.
Accordingly, the information processing apparatus can group users for use in recommending sentences. Since the information processing apparatus attaches an index to the sentences that the user has divided into predetermined units, it is possible to reflect the preferences of each user and to classify the users more appropriately.

(Aspect 2)
An information processing apparatus according to one aspect acquires text information related to text read by a plurality of first users based on user information of each of the plurality of first users grouped by a group setting unit. and a second user and a third user among a plurality of first users grouped by the group setting unit, wherein the text information of the second user and the text information of the third user acquired by the second acquisition unit Based on the sentence information, the second user has a specification unit that specifies sentences that the third user has not read among the sentences that the second user has read, and a recommendation unit that recommends the sentences specified by the specification unit to the third user. You can do it.
A plurality of users in the same group are considered to have similarities in terms of their interest in the text and the points of reference for the text. Therefore, the information processing apparatus can recommend sentences that suit the user's taste to users in the same group.

(Aspect 3)
In one aspect of the information processing device, the correspondence information stored in the storage unit is further associated with recommended sentences recommended for each user classification, and the specifying unit includes a plurality of sentences grouped by the group setting unit. A fourth user among the first users of the fourth user based on the text information of the fourth user acquired by the second acquisition unit among the recommended texts associated in the correspondence information stored in the storage unit The fourth user may specify the recommended sentences that the fourth user has not read, and the recommendation unit may recommend the recommended sentences specified by the specifying unit to the fourth user.
Accordingly, the information processing apparatus can recommend recommended sentences associated with each user classification, that is, each group, to the users classified into the corresponding groups.

(Aspect 4)
In one aspect of the information processing device, the sentence associated with the correspondence information stored in the storage unit is an interview article created when interviewing a researcher, and the specific position associated with the correspondence information is a sentence as a sentence. It is the position of the clause when the interview article is divided into clauses as a predetermined unit, and the first acquisition unit specifies the interview article as a reference for the first user when the first user reads the interview article. It is also possible to obtain user information on the specific position of one or more indicators attached to the clause.
Thereby, the information processing device can classify the user according to the interview article that the user is interested in.

(Aspect 5)
In one aspect of the information processing method, a sentence, a specific position where a user attaches an index to a predetermined unit when the sentence is divided into predetermined units, and a classification of the user estimated based on the sentence and the specific position a first obtaining step of obtaining user information about a specific position marked by the first user when the first user reads a sentence; an estimation step of estimating a classification according to the specific position of the first user based on the user information acquired by the acquisition step and the correspondence information stored in the storage unit; and a group setting step for grouping one user.
Accordingly, the information processing method can achieve the same effect as the information processing apparatus of one aspect described above.

(Aspect 6)
An information processing program of one aspect provides a computer with a sentence, a specific position marked by a user on a predetermined unit when the sentence is divided into predetermined units, and an estimation based on the sentence and the specific position. a storage function for storing correspondence information associated with user classifications; a first acquisition function for acquiring user information relating to a specific position marked by the first user when the first user reads a sentence; an estimation function for estimating a classification corresponding to a specific position of the first user based on the user information acquired by the acquisition function and the correspondence information stored in the storage function; and a group setting function for grouping one user.
Accordingly, the information processing program can achieve the same effect as the information processing apparatus of one aspect described above.

1 information processing device 10 control unit 11 first acquisition unit 12 estimation unit 13 group setting unit 14 second acquisition unit 15 identification unit 16 recommendation unit 21 storage unit 22 communication unit 23 display unit

Claims

A correspondence obtained by associating a sentence, a specific position where a user attaches an index to a predetermined unit when the sentence is divided into predetermined units, and a classification of the user estimated based on the sentence and the specific position. a storage unit that stores information;
a first acquisition unit that acquires user information about a specific position marked by the first user when the first user reads the text;
an estimation unit for estimating a classification corresponding to a specific position of the first user based on the user information acquired by the first acquisition unit and the correspondence information stored in the storage unit;
a group setting unit that groups a plurality of first users for each classification estimated by the estimation unit;
Information processing device.
a second acquisition unit that acquires sentence information related to sentences read by a plurality of first users based on the user information of each of the plurality of first users grouped by the group setting unit;
A second user and a third user among a plurality of first users grouped by the group setting unit, wherein text information of the second user and text of the third user acquired by the second acquisition unit a specifying unit for specifying, based on the information, sentences read by the second user but not read by the third user;
a recommendation unit that recommends the text specified by the specifying unit to a third user;
The information processing apparatus according to claim 1, comprising:
The correspondence information stored in the storage unit is further associated with recommended sentences recommended for each user classification,
The identifying unit selects a fourth user among the plurality of first users grouped by the group setting unit, and selects the recommended text corresponding to the corresponding information stored in the storage unit. Identifying recommended texts not read by the fourth user based on the text information of the fourth user acquired by the second acquisition unit;
The information processing apparatus according to claim 2, wherein the recommendation unit recommends the recommended text specified by the specification unit to the fourth user.
The sentence associated with the correspondence information stored in the storage unit is an interview article created when the researcher was interviewed, and the specific position associated with the correspondence information is the interview article as the sentence. It is the position of the clause when it is divided for each clause as a unit,
When the first user reads the interview article, the first acquisition unit acquires user information about a specific position of one or more indicators attached to a specific phrase of the interview article as a reference for the first user. The information processing apparatus according to any one of claims 1 to 3.
A correspondence obtained by associating a sentence, a specific position where a user attaches an index to a predetermined unit when the sentence is divided into predetermined units, and a classification of the user estimated based on the sentence and the specific position. A computer comprising a storage unit for storing information,
a first obtaining step of obtaining user information about a specific position marked by the first user when the first user reads the text;
an estimation step of estimating a classification corresponding to a specific position of the first user based on the user information acquired by the first acquisition step and the correspondence information stored in the storage unit;
a group setting step of grouping a plurality of first users for each classification estimated by the estimation step;
Information processing method that performs
to the computer,
A correspondence obtained by associating a sentence, a specific position where a user attaches an index to a predetermined unit when the sentence is divided into predetermined units, and a classification of the user estimated based on the sentence and the specific position. a memory function for storing information;
a first acquisition function for acquiring user information about a specific position marked by the first user when the first user reads the text;
an estimation function for estimating a classification corresponding to a specific position of the first user based on the user information acquired by the first acquisition function and the correspondence information stored in the storage function;
A group setting function for grouping a plurality of first users for each classification estimated by the estimation function;
Information processing program that realizes