Program, information processing method, and information processing system

Abstract

To provide a program, an information processing method, and an information processing system that improve usability in a minute book creation tool.SOLUTION: There is provided a function implemented by a processor 23 of a server in an information processing system comprising the server, a plurality of user terminals, and a sound collection device connected via a network. In a specification step executed by a specification unit 235, an output destination to which character generation information is output is specified on a screen for creating a minute book of a meeting. The character generation information is the information of the characters generated on the basis of transcription information or input information, the transcription information is the information of the characters that transcribe the content of the utterance, and the input information is the information received from the user. In an output control step executed by an output control unit, the character generation information is output to the output destination.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present invention relates to a program, an information processing method, and an information processing system.

Background Art

[0002] Conventionally, a system that performs speech recognition from the speech of a person uttered during a meeting has been known. Also, a system that supports the creation of meeting minutes by speech recognition has been known.

[0003] Patent Document 1 discloses a prior art that recognizes speech and supports the creation of meeting minutes.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the present invention, a technique capable of further improving convenience is provided in a meeting minutes creation tool.

Means for Solving the Problems

[0006] According to one aspect of the present invention, a program is provided that causes a computer to execute the following steps. In a specific step in this program, an output destination for outputting character generation information is specified on a screen for creating meeting minutes. The character generation information is information on characters generated based on speech-to-text information or input information. The speech-to-text information is information on characters obtained by speech-to-text conversion of the content of speech. The input information is information received from a user. In an output control step, the character generation information is output to the output destination.

[0007] According to the present disclosure, in a minutes creation tool, convenience can be further improved.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Modes for Carrying Out the Invention

[0009] [Embodiment] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various features shown in the embodiments described below can be combined with each other.

[0010] Incidentally, the program for realizing the software appearing in this embodiment may be provided as a non-transitory computer-readable medium readable by a computer, may be provided so as to be downloadable from an external server, or may be provided so that the program is started on an external computer to realize its function on a client device (so-called cloud computing).

[0011] In addition, in this embodiment, the "unit" may include, for example, hardware resources implemented by a circuit in a broad sense and information processing of software that can be specifically realized by these hardware resources. Also, in this embodiment, various types of information are handled, and these information are represented, for example, by physical values of signal values representing voltage and current, the high and low of signal values as a set of binary bits composed of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0012] In addition, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit, circuitry, a processor, a memory, etc. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (for example, a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0013] 1. Information Processing System 1 FIG. 1 is an example of a configuration diagram showing an information processing system 1. The information processing system 1 includes a server 2, user terminals 3 (for example, user terminals 3-1, 3-2, ···, 3-n), and sound collection devices 4 (for example, sound collection devices 4-1, 4-2, ···, 4-n), and these are connected through a network. These components will be further described. Here, the system exemplified in the information processing system 1 is composed of one or more devices or components.

[0014] 2.1. Server 2 FIG. 2 is an example of a block diagram showing the hardware configuration of the server 2. The server 2 has a communication unit 21, a storage unit 22, and a processor 23, and these components are electrically connected inside the server 2 via a communication bus. Each component will be further described.

[0015] The communication unit 21 preferably uses wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), and wired LAN network communication, but may include wireless LAN network communication, mobile communication such as LTE / 3G, Bluetooth (registered trademark) communication, etc. as required. That is, it is more preferably implemented as a collection of these multiple communication means. That is, the server 2 communicates various information with the user terminal 3 via the network through the communication unit 21. In particular, the server 2 is configured to receive voice data acquired by the sound collection device 4 from the user terminal 3. These details will be described later.

[0016] The storage unit 22 stores various types of information defined as described above. This can be implemented, for example, as a storage device such as a Solid State Drive (SSD) that stores various programs related to the server 2 executed by the processor 23, or as a memory such as a Random Access Memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to the operation of the program. Also, a combination of these may be used. In particular, the storage unit 22 stores voice data. In addition to this, the storage unit 22 stores various programs related to the server 2 executed by the processor 23.

[0017] The processor 23 performs processing and control of the overall operation related to the server 2. The processor 23 is, for example, a Central Processing Unit (CPU) not shown in the figure. The processor 23 realizes various functions related to the server 2 by reading a predetermined program stored in the storage unit 22. That is, the information processing by software stored in the storage unit 22 is specifically realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23. These will be described in more detail in the next section. Note that the processor 23 is not limited to being single, and may be implemented to have a plurality of processors 23 for each function. Also, a combination of them may be used.

[0018] 2.2. User Terminal 3 FIG. 3 is an example of a block diagram showing the hardware configuration of the user terminal 3. The user terminal 3 includes a communication unit 31, a storage unit 32, a processor 33, a display unit 34, and an input unit 35, and these components are electrically connected via a communication bus inside the user terminal 3. Explanation of the communication unit 31, the storage unit 32, and the processor 33 is omitted because it is substantially the same as that of the communication unit 21, the storage unit 22, and the processor 23 in the server 2.

[0019] The display unit 34 may be included in the housing of the user terminal 3 or may be externally attached. The display unit 34 displays a screen of a graphical user interface (GUI) that can be operated by the user. For example, this is preferably implemented by selectively using display devices such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display according to the type of the user terminal 3. Here, the display unit 34 will be described as being included in the housing of the user terminal 3.

[0020] The input unit 35 may be included in the housing of the user terminal 3 or may be externally attached. For example, the input unit 35 may be integrated with the display unit 34 and implemented as a touch panel. With a touch panel, the user can input tap operations, swipe operations, etc. Of course, instead of the touch panel, a switch button, a mouse, a QWERTY keyboard, etc. may be adopted. That is, the input unit 35 receives the operation input made by the user. The input is transferred to the processor 33 via the communication bus as a command signal, and the processor 33 can execute predetermined control or calculation as necessary.

[0021] 2.3. Sound collection device 4 The sound collection device 4 is a so-called microphone configured to be able to convert external sound into a signal. The sound collection device 4 may be provided by directly connecting the sound collection device 4 and the server 2. For example, it is provided in or connected to the user terminal 3.

[0022] The sound collection device 4 is configured to generate voice data by collecting the user's speech. Note that the voice data may be temporarily stored in the memory in the user terminal 3 and does not have to be stored non-volatilely in the storage unit 32. The voice data generated by the sound collection device 4 is configured to be transferable to the server 2 via the network.

[0023] The sound collection device 4 is not particularly limited, but it collects at least voices in the audible range of humans, voices with frequencies between 20 Hz and 20,000 Hz, and converts them into electrical signals. The voice can be monaural or stereo recording. When digitally processing voice data, the sampling rate is, for example, 48000 Hz, 44100 Hz, 32000 Hz, 22050 Hz, 16000 Hz, 11025 Hz, 11000 Hz, 8000 Hz, etc. It may be within any range of the numerical values exemplified here. By increasing the sampling rate, the discretization of the temporal timing of the voice can be performed precisely, and the accuracy of voice recognition can be improved.

[0024] Also, the data collected by the sound collection device 4 may be appropriately compressed by the processor 33 of the user terminal 3. At this time, the compression format may be any of MP3, AAC, WMA, Vorbis, AC3, MP2, FLAC, TAK, etc. Compression can reduce communication traffic due to data transfer from the user terminal 3 to the server 2.

[0025] 3. Functional Configuration In this section, the functional configuration of the embodiment will be described. As described above, the information processing by the software stored in the storage unit 22 is specifically realized by the processor 23, which is an example of hardware, and thus can be executed as each functional unit included in the processor 23 as shown in FIG. 4. FIG. 4 is an example of a block diagram showing the functions realized by the processor 23 of the server 2. As shown in FIG. 4, the processor 23 includes, as functional units, an information transmission / reception unit 230, a display control unit 231, a storage control unit 232, a recording unit 233, a voice recognition unit 234, a specifying unit 235, a generation control unit 236, and an output control unit 237. Each functional unit executes steps with their respective names. For example, the specifying unit 235 executes the specifying step.

[0026] The information transmission / reception unit 230 receives, acquires, or accepts information via the network and the communication unit 21. Also, the information transmission / reception unit 230 transmits information via the communication unit 21 and the network.

[0027] The display control unit 231 controls the screen data to be displayed on the display unit 34 of the user terminal 3. Note that the screen data may be the visual information itself generated in a form visible to the user, such as a screen, an image, an icon, text, etc., or may be rendering information for causing various terminals to display visual information such as a screen, an image, an icon, text, etc.

[0028] The storage control unit 232 stores the template of the minutes of the meeting in the storage unit 22.

[0029] The recording unit 233 stores the voice data acquired via the sound collection device 4 in the storage unit 22.

[0030] The voice recognition unit 234 recognizes the voice data and generates the character conversion information 830 from the voice data.

[0031] The specifying unit 235 specifies the output destination of the data.

[0032] The generation control unit 236 generates character generation information based on the character conversion information or the input information.

[0033] The output control unit 237 outputs the character generation information generated by the generation control unit 236 to the output destination specified by the specifying unit 235.

[0034] The playback unit 238 plays back the voice data recorded by the recording unit 233.

[0035] 4. Information Processing Method In this section, an overview of the information processing method of the aforementioned information processing system 1 will be described.

[0036] 4.1. Overview of the Information Processing Method Using FIG. 5, an example will be described in which, in a meeting attended by a secretary user and participating users, the secretary user creates minutes using a minutes creation tool by the information processing system 1 of the present embodiment. FIG. 5 is an example of an activity diagram showing an outline of information processing executed by the information processing system 1. In the present embodiment, an example will be described in which a tool for API cooperation is specified, a template for cooperating with the tool and the API is created, and minutes are created based on the template.

[0037] Note that the secretary user is the creator of the minutes and uses the user terminal 3-1 and the sound collecting device 4-1. The participating users are the participants in the meeting and use the user terminals 3-2 and the sound collecting devices 4-2. There may be a plurality of participating users. The minutes creation tool of the present embodiment is a tool for creating minutes. More specifically, the minutes creation tool is, for example, a tool in which an information input area 71 and a speech-to-text area 73 can be used, a tool capable of recording the elapsed time of the meeting when text is input, or a tool capable of reflecting the result of speech-to-text in the minutes.

[0038] (Activity A1) First, the information transmission / reception unit 230 receives an instruction to display the management screen 5 (described later with reference to FIG. 6) from the user terminal 3-1 of the secretary user. The display control unit 231 displays the management screen 5 for linking the minutes creation tool with other tools on the display unit 34 of the user terminal 3-1. The information transmission / reception unit 230 receives an instruction to specify another tool to be linked with the minutes creation tool from the user terminal 3-1 of the secretary user via the management screen 5. The cooperation is performed, for example, by API (Application Programming Interface) cooperation, CSV cooperation, or the like. In the present embodiment, by API cooperation, a process is performed in which a part of the data output by the minutes creation tool is reflected as data in a part of the items on the CRM (Customer Relationship Management) tool. The details of Activity A1 will be described in detail with reference to FIG. 6.

[0039] A CRM tool is a tool that supports customer relationship management. CRM tools are used for centralized management of customer information, customer information analysis, promotion management, etc. The CRM tool may be, for example, Salesforce Sales Cloud, Mazrica Sales, Zoho CRM, GENIEE SFA / CRM, Kintone, etc. The tool serving as the output destination may include any tool. In addition to CRM tools, the tool serving as the output destination may include a document creation tool, a presentation tool for supporting presentations, a spreadsheet tool for creating spreadsheets, a project management tool for managing projects, a communication tool for supporting communication among multiple users, a design tool for supporting the creation of designs, a code repository & version management tool for supporting source code management, a database management tool for managing databases, a CMS (Content Management System) tool for supporting the creation of websites, an email marketing tool for supporting email delivery, a calendar tool, a recruitment management system, a storage service, a workflow tool, etc. A document creation tool is a tool that can centrally manage the creation, management, storage, sharing, utilization, and disposal of documents. Also, a document creation tool is used, for example, to improve the efficiency and convenience of document handling. The document creation tool may be Notion, NotePM, Google Docs, Evernote, Zoho Learn, Cacoo, astah, Enterprise Architect, Gridraw, draw.io, etc. The communication tool may include groupware, etc. A calendar tool is a tool for registering schedules, tasks, goals, etc., visually organizing and displaying them, and sharing them with other employees. The calendar tool may be Google Calendar, Outlook, etc. The adoption management system may be ATS (), etc. The storage service is a service that can store data in the disk space for file storage on the Internet. The storage service may be Google Drive, OneDrive, etc. The workflow tool is a tool for streamlining in-house business procedures. The workflow tool may include Job Kan, SmartHR, etc.

[0040] (Activity A2) Subsequently, the information transmission / reception unit 230 receives an instruction to display the template creation screen 6 (described later with reference to FIG. 7) from the user terminal 3-1 of the clerk user. The template creation screen 6 is a screen including an object capable of creating a template in which a template area for linking with the CRM tool is embedded, as will be described later. The display control unit 231 displays the template creation screen 6 on the display unit 34 of the user terminal 3-1. The processor 23 creates a template in response to receiving the template area from the user terminal 3-1 of the clerk user as the minutes template. The storage control unit 232 records the minutes template used when communicating with the other tool. The details of Activity A2 will be described in detail with reference to FIG. 7.

[0041] (Activity A3) Subsequently, the information transmission / reception unit 230 receives an instruction to create minutes using the template from the user terminal 3-1 of the clerk user. The display control unit 231 displays the minutes screen 7 for creating the minutes of the meeting, including the information input area 71 and the transcription area 73, on the display unit 34 of the user terminal 3-1 of the clerk user based on the minutes template. The details of Activity A3 will be described in detail with reference to FIG. 8.

[0042] (Activity A4) Subsequently, in response to receiving an instruction to start a meeting from the user terminal 3-1 of the secretary user, the processor 23 of the server 2 starts processing during the meeting. That is, as processing during the meeting, the processor 23 starts counting the elapsed time of the meeting and starts recording by the minutes creation tool. The processor 23 executes information processing of A6 in parallel with A5.

[0043] (Activity A5) The information transmission / reception unit 230 receives the voice data acquired by the sound collection device 4 of each user (secretary user and participating user) from the user terminal 3. Subsequently, the information transmission / reception unit 230 transmits the voice data received from a certain user to the user terminal 3 owned by a user other than that user. For example, the information transmission / reception unit 230 transmits the voice data received from the user terminal 3-2 owned by the participating user to the user terminal 3-1 of the secretary user. Thereafter, the processor 33 of the participating user outputs the voice data. Subsequently, the recording unit 233 causes the storage unit 22 to record the voice data received from the user terminal 3 used by each user. Until the meeting ends, the processor 23 repeatedly executes the above information processing of A5.

[0044] (Activity A6) The processor 33 of the user terminal 3-1 of the secretary user receives input of information such as characters into the information input area 71 via an operation on the input unit 35 by the secretary user. The information transmission / reception unit 230 receives character data from the user terminal 3-1 used by the secretary user. Subsequently, the display control unit 231 appropriately executes processing related to this character input in the information input area 71 and the time stamp area 72 described later. Until the meeting ends, the processor 23 repeatedly executes the above information processing of A6.

[0045] (Activity A7) Subsequently, during the execution of A5 to A6, the processor 23 of the server 2 receives an instruction to end the meeting, such as pressing a meeting end button on the user terminal 3 of the secretary user. The processor 23 ends the counting of the elapsed time of the meeting and also ends the recording by the minutes creation tool.

[0046] (Activity A8) The processor 33 of the user terminal 3 receives a predetermined operation via the operation of the input unit 35 by the user. When the processor 33 receives the predetermined operation, it transmits information specifying the predetermined operation to the server 2 via the communication unit 31 and the network. The processor 23 of the server 2 receives the information specifying the predetermined operation from the user terminal 3 via the network and the communication unit 21.

[0047] (Activity A9) If the predetermined operation received in A8 is an operation including a request for speech-to-text, the processor 23 of the server 2 proceeds with the information processing to Activity A10. Also, if the predetermined operation received in A8 is an operation including an instruction to complete the minutes, the processor 23 proceeds with the information processing to Activity A14.

[0048] (Activity A10) Subsequently, when a predetermined operation including a request for speech-to-text is received as the predetermined operation in Activity A8, the speech recognition unit 234 performs speech-to-text based on the recorded voice data. When the speech-to-text is completed, the display control unit 231 displays the speech-to-text information 830 shown in FIG. 9 in the speech-to-text area 83.

[0049] (Activity A11) Subsequently, the specifying unit 235 specifies an output destination for outputting character generation information on the screen for creating the minutes of the meeting. The specifying unit 235 may specify the template areas 710 and 711 as the output destination, or may specify any location within the information input area 71 designated by the user as the output destination. Further, the output destination by the specifying unit 235 is not limited to only the screen for creating the minutes of the meeting, and a location designated by the user via another tool linked to the minutes creation tool may be specified as the output destination, or a location determined by the program of another tool linked to the minutes creation tool may be specified as the output destination.

[0050] (Activity A12) Subsequently, the generation control unit 236 generates information of characters consisting of one or more sentences as character generation information by applying an algorithm of any natural language processing (NLP) such as BERT or ChatGPT. Natural language processing includes information processing such as, for example, morphological analysis, syntactic analysis, semantic analysis, and context analysis.

[0051] (Activity A13) Subsequently, the output control unit 237 outputs the character generation information generated by the generation control unit 236 to the output destination specified by the specifying unit 235. The timing of output may be the timing when the character generation information is generated, or the timing specified by the user. Details of Activities A9 to A13 will be described in detail with reference to FIGS. 9 and 10.

[0052] (Activity A14) If, in Activity A8, the operation included an instruction to complete the minutes of the meeting as a predetermined operation, the storage control unit 232 stores the created minutes of the meeting in the storage unit 22.

[0053] Thereafter, the information processing system 1 terminates the information processing.

[0054] 4.2. Details of the information processing method Next, with reference to FIGS. 6 to 10, the parts that were not described in detail in the previous section will be explained. Specifically, the management screen 5 displayed at A1 using FIG. 6, the template creation screen 6 displayed at A2 using FIG. 7, the minutes screen 7 displayed at A3 using FIG. 8, the minutes screen 8 displayed at A9 to A13 using FIG. 9, and the CRM screen 9 displayed at A13 using FIG. 10 will be explained in detail respectively.

[0055] FIG. 6 is a diagram showing an example of the management screen 5. On the management screen 5 of FIG. 6, a list of tools that can be linked is displayed when creating a template for minutes. The management screen 5 is a screen for managing the settings of the minutes creation tool. The management screen 5 at least includes a linked tool area 50. The management screen 5 may further include buttons for transitioning to a screen that can manage workspaces, users, groups, and spaces.

[0056] The linked tool area 50 is an area where information about other tools that can be linked with the minutes creation tool is displayed. In the linked tool area 50, names, icons, etc. that can identify the various tools described above are displayed. The linked tool area 50 includes a linked tool area 500 and an unlinked tool area 501.

[0057] The linked tool area 500 is an area where information about tools that have been linked with the minutes creation tool is displayed. The linked tool area 500 includes the name of the linked tool (for example, "Service A"), information indicating that it has been linked (for example, "linked"), and a template creation button 500a. In response to the pressing of the template creation button 500a by the clerk user, the display control unit 231 displays the template creation screen 6 shown in FIG. 7.

[0058] The unlinked tool area 501 is an area where information about tools that are not linked with the minutes creation tool is displayed. The unlinked tool area 501 includes the name of the linked tool (e.g., "Service B"), information indicating that the tool is not linked (e.g., "unlinked"), and a link button 501a. In response to the secretary user pressing the link button 501a, the display control unit 231 displays the login of the tool associated with the link button. In response to successful login to the tool, the processor 23 starts linking with the tool. Thereafter, the display control unit 231 changes the display of the tool that has started linking from the unlinked tool area 501 to the linked tool area 500.

[0059] FIG. 7 is a diagram showing an example of the template creation screen 6. The template creation screen 6 is a screen for creating minutes template information. The minutes template information is saved in advance as information including the title information of the minutes and information to be input in advance to the minutes, and is used as a template when creating new minutes. The template creation screen 6 in FIG. 7 is a screen for saving information setting API collaboration between Service A as a CRM tool and a minutes creation tool as minutes template information. The template creation screen 6 includes an collaboration option area 60, a title area 61, a collaboration area 62, and a save button 63.

[0060] The linkage option area 60 is an area where options that can be embedded as information to be input in advance into the minutes of the minutes template information are displayed. The linkage option area 60 in Fig. 7 is configured so that items such as purpose, background of inquiry, expected number of users, minutes format, next step, and memo can be set as template areas. The linkage option area 60 may display different options for each linked tool.

[0061] The title area 61 is an area where information on the title of the minutes can be set, and is configured so that, for example, "202YMMDD_[client]_new business negotiation" can be set.

[0062] The linking area 62 is configured to be able to embed various information as templates. For example, the linking area 62 is configured to be able to embed information such as characters, graphs, tables, images, videos, etc. Also, the linking area 62 is configured to be able to drag and drop items from the linking option area 60. The display control unit 231 embeds the item that has received the drag and drop into the template. The specifying unit 235 specifies the location where the drag and drop has occurred as the output destination of the character generation information for the template area of the background or next step of the inquiry. That is, when the specifying unit 235 receives the designation of the output destination of the character generation information on the minutes from the clerk user, it specifies the received output destination. The specification by the specifying unit 235 is not limited to execution on the template creation screen 6, and is also executed when the template area is embedded on the minutes screen 7. According to such a configuration, the destination where the character generation information is output can be specified.

[0063] The save button 63 is a button for saving the minutes template information. The storage control unit 232 stores in the storage unit 22 as the minutes template information set via the title area 61 and the linking area 62 in response to the pressing of the save button 63. That is, the storage control unit 232 stores in the storage unit 22 the output destination of the meeting content information on the minutes received by the specifying unit 235. According to such a configuration, since the output destination of the character generation information on the minutes can be saved and used for creating subsequent minutes, the designation of the output destination etc. can be omitted when creating subsequent minutes.

[0064] Next, while showing Fig. 8, the minutes screen 7 before the meeting will be described using the minutes template information set in Fig. 7. Fig. 8 is a diagram showing an example of the minutes screen 7 before the meeting. The minutes screen 7 is a screen for creating the minutes before the meeting. The minutes screen 7 includes a meeting information area 70, an information input area 71, a timestamp area 72, and a speech-to-text area 73.

[0065] The meeting information area 70 is an area where the outline of the proceedings is displayed. In the example of FIG. 8, "

[0066] The information input area 71 is configured to be able to display the results of character input performed by the clerk user. The input information is treated as input information. The input information is information input via the minutes creation tool. The input information includes, in addition to character input information consisting of characters, information including image data, audio data, video data, and other attached files. The text information in the attached file may be treated as character input information. The character input information may be any information that includes characters, such as bullet-point information, or information consisting only of numbers, symbols, words, etc. In the information input area 71 of FIG. 8, the template area input in the cooperation area 62 of FIG. 7 is input. That is, the information input area 71 is configured to be able to embed the template areas 710 and 711. The template areas 710 and 711 are areas where data is input in a predetermined manner. In the example of FIG. 8, the template area 710 is an area where information on the background of the inquiry is input as character generation information, and the template area 711 is an area where information on the next step is input as character generation information.

[0067] The timestamp area 72 is configured to be able to display time data regarding the elapsed time of the meeting when information is input to the information input area 71. That is, in response to receiving an input of information such as characters to the information input area 71, the processor 23 records the time information of the time when the characters are input to the information input area 71 in the timestamp area 72. For example, assume that the processor 23 receives an input of characters to the information input area 71 when 2 minutes and 3 seconds have elapsed since the start of the meeting. In this case, the processor 23 records time data such as "02:03" at a position beside the position where the characters are input and within the timestamp area 72. Thereby, the time when the characters are input to the minutes of the meeting can be recorded.

[0068] The speech-to-text area 73 is configured to be able to display the speech-to-text information 830 after speech-to-text. In the state before speech-to-text (that is, the state before or during the meeting), since the speech-to-text information 830 is not generated, the speech-to-text information 830 is not displayed in the speech-to-text area 73.

[0069] Next, the minutes screen 8 after the meeting will be described with reference to FIG. 9. FIG. 9 is a diagram showing an example of the minutes screen 8 after the meeting. The minutes screen 8 is a screen for creating the minutes after the meeting. The minutes screen 8 includes a meeting information area 80, an information input area 81, a timestamp area 82, a speech-to-text area 83, and a playback area 85. For the meeting information area 80 after the meeting, refer to the meeting information area 70 before the meeting.

[0070] The information input area 81 after the meeting is configured to be able to display the result of the input of characters performed by the secretary user, similar to the information input area 71 before the meeting. In addition, the information input area 81 after the meeting is configured to be able to receive drag-and-drop as described later. Further, the information input area 81 after the meeting includes linked template areas 810 and 811 to which character generation information is output.

[0071] The character generation information is information of characters generated based on voice data, speech recognition information 830, or input information in the information input area 71. The character generation information includes meeting content information of characters indicating the content of the meeting. The meeting content information is information generated by applying a natural language processing algorithm to the information in the speech recognition information 830 or the information input area 71. The meeting content information includes information on the summary of the meeting, ToDo information after the meeting, information on the decisions made at the meeting, information on the list of key points of the meeting, information on the speeches of the speakers participating in the meeting, information on the names of the persons involved in the meeting, or information on the Q&A of the meeting. For example, a summary is a text written by briefly summarizing what was discussed throughout the meeting. The summary may be restricted to a predetermined number of characters or may not be restricted by the number of characters. ToDo items are items determined during the meeting as the next actions, such as the creation of materials. Decisions are items on which agreement was reached during the meeting, such as the date and time of the next meeting. Key points are a summary of one or more texts in bullet points of the important points in the meeting. The key points may be restricted to a predetermined number of characters or may not be restricted by the number of characters. The information on the speeches of the speakers participating in the meeting may be information summarized for each speaker, information separated for each speech, information in which the information of each speech is associated with time, or information in which the information of each speech is associated with the speaker. The persons involved are information on the names or surnames of the people who appear during the meeting. The persons involved in the meeting may be specified together with their positions, titles, company names, department names, etc. Q&A is information on the combination of questions and answers during the meeting. The information on the Q&A of the meeting may be information in which multiple answers are associated with one question, or information in which multiple questions are associated with one answer. According to such a configuration, information on various aspects of the meeting, such as ToDo after the meeting, decisions made at the meeting, names of the persons involved in the meeting, summary of the meeting, list of key points of the meeting, speeches of the speakers participating in the meeting, or Q&A of the meeting, can be output as character generation information.

[0072] The generated meeting content information varies according to the output destination. For example, when the background of the inquiry and the next step are set as the cooperation template areas 810 and 811, the generation control unit 236 generates a list of the main points of the meeting corresponding to the background of the inquiry and the next step. Also, the output control unit 237 outputs a list of the main points of the meeting corresponding to the background of the inquiry and the next step to the cooperation template areas 810 and 811, respectively. Regarding other examples of the meeting content information that varies according to the output destination, the generation control unit 236 generates the meeting content information in a format corresponding to the tool that is the output destination identified by the identification unit 235. For example, when the column in which the number of people information is emphasized is the output destination, the generation control unit 236 generates the meeting content information in the format of the number of people (3 people). Also, when the columns in which information such as probability (10% etc.), amount (10,000 yen, 100 dollars etc.), date (September 15, 2023 etc.) are emphasized are the output destinations, the generation control unit 236 generates the meeting content information in the corresponding formats. According to such a configuration, it is possible to appropriately generate the character generation information according to the output destination.

[0073] Also, the generation control unit 236 may generate each meeting content information after the speech recognition unit 234 has completed the speech-to-text conversion. Then, the identification unit 235 may identify the output destination based on the information indicated by the meeting content information. For example, the identification unit 235 identifies one or more other tools linked to the minutes creation tool, and further identifies the location where the meeting content information of the minutes creation tool is linked as the output destination on the identified other tool. For example, the identification unit 235 identifies that the information on the main points of the meeting is set as the output destination in a specific item on the CRM tool linked to the minutes creation tool. The output control unit 237 outputs the meeting content information to the output destination of the meeting content information on the other tool identified by the identification unit 235. According to such a configuration, it is possible to output the character generation information to an appropriate output destination based on the content of the character generation information.

[0074] In addition to the functions described above, when the meeting content information is output to the information input area 81, the timestamp area 82 is configured to be able to display time data related to the elapsed time of the meeting at the start of the related speech-to-text information 830. Further, when the meeting content information is output to the information input area 81, the timestamp area 82 is configured to be able to display time data related to the elapsed time of the meeting when the related information input area 81 was input. When information is input to the information input area 81 in a list form, the processor 23 assigns a timestamp (such as "00:30", "02:45", etc. in the example of FIG. 9) for each item listed. In response to the selection of the timestamp, the playback unit 238 moves the position of the seek bar to the elapsed time of the meeting associated with the timestamp. Also, the time may be displayed on the seek bar within the playback area 85. For example, when at the point in time when 30 seconds have elapsed since the start of the meeting, there is a statement such as "I searched because I was curious after asking a friend", the processor 23 may display the text "New customer acquisition" associated with the position corresponding to 30 seconds on the seek bar in the playback area 85.

[0075] The speech-to-text information 830 is information of text that has been speech-to-text (the content of the speech) based on the audio data of the meeting. The speech-to-text information 830 includes speaker information 831, text information 832, and time information. The speaker information 831 is information that can identify the user who made the speech from which the speech-to-text is derived. The text information 832 is information of the text that has been speech-to-text. The time information is information of the time when the audio of the script associated with the script information was uttered during the meeting. The time information is displayed in the timestamp area 82 when it is transferred from the speech-to-text area 83 to the information input area 81. The transfer button is a button that, when pressed, transfers the speech-to-text information 830 associated with the transfer button to the information input area 81. The selection checkbox is a checkbox that can select the speech-to-text information 830 associated with the selection checkbox when a selection is received.

[0076] The playback area 85 is configured to be able to play the audio during the meeting.

[0077] FIG. 10 is a diagram showing an example of the CRM screen 9. The CRM screen 9 is a screen of a CRM tool that is linked to the minutes creation tool via an API. That is, the CRM screen 9 may include some information of the minutes screen 8. In the example of FIG. 10, the information included in the linkage template areas 810 and 811 is displayed as linkage information 90 and 91 on the CRM screen 9. The linkage information 90 includes character generation information indicating the background of the inquiry in the linkage template area 810, and the linkage information 91 includes character generation information indicating the next step in the linkage template area 810. A part of the minutes screens 7 and 8 displayed on the minutes creation tool may be directly displayed on the CRM screen 9. That is, the specific part 235 identifies the CRM screen 9 on the CRM tool that displays the data acquired from the minutes creation tool. The output control unit 237 causes the data to be displayed via the CRM screen 9 of the CRM tool. In this case, the minutes creation tool is an example of the first tool, and the CRM tool is an example of the second tool.

[0078] Note that the minutes screens 7 and 8 of the present embodiment may further have the following features. Note that the description may overlap hereinafter.

[0079] First, while showing FIG. 11, the minutes screen 7 during a meeting will be described. FIG. 11 is a diagram showing an example of the minutes screen 7 during a meeting. The minutes screen 7 is a screen for creating minutes during a meeting. The minutes screen 7 includes a meeting information area 70, an information input area 71, a timestamp area 72, and a speech-to-text area 73. Since the meeting information area 70, the timestamp area 72, and the speech-to-text area 73 are as described above, the description thereof will be omitted.

[0080] The information input area 71 is configured to display the result of character input performed by the secretary user. Further, the information input area 71 is configured to be able to set a format based on the template areas 712, 713, and 714. The template areas 712, 713, and 714 are areas that contain information regarding templates for the format of the minutes. For example, the template areas 712, 713, and 714 are areas that contain template information regarding the topic, template information regarding tables, template information regarding graphs, etc. The template areas 712, 713, and 714 are configured to be arbitrarily set by the user. As a result, it becomes possible for the secretary user to create minutes more efficiently. Also, as a result, it becomes possible to create minutes containing various types of information.

[0081] Next, while showing FIG. 12, the minutes screen 8 after the meeting will be described. FIG. 12 is a diagram showing another example of the minutes screen 8 after the meeting. The minutes screen 8 is a screen for creating the minutes after the meeting. The minutes screen 8 includes a meeting information area 80, an information input area 81, a timestamp area 82, a speech-to-text area 83, a full text selection button 84, and a playback area 85. For the meeting information area 80 after the meeting, refer to the meeting information area 70 during the meeting.

[0082] The information input area 81 after the meeting is configured to be able to display input information such as character input performed by the secretary user, similar to the information input area 71 during the meeting. In addition, the information input area 81 after the meeting is configured to accept a drag-and-drop operation of the speech-to-text information 830. When the information input area 81 after the meeting accepts the drag-and-drop operation, it is configured to be able to display the speech-to-text information 830 in the same manner as the information of the input characters.

[0083] The "drag and drop operation" refers to a concept that includes the operation of pressing a button on a mouse (or other pointing device) while aligning the pointer (arrow) on the target object, moving the pointer to the target location (dragging), and releasing the button at the target location (dropping). When a touch panel is used, the drag and drop operation includes the concept of being performed by touching with a finger, a touch pen, etc. instead of a pointer.

[0084] In the post-meeting timestamp area 82, the first-hour information 820 recorded during the meeting is displayed. Also, in the post-meeting timestamp area 82, the time associated with the first-hour information 820 of the speech-to-text information 830 transcribed from the speech-to-text area 83 is displayed.

[0085] The post-meeting speech-to-text area 83 is configured to be able to display one or more pieces of speech-to-text information 830 that are segmented at a predetermined timing and arranged in chronological order as a result of the speech during the meeting being speech-to-texted. This predetermined timing may be any timing that allows the speech-to-text result to be grasped as the flow of conversation, for example, the timing when there is a pause for breath, the timing when there is a gap, the timing when a sentence that can be delimited by a period, etc. can be determined, or the timing when the speaker changes. As a result, since the speech-to-text result is segmented at each predetermined timing, the secretary user can easily confirm the result.

[0086] The speech-to-text information 830 is information of text generated by speech-to-text conversion based on the audio data of the meeting. The speech-to-text information 830 includes speaker information 831, text information 832, and time information. The speaker information 831 is information that can identify the user who made the speech from which the speech-to-text conversion is derived. The text information 832 is information of the text generated by speech-to-text conversion. The time information is information of the time when the audio of the script associated with the script information was uttered during the meeting. The time information is displayed in the timestamp area 82 when it is transferred from the speech-to-text area 83 to the information input area 81. The transfer button is a button that, when pressed, transfers the speech-to-text information 830 associated with the transfer button to the information input area 81. The selection checkbox is a checkbox that can select the speech-to-text information 830 associated with the selection checkbox when a selection is received.

[0087] The first speech-to-text information 830a is one piece of speech-to-text information 830 arbitrarily selected from among a plurality of pieces of speech-to-text information 830. The first speech-to-text information 830a is configured to be handled as information including first speaker information 831a, first text information 832a, first time information 820, first transfer button 833a, and first selection checkbox 834a. Thereby, the data can be utilized including various information in the result of speech-to-text conversion.

[0088] The processor 23 transfers the first speech-to-text information 830a into the information input area 81 by accepting a drag-and-drop operation of the first speech-to-text information 830a from within the speech-to-text area 83 to the information input area 81. The first speech-to-text information 830a includes first time information 820. The first time information 820 is information of the time when the audio of the text associated with the first speech-to-text information 830a was uttered during the meeting. Thereby, the data can be utilized in the minutes including various information in the result of speech-to-text conversion.

[0089] The selection checkboxes are configured to allow multiple pieces of transcription information 830 to be selected by accepting a selection. The full text selection button 84 allows all of the transcription information 830 to be selected by accepting a selection. The processor 23 selects multiple pieces of transcription information 830 by accepting checks on multiple selection checkboxes or by accepting the full text selection button 84. The processor 23 transcribes the selected multiple pieces of transcription information 830 into the information input area 81 in response to a drag-and-drop operation on the selected multiple pieces of transcription information 830. This allows multiple pieces of transcription information 830 to be transcribed from the transcription area 83 to the information input area 81 at one time.

[0090] The playback area 85 is configured so that audio during the conference can be played back.

[0091] FIG. 13 is a diagram showing an example of the minutes recording screen 8 after drag and drop. The display control unit 231 displays information on the time when the voice of the characters linked to the first transcription information 830a transcribed in the information input area 81 was uttered in a manner that is visible to the user. For example, if the time when the sound of "gu" in "I would like to conduct a customer survey..." linked to the first transcription information 830a was uttered was 12 minutes and 43 seconds after the start of the conference, the display control unit 231 displays "12:43" in the time stamp area 82. This allows the user to easily check the time related to the transcription information.

[0092] In response to a user's clicking on first time information 820, playback unit 238 plays back the audio of the conference from the time associated with first time information 820. Playback of the audio of the conference may end when all of the audio associated with first transcription information 830a has been played back, or all of the audio from the time associated with first time information 820 onward may be played back continuously. This allows the user to easily play back audio from a time related to transcription information 830.

[0093] In addition, when the first speech-to-text information 830a transferred into the information input area 81 is moused over, the display control unit 231 displays the speaker information 812 associated with the first speech-to-text information 830a. The speaker information 812 is information regarding the speaker, and for example, it can be a name, username, user ID, etc. that can identify the speaker. Also, the speaker information 812 may be information that can be changed by the user. Further, instead of mousing over, the display control unit 231 may display the speaker information 812 associated with the first speech-to-text information 830a when the first speech-to-text information 830a is being dragged. Thereby, it becomes possible to easily confirm the speaker associated with the speech-to-text information 830 transferred from the speech-to-text area 83 to the information input area 81.

[0094] FIG. 14 is a diagram showing an example when various operations are to be executed on the minutes screen 8. The filter application information 835 is information on characters obtained by removing characters that have no meaning as the content of the meeting from the characters included in the speech recognition information 830. That is, each of the speech recognition information 830 may include characters called keba that have no meaning as the content of the meeting. Characters that have no meaning as the content of the meeting include some interjections, such as "eh", "ah", "um", "er", "well", "um". That is, the processor 23 controls one or more pieces of speech recognition information 830 as one or more pieces of filter application information 835. The processor 23 receives a drag-and-drop operation of the first filter application information 835a from within the speech recognition area to the information input area 81, and transcribes the first filter application information 835a into the information input area 81. The first filter application information 835a includes second time information 821, and the second time information 821 is information on the time when the voice of the characters associated with the first filter application information 835a was uttered during the meeting. That is, the second time information 821 may shift downward as a result of removing characters that have no meaning as the content of the meeting from the first utterance compared to the first time information 820. Thereby, it is possible to transcribe from the speech recognition area 83 to the information input area 81 in a manner in which characters that have no meaning are removed. Note that the first filter application information 835a is an example of the filter application information 835 and is arbitrarily selected from the filter information in the present embodiment.

[0095] The information input area 81 is configured to be able to display the linked information 813, and the linked information 813 is information that changes in conjunction with the operation of a certain tool. The linked information 813 includes information regarding tools different from the minutes creation tool, for example, information output from any tool such as a CRM tool, a document creation tool, a presentation tool, a spreadsheet tool, a project management tool, a communication tool, a design tool, a code repository & version control tool, a database management tool, a CMS tool, an email marketing tool, etc. The processor 23 updates the linked information 813 in the information input area 81 in conjunction with the update of the information on the tool. In the example shown in FIG. 14, the linked information 813 is information displayed in the form of a line graph in which the sales amount indicating the sales tool is displayed in chronological order. When the sales amount information is updated in the sales tool, the processor 23 updates the linked information 813 in the information input area 81 in conjunction with it. The specific part 235 identifies the minutes screen 8 on the minutes creation tool that displays data obtained from a tool different from the minutes creation tool. The output control part 237 causes the data to be displayed via the minutes screen 8 of the minutes creation tool. At this time, the tool different from the minutes creation tool is an example of the first tool, and the minutes creation tool is an example of the second tool. Thereby, it is possible to include information linked with various tools in the minutes.

[0096] [Information Processing Using Natural Language Processing] In response to an instruction via the input part 35 from the user, the processor 23 applies an arbitrary natural language processing algorithm such as BERT or ChatGPT to the selected speech-to-text information 830 or the information in the selected information input area 81, executes various information processes exemplified below, and outputs arbitrary information to the information input area 81. The position where the information in the information input area 81 is output may be a position specified by the user or a position selected by the natural language processing algorithm. Note that the processor 23 selects the information in the information input area 81 by dragging and selecting a range of the character string in the information input area 81.

[0097] [Drag the text transcript together to extract key points] For example, based on the selected text transcript information 830 or the information within the selected information input area 81, the processor 23 generates key points of the meeting and outputs the key points of the meeting to the information input area 71. The key points are a summary of the important points in the meeting in one or more sentences in a list form. The key points may be restricted to a predetermined number of characters or may not be restricted by the number of characters.

[0098] [Clean-up function (removing fillers, converting spoken language)] For example, based on the selected text transcript information 830 or the information within the selected information input area 81, the processor 23 may perform a clean-up process on the text transcript information 830 and then output it to the information input area 81. The clean-up process may be, for example, a process of removing the above-mentioned fillers or a process of converting spoken language to written language. The process of converting spoken language to written language includes processes such as converting "なので / ので / だから / ですから" to "そのため / ため" and converting "やっぱり" to "やはり".

[0099] [Summary function] For example, based on the selected text transcript information 830 or the information within the selected information input area 81, the processor 23 generates a summary text of the meeting and outputs the summary text of the meeting to the information input area 81. The summary text is a text written by briefly summarizing what was discussed in the entire meeting. The summary text may be restricted to a predetermined number of characters or may not be restricted by the number of characters.

[0100] [Support for extracting next actions and decisions] For example, based on the selected text transcript information 830 or the information within the selected information input area 81, the processor 23 extracts ToDo items or decisions and outputs the extracted ToDo items or decisions to the information input area 81. ToDo items are items determined during the meeting as the next actions, such as the creation of materials. Decisions are items agreed upon during the meeting, such as the date and time of the next meeting.

[0101] [Automatic extraction of agenda] For example, based on the selected speech recognition information 830 or the information in the selected information input area 81, the processor 23 extracts the topics that are key points during the meeting, and outputs the extracted topics to the information input area 81 after the meeting. For example, if the selected speech recognition information 830 is a topic related to business performance, the processor 23 outputs "Development of new customers" etc. as a topic to the information input area 81. This process may be performed based on all the speech recognition information 830 in the speech recognition area 83.

[0102] [Automatically reflected on the seek bar] For example, when the processor 23 extracts the topics that are key points during the meeting based on the selected speech recognition information 830 or the information in the selected information input area 81, the processor 23 may display the time when the topic started on the seek bar in the playback area 85. For example, when a topic related to the development of new customers starts at 25 minutes and 00 seconds from the start time of the meeting, the processor 23 associates and displays the characters "Development of new customers" at the position corresponding to 25 minutes and 00 seconds on the seek bar of the playback area 85. This process may be performed based on all the speech recognition information 830 in the speech recognition area 83.

[0103] [Automatic generation of the outline of the minutes] The processor 23 may generate the outline of the minutes based on the selected speech recognition information 830 and output it to the information input area 81. The outline of the minutes includes the agenda, decisions, ToDo items, summary text, etc. This process may be performed based on all the speech recognition information 830 in the speech recognition area 83.

[0104] According to the present disclosure, in various tools, information can be output more appropriately or the convenience can be improved more.

[0105] [Others] The program is a program that causes one or more computers to execute the following steps. The information processing system 1 includes one or more computers that execute the program. Regarding the information processing system 1 according to the above-described embodiment, it may be a program that causes a computer to function as the processor 23 of the information processing system 1. Alternatively, it may be an information processing method executed by the information processing system 1.

[0106] The server 2 may be in an on-premises form or in a cloud form. As the cloud-form server 2, for example, in the form of SaaS (Software as a Service), cloud computing, etc., the above functions and processes may be provided.

[0107] In the above embodiment, the server 2 performs various storage and controls. However, instead of the server 2, a plurality of external devices may be used. That is, various information and programs may be distributed and stored in a plurality of external devices using blockchain technology or the like.

[0108] At least one of the devices included in the information processing system 1 may be installed outside Japan. For example, the server 2 may be installed outside Japan, and each terminal device may be installed within Japan. Similarly, a user may access the server 2 installed within Japan using his / her terminal device from outside Japan. According to such an aspect, a more convenient experience can be provided to the user by various management forms.

[0109] In the embodiment, the generation control unit 236 has been described as an example of continuously executing the generation of character generation information (conference content information) as a series of processes after the completion of speech recognition. However, in a modified example, the generation control unit 236 may generate the character generation information (conference content information) when receiving an instruction from the user after the completion of speech recognition.

[0110] In the embodiment, an example of generating the minutes screen 7 using the minutes template information has been described. However, in a modification, the minutes screen 7 may be generated without using the minutes template information.

[0111] In the modification, the second time information 821 may be information indicating the same time as the first time information 820 regardless of whether characters having no meaning as the content of the meeting are removed.

[0112] In the modification, the processor 23 may select the information within the speech recognition area 83 by dragging and selecting a character string instead of or in addition to the selection checkbox.

[0113] Furthermore, it may be provided in each of the aspects described below.

[0114] (1) A program for causing a computer to execute the following steps. In a specific step, a destination for outputting character generation information is specified on a screen for creating minutes of a meeting. The character generation information is information of characters generated based on speech recognition information or input information. The speech recognition information is information of characters obtained by speech recognition of the content of a speech. The input information is information received as an input from a user. In an output control step, the character generation information is output to the output destination.

[0115] According to such a configuration, in the minutes creation tool, convenience can be further improved.

[0116] (2) In the program according to (1) above, the character generation information includes meeting content information indicating the content of the meeting. The meeting content information includes information on ToDo after the meeting, information on decisions made at the meeting, information on names of related parties of the meeting, information on speeches of speakers participating in the meeting, information on a summary of the meeting, information on a list of key points of the meeting, or information on question-and-answer sessions of the meeting.

[0117] According to such a configuration, information on various aspects of a meeting, such as ToDo after the meeting, decisions made at the meeting, names of the persons involved in the meeting, summary of the meeting, list of key points of the meeting, statements of the speakers participating in the meeting, or question-and-answer sessions of the meeting, can be output as character generation information.

[0118] (3) In the program described in (2) above, the meeting content information changes according to the output destination specified in the specific step.

[0119] According to such a configuration, character generation information can be appropriately generated according to the output destination.

[0120] (4) In the program described in (2) above, in the specific step, the output destination is specified based on the information indicated by the meeting content information.

[0121] According to such a configuration, character generation information can be output to an appropriate output destination based on the content of the character generation information.

[0122] (5) In the program described in (1) above, in the specific step, when the designation of the output destination of the character generation information on the minutes is received from the user, the received output destination is specified.

[0123] According to such a configuration, the destination to which the character generation information is output can be specified.

[0124] (6) In the program described in (5) above, a storage control step is executed, and in the storage control step, the output destination of the character generation information on the minutes received in the specific step is stored.

[0125] According to such a configuration, the output destination of the character generation information on the minutes can be stored and used for creating subsequent minutes.

[0126] (7) In the program according to (1) above, the output destination is a CRM tool or a document creation tool.

[0127] According to such a configuration, in a CRM tool or a document creation tool, information can be output more appropriately or the convenience can be further improved.

[0128] (8) A program for causing a computer to execute the following steps: In a specific step, identify a screen on a second tool for displaying data acquired from a first tool; in an output control step, display the data via the screen on the second tool; and either the first tool or the second tool is a tool for creating minutes of a meeting.

[0129] According to such a configuration, in a tool for creating minutes of a meeting, the convenience can be further improved.

[0130] (9) An information processing method including each step of the program according to any one of (1) to (8) above.

[0131] According to such a configuration, in a tool for creating minutes of a meeting, the convenience can be further improved.

[0132] (10) An information processing system including a computer that executes the program according to any one of (1) to (8) above.

[0133] According to such a configuration, in a tool for creating minutes of a meeting, information can be output more appropriately or the convenience can be further improved. Of course, this is not the limit.

[0134] Finally, although various embodiments of the present invention have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. Such embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalent scope thereof.

Explanation of Signs

[0135] 1: Information processing system 2: Server 21: Communication unit 22: Storage unit 23: Processor 230: Information transmission / reception unit 231: Display control unit 232: Storage control unit 233: Recording unit 234: Voice recognition unit 235: Identification unit 236: Generation control unit 237: Output control unit 238: Reproduction unit 3: User terminal 31: Communication unit 32: Storage unit 33: Processor 34: Display unit 35: Input unit 4: Sound collection device 5: Management screen 50: Collaboration tool area 500: Linked tool area 500a: Template creation button 501: Unlinked tool area 501a: Link button 6: Template creation screen 60: Collaboration option area 61: Title area 62: Collaboration area 63: Save button 7: Minutes screen 70: Conference information area 71: Information input area 710: Template area 711: Template area 712: Template area 713: Template area 714: Template area 72: Timestamp area 73: Transcription area 8: Minutes screen 80: Conference information area 81: Information input area 810: Linked template area 811: Linked template area 812: Speaker information 813: Linked information 82: Timestamp area 820: First hour information 821: Second hour information 83: Transcription area 830: Transcription information 830a: First transcription information 831: Speaker information 831a: First speaker information 832: Character information 832a: First character information 833a: First transcription button 834a: First selection checkbox 835: Filter application information 835a: First filter application information 84: Full text selection button 85: Playback area 9: CRM screen 90: Linked information 91: Linked information

Claims

1. A program for causing a computer to execute the following steps: In the identification step, an output destination for outputting character generation information on a screen for creating minutes of the meeting is identified; The character generation information is information on characters generated based on transcription information or input information, The transcription information is information of text obtained by transcribing the content of an utterance, The input information is information inputted by a user, In the output control step, the character generation information is output to the output destination. program.

2. The program according to claim 1, The character generation information includes meeting content information indicating the content of the meeting, The meeting content information includes information on to-do items after the meeting, information on decisions made at the meeting, information on names of people involved in the meeting, information on remarks made by speakers participating in the meeting, information on a summary of the meeting, information on a list of key points of the meeting, or information on questions and answers at the meeting. program.

3. The program according to claim 2, the conference content information changes depending on the output destination identified in the identifying step. program.

4. The program according to claim 2, In the specifying step, the output destination is specified based on information indicated by the conference content information. program.

5. The program according to claim 1, In the specifying step, when a designation of an output destination of the character generation information on the minutes is received from a user, the received output destination is specified. program.

6. The program according to claim 5, Execute a storage control step; In the storage control step, the output destination of the character generation information on the minutes accepted in the identification step is stored. program.

7. The program according to claim 1, The output destination is a CRM tool or a document creation tool. program.

8. A program for causing a computer to execute the following steps: In the identification step, a screen on the second tool on which data acquired from the first tool is to be displayed is identified; In the output control step, the data is displayed on the screen of the second tool; One of the first tool and the second tool is a tool for creating minutes of a meeting. program.

9. 1. An information processing method, comprising: The program includes steps according to any one of claims 1 to 8. Information processing methods.

10. An information processing system, A computer that executes the program according to any one of claims 1 to 8. Information processing system.

Images