Data processing apparatus, data processing method, and program

Abstract

To provide a data processing device, data processing method and program, capable of supporting preparation of various types of written reports by a worker.SOLUTION: A data processing device includes: an acquisition section 11 for acquiring voice data; a conversion section 12 for converting voice included in the voice data; a first preparation section 13 for preparing first written report-related data with a part or all of a text arranged in time sequence; and a second preparation section 14 for preparing second written report-related data on the basis of the text when voice data satisfies prescribed conditions.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a data processing apparatus, a data processing method, and a program.

Background Art

[0002] Technologies related to the present invention are disclosed in Patent Documents 1 to 3. Patent Documents 1 and 2 disclose a technology for identifying a speaker of a speech included in voice data of a meeting by voice recognition and creating minutes of the meeting based on the identification result. Patent Document 3 discloses a technology for notifying a track maintenance worker of the approach of a train by means such as pronunciation, light emission, and vibration.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0004] All kinds of operations such as surveys, repairs, and construction are carried out daily on various objects such as artificial objects such as railway lines, roads, bridges, and buildings, and natural objects such as mountains, rivers, and seas. After working at the site, the worker needs to create various reports such as a work report and an incident report (created when an incident occurs), which is very time-consuming. None of Patent Documents 1 to 3 describe or suggest the problem.

[0005] An object of the present invention is to provide a technology for assisting workers in creating various reports.

Means for Solving the Problems

[0006] According to the present invention, acquisition means for acquiring voice data; conversion means for converting the voice included in the voice data into text; first creation means for creating first report-related data in which part or all of the text is arranged in time series; second creation means for creating second report-related data based on the text when the voice data satisfies a predetermined condition; A data processing apparatus having the above is provided.

[0007] Further, according to the present invention, a computer performs an acquisition step of acquiring voice data; a conversion step of converting the voice included in the voice data into text; a first creation step of creating first report-related data in which part or all of the text is arranged in time series; a second creation step of creating second report-related data based on the text when the voice data satisfies a predetermined condition; A data processing method for executing the above is provided.

[0008] Further, according to the present invention, a computer is caused to function as acquisition means for acquiring voice data, conversion means for converting the voice included in the voice data into text, first creation means for creating first report-related data in which part or all of the text is arranged in time series, second creation means for creating second report-related data based on the text when the voice data satisfies a predetermined condition, and a program for causing the computer to function as such is provided.

Advantages of the Invention

[0009] According to the present invention, a technique for assisting an operator in creating various reports is realized.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Mode for Carrying Out the Invention

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same reference numerals are given to the same components, and the description thereof will be omitted as appropriate.

[0012] <First Embodiment> 「Overall Configuration」 First, the overall configuration of the system according to the present embodiment will be described. As shown in FIG. 1, the system 1 according to the present embodiment includes a data processing apparatus 10 and a plurality of operator terminals 20. The system 1 according to the present embodiment is configured to be able to perform data communication between the data processing apparatus 10 and each of the plurality of operator terminals 20. Note that the plurality of operator terminals 20 may be configured to be able to communicate with each other. The communication between the plurality of operator terminals 20 may be performed indirectly via the data processing apparatus 10, or may be performed directly without passing through the data processing apparatus 10.

[0013] 「Functional Configuration of Operator Terminal 20」 Next, the functional configuration of the worker terminal 20 will be described. The worker terminal 20 is a terminal possessed by a worker. One worker possesses one worker terminal 20.

[0014] A worker is a person who performs work at a work site. The work site is a place where the object of work exists. Examples of the object of work include, but are not limited to, artificial objects such as lines, roads, bridges, and buildings, and natural objects such as mountains, rivers, and seas. Examples of the work content include, but are not limited to, investigations, repairs, and construction on the object of work.

[0015] The worker terminal 20 is preferably a wearable terminal such as a headset type, a helmet-mounted type, a head-mounted display type, a glasses type, a watch type, a wristband type, a strap type, or a helmet type. Note that the worker terminal 20 such as a smartphone, a mobile phone, or a tablet terminal may be stored in a pocket of the worker's clothes and used.

[0016] The worker terminal 20 has at least a microphone function that collects the voice uttered by the worker and converts it into voice data, and a communication function that communicates with an external device. The worker terminal 20 may further include an output function that outputs information to the worker. For example, the worker terminal 20 can include at least one output device among a display, a speaker, a warning lamp, and vibration. The worker terminal 20 may include other functions such as a camera function for creating image data, a clock function, and a position information acquisition function (such as a GPS (global positioning system) function).

[0017] During work, the worker keeps the sound collection function of the worker terminal 20 turned on. Each worker terminal 20 collects, via the microphone, the voice uttered by the worker who possesses each worker terminal 20, the voice around the worker, etc., and converts it into voice data. Then, each worker terminal 20 transmits the voice data to the data processing device 10.

[0018] The operator terminal 20 may transmit the created voice data to the data processing device 10 in real-time processing. Alternatively, the operator terminal 20 may store the voice data in the storage device of its own terminal and transmit the voice data accumulated so far to the data processing device 10 collectively at an arbitrary timing. Examples of the timing for collectively transmitting the voice data include the timing when the work is completed and the operator turns off the voice collection function of the operator terminal 20, or the timing when the operator gives an input instructing the upload of data to the operator terminal 20, but it is not limited thereto.

[0019] Note that the plurality of operator terminals 20 may transmit and receive the created voice data to and from each other. And each operator terminal 20 may process the voice data received from another operator terminal 20 and output the voice indicated by the voice data via a speaker. By this processing, a call between operators via the operator terminal 20 is realized. The transmission and reception of voice data among the plurality of operator terminals 20 may be performed via the data processing device 10 or may be performed without passing through the data processing device 10.

[0020] "Functional Configuration of Data Processing Device 10" Next, the functional configuration of the data processing device 10 will be described. The data processing device 10 has a function of processing the voice data acquired from the operator terminal 20 and creating various report-related data.

[0021] FIG. 2 shows an example of a functional block diagram of the data processing device 10. As shown in the figure, the data processing device 10 includes an acquisition unit 11, a conversion unit 12, a first creation unit 13, and a second creation unit 14.

[0022] The acquisition unit 11 acquires voice data. Then, the acquisition unit 11 inputs the acquired voice data to the conversion unit 12.

[0023] For example, the data processing device 10 may include a mixer. Then, the data processing device 10 may mix the voice data transmitted from each of the plurality of worker terminals 20 to create one voice data (voice file). In this case, the acquisition unit 11 acquires this one voice data and inputs it to the conversion unit 12. Alternatively, the acquisition unit 11 may separately acquire the "voice data transmitted from each of the plurality of worker terminals 20" for which the processing by the mixer is not performed, and input each of the plurality of voice data to the conversion unit 12.

[0024] The conversion unit 12 converts the voice included in the voice data acquired by the acquisition unit 11 into text. The voice recognition technology used by the conversion unit 12 is not particularly limited, and any technology can be used. The technical terms of the work may be registered in the dictionary data in advance. By doing so, the accuracy of text conversion is improved. Note that a time stamp is attached to the voice data. By using this time stamp, the date and time when each voice indicated by the text created by the conversion unit 12 was uttered can be specified.

[0025] The first creation unit 13 creates first report-related data in which part or all of the text created by the conversion unit 12 is arranged in time series. The first report-related data is data related to the first report. The worker can create the first report by using the first report-related data.

[0026] The first report is a report created each time the work is performed, and is created to report the content of each work. The first report may be a report called, for example, a "work report", a "work communication", a "daily report", etc. Specific examples of the first report-related data will be described in the following embodiments.

[0027] The second creation unit 14 creates second report-related data based on the text created by the conversion unit 12. The second report-related data is data related to the second report. The worker can create the second report by using the second report-related data.

[0028] The second report is a report created only when a predetermined event occurs during work, and is created to report the content of the occurred event. The predetermined event is, for example, an event that occurs unexpectedly, and examples include incidents, troubles, malfunctions, accidents, etc. The second report may be a report called, for example, an "incident report", a "trouble report", a "malfunction report", etc. Specific examples of the second report-related data will be described in the following embodiments.

[0029] The second creation unit 14 creates second report-related data when the voice data acquired by the acquisition unit 11 satisfies a predetermined condition. The second creation unit 14 does not create second report-related data when the voice data acquired by the acquisition unit 11 does not satisfy the predetermined condition. The predetermined condition is that "the voice data acquired by the acquisition unit 11 indicates the occurrence of a predetermined event". Specific examples of the predetermined condition will be described in the following embodiments.

[0030] The second creation unit 14 may determine whether the above-mentioned predetermined condition is satisfied by analyzing the voice data acquired by the acquisition unit 11, or may determine whether the above-mentioned predetermined condition is satisfied by analyzing the text created by the conversion unit 12.

[0031] Next, an example of the processing flow of the data processing apparatus 10 will be described using the flowchart of FIG. 3.

[0032] When the data processing apparatus 10 acquires voice data (S10), it performs voice recognition processing on the acquired voice data and converts the voice included in the acquired voice data into text (S11). The voice data on which the voice recognition processing is performed may be voice data (voice file) created by mixing voice data transmitted from each of a plurality of worker terminals 20. Alternatively, the voice data on which the voice recognition processing is performed may be each of the voice data transmitted from each of the plurality of worker terminals 20.

[0033] After that, based on the text created in S12, the data processing device 10 creates first report-related data in which part or all of the text is arranged in time series (S12).

[0034] Also, the data processing device 10 determines whether the voice data acquired in S10 satisfies a predetermined condition (S13). The predetermined condition is "the voice data acquired in S10 indicates the occurrence of a predetermined event".

[0035] When the voice data acquired in S10 satisfies the predetermined condition (Yes in S13), the data processing device 10 creates second report-related data based on the text created in S12 (S14). When the voice data acquired in S10 does not satisfy the predetermined condition (No in S13), the data processing device 10 does not create the second report-related data.

[0036] Note that the processing order of the processes in S12 to S14 is not limited to that shown in FIG. 3. S13 and S14 may be performed before S12. Also, S12 and S13 and S14 may be performed in parallel.

[0037] "Hardware Configuration of Data Processing Device 10 and Operator Terminal 20" Next, an example of the hardware configuration of the data processing device 10 and the operator terminal 20 will be described. FIG. 4 is a diagram showing an example of the hardware configuration of the data processing device 10 and the operator terminal 20. Each functional unit provided in each of the data processing device 10 and the operator terminal 20 is realized by an arbitrary combination of hardware and software centered on the CPU (Central Processing Unit) of an arbitrary computer, memory, program loaded into the memory, storage unit such as a hard disk for storing the program (in addition to the program stored in advance at the stage of shipping the device, programs downloaded from storage media such as CDs (Compact Discs) and servers on the Internet can also be stored), and network connection interface. And it is understood by those skilled in the art that there are various modifications to the realization method and device.

[0038] As shown in FIG. 4, each of the data processing device 10 and the operator terminal 20 has a processor 1A, a memory 2A, an input / output interface 3A, a peripheral circuit 4A, and a bus 5A. The peripheral circuit 4A includes various modules. At least one of the data processing device 10 and the operator terminal 20 may not have the peripheral circuit 4A. Note that each of the data processing device 10 and the operator terminal 20 may be composed of a plurality of physically and / or logically separated devices, or may be composed of one physically and logically integrated device. When composed of a plurality of physically and / or logically separated devices, each of the plurality of devices can have the above hardware configuration.

[0039] The bus 5A is a data transmission path for the processor 1A, the memory 2A, the peripheral circuit 4A, and the input / output interface 3A to transmit and receive data to and from each other. The processor 1A is an arithmetic processing device such as a CPU or a GPU (Graphics Processing Unit). The memory 2A is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The input / output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, etc., and an interface for outputting information to an output device, an external device, an external server, etc. The input device is, for example, a keyboard, a mouse, a microphone, etc. The output device is, for example, a display, a speaker, a printer, a mailer, etc. The processor 1A can issue commands to each module and perform operations based on their operation results.

[0040] "Function and Effect" According to the data processing device 10 and the operator terminal 20 of the present embodiment, voice data indicating the voice uttered by the operator can be texturized, and first report-related data used to create a first report can be created based on the text. The first report is created each time work is performed and shows the content of each work.

[0041] In addition, according to the data processing device 10 and the worker terminal 20 of the present embodiment, voice data indicating the voice uttered by the worker can be converted into text, and based on the text, second report-related data used to create a second report can be created. The second report is created only when a predetermined event occurs during the work, and is a report indicating the content of the occurred event and the like.

[0042] As described above, according to the data processing device 10 and the worker terminal 20 of the present embodiment, data (first report-related data and second report-related data) used to create a first report indicating the content of each work and the like, a second report indicating the content of a predetermined event that occurred during the work, and the like can be created based on voice data indicating the voice uttered by the worker.

[0043] The worker can efficiently create the first report and the second report using such first report-related data and second report-related data.

[0044] In addition, according to the data processing device 10 and the worker terminal 20 of the present embodiment, when the voice data satisfies a predetermined condition, second report-related data can be created. When the voice data does not satisfy the predetermined condition, the data processing device 10 does not create the second report-related data. Since the second report-related data can be created only when necessary, it is possible to avoid the inconvenience of creating the second report-related data when it is not necessary.

[0045] <Second Embodiment> In the present embodiment, the content and creation method of the first and second report-related data are further specified.

[0046] "First report-related data" First, a specific example of the first report-related data will be described.

[0047] -First specific example- The first creation unit 13 can create first report-related data in which all of the text created by the conversion unit 12 is arranged in chronological order. In the case of this example, first report-related data in which all of the content spoken by the operator during the work is arranged in chronological order is created. The operator refers to the first report-related data to recall the content and flow of the work and creates the first report.

[0048] -Second specific example- The first creation unit 13 can analyze the text created by the conversion unit 12 and, based on the analysis result, input information into a predetermined format prepared in advance to create first report-related data.

[0049] FIG. 5 schematically shows an example of the first report-related data. The first report-related data includes items of "working date", "working time", "working place", "operator", and "details". The first report-related data may include other items or may not include some of the exemplified items.

[0050] The first creation unit 13 identifies the content of at least a part of a plurality of items included in the first report-related data by analyzing the text created by the conversion unit 12. Note that the first creation unit 13 may identify the content of a part of a plurality of items included in the first report-related data by a method other than analyzing the text created by the conversion unit 12. Hereinafter, an example of a method for identifying the content of each of the above-described items will be described. Note that the example described below is merely an example, and the first creation unit 13 may identify the content of each of the above-described items by other methods (for example, a method using AI (Artificial Intelligence)).

[0051] "Working day" indicates the day on which work is performed. For example, after the operator turns on the sound collection function of the operator terminal 20, the operator utters a predetermined keyword related to the working day (such as "working day") like "Working day, August 13, 2021", and then utters the working day (such as "August 13, 2021"). In this case, the uttered content is included in the text created by the conversion unit 12. The first creation unit 13 identifies the working day by detecting this keyword and the working day uttered subsequently from the text created by the conversion unit 12.

[0052] In addition, the voice data acquired by the acquisition unit 11 may be provided with a timestamp indicating the date and time when the voice was collected. Then, the first creation unit 13 may identify the date indicated by this timestamp as the working day.

[0053] "Working time" indicates the time period during which work is performed. The working time is indicated by, for example, the start time and end time of work. For example, after the operator turns on the sound collection function of the operator terminal 20, the operator utters a predetermined keyword related to the start of work (such as "start of work") and a predetermined keyword related to the end of work (such as "end of work"). In this case, the uttered content is included in the text created by the conversion unit 12. The first creation unit 13 detects this keyword from the text created by the conversion unit 12. Then, the first creation unit 13 identifies the time when the keyword related to the start of work is uttered as the start time of work, and the time when the keyword related to the end of work is uttered as the end time of work.

[0054] "Working location" indicates the location where work is performed. For example, after the operator turns on the sound collection function of the operator terminal 20, the operator utters a predetermined keyword related to the working location (such as "working location") like "Working location, Location XX", and then utters the working location (such as "Location XX"). In this case, the uttered content is included in the text created by the conversion unit 12. The first creation unit 13 identifies the working location by detecting this keyword and the working location uttered subsequently from the text created by the conversion unit 12.

[0055] "Operator" refers to the person who performed the work. For example, after turning on the sound collection function of the operator terminal 20, the operator speaks a predetermined keyword related to the operator (such as "operator"), such as "Operator, Taro Tokyo, Hanako Kyoto", and then speaks the operator (such as "Taro Tokyo, Hanako Kyoto"). In this case, the speech content is included in the text created by the conversion unit 12. The first creation unit 13 identifies the operator by detecting this keyword and the operator spoken subsequently from the text created by the conversion unit 12.

[0056] "Details" indicate the content of the work. For example, the first creation unit 13 can display all or part of the text created by the conversion unit 12 in chronological order in this column.

[0057] Also, in the details column, as shown in the figure, positions for attaching each of multiple types of images may be defined. In the example shown in the figure, positions for attaching "pre-work image", "in-work image", and "post-work image" are defined respectively. Then, the first creation unit 13 can identify each of the multiple types of images from the image data received from the operator terminal 20, and attach the identified various images to predetermined positions in the first report-related data. The details of this process will be described below.

[0058] First, the operator terminal 20 executes shooting based on the camera function provided by the self-terminal and creates image data. A time stamp is attached to the image data. For example, the operator terminal 20 may execute the above shooting at the timing when a shooting instruction input from the operator is received. The shooting instruction input may be an input via a physical button, touch panel, etc. provided by the operator terminal 20, or a voice input of a predetermined keyword via a microphone, or an input of a predetermined gesture via a camera, or others. Then, the operator terminal 20 transmits the created image data to the data processing device 10. The acquisition unit 11 acquires the image data.

[0059] When creating the first report-related data as shown in Fig. 5, the operator adjusts the orientation of the camera to include the work site at each of "before work", "during work", and "after work", and then takes pictures. Also, at the timing of taking each of the various images, the operator utters a plurality of types of shooting-related keywords related to the various images (such as "before-work image", "during-work image", and "after-work image"). In this case, the uttered content is included in the text created by the conversion unit 12.

[0060] The first creation unit 13 detects the plurality of types of shooting-related keywords from the text created by the conversion unit 12. Then, the first creation unit 13 identifies the timing (time) at which each of the plurality of types of shooting-related keywords was uttered, and identifies the image data created at the identified timing (time) as various images. For example, the first creation unit 13 identifies the image data created at the timing (time) when the shooting-related keyword "before-work image" was uttered as the before-work image.

[0061] Note that the "image data created at the timing (time) when the shooting-related keyword was uttered" may be the image data captured at the timing (time) closest to the timing (time) when the shooting-related keyword was uttered among the plurality of image data received from the operator terminal 20. Alternatively, the "image data created at the timing (time) when the shooting-related keyword was uttered" may be the image data captured at the timing (time) closest to the timing (time) when the shooting-related keyword was uttered among the plurality of image data received from the operator terminal 20, and the difference between the shooting time and the timing (time) when the shooting-related keyword was uttered is within the reference time. The timing (time) when each shooting-related keyword was uttered and the shooting time of each image data are identified based on the time stamps attached to the audio data and the image data.

[0062] In this way, the first creation unit 13 identifies the image data captured at the timing when the first shooting-related keyword is uttered as the first type of image data, and can identify the image data captured at the timing when the Nth shooting-related keyword is uttered (N is an integer of 2 or more) as the Nth type of image data. Then, the first creation unit 13 can attach each of the identified multiple types of image data to the positions where each of the multiple types of images defined in the first report-related data is attached. Note that the number of image data attached to the first report-related data is not particularly limited.

[0063] "Second report-related data" Next, a specific example of the second report-related data will be described.

[0064] When the voice data acquired by the acquisition unit 11 satisfies a predetermined condition, the second creation unit 14 creates the second report-related data.

[0065] The predetermined condition is "the voice data acquired by the acquisition unit 11 indicates the occurrence of a predetermined event". More specifically, the predetermined condition is "the voice data acquired by the acquisition unit 11 contains a predetermined second report-related keyword". The "second report-related keyword" is a word related to the occurrence of a predetermined event such as "accident occurred" or "incident occurred".

[0066] The second creation unit 14 may determine whether the above-mentioned predetermined condition is satisfied by analyzing the voice data acquired by the acquisition unit 11, or may determine whether the above-mentioned predetermined condition is satisfied by analyzing the text created by the conversion unit 12.

[0067] Note that the second creation unit 14 can create the second report-related data by using only the part related to the "predetermined event that occurred" in the text created by the conversion unit 12, rather than all of the text created by the conversion unit 12.

[0068] Based on the timing when the second report-related keyword in the voice data acquired by the acquisition unit 11 is uttered, the second creation unit 14 determines "a part of the text" to be used for creating the second report-related data. First, the "second report-related keyword" can include words related to the occurrence of a predetermined event, such as "accident occurred", "incident occurred", etc., and words indicating the resolution of a predetermined event, such as "accident resolved", "incident resolved", etc. Then, the second creation unit 14 can determine the text of the voice from the timing when a word related to the occurrence of a predetermined event is uttered to the timing when a word indicating the resolution of the predetermined event is uttered as "a part of the text" to be used for creating the second report-related data.

[0069] The second creation unit 13 can analyze a part of the text created by the conversion unit 12 and, based on the analysis result, input information into a predetermined format prepared in advance to create the second report-related data.

[0070] FIG. 6 schematically shows an example of the second report-related data. The second report-related data includes items such as "working day", "incident type", "occurrence time", "end time", "occurrence location", "worker", "cause", "countermeasure", "image". The second report-related data may include other items or may not include some of the exemplified items. The second creation unit 14 identifies the content of at least a part of the plurality of items included in the second report-related data by analyzing the text created by the conversion unit 12. Note that the second creation unit 14 may identify the content of a part of the plurality of items included in the second report-related data by a method other than text analysis.

[0071] The second creation unit 14 can identify the content of at least a part of a plurality of items included in the second report-related data by performing the same processing as the processing by the first creation unit 13 described above. That is, the second creation unit 14 can detect a predetermined keyword and the word following it from the text, identify the timing at which a predetermined keyword was uttered based on the timestamp, identify the time of the identified timing, and identify the image data captured at the identified timing (time), thereby identifying the content of each item. Note that the second creation unit 14 may identify the content of each of the above-described items by other methods (for example, a method using AI).

[0072] Other configurations of the data processing apparatus 10 and the worker terminal 20 of the present embodiment are the same as those of the first embodiment.

[0073] According to the data processing apparatus 10 and the worker terminal 20 of the present embodiment, the same operational effects as those of the first embodiment are achieved.

[0074] Further, according to the data processing apparatus 10 and the worker terminal 20 of the present embodiment, for example, as shown in FIGS. 5 and 6, information can be input in a predetermined format including a plurality of items to create first and second report-related data. By using the first and second report-related data filled with information on such a plurality of items, the worker can create the first and second reports more efficiently.

[0075] <Third Embodiment> The system 1 of the present embodiment has a function of outputting information to the worker terminal 20.

[0076] FIG. 7 shows an example of a functional block diagram of the data processing apparatus 10. As shown in the drawing, the data processing apparatus 10 of the present embodiment is different from the data processing apparatus 10 of the first and second embodiments in that it further includes a monitoring unit 15 and an output unit 16.

[0077] The monitoring unit 15 monitors the situation of the operator. For example, when the operator is working on the track, the monitoring unit 15 monitors the positional relationship between the position of the operator and the position of the train. Then, the monitoring unit 15 detects that the train is approaching the operator.

[0078] "Regarding the monitoring of the operator's position" The monitoring of the operator's position can be realized by using any technology. For example, the following means can be considered. Note that the following examples are only examples and are not limited to this.

[0079] - Example 1 of obtaining the operator's position - Each of the plurality of operator terminals 20 is equipped with a position information acquisition function (such as a GPS (global positioning system) function) for acquiring position information indicating the current position. Then, the data processing device 10 acquires the position information acquired by each of the plurality of operator terminals 20. The monitoring unit 15 identifies the position of the operator holding each operator terminal 20 based on the position information.

[0080] - Example 2 of obtaining the operator's position - A plurality of monitoring cameras are installed on the track. Then, the data processing device 10 acquires the images created by each of the plurality of monitoring cameras. The monitoring unit 15 analyzes the image and identifies the position of the operator by identifying which image created by which monitoring camera the operator is included in. In this case, in advance, the feature amounts of the appearances of each of the plurality of operators are registered in the data processing device 10. Then, the monitoring unit 15 realizes the detection of the operator by detecting a person having the feature amount from the image.

[0081] "Regarding the monitoring of the train's position" The monitoring of the train's position can be realized by using any technology. For example, the following means can be considered. Note that the following examples are only examples and are not limited to this.

[0082] - Example 1 of obtaining the train's position - Each of the plurality of trains is equipped with a position information acquisition function (such as a GPS (global positioning system) function) for acquiring position information indicating the current position. Then, the data processing device 10 acquires the position information acquired by each of the plurality of trains. The monitoring unit 15 identifies the position of each train based on the position information.

[0083] -Train Position Acquisition Example 2- The monitoring unit 15 holds the operation schedule of each of the plurality of trains. This operation schedule indicates at what time and minute each train departs from which station and arrives at which station. The monitoring unit 15 estimates the current position of each train based on this operation schedule, a map indicating the position of the train's track, and the standard speed of the train.

[0084] -Train Position Acquisition Example 3- The monitoring unit 15 detects the approach (position) of the train based on the output state of the train approach warning device. The train approach warning device is a device permanently installed on the track (such as at a level crossing or other locations), and it is a device that notifies the surrounding area of the approach state or non-approach state of the train by the lighting state / flashing state of a light or the output sound, etc. The configuration of the train approach warning device is not particularly limited, and any configuration can be adopted.

[0085] In this case, the data processing device 10 has a function of acquiring information indicating the output state of the train approach warning device and specifying the approach (position) of the train based on that information. For example, the data processing device 10 may be communicably connected to the train approach warning device and acquire information indicating the output state from the train approach warning device. Alternatively, when a monitoring server for monitoring the output states of a plurality of train approach warning devices is provided, the data processing device 10 may acquire information indicating the output state of the train approach warning device installed near the work site from the monitoring server. Alternatively, a state monitoring device for monitoring the output state of the train approach warning device installed near the work site may be installed around the train approach warning device every time work is performed. The state monitoring device is, for example, a camera that captures the lighting state / flashing state of the light of the train approach warning device, a microphone that collects the sound output from the train approach warning device, or the like. Then, the data processing device 10 may specify the output state of the train approach device by analyzing the image generated by the camera and the audio data generated by the microphone.

[0086] "Regarding Detection of Approach of Worker and Train" For example, the monitoring unit 15 may detect a situation where "the distance between the position of the worker and the position of the train is equal to or less than the threshold value" as a situation where "the train is approaching". Alternatively, the monitoring unit 15 may detect a situation where "the distance between the position of the worker and the position of the train is equal to or less than the threshold value and the distance is decreasing with time" as a situation where "the train is approaching". Alternatively, the monitoring unit 15 may detect the approach of the worker and the train by detecting that the output state of the train approach warning device installed near the work site indicates the approach (position) of the train.

[0087] When the monitoring unit 15 detects a situation where "the train is approaching", the output unit 16 transmits warning information indicating that the train is approaching to the worker terminal 20 and causes it to be output. The worker terminal 20 outputs the warning information. The worker terminal 20 can output the warning information by displaying the warning information on a display, outputting the warning information from a speaker, lighting a warning lamp, or activating vibration.

[0088] Examples of warning information output from the display or speaker include, for example, "Up train, departing from 〇〇 Station, scheduled to arrive in 〇〇 seconds", "Up train, scheduled to arrive in ○○ seconds, please prepare for evacuation", "Up train, scheduled to arrive in ○○ seconds, please evacuate", "Down train, departing from ○○ Station, scheduled to arrive in seconds", "Down train, scheduled to arrive in 〇〇 seconds, please prepare for evacuation", "Down train, scheduled to arrive in ○○ seconds, please evacuate", etc.

[0089] Note that the content of the warning information may be changed according to the distance between the worker and the train. For example, the following examples are conceivable.

[0090] Warning information when the distance between the worker and the train is between W1 or less and W2 or more: "Up train, departing from 〇〇 Station, scheduled to arrive in 〇〇 seconds" or "Down train, departing from ○○ Station, scheduled to arrive in seconds"

[0091] Warning information when the distance between the worker and the train is less than W2 and more than W3: "Up train, scheduled to arrive in ○○ seconds, please prepare for evacuation" or "Down train, scheduled to arrive in ○○ seconds, please prepare for evacuation"

[0092] Warning information when the distance between the worker and the train is less than W3 and more than W4: "Up train, scheduled to arrive in ○○ seconds, please evacuate" or "Down train, scheduled to arrive in ○○ seconds, please evacuate"

[0093] In addition, the output unit 16 may transmit the text created by the conversion unit 12 to the worker terminal 20 and cause it to be output. The worker terminal 20 displays the text on the display. The worker terminal 20 may display the text on the display according to the operation of the worker. In this way, the worker terminal 20 can display the text on the display at the timing desired by the worker.

[0094] So far, the data processing device 10 has detected the approach of the train and the worker based on the current position of the train and the current position of the worker. As a modification, each worker terminal 20 may perform the detection and output warning information based on the detection result. In this case, each worker terminal 20 grasps the position of the train and the position of its own terminal (worker terminal 20) by the method described above, and detects the approach of the train and the worker based on the result.

[0095] The other configurations of the data processing device 10 and the worker terminal 20 in the present embodiment are the same as those in the first and second embodiments.

[0096] According to the data processing device 10 and the worker terminal 20 in the present embodiment, the same operational effects as those in the first and second embodiments are achieved.

[0097] Further, according to the data processing device 10 and the worker terminal 20 in the present embodiment, useful information can be provided to the worker. For example, warning information indicating that a train is approaching can be provided to the worker working on the track. Based on this warning information, the worker can grasp the approach of the train. By utilizing this function, it is not necessary to arrange a monitor at the work site to monitor the approach of the train.

[0098] <Modification> Next, a modification applicable to the first to third embodiments will be described. Even if the modification is adopted, the same operational effects as those in the above embodiments are achieved.

[0099] "Modification 1" The voice information of each worker is registered in advance. The voice information includes voiceprints. The data processing device 10 uses the voice information to identify the speaker of each utterance included in the voice data. Then, the data processing device 10 creates first report-related data and / or second report-related data further indicating the speaker of each utterance.

[0100] In addition, when the voice information of each worker is registered during the first operation, the identification information of the worker and the voice information may be associated and continuously stored in the storage device. Then, during the second and subsequent operations, the voice information of a predetermined worker may be acquired from the stored information.

[0101] "Modification Example 2" Information indicating the worker who holds each worker terminal 20 is registered in the data processing device 10. The data processing device 10 uses the information to identify the speaker of each utterance included in the voice data. The utterance content of each worker is included in the voice data created by the worker terminal 20 held by each worker. Then, the data processing device 10 creates first report-related data and / or second report-related data further indicating the speaker of each utterance.

[0102] "Modification Example 3" The voice information of each worker is registered in advance. The voice information includes the frequency band of each worker's voice. The data processing device 10 removes the frequency components other than the frequency band indicated by the voice information (noise cut). Then, the data processing device 10 performs voice recognition processing on the components in the frequency band indicated by the voice information to create text.

[0103] In addition, when the voice information of each worker is registered during the first operation, the identification information of the worker and the voice information may be associated and continuously stored in the storage device. Then, during the second and subsequent operations, the voice information of a predetermined worker may be acquired from the stored information.

[0104] In addition, in this specification, "acquisition" means that, based on user input or based on program instructions, "the self-device goes to retrieve data stored in other devices or storage media (active acquisition)", for example, making a request or inquiry to another device and receiving the response, accessing another device or storage media and reading the data, etc., and, based on user input or based on program instructions, "the self-device inputs data output from other devices (passive acquisition)", for example, receiving data distributed (or transmitted, push-notified, etc.), and also selecting and acquiring from the received data or information, and "editing data (textualizing, rearranging data, extracting some data, changing file format, etc.) to create new data and acquiring the new data", including at least one of these.

[0105] Some or all of the above embodiments can also be described as follows, but are not limited thereto. 1. An acquisition means for acquiring audio data, A conversion means for converting the audio included in the audio data into text, A first creation means for creating first report-related data by arranging some or all of the text in time series, A second creation means for creating second report-related data based on the text when the audio data meets a predetermined condition, A data processing device having the above. 2. The data processing device according to 1, wherein the predetermined condition is that a predetermined second report-related keyword is included. 3. The second creation means is Creating the second report-related data based on some of the text, The data processing device according to 2, wherein, based on the timing when the second report-related keyword in the audio data is uttered, a part of the text used for creating the second report-related data is determined. 4. The acquisition means further acquires image data, The audio data and the image data are provided with time stamps. The first creation means detects a plurality of predetermined types of shooting-related keywords from the voice data, identifies the image data captured at the timing when each of the plurality of types of shooting-related keywords is uttered, based on the time stamp, and creates the first report-related data using the identified image data. The data processing apparatus according to any one of 1 to 3. 5. In the first report-related data, the positions for attaching each of the plurality of types of images are determined. The first creation means identifies the image data captured at the timing when the first shooting-related keyword is uttered as the first type of image data, and identifies the image data captured at the timing when the Nth (N is an integer of 2 or more) shooting-related keyword is uttered as the Nth type of image data. The data processing apparatus according to 4, wherein each of the identified plurality of types of image data is attached to the position for attaching each of the plurality of types of images determined in the first report-related data. 6. The data processing apparatus according to any one of 1 to 5, further comprising output means for transmitting information to and causing output on a worker terminal worn by a worker. 7. The worker performs work on a line The output means is the data processing apparatus according to 6, which transmits warning information indicating that a train is approaching to the worker terminal. 8. The output means is the data processing apparatus according to 6 or 7, which transmits the text to the worker terminal. 9. A computer performs an acquisition step of acquiring voice data a conversion step of converting the voice included in the voice data into text a first creation step of creating first report-related data in which part or all of the text is arranged in time series a second creation step of creating second report-related data based on the text when the voice data satisfies a predetermined condition and executes a data processing method. 10. A computer An acquisition means for acquiring audio data, A conversion means for converting the audio included in the audio data into text, A first creation means for creating first report-related data in which part or all of the text is arranged in time series, A second creation means for creating second report-related data based on the text when the audio data satisfies a predetermined condition, A program that functions as.

Explanation of symbols

[0106] 1 System 10 Data processing device 11 Acquisition unit 12 Conversion unit 13 First creation unit 14 Second creation unit 15 Monitoring unit 16 Output unit 20 Operator terminal 1A Processor 2A Memory 3A Input / output I / F 4A Peripheral circuit 5A Bus

Claims

1. An acquisition means for acquiring voice data recording the speech content of an operator; A conversion means for converting the voice included in the voice data into text; A first creation means for creating first report-related data in which part or all of the text is arranged in time series; A second creation means for creating second report-related data based on part of the text when the voice data satisfies a predetermined condition; having The predetermined condition is that a predetermined second report-related keyword is included in the speech content of the operator recorded in the voice data; The second creation means determines whether the second report-related keyword is included in the speech content of the operator recorded in the voice data by analyzing the voice data or the text, A data processing device that determines a part of the text to be used for creating the second report-related data based on the timing when the second report-related keyword in the voice data is uttered.

2. An acquisition means for acquiring voice data recording the speech content of an operator and image data; A conversion means for converting the voice included in the voice data into text; A first creation means for creating first report-related data in which part or all of the text is arranged in time series; A second creation means for creating second report-related data based on the text when the voice data satisfies a predetermined condition; having The predetermined condition is that a predetermined second report-related keyword is included in the speech content of the operator recorded in the voice data; The second creation means determines whether the second report-related keyword is included in the speech content of the operator recorded in the voice data by analyzing the voice data or the text, The voice data and the image data are provided with time stamps, The first creation means detects a plurality of predetermined types of shooting-related keywords from the voice data, identifies the image data taken at the timing when each of the plurality of types of shooting-related keywords is uttered based on the time stamp, and further uses the identified image data to create the first report-related data. A data processing device.

3. In the first report-related data, the positions for attaching each of a plurality of types of images are determined, The first creation means Identify the image data captured at the timing when the first shooting-related keyword was uttered as the first type of image data, and identify the image data captured at the timing when the Nth (N is an integer of 2 or more) shooting-related keyword was uttered as the Nth type of image data. The data processing apparatus according to claim 2, wherein each of the identified plurality of types of image data is attached to a position where each of the plurality of types of images defined in the first report-related data is attached.

4. An acquisition means for acquiring voice data recording the utterance content of an operator; A conversion means for converting the voice included in the voice data into text; A first creation means for creating first report-related data in which part or all of the text is arranged in time series; A second creation means for creating second report-related data based on the text when the voice data satisfies a predetermined condition; An output means for transmitting information to an operator terminal worn by an operator performing work on a line and causing it to be output; A monitoring means for monitoring the position of the operator terminal and the position of the train, and detecting that the relationship between the position of the operator terminal and the position of the train satisfies a predetermined approach condition; having The predetermined condition is that a predetermined second report-related keyword is included in the utterance content of the operator recorded in the voice data. The second creation means determines whether the second report-related keyword is included in the utterance content of the operator recorded in the voice data by analyzing the voice data or analyzing the text. The output means is a data processing apparatus that transmits warning information indicating that a train is approaching to the operator terminal when it is detected that the approach condition is satisfied.

5. A computer An acquisition step of acquiring voice data recording the utterance content of an operator; A conversion step of converting the voice included in the voice data into text; A first creation step of creating first report-related data in which part or all of the text is arranged in time series; A second creation step of creating second report-related data based on part of the text when the voice data satisfies a predetermined condition; executing The predetermined condition is that a predetermined second report-related keyword is included in the utterance content of the operator recorded in the voice data. In the second creation step, Determine whether the second report-related keyword is included in the speech content of the operator recorded in the voice data by analyzing the voice data or the text, A data processing method for determining a part of the text to be used for creating the second report-related data based on the timing when the second report-related keyword in the voice data is uttered. **Claim 6** A computer An acquisition step of acquiring voice data recording the speech content of an operator and image data, A conversion step of converting the voice included in the voice data into text, A first creation step of creating first report-related data in which part or all of the text is arranged in time series, A second creation step of creating second report-related data based on the text when the voice data satisfies a predetermined condition, executes The predetermined condition is that a predetermined second report-related keyword is included in the speech content of the operator recorded in the voice data, In the second creation step, it is determined whether the second report-related keyword is included in the speech content of the operator recorded in the voice data by analyzing the voice data or the text, The voice data and the image data are provided with time stamps, In the first creation step, Detect a plurality of predetermined types of shooting-related keywords from the voice data, identify the image data captured at the timing when each of the plurality of types of shooting-related keywords is uttered based on the time stamp, and further use the identified image data to create the first report-related data. A data processing method. **Claim 7** A computer An acquisition step of acquiring voice data recording the speech content of an operator, A conversion step of converting the voice included in the voice data into text, A first creation step of creating first report-related data in which part or all of the text is arranged in time series, A second creation step of creating second report-related data based on the text when the voice data satisfies a predetermined condition, An output step of transmitting information to and causing to output to an operator terminal worn by an operator performing work on a line, A monitoring step of monitoring the position of the operator terminal and the position of the train, and detecting that the relationship between the position of the operator terminal and the position of the train satisfies a predetermined approach condition, executes The predetermined condition is that a predetermined second report-related keyword is included in the speech content of the operator recorded in the voice data. In the second creation step, it is determined whether the second report-related keyword is included in the speech content of the operator recorded in the voice data by analyzing the voice data or the text. In the output step, when it is detected that the approach condition is satisfied, a data processing method for transmitting warning information indicating that a train is approaching to the operator terminal.

8. A computer An acquisition means for acquiring voice data recording the speech content of an operator, A conversion means for converting the voice included in the voice data into text, A first creation means for creating first report-related data in which part or all of the text is arranged in time series, A second creation means for creating second report-related data based on a part of the text when the voice data satisfies a predetermined condition, Function as The predetermined condition is that a predetermined second report-related keyword is included in the speech content of the operator recorded in the voice data. The second creation means Determines whether the second report-related keyword is included in the speech content of the operator recorded in the voice data by analyzing the voice data or the text. A program for determining a part of the text to be used for creating the second report-related data based on the timing when the second report-related keyword in the voice data is uttered.

9. A computer An acquisition means for acquiring voice data recording the speech content of an operator and image data, A conversion means for converting the voice included in the voice data into text, A first creation means for creating first report-related data in which part or all of the text is arranged in time series, A second creation means for creating second report-related data based on the text when the voice data satisfies a predetermined condition, Function as The predetermined condition is that a predetermined second report-related keyword is included in the speech content of the operator recorded in the voice data. The second creation means determines whether the second report-related keyword is included in the speech content of the operator recorded in the voice data by analyzing the voice data or the text. The voice data and the image data are provided with time stamps. The first creating means is a program that detects a plurality of predetermined types of shooting-related keywords from the voice data, identifies the image data captured at the timing when each of the plurality of types of shooting-related keywords was uttered, based on the time stamp, and further creates the first report-related data using the identified image data.

10. A computer is caused to function as an acquisition means for acquiring voice data recording the speech content of an operator, a conversion means for converting the voice included in the voice data into text, a first creating means for creating first report-related data in which part or all of the text is arranged in time series, a second creating means for creating second report-related data based on the text when the voice data satisfies a predetermined condition, an output means for transmitting information to an operator terminal worn by an operator performing work on a line and causing it to be output, a monitoring means for monitoring the position of the operator terminal and the position of the train, and detecting that the relationship between the position of the operator terminal and the position of the train satisfies a predetermined approaching condition, and the predetermined condition is that a predetermined second report-related keyword is included in the speech content of the operator recorded in the voice data, the second creating means determines whether the second report-related keyword is included in the speech content of the operator recorded in the voice data by analyzing the voice data or the text, and the output means is a program for transmitting warning information indicating that a train is approaching to the operator terminal when it is detected that the approaching condition is satisfied.

Images