JP6559861B1 - Chat analysis device, chat analysis method, and program - Google Patents

Abstract

A chat analysis apparatus for analyzing user communication without using a wearable device is provided. A chat analysis apparatus includes a chat identifier, a plurality of chat information including a user identifier for identifying a text sender, a user identifier for identifying a text recipient, and a team identifier for identifying a team. And a reception unit 11 that receives team management information that associates user identifiers of two or more users belonging to the team, a plurality of chat information, and team management information, and responds to a chat of a user of one team The analysis part 13 which acquires the analysis result regarding communication, and the output part 14 which outputs the analysis result acquired by the analysis part 13 are provided. [Selection] Figure 1

Description

  The present invention relates to a chat analysis device that analyzes chat between users and outputs an analysis result related to communication.

  Conventionally, communication between employees within a company has been quantitatively evaluated by each employee wearing a wearable device (see, for example, Non-Patent Document 1). By using such a wearable device, it is possible to automatically collect action data of face-to-face communication between employees.

Kentaro Nakajima, Katsuhito Uehara, Yasushi Tsuru, “Effects of Corporate Communication Network on Productivity”, Economic Research (Iwanami Shoten), Vol. 69, No. 1, pp. 18-34, 2018

  In the conventional example, each employee needs to wear a wearable device in order to quantify communication between employees. As a result, employees may feel uncomfortable about wearing a wearable device. In the conventional example, action data can be collected only for face-to-face communication. For this reason, behavioral data cannot be collected for employees working from home or on business trips, and there is a problem in that those employees are not included in the evaluation target.

  The present invention has been made to solve the above-described problems, and an object thereof is to provide an apparatus and the like that can perform analysis related to communication between users without using a wearable device.

In order to achieve the above object, a chat analyzing apparatus according to the present invention includes a chat text, a plurality of chat information including a user identifier for identifying a text sender, a user identifier for identifying a text recipient, and a team. A reception unit that receives a team identifier for identifying a team management information that associates user identifiers of two or more users belonging to the team, a plurality of chat information, and team management information. An analysis unit that acquires an analysis result related to communication according to chat and an output unit that outputs the analysis result acquired by the analysis unit are provided.
With such a configuration, it becomes possible to perform an analysis on communication between users based on the communication status by chat. Therefore, the user does not have to wear the wearable device, and communication analysis can be performed without causing discomfort to the user. Also, in the case of chat, the user does not have to be at the same place, so that, for example, communication analysis can be performed including users who are working from home, users who are on a business trip, etc. Become.

In the chat analysis device according to the present invention, the analysis unit may acquire an analysis result including information on the amount of communication between users.
With such a configuration, for example, communication between users can be analyzed by using the number of chats between users, the amount of chat text, and the like.

Moreover, in the chat analysis device according to the present invention, the analysis unit may acquire an analysis result including information on the content of communication between users.
With such a configuration, for example, it is possible to acquire an analysis result such as whether the emotion indicated by the chat text is negative or positive.

In the chat analysis device according to the present invention, the analysis unit may acquire an analysis result including a score related to communication between users.
With such a configuration, for example, it becomes possible to compare with past scores, scores of other teams, etc., and it is easy to grasp changes in communication according to time series, relative to other teams Comparisons can be made easily.

In the chat analysis device according to the present invention, the analysis unit includes the number of chats between users, the number of chat recipients, the number of user pairs connected by chat, the result of sentiment analysis on chat text, and the users who participated in the chat. You may calculate the score regarding the connection between the users which belong to one team using at least any one of the number, the duration of chat, and the amount of text included in chat.
With such a configuration, it becomes possible to know the analysis result regarding the connection between users as a score.

In the chat analysis device according to the present invention, the analysis unit includes the number of chats between users, the number of chat recipients, the number of user pairs connected by chat, the result of sentiment analysis on chat text, and the users who participated in the chat. You may calculate the score regarding the magnitude | size of the influence given to others using at least any one of the number, the duration of chat, and the quantity of the text contained in chat.
With such a configuration, an analysis result related to the magnitude of the influence given to other users by the user can be known as a score.

In the chat analysis device according to the present invention, the analysis unit includes the number of chats between users, the number of chat recipients, the number of user pairs connected by chat, the result of sentiment analysis on chat text, and the users who participated in the chat. A score on the connection between users belonging to one team and the magnitude of the influence each user belonging to the team has on others using at least one of the number, the duration of the chat, and the amount of text included in the chat May be calculated.
With such a configuration, it is possible to know as a score an analysis result regarding the connection between users and the magnitude of the influence of the user on other users.

In the chat analysis device according to the present invention, the analysis unit may acquire an analysis result including a communication type.
With such a configuration, for example, it becomes possible to know the type of communication related to the user or team.

In the chat analysis device according to the present invention, the analysis result may include a relative analysis result related to communication.
With such a configuration, for example, it becomes possible to know relative comparison results between users and teams. More specifically, a user can know that the amount of communication is less than that of other users, and can use the comparison result to present improvement proposals to the user. It becomes possible.

  The chat analysis method according to the present invention is a chat analysis method processed using a reception unit, an analysis unit, and an output unit, and the reception unit identifies a chat text and a text sender. Accepting a plurality of chat information including a user identifier and a user identifier for identifying a text recipient, a team identifier for identifying a team, and team management information for associating two or more users belonging to a team with user identifiers An analysis step in which the analysis unit obtains an analysis result relating to communication according to a chat of a user of one team using a plurality of chat information and team management information, and an output unit obtains in the analysis step And an output step for outputting the analyzed results.

  According to the chat analysis device and the like according to the present invention, it is possible to perform an analysis related to communication between users based on the status of communication using chat.

The block diagram which shows the structure of the chat analyzer by embodiment of this invention The flowchart which shows operation | movement of the chat analyzer by the embodiment The figure which shows an example of the team management information in the embodiment The figure which shows an example of the chat information in the embodiment The figure which shows an example of the display of the analysis result in the embodiment The figure which shows another example of the display of the analysis result in the embodiment Schematic diagram showing an example of the appearance of the computer system in the embodiment The figure which shows an example of a structure of the computer system in the embodiment

  Hereinafter, a chat analysis apparatus according to the present invention will be described using embodiments. In the following embodiments, components and steps denoted by the same reference numerals are the same or equivalent, and repetitive description may be omitted. The chat analysis device according to the present embodiment analyzes communication between users by analyzing chats between users.

  FIG. 1 is a block diagram showing a configuration of chat analysis apparatus 1 according to the present embodiment. The chat analysis device 1 according to the present embodiment performs analysis related to communication between users according to chat, and includes a reception unit 11, a storage unit 12, an analysis unit 13, and an output unit 14. The chat may be anything as long as it can send and receive text messages between users in real time. The chat is not particularly limited, and examples thereof include chat using IRC (Internet Relay Chat) and chat using SLACK (registered trademark). The chat may also include exchanging messages using instant messages such as LINE (registered trademark) and iMessage. This is because they can send and receive messages in real time. As will be described later, the chat to be analyzed is usually a text chat, but in addition to text, an attached file such as a still image, a video, a PDF, a text file, or a spreadsheet file is transmitted and received in the chat. May be.

  The reception unit 11 receives a plurality of chat information and one or more team management information. Note that the chat information and the team management information may be received at the same time, or may be received at different timings. Moreover, the reception part 11 may receive both information by a different method. For example, the reception unit 11 may receive a plurality of chat information and read one or more team management information from a recording medium. The reception unit 11 accumulates the received chat information and team management information in the storage unit 12. Moreover, the reception part 11 may perform reception regarding things other than chat information and team management information. For example, as will be described later, the reception unit 11 may receive designation of a team, a user, and a period for which an analysis result is to be output.

  The chat information is information including a chat text, a user identifier that identifies the sender of the text, and a user identifier that identifies the recipient of the text. With this chat information, the chat status and content can be known. For example, the chat information can be used to know which users have chatted and what content has been exchanged by chat. The chat information may further include the chat posting date and time, and may include information such as a flag indicating whether the recipient has read the chat text (information indicating whether it has been read). Often, the date and time the recipient read the chat text may be included. Chat text is the text of a chat message sent and received by chat. Note that the user identifier for identifying the recipient may be a single user identifier or two or more user identifiers. In the case of one-to-one chat, the former is used, and in the case of group chat, the latter is used. Even if the chat information includes a team identifier that identifies the team of the recipient, the team management information can specify the user identifier of each user included in the team identified by the team identifier. In this case, it may be considered that the user identifier of the recipient is included. As a result, the user identifier for identifying the recipient can be specified. The accepting unit 11 may accept a plurality of chat information at once, or may accept them one by one. In the latter case, for example, every time a chat between users is performed, chat information corresponding to the chat may be accepted.

  The team management information is information that associates a team identifier for identifying a team with user identifiers of two or more users belonging to the team. The team management information can identify users belonging to the team. A team is a group of users. The team may be, for example, an organization such as a company, union, school, or local government, or it may be a subgroup such as a department included in the organization, or a team formed temporarily for chatting. Or other teams. Moreover, the team may be hierarchized. For example, team A may include team A1 and team A2. In that case, the user U101 belonging to the team A1 also belongs to the team A. As an example of the hierarchized team, there are, for example, an organization such as a company, a large department included in the group, a middle department included in the large department, and a small department included in the middle department.

  For example, the reception unit 11 may receive information input from an input device (for example, a keyboard, a mouse, a touch panel, etc.), or may receive information transmitted via a wired or wireless communication line. Information read from a predetermined recording medium (for example, an optical disk, a magnetic disk, a semiconductor memory, etc.) may be received. The reception unit 11 may or may not include a device (for example, a modem or a network card) for reception. The receiving unit 11 may be realized by hardware, or may be realized by software such as a driver that drives a predetermined device.

  When the chat analysis device 1 is a device different from the chat server that manages chat data, the reception unit 11 may receive, for example, a plurality of chat information and team management information from the chat server. . Further, when the chat analysis device 1 is incorporated in a chat server, the reception unit 11 stores, for example, a plurality of chat information and team management information managed by the chat server, and a storage medium in which the chat information is stored. You may read from. Note that the chat analysis device 1 may acquire information managed by the chat server using an API (Application Programming Interface) provided by the chat server.

  The storage unit 12 stores chat information and team management information. They are accumulated by the receiving unit 11 as described above. The storage unit 12 may store other information. The storage in the storage unit 12 may be temporary storage in a RAM or the like, or may be long-term storage. The storage unit 12 can be realized by a predetermined recording medium (for example, a semiconductor memory or a magnetic disk).

  The analysis unit 13 uses the plurality of chat information and the team management information to acquire an analysis result regarding communication according to the chat of the user of one team. That is, the analysis unit 13 performs analysis related to communication in team units. For example, the analysis unit 13 may specify user identifiers of users belonging to the analysis target team using team management information, and perform analysis using chat information including the specified user identifiers. Moreover, the analysis part 13 may perform the analysis regarding the communication in a user unit. Further, the analysis unit 13 may perform analysis for a predetermined period. The predetermined period may be a period specified in advance, or may be a period such as a day unit, a week unit, a month unit, or a year unit. In the latter case, for example, analysis on August 1, analysis on the first week in August, analysis on August, analysis on 2018, and the like may be performed. In the case where the analysis is performed for the predetermined period as described above, the analysis may be performed using only the chat information of the chat message posted within the predetermined period. In addition, for example, the user who receives the analysis result may be able to specify the period.

  The analysis unit 13 may acquire an analysis result including information on the amount of communication between users, for example. From this analysis result, for example, it is possible to know whether sufficient communication is performed between teams or between users. The amount of communication may be, for example, the number of chats or the amount of data transmitted / received by chat. Therefore, for example, if the analysis results show that there is not much communication between teams or users, smoother communication can be achieved by taking measures to solve the problem. Can be done. The score regarding the connection between the users mentioned later is an example of the information regarding the amount of communication between the users.

  For example, the analysis unit 13 may acquire an analysis result including information on the content of communication between users. From this analysis result, it is possible to know, for example, whether or not communication that can affect between teams or between users is performed. The content of the communication may be, for example, whether the result of the emotion analysis of the chat text is positive or negative. The analysis results can also be used to know, for example, whether the team is actively involved in the organization to which the team belongs and whether the user is actively involved in the team to which the user belongs. sell. This is because when a chat with a high degree of positive or negative emotion is performed, it is considered that the user is trying to get involved in the team. So, for example, if the results of this analysis show that a team or a user is not actively involved in the team to which they belong, by taking steps to solve the problem, The satisfaction of the team or the user can be improved, and the team or the user can contribute to the team to which the team belongs. A score relating to the magnitude of the influence given to others, which will be described later, is an example of information relating to the content of communication between users.

  For example, the analysis unit 13 may acquire an analysis result including a score related to communication between users. By obtaining the score, there is a merit that a relative comparison with others and the past becomes possible. Here, a connection score, an engagement score, and a condition score will be specifically described as the communication scores.

  In calculating those scores, the analysis unit 13 may, for example, include the number of chats between users, the number of chat recipients, the number of user pairs connected by chat, the emotion analysis results regarding chat text, the chat You may use at least any one of the number of users who participated in the chat, the duration of the chat, and the amount of text included in the chat.

  The number of chats between users may be, for example, the number of chat messages transmitted and received between users. For example, when one chat message is transmitted from the user A to the user B, the number of chats between the users A and B is counted as “1”.

  The number of chat recipients may be, for example, the number of recipients related to the chat message of interest. The number of recipients may be, for example, the total number of recipients or the number of unique recipients. In the former case, the total number of recipients of the chat message of interest is the number of recipients of the chat. In the latter case, for example, the user identifier of the recipient of the chat message of interest is merged The number of user identifiers as a result of performing the unique process becomes the number of chat recipients.

  The number of user pairs connected by chat may be, for example, the number of user pairs connected by sending and receiving chat messages. The number of pairs may be, for example, the total number of pairs or the number of unique pairs. When a certain chat message is transmitted to a team, the number of pairs of the user of the sender and each user belonging to the team is the number of pairs of users connected by chat. Therefore, when the sender is included in the destination team, “number of team users−1” is the number of user pairs connected by the chat message, and the sender is not included in the destination team. In this case, the number of users of the team is the number of pairs of users connected by the chat message.

  The sentiment analysis result regarding the chat text may be, for example, information indicating whether the chat text is positive or negative, or may be information indicating whether the chat text is positive, negative, or neutral. The chat text is neutral if the sentiment analysis result of the text is neither positive nor negative. Since emotion analysis is publicly known, detailed description thereof is omitted. The emotion analysis may be performed by using machine learning such as SVM or neural network, for example, and may be performed by a rule base that determines whether a positive expression or a negative expression is included in the text. It is also possible to obtain emotion analysis results using Cloud Natural Language (https://cloud.google.com/natural-language/?hl=en) provided by Google (registered trademark). it can. The emotion analysis result is indicated by, for example, a score from −1 to 1, and may be negative as it is closer to −1 and may be positive as it is closer to 1. Further, for example, when the score is in a range from −ε to ε, it may be determined as neutral. Note that ε is a predetermined positive real number sufficiently smaller than 1.

  The number of users who participated in the chat may be, for example, the number of users who transmitted the chat message of interest, or the number of users who received the chat message of interest. May be the total of the number of users who have transmitted and the number of users who have received the message, or the number of users who have read the chat message of interest. From the viewpoint that the user who only receives the chat message does not participate in the chat, the number of users who participated in the chat may be the number of users who transmitted the chat message. The number of users who participated in the chat may be acquired for a predetermined period. The predetermined period may be, for example, a period during which chatting continues.

  The duration of the chat may be, for example, the length of a period during which the chat is continued, that is, a period from when transmission / reception of a series of chat messages between users is started until it is ended. That is, the length of the period from the date and time of the first chat message in the series of chat messages to the date and time of the last chat message is the chat duration. For example, it is determined that a series of chat message transmission / reception has ended when a chat message transmission / reception between certain users has not been performed for a threshold period (for example, 5 minutes, 10 minutes, 30 minutes, or the like). May be.

  The amount of text included in the chat may be, for example, the number of characters in the chat text or the data capacity of the chat text (number of bits, number of bytes). When attention is paid to a plurality of chat messages, the total or average amount of text of the plurality of chat messages may be calculated.

[Connection score]
The analysis unit 13 may calculate a connection score that is a score related to connections between users belonging to one team. For example, the analysis unit 13 has a higher value as the number of chats between users, chat duration, and the amount of text included in the chat increases. The number of chat recipients, the number of user pairs connected by chat, You may calculate the connection score which becomes a low value, so that there are many users who participated in. That is, the connection score may be a value of an increase function that takes at least one or more of the number of chats between users, the chat duration, and the amount of text included in the chat as an argument. The function may be a decreasing function having at least one of the number of chat recipients, the number of user pairs connected by chat, and the number of users participating in chat as arguments. This is because when the number of users is the same, the larger the number of chats between users, the greater the connection between users. Further, when the number of chats is the same, it can be considered that the larger the number of users, the smaller the connection between users. Moreover, the analysis part 13 may calculate a connection score, for example using only the chat message shown that it is not neutral by the emotion analysis result regarding the text of chat. In addition, the number of chats between users on a team, the chat duration, and the amount of text included in the chat is the total number of chats between users belonging to that team, the total chat duration, It may be the total amount of text included in the chat.

Here, calculation of the connection score regarding the team A will be described using an example. In this specific example, a case where the connection score is calculated by the following equation will be described.
Connection score = number of chats between users / number of users participating in chats

  When the connection score related to team A is a connection score related only to chats between users belonging to team A, the analysis unit 13 firstly sends the user of team A to the recipient and the user of team A Identify chat information that contains. And the analysis part 13 acquires the number of chats between users which is the number of specified chat information. Next, the analysis unit 13 acquires the user identifier of the sender of the identified chat information and performs a unique process. And the number of users who participated in the chat, which is the number of user identifiers after the unique processing, is acquired. Finally, the analysis unit 13 calculates a connection score using the above formula.

  On the other hand, when the connection score regarding the team A is the connection score regarding the chat involving the users belonging to the team A, the analysis unit 13 first specifies the chat information whose sender is the user of the team A. The processing after specifying the chat information is the same as described above. In this case, chat messages transmitted from the user of team A to users other than team A are also counted in the number of chats between users.

  In the above description, the case where the number of users who participated in the chat is the number of users who transmitted the chat message has been described. However, as described above, the number of users who participated in the chat also includes the number of users who received the chat message It may be included. In addition, when the connection score regarding the team A is a connection score regarding only the chat between the users belonging to the team A, the number of users who have received the chat message may be counted only for the users belonging to the team A.

  Moreover, the analysis part 13 may calculate the connection score between teams, for example. Specifically, the analysis unit 13 may calculate a connection score between team A and team B. In that case, for example, the analysis unit 13 includes chat information in which the sender is a user of Team A and the receiver includes the user of Team B, and the sender is a user of Team B, and the receiver is a team. The chat information including the user A is specified. And the analysis part 13 acquires the number of chats between users which is the number of specified chat information. Next, the analysis unit 13 acquires the user identifier of the sender of the identified chat information and performs a unique process, and acquires the number of users who participated in the chat, which is the number of user identifiers after the unique process. Finally, the analysis unit 13 calculates a connection score between the team A and the team B by the above formula. As described above, for example, the number of users who participated in the chat may include the number of users who received the chat message.

  Moreover, the connection score regarding the user U may be calculated as follows, for example. First, the analysis unit 13 may identify chat information whose sender is the user U, and use the number of identified chat information as a connection score. First, the analysis unit 13 specifies chat information in which the sender is the user U and chat information in which the user U is included in the receiver, and acquires the number of the specified chat information. Next, the analysis unit 13 acquires the user identifier of the sender of the specified chat information and the user identifier of the receiver, and performs a unique process. Then, the connection score may be calculated by dividing the number of acquired chat information by the number of user identifiers after the unique processing.

[Engagement score]
The analysis unit 13 may calculate an engagement score that is a score related to the magnitude of the influence given to others. The engagement score may be a score related to the magnitude of influence given to others by a user belonging to one team. The engagement score for team A may be calculated by the following equation, for example.
Engagement score = number of post impacts / total number of posts

  The number of posted impacts may be, for example, the total number of recipients of chat messages that are shown to be positive or negative by the emotion analysis result among chat messages transmitted by users belonging to team A. The emotion analysis in this case may classify the chat message into three levels, positive, negative, and neutral. Also, for example, the post impact number may be larger as the chat duration related to the positive or negative chat message is longer. Further, for example, the greater the amount of text in the positive or negative chat message, the larger the number of post impacts may be. Further, for example, the greater the number of unique pairs of users connected by the positive or negative chat message, the larger the number of post impacts may be. For example, the larger the number of unique users who participated in the chat related to the positive or negative chat message, the larger the post impact number may be. The number of post impacts may or may not be calculated only for chat messages in which the recipients include users belonging to team A. In the latter case, a chat message transmitted to a user belonging to other than the team A is also used for calculating the number of posted impacts. The total number of posts may be the total number of chat messages transmitted by users belonging to team A. When the post impact number is calculated only for a chat message in which the recipient includes a user belonging to Team A, the total post count is also transmitted by the user belonging to Team A, and the user belonging to Team A is sent to the recipient. It may be the total number of chat messages included.

  Specifically, the analysis unit 13 may calculate an engagement score as follows. First, the analysis unit 13 specifies chat information that the user of the team A is a sender, and acquires the total number of posts that is the number of the specified chat information. Next, the analysis unit 13 performs emotion analysis on the text included in the identified chat information, and identifies chat information determined to be negative or positive. Then, the number of post impacts is obtained by summing the number of recipients of each chat information determined to be negative or positive. Finally, the analysis unit 13 calculates an engagement score using the above formula.

  Note that the engagement score for the user U is the same as the above except that, in the above process, instead of specifying the chat information that the user of the team A is the sender, the chat information that the user U is the sender is specified. Can be calculated.

  In the above description, a case has been described in which a negative chat message is also used to calculate the number of posted impacts, but this need not be the case. Only positive chat messages may be used for calculating the post impact number.

[Condition score]
The analysis unit 13 may calculate a condition score that is a score related to the connection between users belonging to one team and the magnitude of the influence of each user belonging to the team on the other person. The condition score for team A may be calculated by the following equation, for example.
Condition score = connection score x engagement score

  In addition, a connection score and an engagement score are the scores regarding the team A, and those calculation methods are as above-mentioned.

  Further, the condition score related to the user U can be calculated in the same manner. In that case, the connection score and the engagement score are scores relating to the user U, and the calculation method thereof is also as described above.

[Relative analysis]
The analysis unit 13 may perform a relative analysis regarding communication. In that case, the relative analysis result may be included in the analysis result. The relative analysis may be, for example, a result of comparing a team or user score with an average value or a median value. More specifically, whether the score is higher or lower than the average value or the median value may be included in the relative analysis result. The relative analysis result may include a score deviation value. The deviation value makes it possible to know the position of a certain team's score in the distribution of scores of a plurality of teams, the position of a certain user's score in the distribution of scores of a plurality of users, and the like. Moreover, the analysis part 13 may perform a relative analysis with the past score. In that case, the difference from the past score may be included in the analysis result. Based on the analysis result, it is possible to easily know whether the score has increased or decreased. When performing a relative analysis with the past score, for example, the score may be accumulated in the storage unit 12 every time the score is calculated. The calculated score may be accumulated in the storage unit 12 in association with information for identifying the score, information for identifying the team or user, and information for identifying the period.

[Type of communication]
For example, the analysis unit 13 may acquire an analysis result including a communication type. From this analysis result, for example, it is possible to know the type of communication of the team or the user. The communication type of the team may be, for example, active communication or poor communication. Further, the type of communication of the user may be, for example, positive, initiative, passive, negative, or the like. For example, personnel changes can be made according to the analysis results, and advice can be given to teams and users.

  Specifically, the analysis unit 13 may specify the communication type of team A as follows. For example, the analysis unit 13 acquires a type indicating that the communication of the team A is active when the connection score per unit period of the team A is large, and the communication of the team A is low when the score is small. A certain type may be acquired. Specifically, the analysis unit 13 calculates the connection score of the team A per unit period (for example, 1 hour or 1 day). If the connection score per unit period is larger than a predetermined threshold, a communication type indicating that the communication of team A is active is acquired, and the connection score per unit period is determined in advance. If it is smaller than the determined threshold, a communication type indicating that the communication of team A is poor may be acquired.

  For example, the analysis unit 13 acquires a type indicating that the communication of the team A is active when the period until the reply to the chat in the team A is short, and the communication of the team A is performed when the period is long. A type indicating that the tone is low may be acquired. Specifically, in the chat between the users of Team A, the analysis unit 13 calculates an average time from when a chat message is posted until a reply chat message is posted, and the average time is calculated. Is smaller than the predetermined threshold, the communication type indicating that the communication of the team A is active is acquired, and when the average time is larger than the predetermined threshold, the team A The type of communication indicating that the communication is low may be acquired. The average time may be calculated within a period in which the chat is continued.

  Further, the analysis unit 13 may specify the type of communication of the user U as follows. For example, the analysis unit 13 acquires a type indicating that the communication of the user U is positive when the user U is speaking more than the communication partner user, and if not, the user U A type indicating that U's communication is passive may be acquired. Specifically, the analysis unit 13 specifies chat information included in the sender or the receiver by the user U, and calculates an average value of the number of recipients for the specified chat information. Further, the analysis unit 13 acquires the total number of the specified chat information, and acquires the number of chat information in which the user U is the sender in the specified chat information. Then, when the value obtained by dividing the number of chat information of which the user U is the sender by the total number of the specified chat information is greater than the threshold value determined based on the average value of the number of recipients, The fact that the type is positive may be acquired, and if not, the fact that the type of the user U is passive may be acquired. The threshold value determined based on the average value of the number of recipients may be, for example, the average value of the number of recipients itself, and a small value (for example, 1 or 2, 3) is added to or subtracted from the average value. It may be a value obtained by multiplying the average value by a value close to 1 (for example, 1.1 or 0.9).

  In addition, for example, in the transmission / reception of a series of chat messages, the analysis unit 13 acquires a type indicating that the communication of the user U is the lead when the user U has transmitted the first chat message many times. May be. Specifically, the analysis unit 13 specifies transmission / reception of a series of chat messages included in the sender or receiver by the user U, and the number of times of transmission / reception of the specified series of chat messages (transmission / reception of a series of chat messages is performed). And the number of times the user U has transmitted the first chat message in the series of chat messages is acquired. When the value obtained by dividing the number of times that the user U has transmitted the first chat message by the number of times of transmission / reception of a series of chat messages is greater than a predetermined threshold, the type of the user U is dominant. If not, it may be obtained that the type of the user U is not leading.

  For example, when the number of positive chat messages transmitted by the user U is smaller than the number of negative chat messages, the analysis unit 13 acquires a type indicating that the communication of the user U is negative. May be. Specifically, the analysis unit 13 identifies chat information in which the user U is a sender, and for the identified chat information, the number of chat information in which the text emotion analysis result is positive and the text emotion analysis result. And the number of chat information for which is negative. Then, for example, when the number of negative chat information is greater than the number of positive chat information, the analysis unit 13 may acquire that the type of the user U is negative.

  The output unit 14 outputs the analysis result acquired by the analysis unit 13. For example, the output unit 14 may output an analysis result regarding a designated team or a designated user. In addition, the output unit 14 may output an analysis result regarding a specified period, for example. The designation of the team, the user, the period, etc. may be received by the reception unit 11. When outputting the analysis result of the designated team or the like, the output unit 14 selects the designated one from the analysis results regarding all teams, users, and periods acquired in advance by the analysis unit 13. The result analyzed by the analysis unit 13 may be output according to the designation.

  Here, the output may be, for example, display on a display device (for example, a liquid crystal display or an organic EL display), transmission via a communication line to a predetermined device, printing by a printer, or recording medium. It may be stored in the memory or delivered to other components. The output unit 14 may or may not include an output device (for example, a display device or a printer). The output unit 14 may be realized by hardware, or may be realized by software such as a driver that drives the devices.

Next, the operation of the chat analysis device 1 will be described using the flowchart of FIG.
(Step S101) The reception unit 11 determines whether chat information and team management information have been received. If such information is received, the process proceeds to step S102. If not, the process of step S101 is repeated until such information is received.

  (Step S102) The analysis unit 13 sets a counter i to 1.

  (Step S103) The analysis unit 13 performs a predetermined analysis on the i-th team and acquires the analysis result. The predetermined analysis may be, for example, calculating each of a connection score, an engagement score, and a condition score.

  (Step S104) The analysis unit 13 increments the counter i by 1.

  (Step S105) The analysis unit 13 determines whether or not the i-th team exists. If the i-th team exists, the process returns to step S103, and if not, the process proceeds to step S106.

  (Step S106) The output unit 14 outputs the analysis result acquired by the analysis unit 13. Then, a series of analysis processes relating to communication using chat information ends.

  In the flowchart of FIG. 2, as described above, the reception unit 11 receives designation of a team, a user, and a period, and outputs an analysis result according to the designated team, user, and period. May be. Further, in the flowchart of FIG. 2, only the analysis regarding the team is performed, but the analysis regarding the user may be performed. Further, the order of processing in the flowchart of FIG. 2 is an example, and the order of each step may be changed as long as the same result can be obtained.

Next, the operation of the chat analysis device 1 according to the present embodiment will be described using a specific example.
In this specific example, the chat analysis device 1 is a server, and in response to an instruction from a terminal device (not shown), chat information and team management information are acquired from a chat server (not shown) and analyzed using the acquired chat information and the like. Shall be performed.

  First, the user transmits an instruction to the chat analysis apparatus 1 to analyze the team T101 in the company X from September 2, 2018 to September 8, 2018 by operating the terminal device. To do. Then, the instruction is received by the reception unit 11 of the chat analysis device 1. And the chat analysis apparatus 1 transmits the instruction | indication to the effect of transmitting the chat information regarding the company X, and team management information with respect to a chat server according to the reception. The chat server transmits chat information about the company X and team management information to the chat analysis device 1 in response to the instruction. The transmitted chat information and team management information are received by the reception unit 11 of the chat analysis device 1 and accumulated in the storage unit 12 (step S101).

  3 and 4 are diagrams illustrating an example of team management information and chat information received by the reception unit 11. In FIG. 3, the team management information includes a team identifier for identifying a team and a user identifier for a user belonging to the team. For example, it is indicated that the user identified by the user identifier U101, U102, U103, etc. belongs to the team identified by the team identifier T101 (assuming that this team is the above-mentioned “team T101”). Has been.

  In FIG. 4, the chat information includes the date and time when the chat message was posted, the sender ID for identifying the sender of the chat message, the receiver ID for identifying the recipient of the chat message, and the chat text. It is included. The sender ID is a user identifier. The recipient ID is a user identifier or a team identifier. When the receiver ID is a team identifier, a user belonging to the team identified by the team identifier is a receiver. However, when the sender belongs to the team identified by the team identifier of the receiver ID, it may be considered that the sender is not included in the receiver.

  Next, since the analysis unit 13 has received an instruction to analyze the team T101 from September 2, 2018 to September 8, 2018, the reception unit 11 receives the information on September 2, 2018. Only the chat information having the date and time from the date to September 8, 2018 is extracted. Then, the analysis unit 13 calculates the connection score, the engagement score, and the condition score of the team T101 using the extracted chat information, accumulates these scores in the storage unit 12, and passes them to the output unit 14 (step) S103). Here, it is assumed that the connection score is “7.82”, the engagement score is “12.9”, and the condition score is “100.8”. In addition, the analysis unit 13 calculates the connection score “10.12”, the engagement score “8.8”, the condition score “89” from August 26, 2018 to September 1, 2018, which were calculated in advance. ”Is read from the storage unit 12, and the score difference from the previous period is calculated by subtracting the read score from the calculated score, and the calculation result is also passed to the output unit 14.

  Upon receiving the scores and the differences between the scores, the output unit 14 transmits them to the terminal device that is the source of the analysis instruction (step S106). As a result, as shown in FIG. 5, the terminal device displays the condition score, the engagement score, and the connection score as the analysis results of the team T101 from September 2, 2018 to September 8, 2018. It will be. The difference from the previous period is also displayed. The user who sees the display can know that the connection score for team T101 is slightly lowered, but the engagement score is raised, and as a result, the condition score is also raised.

  The analysis unit 13 may analyze the team T101 and also analyze each user belonging to the team T101. For example, the analysis unit 13 calculates the number of postings of chat messages between users in the team T101 from September 2, 2018 to September 8, 2018, and the engagement score of each user belonging to the team T101. Also good. Then, the output unit 14 is a graph showing the relationship between the user having the line thickness according to the number of postings between the users and the size of the circle according to the user's engagement score (the node indicating the user and the relationship between the nodes). A graphic having an edge indicating) may be output. In that case, for example, as shown in FIG. 6, the graph may also be displayed on the terminal device.

  As described above, according to the chat analysis device 1 according to the present embodiment, it is possible to perform analysis relating to communication between users using chat. Therefore, even if a user does not wear a wearable device, it becomes possible to perform an analysis regarding communication between users, and such an analysis can be performed without causing discomfort to the user. Further, even when the user is working from home and cannot perform face-to-face communication, analysis regarding communication between users can be performed. Further, by calculating the score in the analysis, it becomes easy to compare with the scores of other teams or users, or with the past scores. Further, by performing a relative analysis on the score, it becomes possible to easily know a relative comparison result between users or teams regarding communication.

  In the present embodiment, the case where a score is calculated as an analysis related to communication, that is, a case where a quantitative analysis is performed, has been mainly described, but this need not be the case. For example, a qualitative analysis such as the type of communication may be performed.

  Moreover, the above-mentioned score etc. are examples, and by analyzing chat, the score etc. regarding communications other than the above may be calculated, and the analysis result regarding communications other than the above may be acquired.

  Moreover, although this Embodiment demonstrated the case where the chat information and team management information received by the reception part 11 were accumulate | stored in the memory | storage part 12, it may not be so. When such information is read from the recording medium and accepted, the accepting unit 11 may pass the information directly to the analyzing unit 13. In that case, the chat analysis device 1 may not include the storage unit 12.

  In the above embodiment, each process or each function may be realized by centralized processing by a single device or a single system, or may be distributedly processed by a plurality of devices or a plurality of systems. It may be realized by doing.

  In the above embodiment, the information exchange between the components is performed by one component when, for example, the two components that exchange the information are physically different from each other. It may be performed by outputting information and receiving information by the other component, or when two components that exchange information are physically the same, one component May be performed by moving from the phase of the process corresponding to to the phase of the process corresponding to the other component.

  In the above embodiment, information related to processing executed by each component, for example, information received, acquired, selected, generated, transmitted, or received by each component In addition, information such as threshold values, mathematical formulas, addresses, and the like used by each constituent element in processing may be temporarily or for a long time held in a recording medium (not shown), even if not specified in the above description. Further, the storage of information on the recording medium (not shown) may be performed by each component or a storage unit (not shown). Further, reading of information from the recording medium (not shown) may be performed by each component or a reading unit (not shown).

  In the above embodiment, when information used by each component, for example, information such as a threshold value, an address, and various setting values used by each component may be changed by the user, Even if it is not specified in the description, the user may be able to change the information as appropriate, or may not be so. If the information can be changed by the user, the change is realized by, for example, a not-shown receiving unit that receives a change instruction from the user and a changing unit (not shown) that changes the information in accordance with the change instruction. May be. The change instruction received by the receiving unit (not shown) may be received from an input device, information received via a communication line, or information read from a predetermined recording medium, for example. .

  In the above embodiment, when two or more components included in the chat analysis apparatus 1 have a communication device, an input device, or the like, the two or more components may have a physically single device. Well, or you may have separate devices.

  In the above-described embodiment, each component may be configured by dedicated hardware, or a component that can be realized by software may be realized by executing a program. For example, each component can be realized by a program execution unit such as a CPU reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory. At the time of execution, the program execution unit may execute the program while accessing the storage unit or the recording medium. In addition, the software which implement | achieves the chat analyzer 1 in the said embodiment is the following programs. In other words, the program causes the computer to include chat text, a plurality of chat information including a user identifier that identifies a text sender, a user identifier that identifies a text recipient, and a team identifier that identifies a team. , An accepting unit that receives team management information that associates user identifiers of two or more users belonging to a team, a plurality of chat information, and analysis on communication according to chats of users of one team using team management information It is a program for functioning as an analysis part which acquires a result, and an output part which outputs the analysis result acquired by the analysis part.

  In the program, the functions realized by the program do not include functions that can be realized only by hardware. For example, functions that can be realized only by hardware such as a modem and an interface card in a reception unit that receives information and an output unit that outputs information are not included in at least the functions realized by the program.

  Further, this program may be executed by being downloaded from a server or the like, and a program recorded on a predetermined recording medium (for example, an optical disk such as a CD-ROM, a magnetic disk, a semiconductor memory, or the like) is read out. May be executed by Further, this program may be used as a program constituting a program product.

  Further, the computer that executes this program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  FIG. 7 is a schematic diagram showing an example of the external appearance of a computer that executes the program and realizes the chat analysis apparatus 1 according to the embodiment. The above-described embodiment can be realized by computer hardware and a computer program executed on the computer hardware.

  7, the computer system 900 includes a computer 901 including a CD-ROM drive 905, a keyboard 902, a mouse 903, and a monitor 904.

  FIG. 8 is a diagram showing an internal configuration of the computer system 900. In FIG. 8, in addition to the CD-ROM drive 905, a computer 901 is connected to an MPU (Micro Processing Unit) 911, a ROM 912 for storing a program such as a bootup program, and the MPU 911, and receives instructions of an application program. A RAM 913 that temporarily stores and provides a temporary storage space, a hard disk 914 that stores application programs, system programs, and data, and a bus 915 that interconnects the MPU 911, the ROM 912, and the like are provided. The computer 901 may include a network card (not shown) that provides connection to a LAN, WAN, or the like.

  A program that causes the computer system 900 to execute the function of the chat analysis device 1 according to the above embodiment may be stored in the CD-ROM 921, inserted into the CD-ROM drive 905, and transferred to the hard disk 914. Instead, the program may be transmitted to the computer 901 via a network (not shown) and stored in the hard disk 914. The program is loaded into the RAM 913 when executed. The program may be loaded directly from the CD-ROM 921 or the network. Further, the program may be read into the computer system 900 via another recording medium (for example, a DVD) instead of the CD-ROM 921.

  The program does not necessarily include an operating system (OS) or a third party program that causes the computer 901 to execute the function of the chat analysis device 1 according to the above-described embodiment. The program may include only a part of an instruction that calls an appropriate function or module in a controlled manner and obtains a desired result. How the computer system 900 operates is well known and will not be described in detail.

  Further, the present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, according to the chat analysis device and the like according to the present invention, it is possible to perform an analysis related to communication based on the status of communication using chat. It is useful as a device to perform.

DESCRIPTION OF SYMBOLS 1 Chat analyzer 11 Reception part 12 Storage part 13 Analysis part 14 Output part

Claims (8)

Chat text, a plurality of chat information including a user identifier for identifying a sender of the text, a user identifier for identifying a recipient of the text, a team identifier for identifying a team, and two or more belonging to the team A reception unit for receiving team management information for associating a user identifier of the user;
Using the plurality of chat information and the team management information, an analysis unit that acquires an analysis result including a score related to communication between users according to a chat of a user of one team;
An output unit for outputting the analysis result acquired by the analysis unit,
The said analysis part is a chat analysis apparatus which calculates the engagement score which is a score regarding the magnitude | size of the influence given to others using the following Formula.
Engagement score = number of post impacts / total number of posts (where post impact count is the total number of chat recipients that are shown as positive or negative based on sentiment analysis results, The total number of posts is the total number of chats sent by the user.) The analysis unit is an increasing function that takes at least one or more of the number of chats between users, the duration of chats, and the amount of text included in the chats, and the number of chat recipients and users connected by chat Calculate the connection score for connections between users belonging to one team, which is the value of a function that is a decreasing function that takes at least one of the number of pairs and the number of users who participated in the chat as arguments. The chat analysis device according to claim 1, wherein a condition score is calculated.
Condition score = connection score x engagement score The chat analysis device according to claim 1, wherein the analysis unit acquires an analysis result including a communication type. The chat analysis device according to claim 1, wherein the analysis result includes a relative analysis result regarding communication. A chat analysis method processed using a reception unit, an analysis unit, and an output unit,
The reception unit includes a chat text, a plurality of chat information including a user identifier that identifies a sender of the text, a user identifier that identifies a recipient of the text, a team identifier that identifies a team, A reception step of receiving team management information that associates user identifiers of two or more users belonging to a team;
An analysis step in which the analysis unit acquires an analysis result including a score regarding communication between users according to a chat of a user of one team using the plurality of chat information and the team management information;
The output unit includes an output step of outputting the analysis result acquired in the analysis step;
In the analysis step, a chat analysis method for calculating an engagement score, which is a score related to the magnitude of an influence given to others, using the following equation.
Engagement score = number of post impacts / total number of posts (where post impact number is the total number of chat recipients in the chat sent by the user that are shown positive or negative by the emotion analysis results, The total number of posts is the total number of chats sent by the user.) In the analysis step, the number of chats between users, the chat duration, and an increase function with at least one of the amount of text included in the chat as an argument, and the number of chat recipients and users connected by chat Calculate the connection score for connections between users belonging to one team, which is the value of a function that is a decreasing function that takes at least one of the number of pairs and the number of users who participated in the chat as arguments. The chat analysis method according to claim 5, wherein a condition score is calculated.
Condition score = connection score x engagement score Computer
Chat text, a plurality of chat information including a user identifier for identifying a sender of the text, a user identifier for identifying a recipient of the text, a team identifier for identifying a team, and two or more belonging to the team A reception unit that receives team management information that associates a user identifier of
Using the plurality of chat information and the team management information, an analysis unit that acquires an analysis result including a score related to communication between users according to a chat of a user of one team,
Function as an output unit that outputs the analysis result acquired by the analysis unit;
The said analysis part is a program which calculates the engagement score which is a score regarding the magnitude | size of the influence given to others using following Formula.
Engagement score = number of post impacts / total number of posts (where post impact count is the total number of chat recipients that are shown as positive or negative based on sentiment analysis results, The total number of posts is the total number of chats sent by the user.) The analysis unit is an increasing function that takes at least one or more of the number of chats between users, the duration of chats, and the amount of text included in the chats, and the number of chat recipients and users connected by chat Calculate the connection score for connections between users belonging to one team, which is the value of a function that is a decreasing function that takes at least one of the number of pairs and the number of users who participated in the chat as arguments. The program according to claim 7, wherein a condition score is calculated.
Condition score = connection score x engagement score

Images