SCHEDULE ADJUSTMENT SYSTEM, SCHEDULE ADJUSTMENT METHOD, AND PROGRAM

Abstract

Improve user convenience. [Solution] A communication data acquisition unit (201) of a schedule adjustment system (1) acquires communication data indicating the content of communication made using a communication tool. An adjustment schedule data acquisition unit (203) acquires adjustment schedule data indicating adjustment schedules to be adjusted through communication based on the communication data and a machine learning model capable of language analysis. A schedule transmission unit (206) transmits the adjustment schedule data to a schedule management tool linked to the communication tool.

Description

[Technical field]

[0001] The present disclosure relates to a schedule adjustment system, a schedule adjustment method, and a program. [Background technology]

[0002] Conventionally, communication tools that allow users to communicate with each other via e-mail or the like are known. For example, a user may use a communication tool to arrange a schedule such as a meeting. Once the schedule is finalized, the user registers the schedule in a schedule management tool. When the schedule is arranged and registered in this manner, the user must go back and forth between the communication tool and the schedule management tool, which complicates the user's operations.

[0003] For example, Non-Patent Document 1 describes an email software that is an example of a communication tool. The email software in Non-Patent Document 1 acquires schedule data indicating schedules for flights, accommodations, etc. from emails sent by specific senders such as airlines or accommodations. The email software in Non-Patent Document 1 automatically adds the schedule indicated by the schedule data acquired from the email to a schedule within the email software. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] "Automatically add events from your email to your calendar", Internet, Searched on October 20, 2023, online, https: / / support.microsoft.com / en-gb / office / automatically-add-events-from-your-email-to-your-calendar-32e5cf0c-3e65-4870-9ff9-df3683d3fc97 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the email software in Non-Patent Document 1 can only handle emails in a specific format sent by a specific sender. Emails from people with whom a user is coordinating plans do not have a set format, unlike emails from airlines, accommodations, etc., so the email software in Non-Patent Document 1 cannot obtain plan data. For this reason, the email software in Non-Patent Document 1 lacks versatility and cannot sufficiently improve user convenience.

[0006] One of the objectives of the present disclosure is to improve user convenience. [Means for solving the problem]

[0007] A schedule adjustment system according to one aspect of the present disclosure includes a communication data acquisition unit that acquires communication data indicating the content of communication made using a communication tool, an adjustment schedule data acquisition unit that acquires adjustment schedule data indicating the adjustment schedule that is to be adjusted by the communication based on the communication data and a machine learning model capable of language analysis, and a schedule transmission unit that transmits the adjustment schedule data to a schedule management tool linked to the communication tool. Effect of the Invention

[0008] According to the present disclosure, it is possible to improve user convenience. [Brief description of the drawings]

[0009] [Figure 1] FIG. 2 is a diagram illustrating an example of a hardware configuration of the schedule adjustment system. [Diagram 2] FIG. 13 is a diagram showing an example of a communication screen. [Diagram 3] FIG. 13 is a diagram showing an example of a communication screen. [Figure 4] FIG. 13 illustrates an example of a schedule management screen. [Diagram 5] FIG. 2 is a diagram illustrating an example of functions realized by the schedule adjustment system. [Figure 6] FIG. 2 is a diagram illustrating an example of a training database. [Figure 7] FIG. 2 is a diagram illustrating an example of a communication database. [Figure 8] FIG. 4 is a diagram illustrating an example of a schedule management database. [Figure 9] FIG. 2 is a diagram illustrating an example of a process executed in the schedule adjustment system. [Figure 10] FIG. 2 is a diagram illustrating an example of a process executed in the schedule adjustment system. [Figure 11] FIG. 13 is a diagram showing an example of a communication screen in Modification 1. [Figure 12] FIG. 13 is a diagram showing an example of a communication screen in Modification Example 2. [Figure 13] FIG. 13 is a diagram showing an example of a communication screen in Modification 3. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] [1. Hardware configuration of the schedule adjustment system] An example of an embodiment of a schedule adjustment system, a schedule adjustment method, and a program according to the present disclosure will be described. Fig. 1 is a diagram showing an example of a hardware configuration of a schedule adjustment system. For example, the schedule adjustment system 1 includes a learning terminal 10, a communication server 20, a schedule management server 30, and a user terminal 40. Each of the learning terminal 10, the communication server 20, the schedule management server 30, and the user terminal 40 is connected to a network N such as the Internet or a LAN.

[0011] The learning terminal 10 is a computer that performs learning of a machine learning model described below. For example, the learning terminal 10 is a personal computer, a tablet terminal, or a smartphone. For example, the learning terminal 10 includes a control unit 11, a memory unit 12, a communication unit 13, an operation unit 14, and a display unit 15. The control unit 11 includes at least one processor. The memory unit 12 includes at least one of a volatile memory such as a RAM and a non-volatile memory such as a flash memory. The communication unit 13 includes at least one of a communication interface for wired communication and a communication interface for wireless communication. The operation unit 14 is an input device such as a mouse or a touch panel. The display unit 15 is a liquid crystal or organic EL display.

[0012] The communication server 20 is a server computer. For example, the communication server 20 includes a control unit 21, a storage unit 22, and a communication unit 23. The hardware configurations of the control unit 21, the storage unit 22, and the communication unit 23 may be similar to those of the control unit 11, the storage unit 12, and the communication unit 13, respectively.

[0013] The schedule management server 30 is a server computer. For example, the schedule management server 30 includes a control unit 31, a storage unit 32, and a communication unit 33. The hardware configurations of the control unit 31, the storage unit 32, and the communication unit 33 may be similar to those of the control unit 11, the storage unit 12, and the communication unit 13, respectively.

[0014] The user terminal 40 is a user's computer. For example, the user terminal 40 is a personal computer, a tablet terminal, or a smartphone. For example, the user terminal 40 includes a control unit 41, a storage unit 42, a communication unit 43, an operation unit 44, and a display unit 45. The hardware configurations of the control unit 41, the storage unit 42, the communication unit 43, the operation unit 44, and the display unit 45 may be similar to those of the control unit 11, the storage unit 12, the communication unit 13, the operation unit 14, and the display unit 15, respectively.

[0015] The programs stored in the storage units 12, 22, 32, 42 may be supplied via the network N. The hardware configurations of the learning terminal 10, the communication server 20, the schedule management server 30, and the user terminal 40 are not limited to the example in FIG. 1. For example, at least one of the learning terminal 10, the communication server 20, the schedule management server 30, and the user terminal 40 may include at least one of a reading unit (e.g., a memory card slot) that reads a computer-readable information storage medium and an input / output unit (e.g., a USB terminal) for directly connecting to an external device. The programs stored in the information storage medium may be supplied to at least one of the learning terminal 10, the communication server 20, the schedule management server 30, and the user terminal 40 via at least one of the reading unit and the input / output unit.

[0016] Furthermore, the schedule adjustment system 1 may include at least one computer. The computers included in the schedule adjustment system 1 are not limited to the example of FIG. 1. For example, the schedule adjustment system 1 may include only the learning terminal 10, the communication server 20, and the schedule management server 30. In this case, the user terminal 40 exists outside the schedule adjustment system 1. The schedule adjustment system 1 may include only the communication server 20. In this case, the learning terminal 10, the schedule management server 30, and the user terminal 40 exist outside the schedule adjustment system 1. The schedule adjustment system 1 may include the communication server 20 and other server computers other than the schedule management server 30.

[0017] [2. Overview of the Schedule Adjustment System] In this embodiment, the user adjusts the schedule by using a communication tool. The communication tool is a tool that allows the user to communicate with other people. The communication tool can also be a program that allows the user to send messages to other people. The communication tool may be a publicly known tool. For example, the communication tool may be an email tool, a chat tool, a message application, an SMS (Short Message Service), or an SNS (Social Networking Service).

[0018] In this embodiment, an email tool will be described as an example of a communication tool. For example, a user uses groupware that has a communication tool. The groupware is a program that supports the user's work. The groupware may be either cloud-based or on-premise. In this embodiment, the communication server 20 manages the communication tools. When a user logs into the groupware and selects a communication tool, the user terminal 40 displays a communication screen, which is the screen of the communication tool, on the display unit 45.

[0019] 2 and 3 are diagrams showing an example of a communication screen. In the example of FIG. 2 and FIG. 3, a user named "Saibou Taro" who works at a certain company communicates with an outside person named "Kinto Hanako" by using email to arrange a meeting schedule. A schedule may be one that takes place at a specific date and time and at a specific location. A schedule is not limited to a meeting as shown in FIG. 2 and FIG. 3. For example, a schedule may be a non-work meeting, an outing, a business trip, a seminar, or an interview. A schedule is not limited to one that takes place in real space. A schedule may take place in virtual space or online. For example, a web conference held at a specific URL corresponding to a location on the Internet may correspond to a schedule.

[0020] Hereinafter, a plan that the user adjusts will be referred to as an adjusted plan. The person with whom the user adjusts the plan (the person with whom the user communicates, "Kinto Hanako" in the examples of Figs. 2 and 3) will be referred to as the adjustment partner. For example, the user sends an email to the email address of the adjustment partner, listing multiple dates and times as candidates. The adjustment partner sends an email to the user's email address, listing the date and time that they prefer from the multiple dates and times. In the example of the communication screen SC1 at the top of Fig. 2, the adjustment partner prefers the date and time of "October 26, 2023, 13:00-14:00".

[0021] In this embodiment, the communication server 20 supports the user's adjustment work by identifying the date and time of the planned adjustment from the email based on a machine learning model capable of language analysis. Details of the machine learning model will be described later. For example, when the user selects the button B10 on the communication screen SC1, the communication server 20 uses the machine learning model to identify the date and time of the adjustment partner's request, "October 26, 2023, 13:00-14:00", from the email. The email also includes other dates and times initially presented by the user, but in this embodiment, the machine learning model is learned to identify the date and time included in the relatively new reply content, rather than other dates and times included in the relatively old reply content.

[0022] For example, the communication screen SC1 switches to a reply mode, which is a mode for replying to emails, as shown in the lower part of Fig. 2. The communication screen SC1 in the reply mode includes a display area A11 that shows the date and time of the scheduled adjustment identified by the machine learning model. If the date and time of the scheduled adjustment identified by the machine learning model is incorrect, the user can correct the date and time of the scheduled adjustment from the display area A11.

[0023] For example, when a user selects the button B110 for checking a schedule, the communication server 20 checks the user's schedule based on a schedule management tool of the groupware. The schedule management tool is a tool that manages the user's schedule. In this embodiment, a case will be described in which the schedule management tool is a groupware tool similar to the communication tool, but the schedule management tool does not have to be a groupware tool. In this embodiment, a case will be taken as an example in which the schedule management server 30 manages the schedule management tool.

[0024] Hereinafter, a schedule that has been registered in the schedule management tool is referred to as a registered schedule. For example, the communication server 20 checks whether the date and time of the adjustment schedule is available based on the date and time of the adjustment schedule and the date and time of the registration schedule. When it is confirmed that the date and time of the adjustment schedule is available, the user terminal 40 displays a message indicating that the date and time of the adjustment schedule is available in the display area A11, as shown in the upper part of FIG. 3.

[0025] The machine learning model may identify not only the date and time of the adjustment schedule from the email, but also at least one of the title and memo of the adjustment schedule. For example, when the machine learning model can identify at least one of the title and memo of the adjustment schedule, the user terminal 40 displays at least one of the title and memo of the adjustment schedule in the display area A11. In the example of the communication screen SC1 at the top of FIG. 3, it is assumed that the machine learning model can identify a title such as "YYY Co., Ltd., Kinto-san" from the addressee part of the email. The title is displayed in the display area A11. The user can modify at least one of the title and memo of the adjustment schedule from the display area A11.

[0026] For example, when the user selects the button B111 for sending a schedule, the communication server 20 transmits adjustment schedule data indicating the adjustment schedule to the schedule management server 30 that manages the schedule management tool based on the contents displayed in the display area A11. The schedule management server 30 registers the adjustment schedule in the schedule management tool based on the adjustment schedule data. The communication server 20 generates a draft reply based on a predetermined template. As shown in the lower part of FIG. 3, the user terminal 40 displays on the communication screen SC1 a message indicating that the user's schedule has been sent and a draft reply generated based on the template. When the user selects the button B12 for sending an email, an email is sent to the email address of the person with whom the adjustment is to be made.

[0027] The machine learning model may generate a reply draft. For example, the reply draft generated by the machine learning model may be displayed on the communication screen SC1. When the user selects the button B112, the communication server 20 may cause the machine learning model to modify the reply draft. The machine learning model may modify the reply draft in the same manner as a known interactive model.

[0028] For example, the user may input an instruction such as "Please use a more polite expression." to cause the machine learning model to revise the reply draft. The process in which the machine learning model revises the draft based on the user's instruction may be a known process. When the machine learning model revise the draft based on the user's instruction, the user terminal 40 displays the revised draft on the communication screen SC1. The user may instruct the machine learning model to revise it again. When the user selects a schedule management tool from the communication screen SC1, the user terminal 40 displays a schedule management screen, which is the screen of the schedule management tool, on the display unit 45.

[0029] FIG. 4 is a diagram showing an example of a schedule management screen. As shown in FIG. 4, the schedule management screen SC2 shows a registered schedule registered in the schedule management tool. In the example of FIG. 4, an adjustment schedule (schedule for the date and time "October 26, 2023 13:00-14:00") that the user adjusted with the adjustment partner on the communication screen SC1 is registered in the schedule management tool as a registered schedule. When the user selects a registered schedule displayed on the schedule management screen SC2, the user terminal 40 displays details of the registered schedule on the schedule management screen SC2.

[0030] As described above, the schedule adjustment system 1 uses a machine learning model to identify the date and time of an adjustment schedule described in an email. The schedule adjustment system 1 allows the user to correct the date and time, etc., as necessary, and then transmits adjustment schedule data indicating the identified date and time, etc., to the schedule management tool. By using a machine learning model, the schedule adjustment system 1 can identify the date and time of an adjustment schedule even if the email does not have a defined format, thereby improving user convenience. Details of the schedule adjustment system 1 will be described below.

[0031] [3. Functions realized by the schedule adjustment system] FIG. 5 is a diagram showing an example of functions realized by the schedule adjustment system 1. As shown in FIG.

[0032] [3-1. Functions realized on the learning device] For example, the learning terminal 10 includes a data storage unit 100 and a learning unit 101. The data storage unit 100 is realized by the storage unit 12. The learning unit 101 is realized by the control unit 11.

[0033] [Data storage section] The data storage unit 100 stores data necessary for learning the machine learning model M. For example, the data storage unit 100 stores the machine learning model M. The machine learning model M is a model created based on a machine learning technique. The machine learning model M may be any type of model used in the field of natural language processing. For example, the machine learning model M may be any of supervised learning, semi-supervised learning, and unsupervised learning models.

[0034] In this embodiment, the machine learning model M is a so-called large-scale language model. For example, the machine learning model M may be a large-scale language model such as a Generative Pre-trained Transformer (GPT), a Bidirectional Encoder Representations from Transformers (BERT), a Pathways Language Model (PaLM), or a Large Language Model Meta AI (LLaMA). The machine learning model M may be another model (for example, a neural network or a sequence-to-sequence model) that is not classified as a large-scale language model.

[0035] For example, the machine learning model M includes parameters that are adjusted by learning. The parameters of the machine learning model M are referenced by the program of the machine learning model M. For example, the parameters are weighting coefficients and biases. The parameters may be various well-known parameters. The parameters are not limited to weighting coefficients and biases. For example, the parameters may be matrices referenced when calculating an embedding representation, positional encodings referenced in encoding token positions, or other parameters.

[0036] The machine learning model M includes a program for computing the embedded representation, etc. The program of the machine learning model M includes a code indicating the internal processing of the machine learning model M. For example, the program of the machine learning model M indicates the processing of an encoder that computes the embedded representation, a decoder that creates data for output according to a task such as schedule adjustment, an output layer that performs final output based on the data, and other intermediate layers. When the machine learning model M is a large-scale language model, the machine learning model M also includes a program that indicates the processing of splitting input data into multiple tokens. The program of the machine learning model M may be a publicly known program.

[0037] In this embodiment, a case where a pre-trained large-scale language model corresponds to the machine learning model M is taken as an example. For example, the learning unit 101 described below re-learns the machine learning model M. The re-learning is adjustment of parameters of the pre-trained machine learning model M. For example, the re-learning is fine tuning, transfer learning, or distillation. Instead of re-learning the machine learning model M, the learning unit 101 described below may perform learning of a machine learning model M that has not been pre-trained (machine learning model M whose parameters are initial values) from scratch. The data storage unit 100 stores not only the machine learning model M but also a training database DB1 required for learning.

[0038] 6 is a diagram showing an example of the training database DB1. The training database DB1 is a database in which training data necessary for learning the machine learning model M is stored. For example, the training data includes an input part that is input to the machine learning model M during learning, and an output part that becomes a correct answer during learning. The combination of the input part and the output part may be a combination according to the content of the task executed by the machine learning model M. The training data may be prepared by manual input or by a known tool.

[0039] For example, the input portion of the training data is all or a part of data indicating a training email. The training email may be an email that was actually sent, or may be an email with virtual content. The training email contains some information related to a training schedule. For example, the training email contains the date and time, title, notes, location, participants, or a combination of these, of the training schedule. The training email may contain other information such as greetings or casual conversation unrelated to the schedule.

[0040] For example, the output portion of the training data is a portion to be identified from the training email. The output portion of the training data indicates a portion of the text of the training email. For example, the output portion of the training data is a portion of the training email that describes the date and time, title, notes, location, participants, or a combination thereof, of the training event. The output portion of the training data may be annotated by the creator of the training data or may be annotated by a known tool. In the example of FIG. 6, the output portion of the training data indicates the date and time of the training event.

[0041] For example, as in the emails of FIG. 2 and FIG. 3, multiple dates and times may be described in the relatively old reply content, and the date and time desired by the other party to the adjustment may be described in the relatively new reply content. Training data may be created so that the machine learning model M can handle such emails. For example, the input portion of the training data may be a training email in which multiple dates and times are described in the relatively old reply content, and the date and time desired by the other party to the adjustment is described in the relatively new reply content. The output portion of the training data may be the date and time included in the relatively new reply content. With such training data, the machine learning model can learn which part of the email the date and time described should be identified.

[0042] The data stored in the data storage unit 100 is not limited to the example of this embodiment. The data storage unit 100 may store data necessary for learning the machine learning model M. For example, the data storage unit 100 stores a learning program showing a series of processes in learning the machine learning model M. The formula for the loss function calculated during learning is also shown in the learning program.

[0043] [Learning Department] The learning unit 101 executes learning of the machine learning model M based on each of a plurality of training data stored in the training database DB1. In this embodiment, a case is exemplified in which the learning unit 101 executes learning of the machine learning model M based on a supervised learning algorithm. The learning algorithm may be a known algorithm. For example, the learning unit 101 may execute learning of the machine learning model M based on a semi-supervised learning or unsupervised learning algorithm.

[0044] For example, the learning unit 101 performs learning of the machine learning model M by adjusting parameters of the machine learning model M based on a supervised learning algorithm such that an output portion of the training data is output from the machine learning model M when an input portion of the training data is input to the machine learning model M. The learning unit 101 calculates a loss indicating an error between an output from the machine learning model M when an input portion of the training data is input to the machine learning model M and the output portion of the training data based on a known loss function. The learning unit 101 performs learning of the machine learning model M by adjusting parameters of the machine learning model M such that the calculated loss is small. The learning unit 101 may repeatedly perform learning of the machine learning model M until the loss becomes less than a threshold.

[0045] For example, the machine learning model M during learning divides text indicated by the input portion of the training data into multiple tokens. The machine learning model M encodes each of the multiple tokens and converts them into a sequence of embedded representations. Based on the sequence of embedded representations, the machine learning model M predicts the continuation as necessary and calculates an output according to the task. The greater the difference between the output of the machine learning model M and the output portion of the training data, the greater the loss. The smaller the difference between the output of the machine learning model M and the output portion of the training data, the smaller the loss. This series of processes is executed based on the program of the machine learning model M (e.g., the encoder, decoder, output layer, and other layers) and the current parameters of the machine learning model M.

[0046] The algorithm used in the learning may be a known algorithm. For example, the learning unit 101 executes learning of the machine learning model M based on the backpropagation method. The learning unit 101 may execute learning of the machine learning model M based on an algorithm other than the backpropagation method. For example, the learning unit 101 may execute learning of the machine learning model M based on the gradient descent method, the momentum method, the quasi-Newton method, the conjugate gradient method, the local search method, or other algorithms.

[0047] In this embodiment, the learning unit 101 executes a series of learning processes by executing a learning program stored in the data storage unit 100. The learning unit 101 records the trained machine learning model M in the data storage unit 100. The data storage unit 100 may store both the machine learning model M before learning and the trained machine learning model M. The learning unit 101 transmits the trained machine learning model M to the communication server 20. The trained machine learning model M transmitted to the communication server 20 is made available for use by the user.

[0048] [3-2. Functions realized by the communication server] For example, the communication server 20 includes a data storage unit 200, a communication data acquisition unit 201, a task determination unit 202, an adjustment schedule data acquisition unit 203, a registration schedule data acquisition unit 204, a display control unit 205, a schedule transmission unit 206, and a reply content generation unit 207. The data storage unit 200 is realized by the storage unit 22. Each of the communication data acquisition unit 201, the task determination unit 202, the adjustment schedule data acquisition unit 203, the registration schedule data acquisition unit 204, the display control unit 205, the schedule transmission unit 206, and the reply content generation unit 207 is realized by the control unit 21.

[0049] [Data storage section] The data storage unit 200 stores data necessary for supporting schedule adjustment. For example, the data storage unit 200 stores a communication database DB2 and a trained machine learning model M.

[0050] 7 is a diagram showing an example of the communication database DB2. The communication database DB2 is a database that stores communication data indicating the contents of communication performed using a communication tool. For example, the communication database DB2 stores a communication ID and communication data.

[0051] The communication ID is an ID for the schedule adjustment system 1 to identify communication data. When new communication is performed using a communication tool, the communication server 20 generates new communication data indicating the new communication. The communication server 20 issues a communication ID for the new communication data. The communication server 20 stores the communication ID and the new communication data in the communication database DB2.

[0052] The communication data is text indicating the specific contents of the communication. The text here does not mean data with a txt extension, but at least one combination of letters, numbers, and other symbols. That is, the text is a sentence having a certain length. The communication data may be data with a txt extension. The communication data may be in any data format. For example, in the case where the communication data is email data as in this embodiment, the communication data may be data of a message file with an extension such as msg, or may be data of a character string indicating the body of the email extracted from the email.

[0053] In this embodiment, an example is given in which the communication data is character string data indicating the body of an email. The communication data may indicate a portion other than the body of an email (e.g., a header). The communication data may be data corresponding to the communication tool. The communication data is not limited to email data. For example, the communication data may be data indicating messages exchanged using a chat tool, a messaging app, SMS, or an SNS.

[0054] The data stored in the data storage unit 200 is not limited to the above examples. The data storage unit 200 can store any data. For example, the data storage unit 200 may store a user database in which various data of users are stored. The user database stores data such as user IDs and passwords. The data storage unit 200 may store data of each screen such as the communication screen SC1. The data storage unit 200 may store template data indicating templates of reply contents. The data storage unit 200 may store a database similar to the schedule management database DB3 described later.

[0055] [Communication Data Acquisition Department] The communication data acquisition unit 201 acquires communication data. In this embodiment, since the communication data is stored in the communication database DB2, the communication data acquisition unit 201 acquires the communication data from the communication database DB2. The communication data may be stored in a database other than the communication database DB2. The communication data may be stored in a computer other than the communication server 20. The communication data acquisition unit 201 may acquire the communication data from the other database or the other computer.

[0056] In this embodiment, the communication data acquisition unit 201 acquires communication data of an email designated by the user among emails addressed to the user. For example, when the user selects button B10 in the state of the communication screen SC1 at the top of FIG. 2, the communication data acquisition unit 201 acquires communication data indicating the email being displayed. The communication data acquisition unit 201 may acquire communication data indicating the email being displayed before the user selects button B10. The communication data acquisition unit 201 may acquire communication data indicating an email containing information about the adjustment schedule to be processed.

[0057] [Task Judgment Section] The task determination unit 202 determines whether the task of the machine learning model M is schedule adjustment based on the communication data. The task of the machine learning model M is the content of the processing to be executed by the machine learning model M. The machine learning model M may be a model specialized for a specific task, or may be a model not specialized for a specific task. For example, when the machine learning model M is a highly versatile GPT model, the machine learning model M may not be specialized for a specific task. In this case, the machine learning model M can perform a machine translation task, a summary creation task, a data classification task, or other tasks in addition to the schedule adjustment task. The task to be executed by the machine learning model M may be specified as an input (prompt) to the machine learning model M.

[0058] The method of determining the task of the machine learning model M may be a known method. For example, the task determination unit 202 inputs communication data to the machine learning model M. The machine learning model M divides the text indicated by the communication data into a plurality of tokens. The machine learning model M calculates an embedded expression based on the plurality of tokens, and predicts the continuation of the text as necessary. The machine learning model M analyzes the context of the text based on the calculated embedded expression to identify the task that the machine learning model M should perform.

[0059] For example, when the machine learning model M determines based on the embedded representation that the text indicated by the communication data contains specific text related to schedule adjustment (for example, text indicating some date and time, or text used in schedule adjustment such as "Would the following date and time be convenient for you?"), it determines that the task of the machine learning model M is schedule adjustment. When the machine learning model M determines based on the embedded representation that the text indicated by the communication data does not contain specific words related to schedule adjustment, it determines that the task of the machine learning model M is not schedule adjustment.

[0060] The task determination unit 202 may determine the task of the machine learning model M without inputting communication data to the machine learning model M. For example, the task determination unit 202 may determine whether the task of the machine learning model M is schedule adjustment by determining whether the text indicated by the communication data contains text used in schedule adjustment, such as "meeting," based on a dictionary prepared in advance. Terms indicating the task of schedule adjustment are registered in the dictionary. The task determination unit 202 may determine that the task of the machine learning model M is a task of schedule adjustment when a predetermined number or more of terms registered in the dictionary are present in the text indicated by the communication data.

[0061] As another example, the task determination unit 202 may determine the task of the machine learning model M by using another machine learning model for task determination, separate from the machine learning model M for identifying the date and time of the scheduled adjustment. In this case, the other machine learning model is assumed to have learned the relationship between the training communication data and the task of the machine learning model M. The other machine learning model labels whether or not the communication data input thereto belongs to a schedule adjustment task. The task determination unit 202 may determine that the task of the machine learning model M is schedule adjustment when the label output by the other machine learning model indicates a schedule adjustment task.

[0062] [Data Acquisition Section for Adjustment Plans] The adjustment schedule data acquisition unit 203 acquires adjustment schedule data indicating an adjustment schedule to be adjusted through communication, based on the communication data and a machine learning model M capable of language analysis. The machine learning model M capable of language analysis is a machine learning model M that can calculate an embedded expression when some text is input and output accordingly. The machine learning model M used in the field of natural language processing described above corresponds to the machine learning model M capable of language analysis.

[0063] The adjustment schedule data is data indicating the contents of the adjustment schedule. For example, the adjustment schedule data acquisition unit 203 acquires adjustment schedule data indicating the date and time of the adjustment schedule. In this embodiment, since a situation before the adjustment schedule is confirmed is taken as an example, the candidate date and time of the adjustment schedule corresponds to the date and time of the adjustment schedule. The adjustment schedule may be confirmed on the email, and in this case, the adjustment schedule data may indicate the confirmed date and time of the adjustment schedule, rather than the candidate date and time of the adjustment schedule.

[0064] For example, the adjustment schedule data acquisition unit 203 may acquire adjustment schedule data indicating the date and time of the adjustment schedule and other information about the adjustment schedule. The other information may be information other than the date and time. In this embodiment, the other information is at least one of the title of the adjustment schedule and notes about the adjustment schedule. The other information may be the name of a participant of the adjustment schedule, the company information of the participant, the location where the adjustment schedule is held, or a facility such as a conference room used for the adjustment schedule. In the case of an online conference, the other information may be a URL used in the online conference. Note that the adjustment schedule data may indicate only other information about the adjustment schedule without indicating the date and time of the adjustment schedule. The adjustment schedule data may indicate a part of the text related to the adjustment schedule among the text indicated by the communication data.

[0065] For example, the adjustment schedule data acquisition unit 203 inputs communication data to the machine learning model M. The communication data may be input to the machine learning model M by the task determination unit 202 described above. The machine learning model M acquires a plurality of tokens and calculates an embedded expression as in the flow described above. The machine learning model M analyzes the context of the text based on the embedded expression, and identifies a portion of the text indicated by the communication data that is related to the adjustment schedule. The machine learning model M outputs adjustment schedule data indicating the identified portion. The adjustment schedule data acquisition unit 203 acquires the adjustment schedule data output from the machine learning model M.

[0066] In this embodiment, since the task determination unit 202 performs task determination, the adjustment schedule data acquisition unit 203 acquires adjustment schedule data when the task determination unit 202 determines that the task is schedule adjustment. The adjustment schedule data acquisition unit 203 does not acquire adjustment schedule data when the task determination unit 202 does not determine that the task is schedule adjustment. When the task determination unit 202 does not determine that the task is schedule adjustment, communication data may not be input to the machine learning model M.

[0067] In the case of an interactive machine learning model M, the adjustment schedule data acquisition unit 203 may input data indicating a task to be executed by the machine learning model M together with the communication data to the machine learning model M. For example, when a user selects the button B10, the adjustment schedule data acquisition unit 203 may input data indicating an instruction such as "Please identify and output the date and time, title, and memo of the adjustment schedule from this email" together with the communication data to the machine learning model M. Based on the instruction, the machine learning model M may identify each of the date and time, title, and memo of the adjustment schedule from the text indicated by the communication data. The machine learning model M outputs adjustment schedule data indicating the identified date and time, title, and memo of the adjustment schedule.

[0068] [Data Acquisition Section] The registration schedule data acquisition unit 204 acquires registration schedule data indicating a registration schedule that has already been registered in the schedule management tool. In this embodiment, since the registration schedule data is stored in the schedule management database DB3 stored in the schedule management server 30, the registration schedule data acquisition unit 204 acquires registration schedule data indicating a registration schedule in which the user currently logged in to the groupware is registered as a participant from the schedule management database DB3 stored in the schedule management server 30.

[0069] The registration schedule data may be stored in a database other than the schedule management database DB3. The registration schedule data may be stored in a computer other than the schedule management server 30. The registration schedule data acquisition unit 204 may acquire the registration schedule data from the other database or computer. For example, the registration schedule data acquisition unit 204 acquires registration schedule data indicating the date and time of scheduled registration. The registration schedule data acquisition unit 204 may acquire registration schedule data indicating information other than the date and time of scheduled registration.

[0070] [Display control section] The display control unit 205 causes various screens to be displayed on the user terminal 40. For example, the display control unit 205 causes the user terminal 40 to display the screen by transmitting display data of the screen to be displayed. When the screen is displayed on a browser, the display data of the screen is in HTML format. The display data of the screen may be in any format. For example, when the screen is displayed by a program dedicated to groupware, the display data of the screen may be in any format supported by the program.

[0071] For example, the display control unit 205 causes the user terminal 40 to display a communication screen SC1 based on the communication data. In the example at the top of Fig. 2, the display control unit 205 causes the user terminal 40 to display a communication screen SC1 indicating the contents of an email selected by the user based on the communication data of the email. When the user selects button B10 and the adjustment schedule data is acquired by the adjustment schedule data acquisition unit 203, as shown at the bottom of Fig. 2, the display control unit 205 causes the user terminal 40 to display a communication screen SC1 including the communication content and the adjustment schedule indicated by the adjustment schedule data.

[0072] For example, when the adjustment schedule data indicates the date and time of the scheduled adjustment, as shown in the lower part of FIG. 2, the display control unit 205 causes the user terminal 40 to display a communication screen SC1 including the content of the communication and a display area A11 indicating the date and time of the scheduled adjustment indicated by the adjustment schedule data. In the example shown in the lower part of FIG. 2, the content of the communication and the date and time of the scheduled adjustment indicated by the adjustment schedule data are displayed on the same communication screen SC1. When the adjustment schedule data indicates information other than the date and time of the scheduled adjustment, the display control unit 205 causes the user terminal 40 to display a communication screen SC1 indicating the other information. For example, in the example shown in the upper part of FIG. 3, the display control unit 205 causes the user terminal 40 to display a communication screen SC1 indicating a title acquired as the other information.

[0073] For example, the display control unit 205 may display a communication screen SC1 indicating the content of the communication on the user terminal 40 based on the registration schedule data. For example, the display control unit 205 executes a determination as to whether or not the user's schedule is free based on the adjustment schedule date and time indicated by the adjustment schedule data and the registration schedule date and time indicated by the registration schedule data, and displays the communication screen SC1 on the user terminal 40 based on the execution result of the determination. In the example at the top of FIG. 3, the display control unit 205 displays the execution result of the above determination in the display area A11 based on the registration schedule data and the adjustment schedule data.

[0074] For example, the display control unit 205 determines whether the date and time of the scheduled adjustment overlaps with the date and time of the scheduled registration. If they do not overlap, the display control unit 205 determines that the user has free schedule. Note that the method by which the display control unit 205 determines whether the user has free schedule is not limited to the above example. For example, the display control unit 205 may determine whether there is a scheduled registration within a predetermined time (e.g., one hour) before and after the date and time of the scheduled adjustment. The display control unit 205 determines that the user has free schedule when there is no scheduled registration within a predetermined time (e.g., one hour) before and after the date and time of the scheduled adjustment.

[0075] [Scheduled Transmission Section] The schedule sending unit 206 sends the adjusted schedule data to a schedule management tool that cooperates with the communication tool. In this embodiment, the schedule sending unit 206 sending the schedule adjustment data to the schedule management server 30 corresponds to the schedule sending unit 206 sending the adjusted schedule data to the schedule management tool. When the schedule management tool is managed by a computer other than the schedule management server 30, the schedule sending unit 206 may send the schedule adjustment data to the other computer.

[0076] For example, the schedule sending unit 206 sends the adjustment schedule data to the schedule management tool based on an operation performed on the communication screen SC1. In the examples of FIG. 2 and FIG. 3, the selection of the buttons B110 and B111 corresponds to the operation. When the user selects the button B111 after the user selects the button B110 to check the availability, the schedule sending unit 206 sends the adjustment schedule data to the schedule management tool. The operation that the user can perform on the communication screen SC1 may be any operation. The user's operation is not limited to the selection of the buttons B110 and B111. For example, the user may perform an operation on the input form for the date and time displayed in the display area A11, or may perform an operation on at least one of the input forms for the title and memo of the adjustment schedule displayed in the display area A11.

[0077] In this embodiment, if the adjustment schedule displayed on the communication screen SC1 has not been changed by the user, the schedule sending unit 206 sends the adjustment schedule data acquired by the adjustment schedule data acquiring unit 203 to the schedule management tool. In the examples of Fig. 2 and Fig. 3, if the user does not perform an operation to change the date and time in the date and time input form displayed in the display area A11, the schedule sending unit 206 sends the adjustment schedule data indicating the date and time as is to the schedule management tool.

[0078] For example, when the adjustment schedule displayed on the communication screen SC1 is changed by the user, the schedule sending unit 206 sends adjustment schedule data indicating the adjustment schedule changed by the user to the schedule management tool. In the examples of Fig. 2 and Fig. 3, when the user performs an operation to change the date and time in the date and time input form displayed in the display area A11, the schedule sending unit 206 sends adjustment schedule data indicating the changed date and time to the schedule management tool.

[0079] [Reply content generation section] When adjustment schedule data is transmitted to the schedule management tool, the reply content generation unit 207 generates reply content data indicating reply content in communication. For example, the reply content generation unit 207 generates reply content data indicating the date and time of the adjustment schedule registered in the schedule management tool as a registration schedule. The reply content generation unit 207 may also generate reply content data indicating other content that was not registered in the schedule management tool.

[0080] In the example at the bottom of Fig. 3, the reply content generation unit 207 generates reply content data indicating reply content including a greeting registered as a template, and the name and organization name of the logged-in user. The display control unit 205 transmits the reply content data generated by the reply content generation unit 207 to the user terminal 40, thereby causing the reply content to be displayed on the communication screen SC1. Data in the reply content, such as the user's affiliation and name, is assumed to be stored in advance in the data storage unit 200. The name of the person to be coordinated in the reply content, etc. may be acquired from the email that is the reply source.

[0081] The reply content generation unit 207 may generate reply content data based on the machine learning model M. In this case, the machine learning model M can execute the task of generating reply content. For example, it is assumed that the machine learning model M has learned training data including the date and time of a training schedule and a reply content that is a correct answer. The reply content generation unit 207 inputs data such as the date and time of a registration schedule registered in a schedule management tool to the machine learning model M. The machine learning model M calculates an embedded expression of the data based on parameters adjusted by learning, and outputs reply content data corresponding to the embedded expression. The reply content generation unit 207 acquires reply content data from the machine learning model M.

[0082] For example, in the case of an interactive machine learning model M, the reply content generation unit 207 may cause the machine learning model M to modify the reply content based on an instruction input by the user. For example, when the user inputs an instruction such as "Please use a more polite expression," the reply content generation unit 207 causes the machine learning model M to modify the reply content so that the generated reply content is more polite. In this case, the display control unit 205 transmits data indicating the modified reply content to the user terminal 40, and causes the modified reply content to be displayed on the communication screen SC1. The user may repeat the modification of the reply content while repeating the dialogue with the machine learning model M. The user may modify the reply content generated or modified by the machine learning model M with his or her own hand. Note that the user can input any instruction to the machine learning model M. The input instruction by the user is not limited to the above example. For example, the user may input instructions such as simplification of the reply draft, the language of the reply draft, the number of characters of the reply draft, or other instructions. The machine learning model M may change the reply content based on these instructions.

[0083] [3-3. Functions realized by the schedule management server] For example, the schedule management server 30 includes a data storage unit 300 and a schedule registration unit 301. The data storage unit 300 is realized by the storage unit 32. The schedule registration unit 301 is realized by the control unit 31.

[0084] [Data storage section] The data storage unit 300 stores data necessary for schedule management. For example, the data storage unit 300 stores a schedule management database DB3.

[0085] 8 is a diagram showing an example of the schedule management database DB3. The schedule management database DB3 is a database in which registered schedule data indicating registered schedules registered in the schedule management tool is stored. For example, the schedule management database DB3 stores a schedule ID and registered schedule data. In this embodiment, storing the schedule ID and registered schedule data in the schedule management database DB3 corresponds to registering a registered schedule in the schedule management tool.

[0086] The schedule ID is an ID that the schedule adjustment system 1 uses to uniquely identify a schedule to be registered. When a new schedule to be registered is registered in the schedule management tool, the communication server 20 generates a schedule ID for the new schedule to be registered. The communication server 20 generates registration schedule data indicating the new schedule to be registered. The communication server 20 registers the new schedule to be registered in the schedule management tool by storing the generated schedule ID and registration schedule data in the schedule management database DB3. The registration schedule data is data indicating the specific contents of the schedule to be registered. For example, the registration schedule data indicates the date and time, title, notes, participants, or a combination of these, of the schedule to be registered.

[0087] The data stored in the data storage unit 300 is not limited to the above example. The data storage unit 300 can store any data. For example, the data storage unit 300 may store data of each screen of a schedule management tool.

[0088] [Schedule Registration Department] The schedule registration unit 301 registers the adjustment schedule in the schedule management tool based on the adjustment schedule data transmitted by the schedule transmission unit 206. For example, the schedule registration unit 301 generates registration schedule data for registering the adjustment schedule as a registration schedule based on the adjustment schedule data. If the user does not change the date and time of the adjustment schedule, the registration schedule data indicates the date and time indicated by the adjustment schedule data. The participant indicated by the registration schedule data is the currently logged-in user. It may be possible for the user to specify the participant from the communication screen SC1. The schedule registration unit 301 issues a new schedule ID and registers the adjustment schedule in the schedule management tool by storing the schedule ID and the registration schedule data in the schedule management database DB3.

[0089] [3-4. Functions realized on user terminals] For example, the user terminal 40 includes a data storage unit 400, a display control unit 401, and an operation reception unit 402. The data storage unit 400 is realized by the storage unit 42. Each of the display control unit 401 and the operation reception unit 402 is realized by the control unit 41.

[0090] [Data storage section] The data storage unit 400 stores data necessary for schedule adjustment. For example, the data storage unit 400 stores a browser for displaying various screens of the schedule adjustment system 1. For example, the data storage unit 400 stores a program dedicated to groupware.

[0091] [Display control section] The display control unit 401 causes the display unit 45 to display various screens in the schedule adjustment system 1. For example, the display control unit 401 causes the display unit 45 to display screens such as the communication screen SC1 based on display data received from the communication server 20.

[0092] [Operation reception section] The operation reception unit 402 receives various operations in the schedule adjustment system 1. For example, the operation reception unit 402 receives operations on the communication screen SC1 or the schedule management screen SC2. Data indicating the operation content received by the operation reception unit 402 is transmitted to the communication server 20 as appropriate.

[0093] [4. Processing performed by the schedule adjustment system] Figures 9 and 10 are diagrams showing an example of the processing executed in the schedule adjustment system 1. The processing in Figures 9 and 10 is executed by the control units 21, 31, and 41 executing programs stored in the storage units 22, 32, and 42, respectively. It is assumed that learning of the machine learning model M is completed before the processing in Figures 9 and 10 is executed. The processing in Figures 9 and 10 is an example of the processing included in the schedule adjustment method of this embodiment.

[0094] 9, when a user selects a specific email with a communication tool, the user terminal 40 executes a process with the communication server 20 to display a communication screen SC1 showing details of the email selected by the user (S1). In S1, the communication server 20 generates display data for the communication screen SC1 based on the communication database DB2 and transmits it to the user terminal 40. The user terminal 40 receives the display data for the communication screen SC1 and displays the communication screen SC1 on the display unit 45.

[0095] When the user selects the button B10 on the communication screen SC1, the user terminal 40 transmits a support request to the communication server 20, in order for the user to request support from the machine learning model M (S2). The communication server 20 receives the support request from the user terminal 40 (S3). The communication server 20 refers to the communication database DB2 and acquires communication data of the email to be processed (displayed on the communication screen SC1) (S4). Based on the communication data, the communication server 20 executes processing between the user terminal 40 and the user terminal 40 to set the communication screen SC1 to a reply mode as shown in the lower part of FIG. 2 (S5).

[0096] The communication server 20 determines whether the task of the machine learning model M is schedule adjustment based on the communication data (S6). In S6, if it is determined that the task of the machine learning model M is not schedule adjustment (S6:N), this process ends. In this case, the processes from S7 onwards are not executed. The communication server 20 may display a message on the communication screen SC1 indicating that the machine learning model M cannot assist with schedule adjustment. In this case, the user manually replies to the email and registers the schedule in the schedule management tool from each of the communication screen SC1 and the schedule management screen SC2.

[0097] In S6, if it is determined that the task of the machine learning model M is schedule adjustment (S6: Y), the communication server 20 acquires adjustment schedule data indicating the date and time of the adjustment schedule based on the communication data and the machine learning model M (S7). In S7, the communication server 20 may also cause the machine learning model M to identify at least one of the title and memo of the schedule. The communication server 20 executes a process between the user terminal 40 and the machine learning model M for displaying the date and time of the adjustment schedule indicated by the adjustment schedule data in the display area A11 (S8). In S7, if the adjustment schedule data is not acquired, a message indicating that the adjustment schedule data has not been acquired may be displayed in the display area A11 displayed in S8.

[0098] The user terminal 40 identifies the user's operation performed from the operation unit 44 (S9). In S9, the date and time displayed in the display area A11 is changed, or the button B110 is selected. If another operation is performed, a process corresponding to the other operation is executed, and this process ends. In S9, if the user changes the date and time displayed in the display area A11 (S9: change date and time), the user terminal 40 changes the date and time of the adjustment schedule (S10). In S9, if the user selects the button B110 (S9: request for confirmation), the user terminal 40 transmits a request to confirm the schedule to the communication server 20 (S11). The request for confirmation includes data indicating the date and time displayed in the display area A11.

[0099] The communication server 20 receives a schedule confirmation request from the user terminal 40 (S12). The communication server 20 executes a process to confirm the date and time of the adjustment schedule with the schedule management server 30 (S13). In S13, the communication server 20 requests the user's registered schedule data from the schedule management server 30. The schedule management server 30 refers to the schedule management database DB3, acquires the user's registered schedule data, and transmits it to the communication server 20. The communication server 20 determines whether the date and time of the adjustment schedule is available or not based on the date and time of the adjustment schedule and the date and time indicated by the user's registered schedule data.

[0100] The communication server 20 judges whether the processing result of S13 indicates that the scheduled adjustment date and time is available (S14). If it is judged in S14 that the scheduled adjustment date and time is not available (S14: N), the process proceeds to Fig. 10, and the communication server 20 executes processing between the user terminal 40 and the communication server 20 for displaying a message indicating that the scheduled adjustment date and time is not available on the communication screen SC1 (S15). In this case, the user changes the scheduled adjustment date and time as necessary.

[0101] 10, the communication server 20 executes a process between the user terminal 40 and the user terminal 40 to display a message indicating that the date and time of the adjustment is available based on the adjustment schedule data (S16). If at least one of the title and memo of the schedule is specified in S7, at least one of the title and memo of the schedule is displayed in the display area A11 by the process of S16.

[0102] The user terminal 40 identifies the user's operation performed from the operation unit 44 (S17). In S17, the date and time displayed in the display area A11 is changed, or the button B111 for sending the adjustment schedule is selected. If another operation is performed, a process corresponding to the other operation is executed, and this process ends. In S17, if the user changes the date and time displayed in the display area A11 (S17: change date and time), the user terminal 40 changes the date and time of the adjustment schedule (S18). Thereafter, the process proceeds to S11, and the schedule is confirmed.

[0103] In S17, when the user selects the button B111 for sending the adjustment schedule (S17: Send), the user terminal 40 sends a request to send the adjustment schedule data to the communication server 20 (S19). The send request is data in a predetermined format for the user terminal 40 to request the communication server 20 to send the adjustment schedule data. The communication server 20 receives the send request from the user terminal 40 (S20). The communication server 20 sends the adjustment schedule data to the schedule management server 30 (S21). In S21, if the user has not changed the date and time of the adjustment schedule, the communication server 20 sends the adjustment schedule data acquired in S7 as is. If the user has changed the date and time of the adjustment schedule, the communication server 20 sends adjustment schedule data indicating the changed date and time.

[0104] The schedule management server 30 receives the adjustment schedule data from the communication server 20 (S22). The schedule management server 30 registers the adjustment schedule in the schedule management tool based on the adjustment schedule data (S23). In S23, the schedule management server 30 issues a new schedule ID and creates a new record in the schedule management database DB3. The schedule management server 30 generates registration schedule data for registering the adjustment schedule as a new registration schedule based on the adjustment schedule data, and stores the generated registration schedule data in the new record.

[0105] The communication server 20 generates reply content data based on the adjusted schedule data transmitted to the schedule management tool (S24). The communication server 20 executes a process between the user terminal 40 for displaying the reply content indicated by the reply content data on the communication screen SC1 (S25). The user terminal 40 identifies the user's operation performed from the operation unit 44 (S26). In S26, the button B112 for changing the reply content or the button B12 for sending an e-mail is selected. If another operation is performed, a process corresponding to the other operation is executed, and this process ends.

[0106] In S26, if the user selects the button B112 for changing the reply content (S26: Change), the user terminal 40 executes a process for causing the machine learning model M to change the reply content with the communication server 20 (S27), and returns to the process of S26. In S26, if the user selects the button B12 for sending an email (S26: Send), the user terminal 40 executes a process for sending an email with the communication server 20 (S28), and this process ends. Sending an email may be executed by a known process.

[0107] [5. Summary of the embodiment] The schedule adjustment system 1 of this embodiment acquires adjustment schedule data indicating an adjustment schedule based on communication data and a machine learning model M capable of language analysis. The schedule adjustment system 1 transmits the adjustment schedule data to a schedule management tool linked to a communication tool. In this way, the schedule adjustment system 1 can eliminate the need for a user to register an adjustment schedule in the schedule management tool, thereby improving user convenience. For example, the person making the adjustment does not create an email in a predetermined format, but basically inputs text freely. The schedule adjustment system 1 can acquire adjustment schedule data by utilizing language analysis by the machine learning model M, even if the email does not have such a format. The schedule adjustment system 1 can handle various emails, thereby realizing highly versatile schedule adjustment support.

[0108] Furthermore, the schedule adjustment system 1 registers the adjustment schedule in the schedule management tool based on the adjustment schedule data transmitted by the schedule transmission unit 206. This allows the schedule adjustment system 1 to execute a series of steps from acquiring the adjustment schedule data from email to registering the adjustment schedule in the schedule management tool.

[0109] Furthermore, the schedule adjustment system 1 acquires adjustment schedule data indicating the date and time of the adjustment schedule and other information about the adjustment schedule. The schedule adjustment system 1 can eliminate the need for the user to register not only the date and time of the adjustment schedule but also other information in the schedule management tool, and can therefore effectively improve user convenience. For example, if the schedule adjustment system 1 registers the schedule title and notes as other information about the adjustment schedule in the schedule management tool, the user does not need to manually input the schedule title and notes, and can therefore effectively improve user convenience. Even if the schedule title and notes identified by the machine learning model M are somewhat incorrect, the user only needs to slightly correct the error, and therefore the schedule adjustment system 1 can improve user convenience.

[0110] Furthermore, if the adjustment schedule displayed on the communication screen SC1 has not been changed by the user, the schedule adjustment system 1 transmits the adjustment schedule data acquired by the adjustment schedule data acquisition unit 203 to the schedule management tool. If the adjustment schedule displayed on the communication screen SC1 has been changed by the user, the schedule adjustment system 1 transmits adjustment schedule data indicating the adjustment schedule changed by the user to the schedule management tool. This allows the user to check the adjustment schedule identified by the machine learning model M while checking the email on the communication screen SC1, and to change the adjustment schedule as necessary, so that the schedule adjustment system 1 can effectively improve the user's convenience. For example, the user can register the adjustment schedule in the schedule management tool and reply to the email without going back and forth between the schedule management tool and the communication tool. For example, the user can make changes such as setting a longer time for the schedule, taking into account the content that cannot be read from the text of the email.

[0111] Furthermore, the schedule adjustment system 1 causes a communication screen SC1 showing the content of the communication based on the registered schedule data to be displayed on the user terminal 40. The schedule adjustment system 1 registers the adjusted schedule in the schedule management tool based on the operation performed on the communication screen SC1. This allows the schedule adjustment system 1 to register the adjusted schedule in the schedule management tool after having the user confirm some information about the registered schedule registered in the schedule management tool, making it easier to prevent double bookings or lateness, and effectively improving user convenience.

[0112] Furthermore, the schedule adjustment system 1 judges whether the user's schedule is free or not based on the date and time of the adjustment schedule indicated in the adjustment schedule data and the date and time of the registration schedule indicated in the registration schedule data, and displays a communication screen SC1 on the user terminal 40 based on the result of the judgment. This allows the schedule adjustment system 1 to register the adjustment schedule in the schedule management tool after having the user confirm some information of the registration schedule registered in the schedule management tool, thereby more reliably preventing double bookings, lateness, and the like.

[0113] Furthermore, the schedule adjustment system 1 determines whether the task of the machine learning model M is schedule adjustment based on the communication data. When it is determined that the task is schedule adjustment, the schedule adjustment system 1 acquires adjusted schedule data. The schedule adjustment system 1 can prevent unnecessary processing from being performed on emails unrelated to schedule adjustment, thereby reducing the processing load on the communication server 20. The schedule adjustment system 1 can also prevent text unrelated to schedule adjustment from being acquired from emails unrelated to schedule adjustment, resulting in an erroneous schedule being registered in the schedule management tool.

[0114] Furthermore, when adjustment schedule data is sent to the schedule management tool, the schedule adjustment system 1 generates reply content data indicating reply content in communication. This allows the schedule adjustment system 1 to save the user the trouble of creating a reply to the person with whom the adjustment is being made, thereby effectively improving user convenience.

[0115] [6. Modifications] The present disclosure is not limited to the above-described embodiment, and may be modified as appropriate without departing from the spirit and scope of the present disclosure.

[0116] [6-1. Variation 1] For example, the machine learning model M may identify multiple dates and times for an adjustment schedule from an email. In this case, the display control unit 205 may select one of the multiple dates and times and display the selected one date and time in the display area A11, but in the first modification, the display control unit 205 displays each of the multiple dates and times in the display area A11. The user may select a date and time to register in the schedule management tool from the multiple dates and times displayed in the display area A11.

[0117] 11 is a diagram showing an example of a communication screen SC1 of Modification 1. The adjustment schedule data acquisition unit 203 of Modification 1 acquires adjustment schedule data indicating multiple adjustment schedule dates and times. For example, the machine learning model M identifies at least one date and time from text indicated by the communication data based on an embedded expression calculated from the communication data input to itself. When the machine learning model M identifies multiple dates and times, it outputs adjustment schedule data indicating the multiple dates and times. The adjustment schedule data acquisition unit 203 acquires the adjustment schedule data output from the machine learning model M.

[0118] The display control unit 205 of the first modified example causes the user terminal 40 to display a communication screen SC1 including the content of the communication performed using the communication tool and multiple dates and times indicated by the adjustment schedule data. For example, the display control unit 205 causes the user terminal 40 to display a communication screen SC1 including a display area A11 in which any one of multiple dates and times can be selected. In the example of the communication screen SC1 in FIG. 11, a case where the date and time are selected using a radio button is shown, but the display control unit 205 may display the date and time in a selectable manner using any method. For example, the display control unit 205 may display the date and time in a selectable manner using a check box, a pull-down, or another form.

[0119] The schedule sending unit 206 in the first modification sends to the schedule management tool schedule adjustment data indicating a date and time selected by the user from among the multiple dates and times indicated in the adjusted schedule data. For example, when the user selects one of the multiple dates and times and presses button B110 in the state of the communication screen SC1 in Fig. 11, the schedule sending unit 206 checks the availability of the selected date and time, and then sends the schedule adjustment data indicating the selected date and time to the schedule management tool. This differs from the embodiment in that adjustment schedule data indicating the date and time selected by the user from among the multiple dates and times is sent to the schedule management tool, but the process for sending the adjustment schedule data is as described in the embodiment.

[0120] The schedule adjustment system 1 of the first modified example acquires adjustment schedule data indicating multiple dates and times for an adjustment schedule. The schedule adjustment system 1 displays a communication screen SC1 including the content of the communication made using the communication tool and the multiple dates and times indicated by the adjustment schedule data. The schedule adjustment system 1 transmits to the schedule management tool schedule adjustment data indicating a date and time selected by the user from the multiple dates and times indicated in the adjustment schedule data. The schedule adjustment system 1 can allow the user to select a desired date and time even if the email includes multiple dates and times, thereby effectively improving user convenience.

[0121] [6-2. Variation 2] For example, the communication screen SC1 displayed based on the registration schedule data is not limited to the example of the embodiment. In Modification 2, another aspect of the communication screen SC1 displayed based on the registration schedule data will be described. The display control unit 205 of Modification 2 identifies a registration schedule at least one of before and after the date and time of the adjustment schedule indicated by the adjustment schedule data based on the registration schedule data, and causes the user terminal 40 to display the communication screen SC1 indicating the identified registration schedule.

[0122] 12 is a diagram showing an example of a communication screen SC1 of Modification 2. For example, the display control unit 205 determines whether or not there is a registration schedule within at least one of a predetermined time (e.g., 3 hours) before and after the date and time of the adjustment schedule based on the registration schedule data. When it is determined that there is a registration schedule within the predetermined time, the display control unit 205 displays the registration schedule in the display area A11. In Modification 2, an example is given in which both registration schedules before and after the date and time of the adjustment schedule are subject to judgment, but the judgment may be directed to either the registration schedule before or after the date and time of the adjustment schedule.

[0123] In the example of FIG. 12, the display control unit 205 identifies a registration schedule that ends 30 minutes before the start date and time of the adjustment schedule and a registration schedule that starts one hour after the date and time of the adjustment schedule, and displays these two registration schedules in the display area A11. The user checks the display area A11 and changes the date and time of the adjustment schedule as necessary. The user may change the date and time of the registration schedule without changing the date and time of the adjustment schedule. Note that the display control unit 205 may determine a registration schedule that has the same date as the date and time of the adjustment schedule. The period that the display control unit 205 determines is not limited to the example described in the second modification example, and may be any period.

[0124] The schedule adjustment system 1 of the second modification example identifies a registration schedule at least one of before and after the date and time of the adjustment schedule indicated by the adjustment schedule data, based on the registration schedule data, and displays a communication screen SC1 showing the identified registration schedule on the user terminal 40. This allows the user to register the adjustment schedule in the schedule management tool while checking the registration schedule at least one of before and after the date and time of the adjustment schedule, so the schedule adjustment system 1 can effectively improve user convenience. For example, the user can decide the date and time of the adjustment schedule taking into consideration the travel time from the location of the registration schedule before the adjustment schedule, or the travel time to the location of the registration schedule after the adjustment schedule.

[0125] [6-3. Variation 3] For example, the display control unit 205 may cause the user terminal 40 to display a communication screen SC1 including movement possibility information indicating the possibility of movement based on the date and time and location of the adjustment schedule indicated by the adjustment schedule data and the date and time and location of the registration schedule indicated by the registration schedule data. The movement possibility information is information indicating whether or not the user will be able to make it from the location of the adjustment schedule to the location of the next registration schedule of the adjustment schedule in time. The movement possibility information may also indicate whether or not the user will be able to make it from the registration schedule before the adjustment schedule to the location of the adjustment schedule.

[0126] FIG. 13 is a diagram showing an example of a communication screen SC1 of Modification 3. For example, the display control unit 205 calculates a travel time between a location to be adjusted and at least one of the locations to be registered before and after the location. A known route search algorithm can be used to calculate the travel time. The route search algorithm may calculate a travel time when a user uses a public transportation such as a train or a bus. The route search algorithm may be one adopted in a known map application. The display control unit 205 may calculate the travel time using a known map application.

[0127] For example, each of the location to be adjusted indicated by the adjustment schedule data and the location to be registered indicated by the registration schedule data may indicate an address or latitude and longitude, or may indicate information from which a route search algorithm can estimate an address or latitude and longitude (e.g., a company name or building name). In Modification Example 3, the machine learning model M identifies the location to be adjusted from the body of the email. The training data for the machine learning model M indicates the training location described in the body of the training email. The machine learning model M has learned the training data. The machine learning model M analyzes the body of the email indicated by the communication data, identifies the location described in the body, and outputs the adjustment schedule data.

[0128] For example, the display control unit 205 calculates the time interval between the date and time of the adjustment schedule and the date and time of at least one of the registration schedules before and after the adjustment schedule. At least one of the registration schedules before and after the adjustment schedule may be specified in the same manner as in the second modification. The time interval may be the interval between the start date and time of the adjustment schedule and the end date and time of the registration schedule before the adjustment schedule, or the interval between the end date and time of the adjustment schedule and the start date and time of the registration schedule after the adjustment schedule. The display control unit 205 executes a determination as to whether the calculated movement time is equal to or greater than the calculated time interval. The display control unit 205 causes the movement possibility information to be displayed in the display area A11 based on the execution result of the determination.

[0129] For example, when the calculated travel time is less than the calculated time interval, the display control unit 205 displays travel possibility information indicating that travel is possible in the display area A11. In the example of FIG. 13, the travel time to the location of the next registration schedule of the adjustment schedule is 15 minutes. The time interval between the adjustment schedule and the next registration schedule is one hour. Since the travel time of 15 minutes is shorter than the time interval of one hour, the display control unit 205 displays travel possibility information indicating that travel is possible to the location of the next registration schedule in the display area A11. Conversely, when the calculated travel time is equal to or greater than the calculated time interval, the display control unit 205 displays travel possibility information indicating that travel is not possible in the display area A11.

[0130] The schedule adjustment system 1 of the third modification causes the user terminal 40 to display a communication screen SC1 including movement possibility information indicating the possibility of movement based on the date, time, and location of the adjustment schedule indicated by the adjustment schedule data and the date, time, and location of the registration schedule indicated by the registration schedule data. The schedule adjustment system 1 can allow the user to understand the movement possibility on the communication screen SC1, thereby improving user convenience. For example, the schedule adjustment system 1 can prevent the user from being late for an adjustment schedule or being late for the next registration schedule.

[0131] [6-4. Variation 4] For example, an email that has been replied to multiple times may contain multiple dates and times that the user has provided in the past, or a date and time that did not match up with a schedule. An email may also contain other dates and times, such as the date and time of the email reply. In this case, since the machine learning model M may identify an incorrect date and time, only the part of the email that is likely to be the date and time of the adjustment schedule may be processed by the machine learning model M.

[0132] The adjustment-to-be-adjusted data acquisition unit 203 of the fourth modification example determines a processing target portion to be processed by the machine learning model M from within the communication data, and acquires adjustment-to-be-adjusted data based on the machine learning model M and the processing target portion. The processing target portion is a portion of the text indicated by the communication data. For example, the processing target portion is a relatively new portion of the text indicated by the communication data. In the case of an email, the processing target portion is a relatively new portion of the reply content contained in the email. Similarly, for other communication tools such as chat, the processing target portion may be a relatively new portion of the reply content.

[0133] In the fourth modification, an example is taken of a case where the latest reply portion of an email to which replies are repeated corresponds to the portion to be processed. In the example of the email at the top of FIG. 2, the portion before the portion indicating the user's reply (in FIG. 2, the portion before the line beginning with "2023 / 10 / 20 10:45") is the content of the most recent reply, and so this portion corresponds to the portion to be processed. For example, the adjustment schedule data acquisition unit 203 identifies the portion to be processed based on the position of the quotation marks indicating the reply (in FIG. 2, the symbol "|")

[0134] The adjustment scheduled data acquisition unit 203 may specify a portion up to a predetermined number of lines from the top as the processing target portion, instead of the position of the quotation marks, or may specify a portion up to the line immediately preceding the line in which the email address was found in the body of the email as the processing target portion. The adjustment scheduled data acquisition unit 203 may specify a portion of the email other than the reply date and time as the processing target portion.

[0135] For example, the adjustment schedule data acquisition unit 203 inputs a processing target portion of text indicated by communication data to the machine learning model M. The machine learning model M divides the processing target portion into a plurality of tokens and calculates an embedded expression. The machine learning model M outputs adjustment schedule data indicating the date and time of the adjustment schedule included in the processing target portion based on the calculated embedded expression. The adjustment schedule data acquisition unit 203 acquires the adjustment schedule data output from the machine learning model M. This embodiment differs from the embodiment in that the entire email is not processed by the machine learning model M, but the internal processing of the machine learning model M may be similar to that of the embodiment.

[0136] In addition, when the machine learning model M cannot identify the date and time of the scheduled adjustment from the processing target portion, the adjustment schedule data acquisition unit 203 may input all or a part of the text indicated by the communication data other than the processing target portion to the machine learning model M. For example, the adjustment schedule data acquisition unit 203 may input a portion indicating the most recent reply to the email (in FIG. 2, the portion replied by the user Saibo Taro at "2023 / 10 / 20 10:45") to the machine learning model M. That is, the adjustment schedule data acquisition unit 203 may input relatively new processing target portions to the machine learning model M one after another until the machine learning model M identifies a certain date and time.

[0137] The schedule adjustment system 1 of the fourth modification determines a processing target portion to be processed by the machine learning model M from within the communication data, and acquires adjustment schedule data based on the machine learning model M and the processing target portion. The schedule adjustment system 1 can acquire adjustment schedule data with high accuracy. For example, the schedule adjustment system 1 can prevent an incorrect date and time from being identified from an email that has received repeated replies.

[0138] [6-5. Variation 5] For example, in the embodiment, an example is given of a case where adjustment schedule data is acquired from emails managed by groupware. A user may adjust schedules using other communication tools such as chat or threads in addition to email. For this reason, the schedule adjustment system 1 may be adapted to support each of a plurality of communication tools.

[0139] The communication data acquisition unit 201 of the fifth modification acquires communication data of each of a plurality of communication tools. The plurality of communication tools may be tools of the same groupware, or may be tools that are not particularly related to groupware. In the fifth modification, the communication data acquisition unit 201 acquires communication data of each of a first communication tool that is an email and a second communication tool that is a chat, as an example. The communication data acquisition unit 201 may acquire communication data from each of three or more communication tools. The communication data of each communication tool may be stored in the data storage unit 200, or may be stored in a computer other than the communication server 20.

[0140] The adjustment-scheduled data acquisition unit 203 of the fifth modified example specifies a communication tool from which communication data has been acquired among a plurality of communication tools, and acquires adjustment-scheduled data based on the specified communication tool. For example, when a separate machine learning model M is prepared for each communication tool, the adjustment-scheduled data acquisition unit 203 acquires adjustment-scheduled data based on the machine learning model M corresponding to the communication tool from which communication data has been acquired. Each machine learning model M is assumed to have learned training data created from communication data of the communication tool corresponding to the machine learning model M. Therefore, each machine learning model M has learned the tendency of the communication tool corresponding to the machine learning model M. The internal processing of each machine learning model M may be the same as the internal processing described in the embodiment.

[0141] For example, when one machine learning model M can handle multiple communication tools, the adjustment schedule data acquisition unit 203 inputs not only the communication data but also data indicating the communication tool from which the communication data was acquired to the machine learning model M. The input portion of the training data for the machine learning model M also includes data indicating the communication tool. The machine learning model M is assumed to have been trained so that, when training communication data and data indicating the communication tool corresponding to the communication data are input, the machine learning model M outputs the date and time, etc., included in the text indicated by the communication data. The adjustment schedule data acquisition unit 203 acquires the adjustment schedule data output from the machine learning model M.

[0142] The schedule adjustment system 1 of the fifth modification specifies a communication tool from which communication data has been acquired among a plurality of communication tools, and acquires adjustment schedule data based on the specified communication tool. This allows the schedule adjustment system 1 to handle a plurality of communication tools, thereby effectively improving user convenience. For example, if email is written in a formal style and chat is written in a casual style, the machine learning model M can understand the difference between these styles and specify an adjustment schedule, thereby increasing the accuracy with which the machine learning model M specifies an adjustment schedule.

[0143] [6-6. Other Modifications] For example, two or more of the modifications 1 to 5 may be combined.

[0144] For example, although the example has been given in which the schedule adjustment system 1 includes the learning terminal 10, the schedule adjustment system 1 may not include the learning terminal 10 and may not need to learn the machine learning model M. In this case, the schedule adjustment system 1 may acquire adjustment schedule data based on a known machine learning model M that is provided free of charge or for a fee. The schedule adjustment system 1 may transmit the adjustment schedule data to the schedule management tool without displaying the adjustment schedule indicated by the adjustment schedule data on the communication screen SC1. The schedule adjustment system 1 may transmit the adjustment schedule data to the schedule management tool without checking whether the user is free or not.

[0145] For example, at least one of the communication tool and the schedule management tool may be a tool that is not related to groupware. In the embodiment and the modifications 1 to 5, the case where the user presents candidate dates and times for the adjustment schedule to the person to be adjusted is taken as an example, but the schedule adjustment system 1 may obtain adjustment schedule data indicating the date and time of the adjustment schedule by the same process as in the embodiment and the modifications 1 to 5 even when the person to be adjusted presents candidate dates and times for the adjustment schedule to the user.

[0146] For example, a business providing a communication tool to a user may be different from a business providing a schedule management tool to a user. In this case, these businesses are assumed to cooperate with each other. A communication server 20 managed by a certain business transmits adjustment schedule data to a schedule management server 30 managed by another business. The schedule management server 30 managed by the other business registers an adjustment schedule in a schedule management tool managed by the other business based on the adjustment schedule data. In such a case, a series of steps of acquiring adjustment schedule data, transmitting adjustment schedule data, and registering the adjustment schedule may be performed by executing the same processes as those in the embodiment and the first to fifth modifications. In this case, the schedule adjustment system 1 may not include the schedule registration unit 301. The schedule registration unit 301 may be realized by a system external to the schedule adjustment system 1.

[0147] For example, a single server computer may manage both a communication tool and a schedule management tool. In this case, within the server computer, adjustment schedule data is transmitted from the communication tool to the schedule management tool. This transmission is performed by inter-process communication or the like. A server computer transmits adjustment schedule data from a communication tool stored therein to a schedule management tool stored therein by internal communication. When adjustment schedule data is transmitted by internal communication, this server computer registers the adjustment schedule in the schedule management tool.

[0148] For example, the functions described as being realized by the communication server 20 may be realized by the user terminal 40. In this case, the functions may be realized by a browser script or an application installed in the user terminal 40. For example, each function may be shared by multiple computers, or may be realized by a single computer. [Explanation of symbols]

[0149] 1 Schedule adjustment system, 10 Learning terminal, 11, 21, 31, 41 Control unit, 12, 22, 32, 42 Memory unit, 13, 23, 33, 43 Communication unit, 20 Communication server, 30 Schedule management server, 40 User terminal, 14, 44 Operation unit, 15, 45 Display unit, M Machine learning model, N Network, A11 Display area, B10, B12, B110, B111, B112 Button, DB1 Training database, DB2 Communication database, DB3 Schedule management database, SC1 Communication screen, SC2 Schedule management screen, 100 Data storage unit, 101 Learning unit, 200 Data storage unit, 201 Communication data acquisition unit, 202 Task judgment unit, 203 Adjustment schedule data acquisition unit, 204 Registration schedule data acquisition unit, 205 Display control unit, 206 Schedule transmission unit, 207 A reply content generating unit, 300 a data storage unit, 301 a schedule registration unit, 400 a data storage unit, 401 a display control unit, 402 an operation receiving unit.

Claims

1. a communication data acquisition unit that acquires communication data indicating the content of communication performed using the communication tool; a selection receiving unit that receives a selection of either a first reply using a machine learning model capable of language analysis or a second reply not using the machine learning model; an adjustment schedule data acquisition unit that acquires, when the first reply is selected, adjustment schedule data indicating an adjustment schedule to be adjusted by the communication, based on the communication data and the machine learning model; a display control unit that displays the content of the adjustment schedule indicated by the adjustment schedule data on a communication screen that accepts input of reply content in the first reply; a schedule sending unit that, when an instruction to register the adjustment schedule in a schedule management tool linked to the communication tool is given on the communication screen, registers the adjustment schedule in the schedule management tool by sending the adjustment schedule data to the schedule management tool; Including, the display control unit, when an instruction to register the adjustment schedule in the schedule management tool is received, automatically generates a reply content corresponding to the adjustment schedule and displays the reply content on the communication screen; a reply unit that, when a reply is instructed on the communication screen, replies with the reply content displayed on the communication screen, Scheduling system.

2. the schedule adjustment system further includes a schedule registration unit that registers the adjustment schedule in the schedule management tool based on the adjustment schedule data transmitted by the schedule transmission unit. The schedule adjustment system of claim 1 .

3. The adjustment schedule data acquisition unit acquires the adjustment schedule data indicating a date and time of the adjustment schedule and other information of the adjustment schedule.

3. The schedule adjustment system according to claim 1 or 2.

4. the schedule adjustment system further includes a display control unit that causes a communication screen including content of the communication and the adjustment schedule indicated by the adjustment schedule data to be displayed on a user terminal; The scheduled transmission unit is if the adjustment schedule displayed on the communication screen has not been changed by the user, transmitting the adjustment schedule data acquired by the adjustment schedule data acquisition unit to the schedule management tool; when the adjustment schedule displayed on the communication screen is changed by the user, the adjustment schedule data indicating the adjustment schedule changed by the user is transmitted to the schedule management tool.

3. The schedule adjustment system according to claim 1 or 2.

5. the adjustment schedule data acquisition unit acquires the adjustment schedule data indicating a plurality of dates and times of the adjustment schedule; the schedule adjustment system further includes a display control unit that causes a user terminal to display a communication screen including content of the communication tool and the plurality of dates and times indicated by the adjustment schedule data; the schedule transmission unit transmits, to the schedule management tool, the adjustment schedule data indicating the date and time selected by a user from the plurality of dates and times indicated by the adjustment schedule data.

3. The schedule adjustment system according to claim 1 or 2.

6. The schedule adjustment system comprises: a registration schedule data acquisition unit that acquires registration schedule data indicating registration schedules that have been registered in the schedule management tool; a display control unit that displays a communication screen showing the content of the communication on a user terminal based on the registration schedule data; Further comprising: the schedule transmission unit transmits the adjusted schedule data to the schedule management tool based on an operation performed on the communication screen.

3. The schedule adjustment system according to claim 1 or 2.

7. the adjustment schedule data acquisition unit acquires the adjustment schedule data indicating a date and time of the adjustment schedule; The registration schedule data acquisition unit acquires the registration schedule data indicating a date and time of the registration schedule, the display control unit determines whether or not the user's schedule is free based on the date and time of the adjustment schedule indicated by the adjustment schedule data and the date and time of the registration schedule indicated by the registration schedule data, and causes the communication screen to be displayed on the user terminal based on a result of the determination. The schedule adjustment system of claim 6.

8. the adjustment schedule data acquisition unit acquires the adjustment schedule data indicating a date and time of the adjustment schedule; The registration schedule data acquisition unit acquires the registration schedule data indicating a date and time of the registration schedule, the display control unit, based on the registration schedule data, specifies the registration schedule at least one of before and after the date and time of the adjustment schedule indicated by the adjustment schedule data, and causes the communication screen indicating the specified registration schedule to be displayed on the user terminal. The schedule adjustment system of claim 6.

9. The adjustment schedule data acquisition unit acquires the adjustment schedule data indicating a date and time of the adjustment schedule and a location of the adjustment schedule, The registration schedule data acquisition unit acquires the registration schedule data indicating the date and time of the registration schedule and the location of the registration schedule, the display control unit causes the user terminal to display the communication screen including movement possibility information indicating a movement possibility, based on the date and time and the location of the adjustment schedule indicated by the adjustment schedule data and the date and time and the location of the registration schedule indicated by the registration schedule data. The schedule adjustment system of claim 6.

10. The schedule adjustment system further includes a task determination unit that determines whether a task of the machine learning model is schedule adjustment based on the communication data, the adjustment schedule data acquisition unit acquires the adjustment schedule data when the task is determined to be the schedule adjustment; 3. The schedule adjustment system according to claim 1 or 2.

11. A communication data acquisition unit that acquires communication data indicating the content of communication performed using a communication tool; an adjustment schedule data acquisition unit that determines a processing target portion to be processed by a machine learning model capable of language analysis based on a position of a quotation mark indicating a reply included in the content indicated by the communication data, and acquires adjustment schedule data indicating an adjustment schedule to be adjusted by the communication based on the machine learning model and the processing target portion; a schedule transmission unit that transmits the adjusted schedule data to a schedule management tool that cooperates with the communication tool; A scheduling system including:

12. the schedule adjustment system further includes a reply content generation unit that generates reply content data indicating a reply content in the communication when the adjusted schedule data is transmitted to the schedule management tool; 3. The schedule adjustment system according to claim 1 or 2.

13. the communication data acquisition unit acquires the communication data for each of the plurality of communication tools; the adjustment schedule data acquisition unit identifies the communication tool from which the communication data has been acquired among the plurality of communication tools, and acquires the adjustment schedule data based on the identified communication tool; 3. The schedule adjustment system according to claim 1 or 2.

14. A computer comprising: Acquire communication data indicating the content of communications made through the communication tool; Accepting a selection of either a first reply using a machine learning model capable of language analysis or a second reply not using the machine learning model; When the first reply is selected, adjustment schedule data indicating an adjustment schedule to be adjusted by the communication is acquired based on the communication data and the machine learning model; displaying the content of the adjustment schedule indicated by the adjustment schedule data on a communication screen that accepts input of reply content in the first reply; when an instruction to register the adjustment schedule in a schedule management tool linked to the communication tool is given on the communication screen, the adjustment schedule data is transmitted to the schedule management tool, thereby registering the adjustment schedule in the schedule management tool; when an instruction is given to register the adjustment schedule in the schedule management tool, automatically generating a reply content according to the adjustment schedule and displaying the reply content on the communication screen; When a reply is instructed on the communication screen, a reply is made with the reply content displayed on the communication screen. How to adjust schedule.

15. a communication data acquisition unit for acquiring communication data indicating the content of communication carried out using the communication tool; a selection receiving unit that receives a selection of either a first reply using a machine learning model capable of language analysis or a second reply not using the machine learning model; an adjustment schedule data acquisition unit that acquires, when the first reply is selected, adjustment schedule data indicating an adjustment schedule to be adjusted by the communication, based on the communication data and the machine learning model; a display control unit that displays the content of the adjustment schedule indicated by the adjustment schedule data on a communication screen that accepts input of reply content in the first reply; a schedule sending unit that, when an instruction to register the adjustment schedule in a schedule management tool linked to the communication tool is given on the communication screen, registers the adjustment schedule in the schedule management tool by sending the adjustment schedule data to the schedule management tool; The computer functions as the display control unit, when an instruction to register the adjustment schedule in the schedule management tool is received, automatically generates a reply content corresponding to the adjustment schedule and displays the reply content on the communication screen; a reply unit that replies with the reply content displayed on the communication screen when a reply is instructed on the communication screen; A program for causing the computer to function as a

Images