Analytical equipment, analytical methods, and analytical programs

Abstract

To improve user motivation. [Solution] In the analysis device 10, the acquisition unit 15a acquires text data representing the content of conversations between multiple users. The generation unit 15b inputs the text data into the model 14a and generates data that counts words corresponding to an indicator of contribution to the conversation.

Description

Technical Field

[0001] The present invention relates to an analysis device, an analysis method, and an analysis program.

Background Art

[0002] In recent years, on Web conferencing systems, there has been an increasing number of cases where members of a work team conduct discussions using chat or the like. Also, at such times, a service is known in which thank-you cards are exchanged among team members to facilitate smooth communication within the team (see Non-Patent Document 1).

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the conventional technology is limited to actively conveying gratitude, that is, praise, from team members to members. Therefore, it is difficult to eliminate the influence of tension or the like due to differences in positions within the team, and it is difficult to say that it can improve the motivation of users.

[0005] The present invention has been made in view of the above, and an object thereof is to improve the motivation of users.

Means for Solving the Problems

[0006] To solve the above-mentioned problems and achieve the objective, the analysis device according to the present invention is characterized by comprising: an acquisition unit that acquires text data representing the content of conversations between multiple users; and a generation unit that inputs the text data into a model and generates data that counts words corresponding to an index relating to the degree of contribution to the conversation. [Effects of the Invention]

[0007] According to the present invention, it is possible to improve user motivation. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is a diagram illustrating the overview of the analytical instrument. [Figure 2] Figure 2 is a schematic diagram illustrating the general configuration of the analytical instrument. [Figure 3] Figure 3 is a diagram illustrating the processing of the analytical instrument. [Figure 4] Figure 4 is a diagram illustrating the processing of the analytical instrument. [Figure 5] Figure 5 is a diagram illustrating the processing of the generation unit. [Figure 6] Figure 6 is a diagram illustrating the processing of the generation unit. [Figure 7] Figure 7 is a schematic diagram illustrating the processing of the presentation section. [Figure 8] Figure 8 is a diagram illustrating the processing of the presentation section. [Figure 9] Figure 9 is a flowchart illustrating the analysis process. [Figure 10] Figure 10 illustrates a computer running an analysis program. [Modes for carrying out the invention]

[0009] Hereinafter, one embodiment of the present invention will be described in detail with reference to the drawings. However, the present invention is not limited by this embodiment. Furthermore, in the drawings, the same parts are denoted by the same reference numerals.

[0010] [Overview of the analytical instrument] Figure 1 is a diagram illustrating the overview of the analysis device. The analysis device 10 of this embodiment acquires text data representing the content of conversations between multiple users, inputs the text data into a model, and generates data that counts words corresponding to an index of contribution to the conversation. For example, as illustrated in Figure 1, the analysis device 10 inputs text data representing the content of conversations (discussions) via chat on a web conferencing system into a model, and generates data that counts words corresponding to an index of contribution to the conversation, thereby automatically counting words (contribution words) that correspond to an index of contribution to the conversation from each member's statements (posts) (see Figure 1(1)→(2)). Here, "conversation" includes, for example, work-related discussions, meetings, and consultations. "Statement" includes, for example, chat posts. The index of contribution is, for example, empathy, praise, support, and suggestions from other members in response to a member's statement. In the example shown in Figure 1(2), contribution words are automatically counted for members Taro and Hanako.

[0011] The analysis device 10 then aggregates and visualizes the counted words (see Figure 1(2)→(3)). In the example shown in Figure 1(3), the aggregated results are displayed as a contribution dashboard, showing Hanako and Taro's contribution words with points corresponding to the number of occurrences.

[0012] In this way, the analysis device 10 acquires text data representing the content of conversations between multiple users, inputs the text data into a model, and generates data that counts words corresponding to an indicator of contribution to the conversation, thereby improving user motivation. For example, the analysis device 10 can automatically visualize the contribution of each team member in a friendly atmosphere, regardless of their position or senior / junior status within the team. Therefore, the analysis device 10 can improve user motivation while also improving the psychological safety of the members.

[0013] [Configuration of the Analysis Device] FIG. 2 is a schematic diagram illustrating the general configuration of the analysis device. FIGS. 3 and 4 are diagrams for explaining the processing of the analysis device. First, as illustrated in FIG. 2, the analysis device 10 of the present embodiment is realized by a general-purpose computer such as a personal computer, and includes an input unit 11, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15.

[0014] The input unit 11 is realized using an input device such as a keyboard or a mouse, and inputs various instruction information such as a processing start to the control unit 15 in response to an input operation by an operator. The output unit 12 is realized by a display device such as a liquid crystal display, a printing device such as a printer, or the like.

[0015] The communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between an external device via a network and the control unit 15. For example, the communication control unit 13 controls communication between the control unit 15 and a server of a web conference service that is a processing target of the analysis processing described later, a user terminal, or the like.

[0016] The storage unit 14 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. In the storage unit 14, a processing program for operating the analysis device 10, data used during the execution of the processing program, and the like are stored in advance, or temporarily stored each time processing is performed. Note that the storage unit 14 may be configured to communicate with the control unit 15 via the communication control unit 13. In the present embodiment, a model 14a provided with a prompt, which is used in the analysis processing described later, is stored in the storage unit 14.

[0017] The control unit 15 is implemented using a CPU (Central Processing Unit) or the like, and executes a processing program stored in a memory. As a result, as illustrated in FIG. 2, the control unit 15 functions as an acquisition unit 15a, a generation unit 15b, and a presentation unit 15c. Note that these functional units may be implemented, in part or in whole, by different hardware. For example, the acquisition unit 15a may be implemented in a device different from other functional units. Also, the control unit 15 may include other functional units.

[0018] The acquisition unit 15a acquires text data representing the content of conversations among a plurality of users. Here, as described above, conversations include work discussions, meetings, consultations, chat entries, and the like. Specifically, first, the acquisition unit 15a acquires a token for participating in a Web conferencing service (see FIG. 3(1)). Next, the acquisition unit 15a acquires conditions (data acquisition conditions) for specifying an analysis processing target from the storage unit 14 (see FIG. 3(2)). Then, the acquisition unit 15a acquires text data representing the content of conversations such as chats on the Web conferencing system that match the data acquisition conditions from a server of the Web conferencing service or the like via the communication control unit 13 (see FIG. 3(3)).

[0019] Here, FIG. 4 illustrates the content of conversations among a plurality of users who are processing targets. In the example shown in FIG. 4, for example, text data such as "Thank you for your prompt reply!" from user B is acquired. At that time, in addition to the text data, the acquisition unit 15a may acquire marks such as "like".

[0020] The acquisition unit 15a stores the information acquired in advance in the storage unit 14 as message data (see FIG. 3(4)). Note that the acquisition unit 15a may transfer the acquired information to the generation unit 15b described below in real time without storing it in the storage unit 14.

[0021] Also, the acquisition unit 15a may use, as text data of a processing target, data obtained by converting voice data of a conversation into text data by voice recognition or the like.

[0022] Returning to the explanation of Figure 2, the generation unit 15b inputs text data into the model 14a and generates data that counts the words corresponding to the indicator of contribution to the conversation. Specifically, the generation unit 15b obtains text data (message data) from the storage unit 14 (see Figure 3(5)) and inputs it into the model 14a as shown in Figure 3(7).

[0023] For example, indicators related to contribution include empathy, praise, suggestions, questions, and support from other users in response to a user's statement. The generation unit 15b then counts one or more words related to empathy, praise, suggestions, questions, and support from other users in response to a user's statement as words corresponding to the indicators related to contribution. As mentioned above, a statement includes chat entries, etc.

[0024] Here, Figures 5 and 6 are diagrams illustrating the processing of the generation unit. First, Figure 5 shows an example of an indicator related to contribution.

[0025] Empathy involves nodding in agreement, showing interest, offering encouragement, and being considerate; for example, words like "That's right," "Indeed," and "I see." Praise involves praising and expressing gratitude; for example, words like "Thank you," "That's wonderful," and "Amazing."

[0026] A suggestion is when you express your opinion, make a proposal, or state a conclusion, and includes words such as "I think that..." or "I feel that...". A question is when you ask for guidance or make a statement to deepen the other person's understanding, and includes words such as "Please tell me about..." or "What is...?". Support is when you help or cooperate, and includes words such as "I'll do it," "Shall I support you?", "Let's work together," or "I'll cooperate."

[0027] Furthermore, if the acquisition unit 15a acquires marks such as "like" in addition to text data, the statements (posts) to which the "like" mark is attached may be used as words corresponding to the contribution indicator "empathized with".

[0028] Furthermore, Model 14a is a machine learning model that can be used via APIs (Application Programming Interfaces) from various service providers. Model 14a is a natural language processing model, or Large-Language-Model (LLM), trained using a large amount of text data, and generates sentence data (text) in a natural context. Model 14a is, for example, OpenAI's GPT (Generative Pre-trained Transformer).

[0029] The generation unit 15b prompts model 14a to count the words corresponding to the contribution indicators contained in the text data input to model 14a (see Figures 3(6)-(7)). In this case, when text data is input to model 14a (see Figure 3(7)), it generates data that counts the words corresponding to the contribution indicators (see Figure 1(2)).

[0030] In the example shown in Figure 1(2), words corresponding to indicators of contribution are counted for each member. For example, for Taro, one of the members, "Thank you" is counted as a word of praise for his contribution.

[0031] Here, Figure 6 illustrates the prompts given to Model 14a. The prompts illustrated in Figure 6 include instructions for Model 14a to be a very excellent linguist (Block B1), to count the number of words or phrases that correspond to the contribution indicators if they exist (Block B2), and specific examples of words or phrases that correspond to each contribution indicator (Block B3). In Block B2, Model 14a is instructed to count the number of words or phrases that correspond to each of the contribution indicators: empathy, praise / thanks / gratitude, suggestions / opinions, and questions.

[0032] Model 14a, by operating according to prompts, generates data that counts words corresponding to contribution indicators from the input text data. The generation unit 15b stores the generated data as analysis results in the storage unit 14 (see Figure 3(8)).

[0033] Furthermore, the generation unit 15b collects the amount of token usage corresponding to the amount of text data input to the model 14a and stores it in the storage unit 14 (see Figure 3(9)).

[0034] Returning to the explanation of Figure 2, the presentation unit 15c aggregates the data generated over a predetermined period and presents the aggregated results (see Figure 3(10)). For example, the presentation unit 15c accepts a specification of at least one of the period and the team to which the user belongs, and presents the aggregated results within the scope of that specification.

[0035] Here, Figures 7 and 8 are diagrams illustrating the processing of the presentation unit. Figures 7 and 8 illustrate contribution dashboards that show aggregated results. In the example shown in Figure 7, the presentation unit 15c accepts the specification of the period from December 1st to December 31st, 2023, and all teams, and presents the aggregated results of contribution words for users A to E during this period.

[0036] Furthermore, in the example shown in Figure 7, comments (posts) that receive a "like" mark are counted as contributing words that "resonated." In addition, points corresponding to the number of times each user has contributed words are displayed as contribution points.

[0037] Furthermore, in the example shown in Figure 7, multiple channels consisting of agenda items, small groups of members, etc., can be set up under the team to which the user belongs. In this case, the presentation unit 15c can also accept the specification of teams and channels and present the aggregated results for that range.

[0038] Furthermore, Figure 8 illustrates the display of counted contribution words. In the example shown in Figure 8, for example, posts containing "thank you" that were counted as a contribution word for "praise" by user B are displayed. The display unit 15c may also display such counted contribution words below or on the next page of the contribution dashboard exemplified in Figure 7.

[0039] In this way, it becomes possible to quantitatively visualize whose posts contributed to the team in conversations among team members. Furthermore, it becomes possible to see at a glance which posts contributed. Therefore, regardless of differences in position within the team, it becomes possible to improve psychological safety and increase user motivation in a harmonious atmosphere.

[0040] [Analysis Processing Procedure] Next, with reference to Figure 9, an example of the analysis process performed by the analysis apparatus 10 according to this embodiment will be described. Figure 9 is a flowchart illustrating the analysis process procedure. The flowchart in Figure 9 starts, for example, when an input instructing the start of the analysis process is received.

[0041] First, the acquisition unit 15a acquires text data representing the content of a conversation between multiple users (step S1). For example, the acquisition unit 15a acquires text data representing the content of a conversation via chat on a web conferencing system.

[0042] Next, the generation unit 15b inputs the acquired text data into the model 14a and generates data that counts the words corresponding to the indicators of contribution to the conversation (step S2). For example, the indicators of contribution include empathy, praise, suggestions, questions, and support from other users to the user's statements. The generation unit 15b then counts one or more of the words related to empathy, praise, suggestions, questions, and support from other users to the user's statements as words corresponding to the indicators of contribution. The generation unit 15b also prompts the model 14a to count the words corresponding to the indicators of contribution contained in the text data input to the model 14a.

[0043] Then, the presentation unit 15c aggregates the data generated during a predetermined period and presents the aggregated results (step S3). For example, the presentation unit 15c accepts a specification of at least one of the period and the team to which the user belongs, and presents the aggregated results as a contribution dashboard within the scope of the specification. This completes the series of analysis processes.

[0044] [effect] As described above, in the analysis device 10 of the above embodiment, the acquisition unit 15a acquires text data representing the content of conversations between multiple users. The generation unit 15b inputs the text data into the model 14a and generates data that counts words corresponding to an indicator of contribution to the conversation.

[0045] Specifically, the generation unit 15b counts one or more words from among those related to empathy, praise, suggestions, questions, and support from other users in response to a user's statement, as words corresponding to the contribution indicator. The generation unit 15b also prompts model 14a to count words corresponding to the contribution indicator contained in the text data input to model 14a.

[0046] This allows for the automatic visualization of each team member's contribution, regardless of their position or role within the team, while maintaining a harmonious atmosphere. Therefore, it is possible to improve the psychological safety of team members while also increasing user motivation.

[0047] Furthermore, the display unit 15c aggregates the data generated over a predetermined period and presents the aggregated results. This makes the increase in the overall team contribution visible to all members, thus enabling further improvement in user motivation.

[0048] Furthermore, the presentation unit 15c accepts the user's designation of at least one of the specified period and team, and presents the aggregated results within the scope of that designation. This allows for a more concrete understanding of each member's contribution, thereby further improving the user's motivation.

[0049] [System configuration, etc.] Each component of the illustrated device is a functional concept and does not necessarily have to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions. Furthermore, each processing function performed by each device can be implemented, all or any part of it, by a CPU or GPU and programs that are analyzed and executed by that CPU or GPU, or by hardware using wired logic.

[0050] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified.

[0051] [program] It is also possible to create a program that describes the processing performed by the analytical apparatus described in the above embodiment in a computer-executable language. For example, it is possible to create a program that describes the processing performed by the analytical apparatus 10 according to the embodiment in a computer-executable language. In this case, the same effects as in the above embodiment can be obtained by having the computer execute the program. Furthermore, the same processing as in the above embodiment may be achieved by recording such a program on a computer-readable recording medium and having the computer read and execute the program recorded on this recording medium.

[0052] Figure 10 shows an example of a computer running an analysis program. Computer 1000 includes, for example, memory 1010, CPU 1020, hard disk drive interface 1030, disk drive interface 1040, serial port interface 1050, video adapter 1060, and network interface 1070. These components are connected by bus 1080.

[0053] Memory 1010 includes ROM (Read Only Memory) 1011 and RAM 1012. ROM 1011 stores, for example, a boot program such as BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1031. The disk drive interface 1040 is connected to the disk drive 1041. A removable storage medium, such as a magnetic disk or optical disk, is inserted into the disk drive 1041. A serial port interface 1050 is connected to, for example, a mouse 1051 and a keyboard 1052. A video adapter 1060 is connected to, for example, a display 1061.

[0054] Here, the hard disk drive 1031 stores, for example, the OS 1091, the application program 1092, the program module 1093, and the program data 1094. The information described in the above embodiment is stored, for example, in the hard disk drive 1031 or the memory 1010.

[0055] Furthermore, the analysis program is stored in the hard disk drive 1031 as a program module 1093 containing instructions to be executed by the computer 1000, for example. Specifically, the program module 1093 containing instructions for each process executed by the analysis device 10 described in the above embodiment is stored in the hard disk drive 1031.

[0056] Furthermore, the data used for information processing by the analysis program is stored as program data 1094, for example, in the hard disk drive 1031. The CPU 1020 then reads the program module 1093 and program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as needed and executes the procedures described above.

[0057] Furthermore, the program module 1093 and program data 1094 related to the analysis program are not limited to being stored on the hard disk drive 1031; for example, they may be stored on a removable storage medium and read by the CPU 1020 via a disk drive 1041 or the like. Alternatively, the program module 1093 and program data 1094 related to the analysis program may be stored on another computer connected via a network such as a LAN (Local Area Network) or WAN (Wide Area Network) and read by the CPU 1020 via a network interface 1070.

[0058] Although embodiments applying the invention made by the present inventors have been described above, the present invention is not limited by the descriptions and drawings that constitute part of the disclosure of the present invention in this embodiment. That is, all other embodiments, examples, and operational techniques made by those skilled in the art based on this embodiment are included in the scope of the present invention. [Explanation of symbols]

[0059] 10 Analyzer 11 Input section 12 Output section 13 Communication Control Unit 14 Storage section 14a Model 15 Control Unit 15a Acquisition part 15b Generator 15c Presentation section

Claims

1. An acquisition unit that acquires text data representing the content of conversations between multiple users, A generation unit inputs the aforementioned text data into a model and generates data that counts words corresponding to an indicator of contribution to the conversation, An analytical apparatus characterized by having the following features.

2. The analysis apparatus according to claim 1, characterized in that the generation unit counts one or more words from among words relating to empathy, praise, suggestions, questions, and support from other users to a user's statement as words corresponding to the indicator of contribution.

3. The analysis apparatus according to claim 1, characterized in that the generation unit gives the model a prompt that instructs the model to count the words corresponding to the contribution index contained in the text data input to the model.

4. The analytical apparatus according to claim 1, further comprising a display unit that aggregates the data generated over a predetermined period and presents the aggregated results.

5. The analysis apparatus according to claim 4, characterized in that the display unit accepts a designation of at least one of the period and the team to which the user belongs, and presents the aggregated results within the scope of said designation.

6. An analytical method performed by an analytical device, The process involves obtaining text data representing the content of conversations between multiple users, A generation process involves inputting the aforementioned text data into a model and generating data that counts the words corresponding to an indicator of contribution to the conversation, An analytical method characterized by including [a certain component].

7. A retrieval step to obtain text data representing the content of conversations between multiple users, A generation step involves inputting the aforementioned text data into a model and generating data that counts words corresponding to an indicator of contribution to the conversation, An analysis program characterized by having a computer execute it.

Images