WO2022124399A1

WO2022124399A1 - Information processing device

Info

Publication number: WO2022124399A1
Application number: PCT/JP2021/045538
Authority: WO
Inventors: 三喜男川島; 拓也齋藤; 祐斗仲上; 和弘菅沼; 省吾林
Original assignee: 正林真之
Priority date: 2020-12-10
Filing date: 2021-12-10
Publication date: 2022-06-16
Also published as: JPWO2022124399A1

Abstract

The present invention addresses the problem of enabling determination of a person suitable as a person to participate in a meeting to be held, with higher accuracy and with further ease as compared with the conventional technologies.　A voice acquisition unit 101 acquires voice data V of a meeting M. A meeting determination unit 102 extracts n-number of comments C included in the voice data V acquired by the voice acquisition unit 101, and identifies attendants A who have made the n-number of comments C, respectively. An attendant management unit 103 manages attendant IDs for uniquely differentiating attendants A identified as speakers by the meeting determination unit 102, in association with a theme T of the meeting and the comments. A candidate proposal unit 106 proposes at least one candidate suitable as an attendant of a meeting to be newly held, on the basis of information managed by the attendant management unit 103 and information including at least the theme T of the meeting to be newly held. The problem is solved thereby.

Description

Information processing equipment

The present invention relates to an information processing device.

Conventionally, there has been a technique for making proposals for attendees of a newly held meeting based on the content of the statements of those who attended the held meeting and the theme of the newly held meeting (for example, patent documents). 1).

Japanese Unexamined Patent Publication No. 2012-147277

However, there is a demand for the development of a method that can accurately and easily determine an appropriate person to participate in a conference to be held, including the technique of Patent Document 1, rather than the conventional technique.

The present invention has been made in view of such a situation, and it is intended to enable an accurate and easy determination of an appropriate person to attend a conference to be held, rather than the conventional technique. The purpose.

In order to achieve the above object, the information processing apparatus according to one aspect of the present invention is
An acquisition method for acquiring conference audio data,
Specific means for identifying each speaker of a predetermined unit of speech included in the voice data acquired by the acquisition means, and
A management means for associating the theme of the conference with the information indicating the speaker specified by the specific means and managing the remarks as the first information.
Based on the first information managed by the management means and the second information including at least the theme of the newly held meeting, one or more suitable candidates for attending the meeting are proposed. Proposal means and
To prepare for.

According to the present invention, it is possible to accurately and easily determine an appropriate person to participate in a conference to be held, as compared with the conventional technique.

It is a figure which shows the outline of this service which can be realized by the information processing system to which the server which concerns on one Embodiment of this invention is applied. It is a figure which shows the specific example of the method of classifying and managing attendees based on the quantity and quality of the remarks in a meeting in the outline of this service of FIG. It is a figure which shows the example different from FIG. 2 among the concrete examples of the method of classifying and managing attendees based on the quantity and quality of speech at a meeting in the outline of this service of FIG. It is a figure which shows an example of the structure of the information processing system to which the server which concerns on one Embodiment of this invention is applied. It is a block diagram which shows an example of the hardware composition of the server among the information processing system shown in FIG. FIG. 3 is a functional block diagram showing an example of a functional configuration for executing a candidate proposal process among the functional configurations of the server of FIG. 5 constituting the information processing system of FIG. 4.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

First, with reference to FIGS. 1 to 3, a service (hereinafter referred to as "the service") that can be realized by an information processing system (see FIG. 4 described later) to which the server 1 according to the embodiment of the present invention is applied. I will explain the outline of (call).

FIG. 1 is a diagram showing an outline of this service that can be realized by an information processing system to which a server according to an embodiment of the present invention is applied.

This service is a service provided to the organizer H by the service provider (not shown).
Attendee A is a person who attends or attends the conference M.
The organizer H is a person who hosts the holding of the conference M attended by the attendee A. In some cases, attendee A also serves as organizer H.
The format of the conference M is not particularly limited, but in the present embodiment, a face-to-face format and a remote format are adopted as the format of the conference M. The "face-to-face format" is a format of a conference in which attendee A meets in a conference room or the like in the real world. "Remote format" is a format of a conference via the Internet. The format of the conference M can be arbitrarily selected by each attendee A according to his / her own situation (for example, commuting or working from home).

FIG. 1 shows the state of the first meeting M1 held in the meeting room of a certain company. It is assumed that the attendees A1 to A3 attend the meeting M1 in a face-to-face manner, and the attendees A4 and A5 attend in a remote manner.

In the conference M1, each of the remarks C1 to C5 of the attendees A1 to A5 is acquired by the server 1 as voice data V (step S1).
Specifically, each of the remarks C1 to C3 of the attendees A1 to A3 is input by the voice input function of the microphone device 4 arranged in the conference room, and is acquired by the server 1 as voice data V. Here, one microphone device 4 may be arranged in the conference room as shown in FIG. 1, but one microphone device 4 may be arranged in front of each of the attendees A1 to A5.
In addition, each of the remarks C4 and C5 of the attendees A4 and A5 is a voice input function of the information processing device 2 (hereinafter, "attendee terminal 2") such as a personal computer operated by each of the attendees A4 and A5. Is input by and is acquired by the server 1 as voice data V4 and V5, respectively.

During or after the conference M1, the server 1 extracts and analyzes n statements C (n is an integer value of 1 or more) included in the acquired voice data V, V4, and V5, respectively (step). S2).
Here, the method of analysis by the server 1 is not particularly limited. For example, the extracted n remarks C may be converted into text data and analyzed by text mining. Further, for example, analysis may be performed on the voice data itself without converting the extracted n speeches C into text data.

The server 1 estimates the theme T of the conference M1 based on the result of the analysis of n statements C (step S3). When the theme T is estimated, the statement C and the theme T are associated and managed. Specifically, for example, when the theme T "about the commercialization of the new technology Z" is estimated, the statement C and the theme T "about the commercialization of the new technology Z" are managed in association with each other. ..
Here, the estimation of the theme T by the server 1 can be performed in a conference unit, but when the conference M1 is composed of a plurality of parts (for example, when the conference M1 is divided into a first part and a second part). , It is also possible to estimate the theme T in units of copies. It is also possible to estimate the theme T in time zone units. Therefore, it is possible to associate a plurality of themes T with one statement C. Specifically, for example, the theme T estimated in the conference unit and the theme T estimated in the department unit can be managed in association with the statement C.
As described above, in this service, the theme T can be estimated based on the analysis result of the acquired voice data V, but the present invention is not limited to this, and the organizer H can manually input the theme T.

The server 1 identifies each speaker of the n speeches C included in the voice data V based on the result of the analysis of the n speeches C (step S4).
The method for specifying the speaker by the server 1 is not particularly limited. For example, the speaker is specified based on the recognition result of the voice data V and the data indicating the characteristics of the voice of the attendee A acquired in advance. May be good.
Specifically, for example, in the example of FIG. 1, each of the remarks C1 to C3 of the attendees A1 to A3 that may be included in the voice data V is specified. Further, the remark C4 of the attendee A4 that can be included in the voice data V4 is specified, and the remark C5 of the attendee A5 that can be included in the voice data V5 is specified.
As a result, each speaker of the n remarks C spoken at the conference M1 is specified, so that the remark contents of each attendee A of the conference M1 can be recorded and managed. That is, when the server 1 identifies the person who made the statement C, the server 1 manages the speaker (attendee A), the statement C, and the theme T in association with each other.

The server 1 classifies and manages the attendees A based on the quantity, quality, and the like of the remarks in the conference M (step S5).
Specifically, the server 1 determines the amount of speech in the conference M1 (for example, the number of speeches, the number of characters, etc.), the relationship between the theme T of the conference M1 and the content of the speech C, etc., based on the analysis result of the speech C. Attendees A are classified based on this.
The relationship between the theme T of the conference M1 and the content of the remark C can be expressed by using an index of "theme matching degree" or "theme deviation degree".

"Theme matching degree" is an index that normalizes the degree of relevance between the content of remark C and the content of theme T by comparing them. If the theme matching degree of the statement C is small, the statement C is a statement whose content does not follow the theme T of the conference M1. On the other hand, if the theme matching degree of the statement C is large, the statement C is a statement whose content is in line with the theme T of the conference M1.

Further, the "theme divergence degree" is an index obtained by comparing the content of the theme T of the conference M1 and the content of the remark C and normalizing the low relevance between the two. If the degree of divergence in the theme of the statement C is small, the statement C is a statement whose content is in line with the theme T of the conference M1. On the other hand, if the degree of the theme deviation of the statement C is large, the statement C is a statement whose content does not follow the theme T of the conference M1.
In this way, in this service, attendees are based on indicators such as the amount of remarks (for example, the above-mentioned "speech amount") and quality (for example, the above-mentioned "theme matching degree" and "theme divergence degree") in the conference M1. Classify and manage A. A specific example of a method for classifying and managing attendees A will be described later with reference to FIGS. 2 and 3.

When the next meeting M2 is scheduled to be held after the end of the meeting M, the organizer H sets the requirements for holding the meeting M2 (hereinafter referred to as "meeting requirements") (step S6).
The meeting requirements are set by the organizer H inputting predetermined items into the information processing device 3 (hereinafter, "organizer terminal 3") such as a personal computer. There are no particular restrictions on what kind of meeting requirements are set. For example, the schedule of the next meeting M, the content of the theme T, the number and types of attendees A, and the like can be set as meeting requirements.
Specifically, for example, in order to realize the final discussion while maintaining the theme T of "commercialization of new technology Z" as in the previous meeting M1, so that a solid person becomes attendee A. You can also set meeting requirements. Further, for example, the meeting requirement can be set so that the person who speaks a lot accounts for the majority of the attendees A. Further, for example, in order to realize free discussion, it is possible to set a meeting requirement that "theme T is not decided".

When the input work of the conference requirements by the organizer H is completed, the server 1 proposes by extracting one or more candidates having high conformity to the conference requirements and presenting them to the organizer H (step S7). The reason why "one or more people" is used here is that the customer may participate in the conference M.
The relationship between the meeting requirements of the meeting M2 and the candidates can be expressed by using an index called "requirement matching degree". The "requirement matching degree" is an index obtained by comparing the contents of the meeting requirements with the information of the candidates and normalizing the high degree of relevance between the two. The higher the "requirement matching degree" of the candidate, the higher the suitability for the meeting requirements, and the easier it is to be extracted as a candidate attending the meeting M2. Information indicating one or more extracted candidates is not shown, but is displayed on the organizer terminal 3 in a ranking format, for example.

2 and 3 show specific examples of a method of classifying and managing each of the attendees A of m people (m is an integer value of 1 or more) based on the quantity and quality of the remarks C in the conference M. Has been done.
In (A) of FIG. 2, as a specific example of a method of classifying and managing each of m attendees A, it is stored in a database provided in the server 1 (for example, attendee DB181 of FIG. 6 described later). An example of the information is shown.

That is, in the database provided in the server 1, information on each of the m attendees A identified as speakers in any of the conferences M held k times in the past (k is an integer value of 1 or more). (Hereinafter referred to as "attendee information") is stored. The attendee information includes an ID that uniquely identifies the attendee A (hereinafter referred to as "attendee ID") and an ID that uniquely identifies the conference M (hereinafter referred to as "meeting ID"). , The content of the theme T, the content of the remark C, the amount of remark, and the degree of theme matching.

Specifically, for example, as shown in FIG. 2A, the attendee A1 having the attendee ID of "0001" is the conference M1 having the conference ID of "101" (theme T is "new technology Z". Attending "Commercialization"), he made a statement C1 with the content "XXXXXX". Attendees A1 were classified as "large" in the amount of speech and "50%" in the theme matching degree. That is, although the content of the remark C1 when the attendee A1 attended the conference M1 was large in volume, it was not necessarily highly relevant to the theme T.

Further, for example, the attendee A2 whose attendee ID is "0002" attends the conference M1 whose conference ID is "101" (theme T is "commercialization of new technology Z") and "XXX". I made a statement C2 with the content "XX". Attendees A2 were classified as "small" in the amount of speech and "80%" in the theme matching degree. That is, the content of the remark C2 when the attendee A2 attended the conference M1 was considered to be appropriate because it was highly relevant to the theme T, although the volume was small.

Further, for example, the attendee A3 whose attendee ID is "0003" attends the conference M1 whose conference ID is "101" (theme T is "commercialization of new technology Z") and "XXX". I made a statement C3 with the content "XX". Attendees A3 were classified as "medium" in the amount of speech and "20%" in the theme matching degree. That is, the content of the remark C3 when the attendee A3 attended the conference M1 was considered to have little relevance to the theme T, although the volume was normal.

Further, for example, the attendee A4 whose attendee ID is "0004" attends the conference M1 whose conference ID is "101" (theme T is "commercialization of new technology Z") and "XXX". I made a statement C4 with the content "XX". Attendees A4 were classified as "large" in the amount of speech and "90%" in the theme matching degree. That is, it was noted that the content of the remark C4 when the attendee A4 attended the conference M1 had a large volume and was highly related to the theme T.
In this way, all the remarks C of the attendees A1 to A4 who attended the conference M1 are stored in the database of the server 1, and can be classified from the two viewpoints of the amount of remarks and the theme matching.
As a result, the organizer H can select a more appropriate person by referring to the attendee information stored in the database of the server 1 when selecting the candidate of the attendee A of the conference M2 to be held.

In this service, attendees A can be classified using, for example, a graph as shown in FIG. 2B.
In FIG. 2B, attendees A1 to A4 who attended the conference M1 using the graph G shown by the horizontal axis L1 indicating the magnitude of the amount of speech and the vertical axis L2 indicating the degree of theme matching. A concrete example of the method of classifying is shown. That is, in the graph G shown in FIG. 2 (B), four attendees A (attendees A1 to A4) among the m attendees A stored in the database shown in FIG. 2 (A) are shown. An example of classification is shown.

For example, as shown in FIG. 2A, the attendee A1 of the conference M1 has a “large” amount of speech and a “50%” theme matching degree, so that the position of the point P1 on the graph G is located. are categorized.
Further, for example, the attendee A2 of the conference M1 has a speech amount of "small" and a theme matching degree of "80%" as shown in FIG. 2A, so that the point P2 on the graph G has a speech amount of "small". Classified by position.
Further, for example, as shown in FIG. 2A, the attendee A3 of the conference M1 has a “medium” amount of speech and a “20%” theme matching degree, so that the point P3 on the graph G has a speech volume of “medium”. Classified by position.
Further, for example, as shown in FIG. 2A, the attendee A4 of the conference M1 has a “large” amount of speech and a “90%” theme matching degree, so that the point P4 on the graph G Classified by position.

As described above, in this service, all the remarks C of each of the four attendees A (attendees A1 to A4) who attended the conference M1 are stored in the database of the server 1. In addition, each of the attendees A1 to A4 is classified from the two viewpoints of the amount of speech of the attendee A and the theme matching.
As a result, the organizer H can refer to the graph G generated by the server 1 when selecting the candidate for the attendee A of the conference M2 to be held, so that the attendees A1 to A4 can be seen at a glance. It is possible to grasp the relationship between the amount of speech and the degree of theme matching. As a result, it becomes possible to quickly select a more appropriate person.

FIG. 3 shows, as a specific example of the method of classifying and managing each of the m attendees A, among the examples of the information stored in the database provided in the server 1, FIG. Is shown a different example.

That is, the database shown in FIG. 3 stores the attendee information of each of the m attendees A identified as speakers in any of the k meetings M held. The attendee information shown in FIG. 3 includes the attendee ID of attendee A, the content of the experience of attendee A, the conference ID of the conference M, the content of the theme T of the conference M, and the content of the remark C. The amount of speech and the degree of theme matching are included.
That is, according to the example of FIG. 3, since the experience of the attendee A is added to the example of (A) of FIG. 2, it is possible to select a person with higher accuracy according to the actual situation.

Specifically, for example, as shown in FIG. 3, the attendee A1 whose attendee ID is “0001” has experience as a “Z development leader” and has a conference M1 (theme T) whose conference ID is “101”. Attended "Commercialization of New Technology Z") and made a statement C1 with the content of "XXXXXX". Attendees A1 were classified as "large" in the amount of speech and "50%" in the theme matching degree. That is, although the content of the remark C1 when the attendee A1 attended the conference M1 was large in volume, it was not necessarily highly relevant to the theme T.

Further, for example, the attendee A2 whose attendee ID is "0002" is a "section manager of the sales department", and the conference M1 whose conference ID is "101" (theme T is "commercialization of new technology Z"). Attended the meeting and made a statement C2 with the content of "XXXXXX". Attendees A2 were classified as "small" in the amount of speech and "80%" in the theme matching degree. That is, the content of the remark C when the attendee A2 attended the conference M1 was considered to be appropriate because it was highly relevant to the theme T, although the volume was small.

For example, attendee A3 whose attendee ID is "0003" is a section chief of the general affairs department and attends conference M1 whose conference ID is "101" (theme T is "commercialization of new technology Z"). Then, he made a statement C3 with the content of "XXXXXX". Attendees A3 were classified as "medium" in the amount of speech and "20%" in the theme matching degree. That is, the content of the remark C3 when the attendee A3 attended the conference M1 was considered to have little relevance to the theme T, although the volume was normal.

Further, for example, the attendee A4 whose attendee ID is "0004" is the section chief of the Intellectual Property Department, and the conference M1 whose conference ID is "101" (theme T is "commercialization of new technology Z"). Attended the meeting and made a remark C4 with the content of "XXXXXX". Attendees A4 were classified as "large" in the amount of speech and "90%" in the theme matching degree. That is, the content of the remark C4 when the attendee A4 attended the conference M1 was noted to have a large volume and a high relevance to the theme T.

As described above, in this service, all the remarks C of the attendees A1 to A4 who attended the conference M1 are stored in the database of the server 1. In addition, attendee A is classified from a plurality of viewpoints such as experience of attendee A, amount of speech, and theme matching.
As a result, the organizer H can select a more appropriate person by referring to the attendee information stored in the database of the server 1 when selecting the candidate of the attendee A of the conference M2 to be held. Specifically, for example, "I want flexible opinions about the new business at the next meeting, so I want to select attendees mainly from people other than the development department." It will be possible.

Next, with reference to FIG. 4, the configuration of the information processing system that realizes the provision of the above-mentioned service, that is, the information processing system to which the server 1 according to the embodiment of the information processing apparatus of the present invention is applied will be described. do.
FIG. 4 is a diagram showing an example of the configuration of an information processing system to which the server according to the embodiment of the present invention is applied.

The information processing system shown in FIG. 4 is configured to include a server 1, an attendee terminal 2, a host terminal 3, and a microphone device 4.
The server 1, the attendee terminal 2, the organizer terminal 3, and the microphone device 4 are connected to each other via a predetermined network NW such as the Internet and a LAN (Local Area Network).

Server 1 is an information processing device managed by a service provider (not shown). The server 1 executes various processes for realizing this service while appropriately communicating with the attendee terminal 2, the organizer terminal 3, and the microphone device 4.

The attendee terminal 2 is an information processing device operated by attendee A who attends the conference M remotely. The attendee terminal 2 is composed of a smartphone, a tablet, a personal computer and the like. Although only one attendee terminal 2 is drawn in FIG. 4, this is simplified to help the explanation. That is, in reality, there may be as many attendee terminals 2 as there are attendees A who attend the conference M in a remote manner.

The organizer terminal 3 is an information processing device operated by the organizer H of the conference M. The organizer terminal 3 is composed of a smartphone, a tablet, a personal computer and the like.

Here, for example, as in the example of FIG. 1 described above, when there is a person who attends the meeting M not in the remote form but in the face-to-face form, the meeting room or the like where the meeting M is held is used. The microphone device 4 is installed. The microphone device 4 is not particularly limited as long as it has a function of inputting the voice of the attendee A of the conference M to the server 1. Therefore, the microphone device 4 may or may not be connected to the network NW. When the microphone device 4 is connected to the network NW, the voice data V is input to the server 1 via the network NW. When the microphone device 4 is not connected to the network NW, the voice data V is input to the server 1 via a predetermined storage medium. Examples of the predetermined storage medium include a voice recorder, a smartphone, and the like.

FIG. 5 is a block diagram showing an example of the hardware configuration of the server in the information processing system shown in FIG.

The server 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an input unit 16, and an output unit 17. , A storage unit 18, a communication unit 19, and a drive 20.

The CPU 11 executes various processes according to the program recorded in the ROM 12 or the program loaded from the storage unit 18 into the RAM 13.
Data and the like necessary for the CPU 11 to execute various processes are also appropriately stored in the RAM 13.

The CPU 11, ROM 12 and RAM 13 are connected to each other via the bus 14. An input / output interface 15 is also connected to the bus 14. An input unit 16, an output unit 17, a storage unit 18, a communication unit 19, and a drive 20 are connected to the input / output interface 15.

The input unit 16 is composed of, for example, a keyboard or the like, and inputs various information.
The output unit 17 is composed of a display such as a liquid crystal display, a speaker, or the like, and outputs various information as images or sounds.
The storage unit 18 is composed of a DRAM (Dynamic Random Access Memory) or the like, and stores various data.
The communication unit 19 communicates with other devices (for example, the attendee terminal 2, the organizer terminal 3, and the microphone device 4 in FIG. 2) via the network NW including the Internet.

A removable media 40 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately mounted on the drive 20. The program read from the removable media 40 by the drive 20 is installed in the storage unit 18 as needed.
Further, the removable media 40 can also store various data stored in the storage unit 18 in the same manner as the storage unit 18.

Although not shown, the attendee terminal 2 and the organizer terminal 3 in FIG. 4 can have basically the same configuration as the hardware configuration shown in FIG. Therefore, the description of the hardware configuration of the attendee terminal 2 and the organizer terminal 3 will be omitted.

By collaborating with various software and various hardware constituting the information processing system of FIG. 4 including the server 1 of FIG. 5, various processes including the candidate proposal process can be executed. As a result, the service provider can provide the above-mentioned service to the organizer H.
The “candidate proposal process” refers to a process of supporting the selection of candidates who will attend the meeting M scheduled to be held.
Hereinafter, with reference to FIG. 6, a functional configuration for executing the candidate proposal process executed in the server 1 of FIG. 5 constituting the information processing system of FIG. 4 will be described.

FIG. 6 is a functional block diagram showing an example of a functional configuration for executing a candidate proposal process among the functional configurations of the server of FIG. 5 constituting the information processing system of FIG. 4.

As shown in FIG. 6, when the server 1 of FIG. 5 executes the candidate proposal process, in the CPU 11, the voice acquisition unit 101, the conference determination unit 102, the information management unit 103, and the attendee classification unit 104 , The meeting requirement acquisition unit 105 and the candidate proposal unit 106 function.

Further, an attendee DB 181 and a conference DB 182 are provided in one area of the storage unit 18 of the server 1.
The attendee DB 181 stores the attendee information of m attendees A who attended one or more of the meetings M held k times. The conference DB 182 stores the conference information of the conference M held k times.

The voice acquisition unit 101 acquires the voice data V of each of the plurality of attendees A who attended the conference M. The voice data V acquired by the voice acquisition unit 101 is stored and managed in the conference DB 182.

The conference determination unit 102 determines the content of the conference M. Further, the meeting determination unit 102 identifies the attendee A who has made a statement C in the meeting M.
Specifically, in the conference determination unit 102, the speech extraction unit 121, the speech analysis unit 122, the theme estimation unit 123, and the speaker identification unit 124 function.

The remark extraction unit 121 extracts one or more remarks C included in the voice data V acquired by the voice acquisition unit 101.

The speech analysis unit 122 analyzes n speeches C extracted by the speech extraction unit 121. The method used by the speech analysis unit 122 to analyze the speech C is not particularly limited. As described above, for example, analysis by text mining, analysis targeting the voice data V itself, and the like are performed.

The theme estimation unit 123 estimates one or more themes T of the conference M based on the result of analysis by the speech analysis unit 122. The theme T can be estimated by the theme estimation unit 123 in units of conference M, but it can also be estimated in units of department when the conference M is composed of a plurality of departments. It is also possible to estimate the theme T in time zone units.

The speaker identification unit 124 identifies the attendee A who has spoken each of the n speeches C included in the voice data V. The method used by the speaker identification unit 124 to identify the attendee A who has spoken the statement C is not particularly limited. As described above, the speaker can be identified based on the recognition result of the voice data V and the data indicating the characteristics of the voice of the attendee A acquired in advance.

The information management unit 103 manages the information stored in each of the attendee DB 181 and the conference DB 182.
Specifically, the information management unit 103 associates the attendee IDs of the attendees A identified as speakers with the themes T of the conferences M1 to Mk and the remarks C, and attendance information. Manage as. The attendee information is stored and managed in the attendee DB181 as described above.
Further, the information management unit 103 stores and manages the voice data V acquired by the voice acquisition unit 101 in the conference DB 182.

The attendee classification unit 104 classifies the attendee A based on the analysis result of the remark C by the remark analysis unit 122. Specifically, the attendee classification unit 104 classifies attendees A based on the amount of speech, the degree of theme matching, and the like.

The meeting requirement acquisition unit 105 acquires the holding requirement information.
That is, the conference requirement acquisition unit 105 acquires the holding requirement of the meeting M to be held, which is input to the organizer terminal 3, as the holding requirement information. Further, the conference requirement acquisition unit 105 acquires the holding requirement of the conference M scheduled to be held as the holding requirement information based on the result of the analysis by the remark analysis unit 122 described above.
Specifically, for example, at the end of the held conference M, the organizer H who attended the conference M as the attendee A may refer to the contents of the conference M scheduled to be held next time. In such a case, the conference requirement acquisition unit 105 acquires the holding requirement of the conference M scheduled to be held as the holding requirement information based on the result of the analysis by the remark analysis unit 122 targeting the remark C of the organizer H. ..

The candidate proposal unit 106 proposes one or more candidates suitable as attendee A of the newly held conference M based on the attendee information and the holding requirement information.
Specifically, in the candidate proposal unit 106, the candidate extraction unit 161 and the display control unit 162 function.
The candidate extraction unit 161 selects one or more candidates suitable as attendee A of the newly held conference M based on the attendee information managed by the information management unit 103 and the holding requirement information. Extract.
The display control unit 162 executes control to display one or more candidates extracted by the candidate extraction unit 161 on the organizer terminal 3.

Since the information processing device of FIG. 5 has the above-mentioned functional configuration, the organizer H of the conference M requests the person who is most suitable for the conference M to attend without having to worry about the selection of the attendee A of the conference M. can do.
As a result, it is possible to reduce the time cost for selecting the attendee A of the conference M, and it is possible to realize a fruitful conference by selecting people with high accuracy. It can also be useful for personnel evaluation within the organization.

Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the range in which the object of the present invention can be achieved are included in the present invention. Consider it as.

In the above-described embodiment, the candidate proposal unit 106 proposes one or more candidates suitable as attendee A of the newly held conference M based on the attendee information and the holding requirement information. However, it is preferable that the attendee information includes the information described below.

For example, the attendee information may include an evaluation from another attendee A (eg, attendee A2) regarding the attendee A (eg, attendee A1).
Specifically, for example, the attendee A attending the conference M collects information on the evaluation of the speaker at the time of the conference M. In the following explanation, each attendee A has a button (hereinafter referred to as a “like button”) that is recognized as having a good evaluation for the speaker when the button is pressed or immediately before the button is pressed. Describe as being distributed.
That is, the attendee A presses the like button when he / she finds that the speaker's remark is good at the conference M. The fact that the like button is pressed by the attendee A is collected in the server 1, and the server 1 manages the information indicating that fact as a part of the attendee information.

For example, suppose that the theme T in this conference M is brainstorming related to a predetermined content, and the theme T in the next conference M to be newly held is a deep dive of a plurality of ideas born as a result of brainstorming. .. Therefore, the next meeting M will be held separately for each of the multiple ideas created as a result of brainstorming.
In such a case, the Candidate Proposal Department 106 likes the attendee A1 who has spoken about the idea as the attendee A for the conference M whose theme T is Fukahori of one idea, and when he / she makes the remark. It is possible to propose the attendee A2 who pressed the button. As a result, it is expected that the conference M with the theme T of Fukahori of a certain idea will be excited and the conference M of the theme T will be held more appropriately.

For example, it is assumed that the theme T of the conference M is "to summarize the discussions so far and confirm the agreement". In this case, it is possible to propose to other attendees A a person who appropriately presses the like button as attendee A. As a result, those who respect the opinions of other attendees A and who do not give consent to those who may be missing are not proposed as candidates for attendee A of the above-mentioned theme T meeting M. Can be.

Also, for example, it is assumed that the newly held conference M should carefully discuss whether there is any mutual oversight. In such a case, the candidate proposal unit 106 can easily propose a plurality of attendees A who are not related to pressing the like button as candidates. It is hoped that this will lead to more careful discussions by taking a proper and critical view of each other.
As described above, the candidate proposal unit 106 is one person who is more suitable as the attendee A of the newly held meeting M by the attendee information including the information indicating that the like button is pressed by the attendee A. The above candidates can be proposed.

It should be noted that the display or the like of the attendee terminal 2 may indicate that the like button was pressed during the conference M. As a result, attendees A can share that they have been evaluated well by each other. That is, for example, since it is not necessary to share the evaluation by voice or the like, the progress of the conference M becomes smoother. Furthermore, since the speaker can grasp that his / her own remark is evaluated well, it is expected that the remark is further promoted and the place of the conference M becomes better. ..

Further, unlike the above example, the fact that the like button is pressed during the conference M may not be shared during the conference M. For example, there is a possibility that the like button is pressed in consideration of the mutual relationship between attendees A (for example, a boss and a subordinate). Since the fact that the like button is pressed is not shared during the conference M, it is expected that the frequency of such pressing is reduced.

Further, the like button may not be used during the conference M, but may be pressed after the conference M ends. As a result, it is evaluated whether or not the attendee A of the current conference M was appropriate, and the candidate proposal unit 106 proposes one or more more suitable candidates as the attendee A of the newly held conference M. can do.
Furthermore, the like button may be able to obtain information indicating which attendees have a good rating. As a result, when the like button is pressed during the meeting M, it is possible to give a good evaluation to the attendee A who is not the speaker at that time. Further, for example, when pressed after the end of the conference M, it is possible to give a good evaluation to any attendee A by summarizing the entire conference M after the end of the entire conference M.
In this way, by using the like button, the candidate proposal unit 106 uses the subjective evaluation of the participant A in the conference M to be more suitable as the attendee A of the newly held conference M1. You will be able to make proposals for the above candidates.
That is, for example

Further, for example, the speaker may be evaluated by using the following elements without being limited to the like button.
That is, for example, the excitement of the conference M can be evaluated by the fluctuation of the loudness of the voice. This makes it possible to evaluate the speaker.
Further, for example, it is possible to evaluate whether the statement C is captured positively or negatively in the conference M due to the fluctuation of the tone of the voice.
Further, for example, at the meeting M, the attendee A who speaks regularly can be given a good evaluation. That is, for example, it is possible to give a good evaluation to the attendee A who can make a statement C regardless of the difference between the first and second half of the meeting M and the situation.

Further, for example, in the above-described embodiment, the relationship between the theme T of the conference M1 and the content of the statement C can be expressed by using an index of "theme matching degree" or "theme deviation degree". The following indicators can also be adopted.
That is, for example, in the above-described embodiment, the one with a high degree of relationship between the theme T and the content of the statement C has a high degree of theme matching, and the one with a low degree of relevance has a high degree of theme divergence. These indicators may be used not only as high or low relevance but also as separate indicators as follows.

That is, for example, it is assumed that the theme T of the conference M is "commercialization of new technology Z". At this conference M, it is assumed that the remark C of the attendee A is "not only commercialization but also attention should be paid to the sales channel". If this statement C is an important matter, it can be said that attendee A makes an important statement C in the situation of the conference M, although the degree of theme divergence is high.
Further, for example, it is assumed that the theme T of the conference M is "about new technology Z". At this conference M, it is assumed that a statement C of a new idea leading to the development of the new technology Y is made. Further, it is assumed that various remarks C are made as brainstorming. It can be said that such a statement C was also an important statement C, although the degree of theme divergence was high.
The same applies not only to the degree of theme divergence but also to the degree of theme matching. That is, for example, even if a statement C having a high degree of theme matching is made while brainstorming is being performed, the brainstorming is interrupted.
The degree of theme matching and the degree of theme divergence can be used not only as an indicator of the degree of relevance but also as a separate index for evaluation according to the situation of the conference M. As a result, by evaluating the attendee A who can make a statement C according to the situation of the meeting M, the candidate proposal unit 106 has one or more more suitable as the attendee A of the newly held meeting M. You will be able to make suggestions for candidates.

Further, for example, the evaluation criteria of the speaker and the attendee A can be different depending on the stage of the conference M (for example, the first half and the second half). That is, for example, in the first half of the conference M, a person who can confirm the situation in the conference M before that and speak about the content of the development of the discussion content can be evaluated as a good evaluation.
Further, for example, in the latter half of the conference M, a person who can summarize the contents of the discussion so far can be evaluated as a good evaluation.

Further, for example, the candidate proposal unit 106 can propose candidates for each stage (for example, the first half and the second half) of the newly held conference M as candidates for the newly held conference M. That is, for example, a person who can conclude a discussion can be proposed as a candidate who will attend the latter half of the conference M.

Further, for example, when the schedule of the newly held conference M is set in advance, the candidate proposal unit 106 can propose a person who can participate in the conference M as a candidate.
That is, the candidate proposal unit 106 may propose a candidate not only based on the theme T of the conference M but also based on information indicating other conditions such as a schedule. Furthermore, the server 1 may output the theme T in which the conference M is expected to proceed more appropriately in the candidate proposed by the candidate proposal unit 106.
Specifically, for example, server 1 proposes many candidates suitable for the above-mentioned brainstorming based on a preset schedule of a newly held conference M, etc., and further discusses themes in the future. From among T, brainstorming can be proposed as the theme T.
As a result, an appropriate theme T is selected in the schedule on the premise of a plurality of conferences M to be newly held thereafter, so that more efficient progress is expected for the plurality of conferences M as a whole.

For example, in the above-described embodiment, the theme T is estimated in units of meetings, departments, and time zones, but the present invention is not limited to this. For example, the theme T can be estimated in units of remarks. As a result, for example, the theme T is presumed even for a sudden remark, so that it can be useful for the selection of the attendee A of the meeting M from the next time onward.

Further, for example, in the example of FIG. 1, each of the remarks C1 to C5 of the attendees A1 to A5 is one, but this is simplified to help the understanding of the explanation. That is, in reality, there may be a plurality of statements C1 to C5 of each of the attendees A1 to A5.

Further, for example, in the example of FIG. 2, the amount of speech of attendee A and the degree of theme matching are adopted as indicators for classifying attendee A. Further, in the example of FIG. 3, the experience, the amount of speech, and the theme matching degree of the attendee A are adopted as the indexes for classifying the attendee A. However, the present invention is not limited to these, and a new index may be additionally provided, or the attendee A may be classified by another index instead of these indexes. Further, the number of indicators is not particularly limited, and may be one or four or more. For example, the status, influence, gender, age, etc. of attendee A can be used as an index. This makes it possible to select a person who considers not only the quantity and quality of the speaker's speech so far, but also the speaker's experience, position, influence, gender, age, and the like. As a result, it is possible to select people with higher accuracy, and it is possible to realize a more fruitful meeting.

Further, the system configuration shown in FIG. 4 and the hardware configuration of the server 1 shown in FIG. 5 are merely examples for achieving the object of the present invention, and are not particularly limited.

Further, the functional block diagram shown in FIG. 6 is merely an example and is not particularly limited. That is, it suffices if the information processing system of FIG. 4 has a function capable of executing the above-mentioned candidate proposal processing as a whole, and what kind of functional block and database is used to realize this function is particularly shown in the figure. It is not limited to the example of 6.

Further, the location of the functional block and the database is not limited to FIG. 6, and may be arbitrary.
In the example of FIG. 6, the candidate proposal process is configured to be performed under the control of the CPU 11 of the server 1 of FIG. 5 constituting the information processing system of FIG. 4, but is not limited thereto. For example, at least a part of the functional block and the database arranged on the server 1 side may be provided in the attendee terminal 2, the organizer terminal 3, the microphone device 4, or another information processing device (not shown). ..

Further, the series of processes described above can be executed by hardware or software.
Further, one functional block may be configured by a single piece of hardware, a single piece of software, or a combination thereof.

When a series of processes are executed by software, a program constituting the software is installed in a computer or the like from a network or a recording medium.
The computer may be a computer embedded in dedicated hardware.
Further, the computer may be a computer capable of executing various functions by installing various programs, for example, a general-purpose smartphone or a personal computer in addition to a server.

The recording medium containing such a program is not only composed of removable media (not shown) distributed separately from the main body of the device in order to provide the program to the user, but also is preliminarily incorporated in the main body of the device to the user. It is composed of the provided recording media and the like.

In this specification, the steps for describing a program recorded on a recording medium are not only processed in chronological order but also in parallel or individually, even if they are not necessarily processed in chronological order. It also includes the processing to be executed.

Summarizing the above, it is sufficient that the information processing apparatus to which the present invention is applied has the following configuration, and various embodiments can be taken.
That is, the information processing apparatus to which the present invention is applied is
An acquisition means (for example, the voice acquisition unit 101 of FIG. 6) for acquiring voice data (for example, voice data V of FIG. 1) of a conference (for example, the first to kth conference M of FIG. 1).
Specific means (for example, FIG. 1) for identifying each speaker (for example, attendee A in FIG. 1) of a predetermined unit of speech (for example, the above-mentioned n speeches C) included in the voice data acquired by the acquisition means. Meeting judgment unit 102) of 6 and
The information indicating the speaker (for example, the attendee ID in FIG. 2) specified by the specific means is associated with the theme of the conference (for example, the theme T in FIG. 1) and the statement, and the first information (for example) For example, a management means (for example, the information management unit 103 in FIG. 6) managed as attendee information in FIG. 1 and
The first information managed by the management means and the second information including at least the theme of the newly held meeting (for example, the kth meeting M in FIG. 1) (for example, the holding requirement information in FIG. 1) Based on the proposal means (for example, the candidate proposal unit 106 in FIG. 6) that proposes one or more suitable candidates as attendees of the conference.
To prepare for.

That is, when the voice data of the conference is acquired, the remarks of a predetermined unit included in the voice data are extracted, and the speakers of the remarks of the predetermined unit are specified. Then, the theme of the conference and the content of the remark are associated with the information indicating the specified speaker and managed. When a new meeting is scheduled, one or more suitable attendees for the new meeting will be based on the information that is managed and at least the theme of the new meeting. Candidates are proposed.
This allows the conference organizer to ask the person who is most suitable for the conference to attend the conference without having to worry about selecting the attendees of the conference.
As a result, it is possible to reduce the time cost for selecting the attendees of the meeting and to realize a fruitful meeting in which the risk of selection mistakes is reduced.

Further, an estimation means (for example, the theme estimation unit 123 in FIG. 6) for estimating one or more themes of the conference based on the result of analyzing the voice data acquired by the acquisition means is further provided.
The management means
The information indicating the speaker can be managed as the first information by associating the theme estimated by the estimation means with the speech.

That is, the theme of the conference is estimated based on the audio data of the conference. Then, the estimated conference theme and the content of the remark are associated with the information indicating the specified speaker and managed.
As a result, for example, even if the content of the meeting temporarily deviates from the original theme while the meeting is in progress, the theme (theme different from the original theme) is associated with the remark. Can be managed.
As a result, it is possible to deal with an actual meeting that does not always proceed according to the original theme. Specifically, for example, while the original theme of the meeting is "excavation of inventions", the content of the meeting may temporarily shift to the theme of "financing" due to the flow of the story. .. Even in such a case, the statement about "financing" will not be associated with the theme of the conference "discovering inventions".

In addition, the management means is
Information related to the experience of the speaker (for example, the experience of the attendee included in the attendee information in FIG. 3) is further associated with the information indicating the speaker and managed as the first information.
The proposing means proposes one or more candidates suitable as attendees of the newly held meeting based on the first information managed by the management means and the second information. be able to.

That is, the information indicating the speaker is associated with the information related to the experience of the speaker and managed. Then, when a new conference is scheduled, it is appropriate as a attendee of the newly held conference based on the managed information and the information including at least the theme of the newly held conference. More than one candidate is proposed.
This makes it possible to select a person who considers not only the quantity and quality of the speaker's speech at the conference but also the speaker's experience.
As a result, it is possible to realize more accurate selection of personnel.

1 ... server, 2 ... attendee terminal, 3 ... organizer terminal, 4 ... microphone device, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ...・ Bus, 15 ... Input / output interface, 16 ... Input unit, 17 ... Output unit, 18 ... Storage unit, 19 ... Communication unit, 20 ... Drive, 40 ... Removal Media, 101 ... Voice acquisition department, 102 ... Meeting judgment department, 103 ... Information management department, 104 ... Attendee classification department, 105 ... Meeting requirement acquisition department, 106 ... Candidates Proposal unit, 121 ... Speaking extraction unit, 122 ... Speaking analysis unit, 123 ... Theme estimation unit, 124 ... Speaker identification unit, 161 ... Candidate extraction unit, 162 ... Display Control unit, 181 ... Attendee DB, 182 ... Meeting DB, A ... Attendees, H ... Organizer, M ... Meeting, V ... Voice data, C ... Remarks , T ... Theme, NW ... Network

Claims

An acquisition method for acquiring conference audio data,
Specific means for identifying each speaker of a predetermined unit of speech included in the voice data acquired by the acquisition means, and
A management means for associating the theme of the conference with the information indicating the speaker specified by the specific means and managing the remarks as the first information.
Based on the first information managed by the management means and the second information including at least the theme of the newly held meeting, one or more suitable candidates for attending the meeting are proposed. Proposal means and
Information processing device equipped with.
Further provided with an estimation means for estimating one or more themes of the conference based on the result of analyzing the audio data acquired by the acquisition means.
The management means
The information indicating the speaker is associated with the theme estimated by the estimation means and the statement, and is managed as the first information.
The information processing apparatus according to claim 1.
The management means
Information related to the experience of the speaker is further associated with the information indicating the speaker and managed as the first information.
The proposing means proposes one or more candidates suitable as attendees of the newly held meeting based on the first information managed by the management means and the second information. ,
The information processing apparatus according to claim 1 or 2.