Text generation device, text generation method, and program

Abstract

To provide a text generation device that assists a person engaged in an operation in decision making and business operation.SOLUTION: A text generation device 100 comprises: an operation information acquisition unit 101 that acquires operation information after the change of a transportation device; a management unit 102 that manages the operation information for each unique number of the transportation device; and a first generation unit 103 that generates a text for notifying a person engaged in an operation of the transportation device of the unique number, of the operation information for each attribute of the person.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a text generation device, a text generation method, and a program. [Background technology]

[0002] There is a technology for issuing instructions to each crew member when a train operation disorder occurs. For example, Patent Document 1 discloses a method for transmitting a train operation rescheduling plan to change or modify the train schedule to station staff, drivers, and conductors in order to ensure safe operation when the train schedule is disrupted due to an accident, breakdown, etc. Patent Document 2 discloses an operation information distribution device and operation information distribution method that can automatically instruct each crew member on the appropriate work content when a train operation disorder occurs. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2003-072554 A [Patent Document 2] JP 2011-063213 A Summary of the Invention [Problem to be solved by the invention]

[0004] The invention disclosed in Patent Document 1 is based on the premise that the same train rescheduling plan is communicated to all parties involved in train operation. The invention disclosed in Patent Document 2 is based on the premise that only the crew members on board the vehicle are instructed on the work content. When the operation schedule of transportation equipment, including trains, is changed, the content that needs to be notified varies depending on the position of the parties involved in the operation of the transportation equipment. In this case, it is time-consuming to generate notification messages individually for each party. Therefore, a method for efficiently notifying each party of changes in operation information is required.

[0005] An object of the present invention is to efficiently generate a message to notify each of the relevant parties of changed operation information. [Means for solving the problem]

[0006] A text generation device in one embodiment of the present invention includes an operation information acquisition means for acquiring operation information after a change has been made to a transport equipment, a management means for managing operation information for each unique number of the transport equipment, and a generation means for generating text to notify of the operation information for each attribute of a person involved in the operation of the transport equipment with the unique number.

[0007] In one embodiment of the present invention, a text generation method involves a computer acquiring operation information after a change has been made to a transport equipment, managing the operation information for each unique number of the transport equipment, and generating text to notify the operation information for each attribute of a person involved in the operation of the transport equipment with the unique number.

[0008] A program in one embodiment of the present invention causes a computer to execute a process of acquiring operation information after a change has been made to a transport equipment, managing the operation information for each unique number of the transport equipment, and generating text to notify the operation information for each attribute of a person involved in the operation of the transport equipment with the unique number. Effect of the Invention

[0009] According to the present invention, a document for notifying each relevant person about changed operation information can be efficiently generated. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram of a configuration including a sentence generation device according to the present disclosure. [Diagram 2] FIG. 2 is a diagram showing a hardware configuration in which the text generation device according to the present disclosure is realized by a computer device and its peripheral devices. [Diagram 3] FIG. 3 is an example of managing operation information in this disclosure. [Figure 4] FIG. 4 shows another example of managing operation information in the present disclosure. [Diagram 5] FIG. 5 shows another example of management of operation information in the present disclosure. [Figure 6] FIG. 6 shows an example of generating a sentence for notifying train operation information in this disclosure. [Figure 7] FIG. 7 shows an example of generating a sentence for notifying train operation information in this disclosure. [Figure 8] FIG. 8 shows an example of generating a sentence for notifying train operation information in this disclosure. [Figure 9] FIG. 9 is a flowchart showing an outline of the operation of the sentence generation device according to the present disclosure. [Figure 10] FIG. 10 is a block diagram including the configuration of a sentence generation device according to the present disclosure. [Figure 11] FIG. 11 is a flowchart showing an outline of the operation of the sentence generation device according to the present disclosure. [Figure 12] FIG. 12 is a block diagram including the configuration of a sentence generation device according to the present disclosure. [Figure 13] FIG. 13 is an example of a sentence for notifying schedule information generated by the second generating unit in this disclosure. [Figure 14] FIG. 14 is a flowchart showing an outline of the operation of the sentence generation device according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] First Embodiment Hereinafter, an embodiment of the present invention will be described with reference to the drawings. However, the embodiment is not limited to the description of the drawings.

[0012] Fig. 1 is a block diagram including a configuration of a text generation device 100 in the first embodiment. When an operational failure occurs in a transport equipment and an operation schedule needs to be changed, the text generation device 100 is used to generate text to notify each person involved in the transport equipment of the changed operation information. As shown in Fig. 1, the text generation device 100 includes an operation information acquisition unit 101, a management unit 102, and a first generation unit 103.

[0013] In this embodiment, the transportation equipment is mainly described as a railway vehicle, but the present invention is not limited to railway vehicles and can be applied to public transportation such as buses, ships, and airplanes that operate according to a predetermined operating schedule.

[0014] FIG. 2 is a diagram showing an example of a hardware configuration in which the text generation device 100 of the present disclosure is realized by a computer device 500 including a processor. As shown in FIG. 2, the text generation device 100 includes a processor 501, a memory such as a ROM (Read Only Memory) 502 and a RAM (Random Access Memory) 503, a storage device 505 such as a hard disk for storing a program 504, a communication interface 508 for network connection, and an input / output interface 509 for inputting and outputting data. The processor 501 controls the entire computer device 500. As the processor 501, for example, a CPU (Central Processing Unit), a DSP (Digital Signal Processor), a GPU (Graphics Processing Unit), a MPU (Micro Processing Unit), an FPU (Floating point number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof can be used. In the first embodiment, the text generation device 100 is connected to each component via a bus 510. Furthermore, the sentence generation device 100 shown in FIG. 1 can also be configured using cloud computing or the like.

[0015] The processor 501 operates an operating system to control the entire text generation device 100 according to the first embodiment of the present invention. The processor 501 also reads out programs and data from a recording medium 506 mounted in a drive device 507 or the like into a memory. The processor 501 also functions as the operation information acquisition unit 101, the management unit 102, and the first generation unit 103 in the text generation device 100, or as a part of these, and executes processes or commands in the flowchart shown in Fig. 9, which will be described later, based on the programs.

[0016] The recording medium 506 is, for example, an optical disk, a flexible disk, a magneto-optical disk, an external hard disk, or a semiconductor memory. The semiconductor memory, which is a part of the recording medium, is a non-volatile storage device, and stores the program therein. The program may also be downloaded from an external computer (not shown) connected to a communication network.

[0017] As described above, the first embodiment shown in Fig. 1 is realized by the computer hardware shown in Fig. 2. However, the means for realizing each part of the text generation device 100 in Fig. 1 is not limited to the configuration described above. The text generation device 100 may be realized by one physically combined device, or may be realized by a system consisting of two or more physically separated devices connected by wire or wirelessly.

[0018] The operation information acquisition unit 101 is a means for acquiring operation information after a change of transportation equipment. The operation information includes, for example, an operation schedule and a maintenance work schedule of each transportation equipment operating in an arbitrary operation section. For example, if the transportation equipment is a railroad vehicle, information such as the railroad vehicle vehicle number, train number, departure station, arrival station, departure time, arrival time, driver name, maintenance work time zone, maintenance work location, and maintenance worker name is included. The operation information acquisition unit 101 may acquire information in which the operation information of multiple transportation equipment is represented in a diagram format for each operation section.

[0019] The changed operation information is operation information that has been changed from a predetermined operation schedule due to operational failure of transportation equipment or the like. The changed operation information may be information obtained by using a known AI (Artificial Intelligence) simulator technology. For example, an AI simulator accepts input of operation information such as departure station, arrival station, departure time, arrival time, vehicle number, and driver name before the change of the railway vehicle, and changes to the operation information. The changes may be, for example, a part or all of a specific service, or a service within a predetermined range. Then, the AI ​​simulator outputs the departure station, arrival station, departure time, arrival time, vehicle number, driver name, and the like after the change. For example, such an AI simulator uses an algorithm obtained by learning using an evaluation function that gives a higher evaluation the closer the state is to a state defined as a target state of the railway vehicle during normal operation. The operation information acquisition unit 101 acquires the changed operation information from, for example, an AI simulator configured as a device separate from the sentence generation device 100.

[0020] The management unit 102 is a means for managing operation information for each unique number of transportation equipment. For example, the management unit 102 links the changed operation information to each unique number of transportation equipment and stores it in the storage device 505. In this embodiment, when the transportation equipment is a railroad vehicle, the unique number is a vehicle number, which is a unique symbol or number assigned to each vehicle.

[0021] FIG. 3 is an example of managing operation information in the present disclosure. As shown in FIG. 3, operation information of vehicle numbers "1001" and "2001" is managed in a different table. FIG. 4 and FIG. 5 are another example of managing operation information in the present disclosure. In the example of FIG. 4, the route name, departure station, arrival station, departure time, and arrival time of each passenger who boards vehicle number "1001" are managed. In the example of FIG. 5, the vehicle number "1001", the route name, the work section, the work start time, the work end time, the work content, and the worker name are managed. As shown in FIG. 4 and FIG. 5, the management unit 102 may manage the operation information by linking it to the attributes of the related parties involved in the operation of the transportation equipment in addition to the unique number of the transportation equipment. The related parties are people who have some kind of relationship with the operation of the transportation equipment. The attributes of the related parties are classified according to their positions in relation to the operation of the transport equipment, and specifically include a driver who drives the transport equipment, a manager who manages the operation of the transport equipment, a maintenance worker who performs maintenance work on the transport equipment, a security officer who guides people or cars when congestion occurs due to a transport equipment operation disorder, an emergency vehicle officer who responds to troubles due to an operation disorder, and passengers who plan to board the transport equipment, etc. In addition, when the transport equipment is a railroad vehicle, the related parties may include employees of other railroad companies or bus operators who use the railroad vehicle with that vehicle number as a substitute for transportation, employees of medical institutions around the station, and managers of railroad depots, etc.

[0022] The first generation unit 103 is a means for generating a sentence for notifying operation information for each attribute of a related person involved in the operation of a transportation machine having a unique number. The first generation unit 103 extracts notification information to be notified from the operation information for each attribute of the related person, and generates a sentence including the extracted notification information. The first generation unit 103 extracts notification information that needs to be notified for each attribute of the related person.

[0023] For example, for a train driver, the first generation unit 103 extracts the train number, departure station, arrival station, departure time, and arrival time of the train to be driven as notification information, and generates a sentence notifying them. Also, for a train passenger, the first generation unit 103 extracts the train number, departure station, arrival station, departure time, and arrival time of the train, and generates a sentence notifying them. For a train maintenance worker, the first generation unit 103 extracts the train number, work location, and work content of the train to be worked on, and generates a sentence notifying them.

[0024] In this embodiment, a format prepared for each attribute of a related person is stored in the storage device 505, and the first generating unit 103 may generate a notification sentence by inserting the extracted notification information according to the format. The first generating unit 103 may generate a sentence including notification information by using a learning model generated by additionally learning the correspondence between notification information and sentences including notification information based on a trained language model.

[0025] Here, the language model will be described in detail. The language model is a machine learning model trained to generate text based on an input text. More specifically, the language model is a model that learns the relationships between words in a sentence, and generates related strings related to a target string from the target string. By using a language model that has been trained with sentences and sentences of various contexts, it is possible to generate related strings with appropriate content related to the target string.

[0026] For example, a case where a language model is used in question answering will be described. The language model receives an input of a question such as "What kind of country is Japan?" as a target string. The language model generates a string such as "Japan is an island country in the northern hemisphere..." as an answer to the question.

[0027] The learning method of the language model is not particularly limited, but as an example, it may be one that is learned to output at least one sentence including an input string. As a specific example, the language model is GPT (Generative Pre-Training) that outputs a sentence including an input string by predicting a string that is likely to follow the input string. In addition, for example, T5 (Text-to-Text Transfer Transformer), BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly optimized BERT approach), ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately), etc. are also language models.

[0028] Furthermore, the character string generated by the language model is not limited to a natural language. For example, the language model may output an artificial language (such as a program source code) for a character string input in a natural language. For example, the language model accepts an input question such as "How can I retrieve data containing a specific character string from a database?" as a target character string. The language model may output a program source code for performing database processing. Alternatively, the language model may output a natural language corresponding to a character string input in an artificial language.

[0029] Furthermore, the content generated by the language model is not limited to character strings. For example, the language model may generate image data, video data, audio data, or other data formats corresponding to the input character string.

[0030] Here, an example of generating a sentence for notifying the operation information of a railway vehicle will be described with reference to figures. Figs. 6 to 8 are examples of generating a sentence for notifying the operation information of a railway vehicle in the present disclosure. The example in Fig. 6 is a sentence to be notified to a driver. As shown in Fig. 6, the sentence generated by the first generation unit 103 includes a sentence including the vehicle number of the railway vehicle driven by the driver as well as the departure time and arrival time at each station. In the example in Fig. 6, the departure station, arrival station, departure time, and arrival time are shown in a table. The sentence generated by the first generation unit 103 may include a map and a graph in addition to the table.

[0031] A description will be given of an example of a method in which the first generation unit 103 generates a sentence using a language model. The first generation unit 103 generates a character string (also called a "prompt") to be input to the language model based on the extracted notification information.

[0032] A prompt may be generated based on the information generated by the first generation unit 103. For example, a case will be described in which the first generation unit 103 extracts the vehicle number, departure station, arrival station, departure time, and arrival time of a railway vehicle driven by Driver A as notification information, and generates a notification message for Driver A of the railway vehicle. In such a case, the first generation unit 103 generates a prompt as follows. (prompt) Please write a letter informing Driver A of the following: Departure station: XX station, Arrival station: XX station, Departure time: XX station, Arrival time XX station

[0033] The first generation unit 103 can input the above-mentioned prompt into a language model and generate a sentence as shown in Fig. 6. The above-mentioned prompt may be different depending on the destination of the notification message and the data extracted by the first generation unit 103. For example, the first generation unit 103 can use a fixed phrase determined in advance for each related person as a prompt.

[0034] The example in Fig. 7 is a message to be notified to passengers of a railway vehicle. As shown in Fig. 7, the message generated by the first generation unit 103 includes, for example, the train number of the railway vehicle to be boarded, the departure station, the departure time, the arrival station, and the arrival time. If the railway vehicle to be boarded is out of service, the first generation unit 103 may generate a message to notify the passengers of the suspension of service.

[0035] The example in Fig. 8 is a text to be notified to a maintenance worker. As shown in Fig. 8, the text generated by the first generation unit 103 includes, for example, the vehicle number of the maintenance work target, the work section, the work content, the work start time, and the work end time. Also, as shown in Fig. 8, the first generation unit 103 may generate a text that allows the user to understand changes from the planned work content.

[0036] 9 is a flowchart showing an outline of the operation of the sentence generation device 100 according to the present disclosure. Note that the process according to this flowchart may be executed based on program control by the above-mentioned processor.

[0037] As shown in Fig. 9, first, the operation information acquisition unit 101 acquires operation information after the change of the transportation equipment (step S101). Next, the management unit 102 manages the operation information for each unique number of the transportation equipment (step S102). Finally, the first generation unit 103 generates a sentence to notify the operation information for each attribute of the person involved in the operation of the transportation equipment with the unique number (step S103). With this, the sentence generation device 100 ends the sentence generation process.

[0038] In the text generation device 100 of this embodiment, the management unit 102 manages operation information for each unique number of transportation equipment. Then, the first generation unit 103 generates text to notify the operation information for each attribute of the parties involved in the operation of the transportation equipment with the unique number. This makes it possible to efficiently generate text to notify each party of the changed operation information without generating notification sentences individually. Therefore, even if a sudden change in the schedule is made due to an accident or the like, the text generation device 100 of this embodiment can support the parties in making quick decisions and carrying out their work.

[0039] <Variation 1> Next, a modified example of the first embodiment of the present disclosure will be described, focusing on differences from the first embodiment. Note that each modified example can be applied in combination. That is, the text generation device 120 in modified example 2 described later may include the external information acquisition unit 113 in this modified example. The text generation device 110 in this modified example does not use the notification information included in the operation information as it is, but generates a text for notifying the operation information for each attribute of the related person based on the notification information and external information.

[0040] 10 is a block diagram including the configuration of a text generation device 110 in the present disclosure. The text generation device 110 includes an external information acquisition unit 113 in addition to the configuration of the text generation device 100. That is, the text generation device 110 includes an operation information acquisition unit 111, a management unit 112, an external information acquisition unit 113, and a first generation unit 114. The configurations of the operation information acquisition unit 111 and the management unit 112 are similar to the corresponding components in the first embodiment, and therefore detailed description thereof will be omitted.

[0041] The external information acquisition unit 113 is a means for acquiring external information related to the notification information. The external information is, for example, information that is publicly available on the Web and can be acquired by anyone. The external information acquisition unit 113 analyzes the contents of the notification information and acquires external information related to the analyzed contents.

[0042] The external information acquisition unit 113 may acquire, for example, information on an event to be held at an event venue around a station during a time period when a train departs or arrives, based on a station name and a departure time or an arrival time. The event information may include an event start time, an end time, a visitor forecast, a congestion forecast, and the like. The external information acquisition unit 113 may also acquire, for example, information on an accident that occurred around a station before a predetermined time. The accident information may include information indicating the status of the accident, such as injuries. The external information acquisition unit 113 may also acquire information on a weather forecast around a station. When a train is suspended or significantly delayed, the external information acquisition unit 113 may acquire information on a train that a passenger who was scheduled to board the train can board instead. Furthermore, the external information acquisition unit 113 may acquire a seat number of a train that a passenger who was assigned a seat in the train that the passenger was scheduled to board will board instead.

[0043] In addition to the functions of the first generating unit 103, the first generating unit 114 generates a sentence for notifying operation information for each attribute of a related person involved in the operation of a transportation machine having a unique number based on the notification information and the external information. The first generating unit 114 extracts external information that needs to be notified for each attribute of the related person, and generates a sentence including the extracted external information. For example, when congestion is predicted due to an event, the first generating unit 114 may generate a sentence for a driver including a predicted occupancy rate of the railway vehicle to be driven. Furthermore, the first generating unit 114 may generate a sentence for a passenger including a predicted occupancy rate of the railway vehicle to be driven or a predicted congestion rate around the departure station or the arrival station. Furthermore, the first generating unit 114 may generate a sentence for notifying a security person of a guidance instruction around the station when congestion is predicted due to an event. Furthermore, the first generating unit 114 may generate a sentence for notifying a person in charge of an emergency vehicle or a medical institution of the situation of the accident when an accident occurs.

[0044] Furthermore, if the railcar that the passenger plans to board is cancelled or significantly delayed, the first generation unit 114 may generate a sentence notifying the passenger of the details, or may generate a sentence notifying the passenger of the details of the railcar that the passenger will board instead. Furthermore, for a passenger who has a reserved seat in a railcar, the first generation unit 114 may generate a sentence including the seat number of the railcar that the passenger will board instead. The above-mentioned sentences generated by the first generation unit 114 are merely examples, and the sentences generated by the sentence generation device 100 are not limited to these.

[0045] 11 is a flowchart showing an outline of the operation of the sentence generation device 110 according to the present disclosure. Note that the processing according to this flowchart may be executed based on program control by the above-mentioned processor.

[0046] As shown in FIG. 11, first, the operation information acquisition unit 111 acquires operation information after the change of the transport equipment (step S111). Next, the management unit 112 manages the operation information for each unique number of the transport equipment (step S112). Next, the external information acquisition unit 113 acquires external information related to the notification information (step S113). Finally, the first generation unit 114 generates a sentence for notifying the operation information for each attribute of the parties involved in the operation of the transport equipment with the unique number based on the notification information and the external information (step S114). With this, the sentence generation device 110 ends the sentence generation process.

[0047] In this modification, the external information acquisition unit 113 acquires external information related to the notification information, and the first generation unit 114 generates text for notifying the operation information for each attribute of the person involved in the operation of the transportation equipment with the unique number based on the notification information and the external information. In this way, by combining the notification information with the related external information, more practical information can be provided to each person involved.

[0048] <Variation 2> Next, another modified example of the first embodiment of the present disclosure will be described, focusing on the differences from the first embodiment. Fig. 12 is a block diagram including the configuration of a text generation device 120 in the present disclosure. In this modified example, a text generation system 12 may be configured having the text generation device 120 and a display device 220 connected to the text generation device 120 through a network.

[0049] The text generation device 120 in this modification transmits text notifying operation information to the display device 220 that is visually recognized by the relevant person, and generates text notifying schedule information in response to a schedule information notification request from the destination display device 220. The display device 220 is a device used by the relevant person involved in the operation of the transport equipment, and may be a terminal carried by each of the relevant person. The display device 220 may also be a signage installed at a station or an event venue.

[0050] The sentence generation device 120 includes a transmitting unit 124, a receiving unit 125, and a second generating unit 126 in addition to the components of the sentence generation device 100. That is, the sentence generation device 120 includes an operation information acquisition unit 121, a management unit 122, a first generating unit 123, a transmitting unit 124, a receiving unit 125, and a second generating unit 126. The configurations of the operation information acquisition unit 121 and the first generating unit 123 are similar to the corresponding components in the first embodiment, so detailed descriptions thereof will be omitted.

[0051] In addition to the functions of the management unit 102, the management unit 122 manages operation information for each related party. The operation information in this modification is scheduled operation information, and includes operation information that has not been changed from predetermined operation information. For each related party, it refers to each related party involved in the operation of the transportation equipment. The management unit 122 manages the operation information of the transportation equipment by linking it with information that identifies each related party.

[0052] The transmission unit 124 is a means for transmitting the text generated by the first generation unit 123 to the display device 220 where the related person can view it. The transmission unit 124 transmits the text generated for each attribute of the related person to a contact address registered in advance, for example.

[0053] The receiving unit 125 is a means for receiving a notification request for schedule information from the destination display device 220. The receiving unit 125 receives a notification request for schedule information inputted, for example, by characters or voice to the display device 220. When the receiving unit 125 receives the notification request for schedule information, it outputs the information to the second generating unit 126.

[0054] The second generating unit 126 generates a sentence for notifying a specific related person of schedule information based on the operation information managed for each related person. The transmitting unit 124 generates a sentence for notifying the schedule information of the related person who received the schedule notification request. In this modification, the method of generating a sentence for notifying the schedule information by the second generating unit 126 is similar to that of the first generating unit 123. That is, the second generating unit 126 may generate a notification sentence by inserting operation information that needs to be notified according to a format prepared for each attribute of the related person. In addition, the second generating unit 126 may generate a sentence for notifying the schedule information using a learning model generated by additionally learning the correspondence between the operation information and the sentence for notifying the schedule information based on a learned language model. The language model is similar to the language model described above.

[0055] The sending unit 124 sends the text generated by the second generating unit 126 to the display device 220 that is the sender of the notification request.

[0056] Fig. 13 is an example of a sentence for notifying schedule information generated by the second generation unit 126 in the present disclosure. The example in Fig. 13 is a sentence of schedule information to be notified to a driver. As shown in Fig. 13, the sentence generated by the second generation unit 126 includes a sentence including the vehicle number of the railway vehicle driven by the driver, and the departure time and arrival time at each station. In the example in Fig. 13, the vehicle number, line name, departure station, arrival station, departure time, and arrival time are shown in a table, but this information may be shown in a sentence.

[0057] 14 is a flowchart showing an outline of the operation of the sentence generation device 120 in the modified example of the first embodiment. Note that the process according to this flowchart may be executed based on the program control by the above-mentioned processor.

[0058] As shown in FIG. 14, first, the operation information acquisition unit 121 acquires operation information after the change of the transportation equipment (step S121). Next, the management unit 122 manages the operation information for each unique number of the transportation equipment (step S122). The management unit 122 also manages the operation information for each related person (step S123). Next, the first generation unit 123 generates a text notifying the operation information for each attribute of the related person involved in the operation of the transportation equipment with the unique number (step S124). Next, the transmission unit 124 transmits the text to the display device 220 that the related person visually recognizes (step S125). Next, when the reception unit 125 receives a notification request for schedule information from the destination display device 220 (S126; YES), the second generation unit 126 generates a text notifying the schedule information (step S127). Next, the transmission unit 124 transmits the text notifying the schedule information to the display device 220 that is the transmission source of the notification request (step S128). On the other hand, in S126, if a schedule notification request is not received from the destination display device 220 (S126; NO), this flow ends. With the above, the writing generation device 120 ends the writing generation process.

[0059] In the text generating device 120 of this modified example, the management unit 122 manages operation information for each related party. When the receiving unit 125 receives a notification request for schedule information from the destination display device 220, the second generating unit 126 generates text for notifying the related party of the schedule information based on the operation information managed for each related party, and the transmitting unit 124 transmits the text for notifying the schedule information to the display device 220. This makes it possible to easily notify different schedule information for each related party.

[0060] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications that a person skilled in the art can understand within the scope of the present invention can be made to the configuration and details of the present invention. The present disclosure may include embodiments in which the matters described in this specification are appropriately combined or replaced as necessary. For example, matters described using a specific embodiment may be applied to other embodiments to the extent that no contradiction occurs. For example, although multiple operations are described in order in the form of a flowchart, the order of description does not limit the order in which the multiple operations are performed. Therefore, when implementing each embodiment, the order of the multiple operations can be changed to the extent that the content is not affected. Specifically, in the flowchart of FIG. 14, the flows of S123 and S124 may be performed at the same time. Also, in the flowchart of FIG. 14, the flow of S126 may be omitted. In other words, even if the receiving unit 125 does not receive a schedule notification request from the display device 220, the second generating unit 126 may generate text notifying each related party of the schedule information based on operation information managed for each related party, and the transmitting unit 124 may transmit the generated text to each of the display devices 220. [Explanation of symbols]

[0061] 12 Text Generation System 100, 110, 120 sentence generator 101, 111, 121 Operation information acquisition department 102, 112, 122 Management Department 103, 114, 123 First generation part 113 External Information Acquisition Department 124 Transmitter 125 Receiving unit 126 Second Generation 220 Display device 500 Computer equipment 501 Processor 502 ROM 503 RAM 504 Program 505 Storage device 506 Recording media 507 Drive Unit 508 Communication Interface 509 Input / Output Interface 510 Bus

Claims

1. An operation information acquisition means for acquiring operation information after the change of the transportation equipment; A management means for managing the operation information for each unique number of the transportation equipment; A text generating device comprising: a generating means for generating a text for notifying operation information for each attribute of a person involved in the operation of a transportation device having a unique number.

2. 2. The text generating device according to claim 1, wherein the generating means extracts notification information to be notified from the operation information for each attribute of the person concerned, and generates the text including the notification information.

3. The text generation device according to claim 2 , wherein the generating means generates the text using a machine learning model trained to generate text based on input text.

4. The apparatus further includes an external information acquisition unit that acquires external information related to the notification information, The text generating device according to claim 2 , wherein the generating means generates the text based on the notification information and the external information.

5. 2. The text generating device according to claim 1, further comprising a transmitting means for transmitting the text to a display device for viewing by a participant.

6. The management means further manages the operation information for each related person, 2. The text generating device according to claim 1, further comprising a second generating means for generating a text for notifying a specific related person of schedule information based on the operation information managed for each related person.

7. a transmitting means for transmitting the text to a display device for viewing by a person concerned; and a receiving means for receiving a notification request for schedule information from the display device that has transmitted the text, the second generating means generates a sentence for notifying the schedule information when the notification request is received; 7. The text generating device according to claim 6, wherein said transmission means transmits said schedule information to a display device that is a source of said notification request.

8. the transportation equipment is a rail vehicle, The text generation device according to any one of claims 1 to 7, wherein the unique number is a vehicle number of a railway vehicle.

9. The computer Obtain operation information after changes to transportation equipment, Manage the operation information for each unique number of the transportation equipment; A text generation method for generating text for notifying operation information of a transportation device having a unique number for each attribute of a person involved in the operation of the transportation device.

10. Obtain operation information after changes to transportation equipment, Manage the operation information for each unique number of the transportation equipment; A program that causes a computer to execute a process of generating text for notifying operation information for each attribute of a person involved in the operation of a transportation device having a unique number.

Images