JP6999514B2 - Idea support system - Google Patents

Description

Patent Law Article 30 Paragraph 2 Applicable Meeting Name: JUNCTION TOKYO 2018 Presentation Date: March 3, 2013 25th Publisher: Shouta Suzuki

The present invention relates to an idea support system that supports idea creation.

When creating an idea by brainstorming, for example, a sticky note containing the idea is attached to a whiteboard so that participants can share the idea. If the participants are physically separated, a similar mechanism may be realized by a method similar to an electronic conference. In this case, by pasting an electronic sticky note that electronically imitates the sticky note on the screen, the idea described by the electronic sticky note can be shared between remote locations.

The following Patent Document 1 describes an electronic conference system using an electronic sticky note. The document states, "On a terminal with a low screen resolution or a small screen size, it is not possible to display all the electronic sticky notes used in the electronic sticky note conference at once, and it is difficult for the user to recognize the information on the electronic sticky notes outside the display area. , Convenience was reduced. "The electronic sticky note cluster is an electronic sticky note conference terminal that holds one or more electronic sticky notes containing position information on a virtual board and clusters based on the position of the electronic sticky notes." Is generated, the position of the electronic sticky note cluster on the virtual board is calculated, and the electronic sticky note and the object corresponding to the electronic sticky note cluster are arranged on the virtual board according to the set display conditions. , When displaying a part of the area of the virtual board, as an object corresponding to the electronic sticky note cluster, to the position of the electronic sticky note cluster to which the electronic sticky note not arranged in the displayed area belongs. Show shortcut objects. 』(See summary).

JP-A-2015-090607

When brainstorming using paper sticky notes, grouping sticky notes with similar ideas may encourage the creation of new ideas. On the other hand, in the conventional electronic sticky note system, the electronic sticky notes are not grouped, or even if they are grouped, the participants usually group them manually. Further, in Patent Document 1, although the electronic sticky notes are clustered, this does not focus on the description content of the electronic sticky notes, but merely clusters them according to the arrangement position of the electronic sticky notes.

The present invention has been made in view of the above-mentioned problems, and when a discussion for creating an idea is conducted between remote areas, each idea presented by a participant is manually operated according to the content thereof. The purpose is to provide a technology for automatically grouping regardless.

The idea support system according to the present invention groups idea memos by clustering until the client terminal performs a change operation on the group, and after the client terminal performs the change operation on the group, it becomes an idea memo. Grouping is carried out based on the result of learning the correspondence with the group.

According to the idea support system according to the present invention, when a discussion for creating an idea is conducted between remote locations, the ideas can be automatically grouped according to the contents of the idea.

It is a block diagram of the idea support system 10 which concerns on Embodiment 1. This is a screen example of the idea board screen 111. This is an example of the relationship graph generated by the relationship graph generation unit 124. It is a figure explaining the countdown function. This is an example of displaying the statistics of the number of posted idea memos 1111. This is an example of displaying a web page related to the topic currently being discussed.

<Embodiment 1>
FIG. 1 is a block diagram of an idea support system 10 according to the first embodiment of the present invention. The idea support system 10 is a system that supports the implementation of idea creation activities such as brainstorming between remote locations. The idea support system 10 has a configuration in which a client terminal and a server 100 are connected via a network 300. FIG. 1 shows an example in which three client terminals 201 to 203 are connected.

Since each client terminal has the same configuration, the client terminal 201 will be described below unless otherwise specified. The client terminal 201 is a terminal used by a participant who participates in an idea creation activity. Participants participate in the discussion on the idea board screen described later provided by the server 100, and share the discussion with other participants through the screen.

The server 100 generates an idea board screen for providing an online discussion place in which each client terminal participates. When each client terminal posts an idea memo to be described later on the screen, the idea memo is shared among the participants and the discussion proceeds. The server 100 includes a screen generation unit 110 and a grouping unit 120. The grouping unit 120 further includes a feature vector calculation unit 121, a clustering unit 122, a learner 123, and a relationship graph generation unit 124.

The screen generation unit 110 generates an idea board screen and transmits it to each client terminal. The idea board screen can be generated as, for example, a web page. In this case, each client terminal accesses the idea board screen using a web browser. A specific example of the idea board screen will be described later.

The grouping unit 120 groups the idea memos posted on the idea board screen according to the contents. The screen generation unit 110 arranges each idea memo on the idea board screen according to the result of the grouping. Each functional unit included in the grouping unit 120 will be described together with a specific example of the grouping process.

FIG. 2 is a screen example of the idea board screen 111. The screen generation unit 110 transmits an idea board screen 111 as illustrated in FIG. 2 to each client terminal. Each client terminal advances the discussion by sharing the idea on the idea board screen 111.

When the participant presses the new memo button 1114 on the idea board screen 111, a dialog (not shown) for inputting a new idea memo is displayed on the screen. Participants enter their ideas as strings on the dialog. The client terminal sends the character string to the server 100. The screen generation unit 110 receives the character string and creates an idea memo 1111 containing the character string on the idea board screen 111. The idea memo 1111 can be used like an electronic sticky note. The number at the lower right of the idea memo 1111 is an identifier that identifies the client terminal (that is, the participant) who posted the idea memo. For example, "1" indicates that it is an idea memo posted from the client terminal 201.

The grouping unit 120 groups each idea memo 1111 according to the description contents of each idea memo 1111. Each column in FIG. 2 represents one group, and in FIG. 2, it is grouped into three groups. The screen generation unit 110 arranges each idea memo 1111 in the area 1112 on the idea board screen 111 according to the grouping result. The grouping procedure will be described later.

The grouping unit 120 further defines a tag 1113 that outlines the description contents of the idea memo 1111 belonging to each group. The screen generation unit 110 arranges the tag at an appropriate position corresponding to each group on the idea board screen 111. In FIG. 2, it was placed at the top of each group. The procedure for defining the tag 1113 will be described later.

The relationship graph button 1116 is a button for displaying the relationship graph described later on the screen. When the participant presses the relationship graph button 1116, the relationship graph generation unit 124 generates the relationship graph, and the screen generation unit 110 transmits the relationship graph to the client terminal. The procedure for generating the relationship graph will be described later.

<Embodiment 1: Initial grouping>
Participants, in principle, proceed with the discussion by posting new idea memos 1111 in sequence. However, participants can also change the group composition on the idea board screen 111. For example, a new group can be created manually (new group button 1115), or the idea memo 1111 belonging to one group can be moved to another group by dragging the mouse. These operations will be called group change operations.

The grouping unit 120 groups the idea memos 1111 by different methods before and after the group change operation is performed. In the following, first, the grouping before the group change operation is performed will be described.

Before the group change operation is performed, the grouping unit 120 groups each idea memo 1111 by a clustering process every time a new idea memo 1111 is posted. Specifically, the feature vector calculation unit 121 calculates the TF-IDF (Term Frequency-Invested Frequency) value of the word in each idea memo 1111 with all the idea memos 1111 on the idea board screen 111 as a population. , The feature vector of each idea memo 1111 is created by arranging the TF-IDF values according to an appropriate word order. The clustering unit 122 groups each idea memo 1111 into one or more groups by performing a clustering process such as a K-means method on the feature vector.

<Embodiment 1: Grouping after group change operation>
After the group change operation is performed, the grouping unit 120 uses the learner 123. Specifically, the learner 123 is made to learn the correspondence between each idea memo 1111 and each group on the idea board screen 111. When a new idea memo 1111 is posted, the feature vector of the new idea memo 1111 is input to the learner 123 to classify the new idea memo 1111 into one of the existing groups. The learning by the learning device 123 is performed every time the group change operation is performed.

Specifically, the learning by the learning device 123 can be carried out as follows, for example. The feature vector calculation unit 121 creates a feature vector of each idea memo 1111 by arranging the TF values of the words included in each idea memo 1111 according to an appropriate word order. The learner 123 associates each idea memo 1111 with each group by learning the correspondence between the feature vector of each idea memo 1111 and the existing group. When a new idea memo 1111 is posted, the new idea memo 1111 is associated with the existing group according to the correspondence.

The reason for changing the grouping procedure before and after the group change operation is as follows. At the stage where the participants have not changed the group composition by manual operation (group change operation), there is a possibility that the discussion on the idea board screen 111 has not sufficiently progressed. Therefore, it is desirable to group them mechanically by clustering. On the other hand, it is assumed that the participants change the group composition, for example, when the discussion progresses to some extent and the participants themselves want to specify the group composition. Therefore, since it is desirable to follow the group structure specified by the participants themselves after that, the idea memo 1111 newly added after learning the group structure specified by the participants themselves by the learner 123. The learner 123 automatically reflects the designation by the participants as a grouping result.

Since the group change operation specifies the intention of the participants to be learned for the learner 123, it has the same effect as the teacher signal in supervised learning. On the other hand, since the group change operation by the participants has not yet occurred at the time of performing clustering, it can be said that the grouping by clustering is the same process as performing unsupervised learning about the group composition.

<Embodiment 1: Tagging>
The grouping unit 120 can attach the tag 1113 of each group, for example, by the following procedure. The grouping unit 120 calculates the TF-IDF value of the word in all the idea memos 1111 belonging to the group for each group. The grouping unit 120 picks up a predetermined number of words (two in FIG. 2) in descending order of the calculated TF-IDF value, and sets the picked up words as the tag 1113 of the group. The grouping unit 120 performs the same processing for each group.

<Embodiment 1: Relationship Graph>
FIG. 3 is an example of a relationship graph generated by the relationship graph generation unit 124. The relationship graph generation unit 124 generates a group feature vector representing the features of the group from the character string in which the words of all the idea memos 1111 belonging to each group are concatenated. The relationship graph generation unit 124 generates a relationship graph by arranging the group feature vector on the coordinate space with each element of the group feature amount vector as a value of each dimension.

Since the number of dimensions of the group feature vector is often three or more, the number of dimensions of the coordinate space of the relationship graph is also three or more. As illustrated in FIG. 3, when it is desired to present a two-dimensional relationship graph, the number of dimensions of the group feature vector is compressed to two dimensions by an appropriate algorithm, and then the compressed group feature vector is compressed into a two-dimensional coordinate space. It should be placed in. The same applies when a coordinate space having three or more dimensions is used.

Participants looking at the relationship graph can visually grasp the distance between the topics being discussed at that time. As a result, for example, it is possible to obtain hints on topics that have not yet been discussed and to develop new discussions. For example, in FIG. 3, since the distance between the group 1 and the group 2 is large, it may be possible to obtain a hint that the topic corresponding to the part between the groups has not been sufficiently discussed.

The grouping unit 120 can also perform the following processing using the relationship graph. Participants specify the coordinates on the relationship graph where the discussion is not expected to be sufficient (ie, the voids on the relationship graph). The grouping unit 120 receives the coordinates and specifies a feature vector corresponding to the coordinates in the coordinate space. The grouping unit 120 newly creates a new group having the specified feature vector as a group feature vector, and arranges it on the idea board screen 111. The new group has a tag 1113 derived from the identified group feature vector, and the idea memo 1111 becomes an empty group. This can encourage participants to start discussions related to the new group.

The grouping unit 120 can also perform the following processing using the relationship graph. When the participant specifies the coordinates on the relationship graph as described above, the grouping unit 120 specifies the feature vector corresponding to the coordinates, and newly generates a new idea memo 1111 from the specified feature vector. Place it on the idea board screen 111. For example, a word having a particularly large TF-IDF value among the feature vectors is used, and particles and the like are appropriately supplemented to automatically generate a sentence corresponding to the feature vector. The automatically generated sentence may be used as a new idea memo 1111. As a method for specifying the feature vector corresponding to the coordinates on the relation graph, for example, the following can be considered.

(1) Map the feature vector of the group to the coordinate space (obtain the coordinate value).
(2) All the elements of the result of morphological analysis of the sentence of each idea memo are set as a population, and one or more arbitrary number of elements are randomly extracted from them, for example, and they are made into a pseudo group. Create multiple pseudo groups, generate their feature vectors, and then map them to the coordinate space. (3) Between the feature vectors in steps (1) and (2) and the coordinate values on the relationship graph. By memorizing the correspondence, the feature vector can be specified from the coordinate values. When compressing the number of dimensions of the relationship graph, the correspondence between the coordinate values and the feature vector in the compressed coordinate space is stored.
(4) When the user specifies a coordinate value on the relation graph, the feature vector associated with the coordinate value is specified.

<Embodiment 1: Summary>
The idea support system 10 according to the first embodiment groups idea memos 1111 by clustering before the client terminal performs the group change operation. Thereby, for example, the idea memo 1111 can be automatically grouped even when the discussion of the participants is not sufficiently advanced.

In the idea support system 10 according to the first embodiment, when the client terminal performs the group change operation, the learning device 123 learns the correspondence relationship between the changed group configuration and the idea memo 1111 belonging to each group. Then, the new idea memo 1111 is classified according to the learning result. As a result, the group composition intended by the participants can be automatically reflected in the new idea memo 1111 added after that.

The idea support system 10 according to the first embodiment creates a relationship graph between groups. Further, by specifying the coordinates on the relationship graph, it is possible to automatically generate a new group or a new idea memo 1111 corresponding to the coordinates. As a result, participants can get hints about the direction of new discussions, and further promote this by automatically generating new groups and new idea memos 1111.

<Embodiment 2>
In the second embodiment of the present invention, other functions that are desirable to be provided in the idea support system 10 will be described. Since the system configuration is the same as that of the first embodiment, other functions not described in the first embodiment will be mainly described below.

FIG. 4 is a diagram illustrating a countdown function. When a participant posts an idea memo 1111, it may be desirable to set a certain deadline because it encourages the participant to concentrate on the discussion. Therefore, the countdown start unit 1117a may be provided on the idea board screen 111. When the participant inputs a numerical value to the countdown start unit 1117a and presses the start button, the server 100 starts the countdown. Each client terminal periodically inquires about the count value held by the server 100, and when the count value becomes 0, for example, displays a dialog 1117b indicating that fact. As a result, when any participant specifies a countdown, the countdown operation can be shared by all client terminals. In FIG. 4, the idea memo 1111 and the group are omitted for convenience of description. Similarly, in the following drawings, they will be omitted as appropriate.

FIG. 5 is an example of displaying the statistics of the number of posted idea memos 1111. The server 100 may total the number of posted idea memos 1111 for each participant (that is, for each client terminal) and display it on the idea board screen 111. For example, the aggregation result as shown in FIG. 5 may be displayed by pressing an appropriate button. This makes it possible to encourage participants with a small number of posts to participate in more active discussions.

FIG. 6 is an example of displaying a web page related to the topic currently being discussed. By calculating the idea memo 1111 and the feature vector of the group, the grouping unit 120 can grasp a rough topic of the content currently being discussed on the idea board screen 111. The screen generation unit 110 acquires a web page (for example, a news article on the web) related to the topic from a search site or the like and displays it in a dialog 1118 or the like on the idea board screen 111 to the participants. It can give an opportunity to gain new awareness. For example, the function as shown in FIG. 6 can be implemented by issuing a query to the search site using the tag 1113 as a search keyword and displaying the top several items from the results in the dialog 1118.

When the discussion using the idea board screen 111 is interrupted, it is desirable that the contents of the idea board screen 111 at the time of interruption can be reproduced later. Therefore, the server 100 may save the configuration of the group arranged on the idea board screen 111 and the idea memo 1111 belonging to the group in an appropriate file format (for example, CSV format). Further, the stored data may be transmitted in response to a request from the client terminal. When the discussion is resumed, the server 100 or the client terminal can reproduce the state of the idea board screen 111 at the time of interruption by using the stored data.

<About a modification of the present invention>
In the above embodiment, each functional unit included in the server 100 can be implemented, for example, by executing software that implements the function by an arithmetic unit such as a CPU (Central Processing Unit).

In the above embodiment, as the learning device 123, one that implements an appropriate learning method suitable for processing such as document classification can be adopted. For example, the learner 123 can be implemented by logistic regression.

In the above embodiment, it has been described that the feature vector calculation unit 121 uses the TF value or the TF-IDF value as the idea memo 1111 or the feature vector of the group, but other appropriate feature quantities may be used as the feature vector.

In the above embodiment, when the client terminal is implemented by a mobile terminal such as a smartphone, an interface for posting the idea memo 1111 may be implemented by using the manual input function provided in the mobile terminal. In this case, a smartphone application or the like that implements the function may be used.

In the above embodiment, the server 100 is provided with a screen generation unit 110 and a grouping unit 120, but these functional units can be implemented in individual servers and then cooperate with each other by mutual communication to obtain the same function. It may be realized. Further, the data held by the server 100 may be stored in a database or the like on another server. For example, the screen generation unit 110 can be implemented on the web application server, the grouping unit 120 can be implemented on the document processing server, and the database can be implemented on the database server.

10: Idea support system 100: Server 110: Screen generation unit 120: Grouping unit 121: Feature vector calculation unit 122: Clustering unit 123: Learner 124: Relationship graph generation unit 201 to 203: Client terminal 300: Network

Claims (12)

An idea support system that supports the creation of ideas.
One or more client terminals that input a character string expressing an idea,
A server computer that receives a character string input by the client terminal via a network, generates a screen that displays the character string together with the identifier of the client terminal, and transmits the character string to the client terminal.
Equipped with
Each time the server computer receives the character string from the client terminal, the server computer configures the idea memo as one idea memo by assigning a partition for distinguishing the character string from the other character strings, and then sets each idea memo. Divide into one or more groups and arrange them on the screen.
The client terminal performs a group change operation of moving the idea memo between the groups on the screen or adding a new group on the screen.
When the server computer receives the character string from the client terminal before receiving the group change operation from the client terminal, the server computer performs document clustering for each idea memo arranged on the screen. By doing so, each idea memo is grouped into one or more groups on the screen.
When the server computer receives the group change operation from the client terminal, the server computer performs a learning step of causing the learner to learn the correspondence between each group and each idea memo created by the group change operation. ,
When the server computer receives a new character string from the client terminal after performing the learning step, the server computer creates a new idea memo corresponding to the character string on the screen and the learning device. An idea support system characterized by carrying out a new addition step of classifying the idea memo into one of the above groups using the above. The server computer in the learning step
Steps to create a feature vector for each idea memo,
A step of associating each idea memo with each group in the learner by having the learner learn the correspondence between the identifier of each group and the feature vector.
The idea support system according to claim 1, which comprises executing. In the step of creating the feature vector of each idea memo, the server computer creates a vector having a list of TF values of the words included in each idea memo as a component as a feature vector of each idea memo. 2. The idea support system according to claim 2. The server computer is used in the new addition step.
Steps to create a feature vector for the new idea memo,
A step of classifying the new idea memo into one of the groups by inputting the feature vector of the new idea memo into the learning device.
The idea support system according to claim 1, which comprises executing. The server computer performs a tagging step of assigning a tag composed of words summarizing the contents of the idea memo belonging to the group to the group on the screen.
The server computer in the tagging step
A step of calculating the TF-IDF value of a word included in the idea memo belonging to each group, with each group as a population.
A step of extracting a predetermined number of words included in each idea memo for each group in order from the one having the largest TF-IDF value.
The step of determining the extracted word as a tag of the group,
The idea support system according to claim 1, which comprises executing. The server computer generates a relationship graph in which the correlation between the groups is described by a graph representation and transmits the relationship graph to the client terminal.
When the server computer generates the relationship graph, the server computer may generate the relationship graph.
A step of generating a group feature vector representing the features of the group from a character string concatenating all the words of the idea memo belonging to the group.
A step of generating the relationship graph by arranging the group feature vector on the coordinate space,
The idea support system according to claim 1, which comprises executing. The client terminal transmits a coordinate specification input for designating the coordinates in which the group is not arranged in the relationship graph to the server computer.
The server computer specifies a feature vector at a position corresponding to the coordinate designation input on the relationship graph, and creates a new group having the specified feature vector as the group feature vector on the screen. The idea support system according to claim 6, which is characterized by being arranged in. The client terminal transmits a coordinate specification input for designating the coordinates in which the group is not arranged in the relationship graph to the server computer.
The server computer specifies a feature vector at a position corresponding to the coordinate designation input on the relationship graph, and creates a new idea memo using the specified feature vector and arranges it on the screen. The idea support system according to claim 6, characterized in that. The client terminal sends a time limit specification input for specifying a time limit for inputting the character string to the server computer.
When the server computer receives the deadline specified input, the server computer activates a timer that times out at the specified deadline.
The client terminal inquires the server computer of the count value of the timer at predetermined time intervals, and displays a message to that effect on the screen when the timer times out. The idea support system described in item 1. The idea according to claim 1, wherein the server computer aggregates the number of the character strings transmitted to the server computer for each client terminal and transmits the aggregated result to the client terminal. Support system. The server computer estimates the topic of each idea memo arranged on the screen by using the feature vector of each idea memo, and acquires a web page related to the estimated topic from the search site. The idea support system according to claim 2, wherein the idea support system is displayed on the screen. Claim 1 is characterized in that the server computer creates save data describing each idea memo arranged on the screen and a group to which each idea memo belongs and transmits the save data to the client terminal. Described idea support system.

Images