JP2020106656A - Simulation evaluation device, train operation simulation system, train operation simulation evaluation method, and program - Google Patents

Abstract

To evaluate correctly an utterance content of a trainee without requiring labor or time of a user (instructor on train operation or the like).SOLUTION: In a simulator controller 21, an utterance voice of an operator is acquired by a voice acquisition control part 58, and the acquired utterance voice of the operator is speech-recognized by a speech recognition processing part 59, and in an utterance content evaluation part 63, an utterance content by the operator is evaluated by comparing the utterance content by the operator acquired by speech recognition with expert speech information which is a standard utterance content to be uttered by the operator in train operation simulation.SELECTED DRAWING: Figure 2

Description

The present invention relates to a simulation evaluation device, a train operation simulation system, a train operation simulation evaluation method, and a program.

As a technique related to train driving training, there is known a technique of simulating a simulated operation of a train (railroad vehicle) and evaluating a confirmation operation of a user (for example, see Patent Document 1).

JP, 2014-71319, A

If an abnormal event is found in the simulation for driving training, the trainee must make an emergency stop and report to the transportation order. That is, in the simulation, not only the driving technique but also the content of the report to the transportation command when an abnormal event is discovered must be evaluated.

According to the technique of Patent Document 1, it is possible to evaluate whether or not the trainee was able to correctly direct his or her line of sight to the traffic light set in the simulated railway operation section. However, Patent Document 1 does not describe the evaluation of the trainee's speech.

Conventionally, when an abnormal event is found, evaluation of the content of the report to the transportation command is performed, for example, by a training instructor listening to the content of each trainee's utterance and taking notes, or installing a microphone etc. in the simulator. By doing so, the utterances of the trainees were recorded, and it was performed based on those records. That is, the evaluation of the utterance content during the conventional simulation training is performed by the training instructor directly listening to the utterance content of each trainee, and it takes time to correctly evaluate the utterance content of many trainees. It took time and effort.

Therefore, the present invention solves the above problem, that is, a simulation evaluation device, a train operation simulation system, and a train operation simulation that can correctly evaluate the utterance content of a trainee when an abnormal event is discovered. The purpose is to provide an evaluation method and a program.

In order to solve the above-mentioned problems, one aspect of a simulation evaluation device of the present invention is a voice acquisition control unit that controls acquisition of a voice uttered by an operator of a train driving simulator during train driving simulation executed by a train driving simulator. And a voice recognition processing unit for recognizing the voice uttered by the operator acquired by the control of the voice acquisition control unit, the utterance content of the operator obtained by the voice recognition by the voice recognition processing unit, and the operation in the train driving simulation. And a reference utterance content to be uttered by the operator to evaluate the utterance content of the operator.

In another aspect of the simulation evaluation apparatus of the present invention, the evaluation unit, for each scene of the train driving simulation, the reference utterance content corresponding to the scene and the utterance content of the operator of the scene obtained by the processing of the voice recognition processing unit. Is compared with each other to evaluate the utterance content of the operator.

In another aspect of the simulation evaluation apparatus of the present invention, the evaluation unit extracts a keyword from the voice recognition result obtained by the process of the voice recognition processing unit and compares the extracted keyword with the keyword included in the reference utterance content. Then, the content of the utterance of the operator is evaluated based on the comparison result.

In another aspect of the simulation evaluation device of the present invention, the evaluation unit compares the extracted keyword classification ratio with the ratio of the keyword classification included in the reference utterance content to the reference utterance content, and the operator's utterance Characterized by evaluating the content.

According to another aspect of the simulation evaluation apparatus of the present invention, the evaluation unit evaluates the utterance content of the operator based on the matching rate between the voice recognition result obtained by the processing of the voice recognition processing unit and the reference utterance content. Is characterized by.

In another aspect of the simulation evaluation apparatus of the present invention, the evaluation unit further determines the utterance content of the operator based on whether or not there is a quantitative word in the voice recognition result obtained by the processing of the voice recognition processing unit. Characterized by evaluation.

Another aspect of the simulation evaluation apparatus of the present invention is that the voice recognition processing unit digitizes at least one of the pitch or speed of the speech of the operator whose acquisition is controlled by the voice acquisition control unit, The evaluation unit is characterized by further evaluating the utterance content of the operator based on the height or speed of the uttered voice digitized by the processing of the voice recognition processing unit.

Another aspect of the simulation evaluation apparatus of the present invention is an operation acquisition control unit that controls acquisition of an operation input to a train driving simulator, and an image data generation control unit that controls generation of image data to be displayed and output to the train driving simulator. The evaluation unit further includes, when the operation acquisition control unit controls the acquisition of the operation input for the emergency stop, and the image data generation control unit controls the generation of the simulation image that requires the emergency stop. Or, if the voice recognition result obtained by the processing of the voice recognition processing unit is a predetermined wording indicating the start of communication, after that timing, the utterance content of the operator obtained by the processing of the voice recognition processing unit It is characterized by starting the evaluation of.

Another aspect of the simulation evaluation apparatus of the present invention is an operation acquisition control unit that controls acquisition of an operation input to a train driving simulator, and an image data generation control unit that controls generation of image data to be displayed and output to the train driving simulator. Further, the voice recognition processing means, when the operation acquisition control means controls the acquisition of the operation input of the emergency stop, or the image data generation control unit generates the simulation image that requires the emergency stop. When controlled, the voice recognition of the uttered voice of the operator whose acquisition is controlled by the voice acquisition control means is started after that timing.

One aspect of the train driving simulation system of the present invention is that a train driving simulator displays a simulation screen display unit that displays a display screen corresponding to each scene of a scenario that is progressed in the simulation, and a trainee who performs driving training has a simulation screen. With reference to the image displayed by the display unit, a driving simulator that performs an operation, and a sound collection unit that collects the voice uttered by the operator of the driving simulator, and the simulation evaluation device uses the sound collection unit. A voice acquisition control unit that controls the acquisition of the uttered voice of the train-training simulator operator, a voice recognition processing unit that recognizes the uttered voice of the operator acquired by the control of the voice acquisition control unit, and a voice. It has an evaluation unit that compares the utterance content of the operator obtained by the voice recognition by the recognition processing unit with the reference utterance content that the operator should utter in the train driving simulation, and evaluates the utterance content of the operator. Characterize.

One aspect of the train operation simulation evaluation method of the present invention is a voice acquisition control step for controlling acquisition of a voice uttered by an operator of a train driving simulator being executed by a train driving simulator, and a voice acquisition control step. The voice recognition processing step for recognizing the voice uttered by the operator whose acquisition is controlled by the processing of step 1, the utterance content of the operator obtained by the voice recognition processing in the voice recognition processing step, and the operator's utterance in the train driving simulation. And an evaluation step of comparing the utterance content of the operator with the reference utterance content to be spoken.

One aspect of the program of the present invention is a computer that controls a train driving simulator for train training of a train, and a train driving simulator executed by the train driving simulator acquires a speech voice of an operator of the train driving simulator being executed. A voice acquisition control step for controlling a voice recognition control step for recognizing the voice uttered by the operator whose acquisition is controlled by the processing of the voice acquisition control step, and an operator obtained by the voice recognition processing of the voice recognition processing step. And a reference utterance content to be uttered by the operator in the train driving simulation, and an evaluation step of evaluating the utterance content of the operator is executed.

According to the present invention, it is possible to correctly evaluate the utterance content of the trainee.

It is a figure which shows the structure of the train operation simulation system 1. It is a figure which shows the function structure of the simulator control apparatus 21a. It is a figure which shows the example of memory of a keyword. It is a figure which shows the example of the utterance content of the report to an expert's transportation instruction. It is a figure which shows the example of the voice recognition result of the utterance content of a simulator operator. It is a figure for explaining an example of an evaluation result. 6 is a flowchart for explaining a simulation process 1. It is a flow chart for explaining utterance contents evaluation processing 1. 9 is a flowchart for explaining utterance content evaluation processing 2. It is a flow chart for explaining utterance content evaluation processing 3. 9 is a flowchart for explaining utterance content evaluation processing 4. It is a figure which shows the function structure of the simulator control apparatus 21b. 6 is a flowchart for explaining a simulation process 2.

Hereinafter, a train operation simulation system 1 including a simulator control device 21 according to an embodiment of the present invention will be described with reference to FIGS. 1 to 13.

A train operation simulation system 1 according to an embodiment of the present invention will be described with reference to FIG.

When an abnormal event occurs in the simulation, the trainee performs a predetermined operation such as an emergency stop and a report to a transportation command corresponding to the abnormal event. Therefore, in the train operation simulation system 1 which is an embodiment of the present invention, the speech content of the trainee simulator operator is acquired and the speech recognition is performed to evaluate the speech content.

The train operation simulation system 1 includes a simulator control unit 11, a train operation simulator unit 12, and a network 13. The simulator control unit 11 includes a simulator control device 21, an operation input device 22, a display device 23, and a printer 24. The train driving simulator unit 12 includes a simulation screen display device 31, a driving operation simulator 32, and a sound collecting device 33. In the example of FIG. 1, only one set of the simulation screen display device 31, the driving simulator 32, and the sound collection device 33 that configure the train driving simulator unit 12 is shown, but a plurality of people can train at the same time. In some cases, a plurality of these may be provided.

The simulator control device 21 of the simulator control unit 11 communicates with the train operation simulator unit 12 via the network 13 and operates the train based on the operation input of the user (trainer related to train operation) supplied from the operation input device 22. The execution of the simulation by the simulator unit 12 is controlled, and the training result is evaluated. Specifically, the simulator control device 21 acquires information about the operation of a simulator operator (a person who trains driving skills, etc.) from the driving operation simulator 32, and displays it on the simulation screen display device 31 based on the information. Control the displayed image. In addition, the simulator control device 21 acquires the utterance voice of the simulator operator from the sound collection device 33, performs voice recognition, and evaluates the utterance content.

The operation input device 22 is composed of, for example, an input device such as a keyboard, a mouse, a touch pad, etc., receives an operation input of a user (an instructor regarding train driving, etc.), and supplies it to the simulator control device 21.

The display device 23 displays information for prompting a user (instructor or the like regarding train driving) to input an operation using the operation input device 22. The information for prompting the operation input includes, for example, information for selecting a simulation condition such as a simulation route name and weather. Further, the display device 23 receives, from the simulator control device 21, information corresponding to a simulation result including an evaluation result of utterance content, which will be described later, and outputs the information.

The printer 24 receives the information corresponding to the simulation result including the evaluation result of the utterance content, which will be described later, from the simulator control device 21 and prints it out.

The simulation screen display device 31 of the train operation simulator unit 12 displays the simulation screen generated by the simulator control device 21 of the simulator control unit 11.

The driving operation simulator 32 has a form simulating a driver's seat or a crew room, and is provided with levers and buttons necessary for driving, instruments, etc., and, for example, train operation such as a timetable and an operation table. Necessary equipment is equipped for. The driving operation simulator 32 supplies an operation input executed by a simulator operator (a person who trains driving skills) to the simulator control device 21 via the network 13.

The sound collector 33 collects the utterance of the simulator operator and supplies it to the simulator controller 21. The sound collection device 33 may be realized as, for example, a microphone that is a non-wearable stationary device installed in front of the simulator operator as shown in FIG. 1, or may be worn by a user such as a headset. It may be implemented as a wearable device.

The simulator control device 21 of the simulator control unit 11 will be described using two functional configuration examples. First, a simulator control device 21a as a first configuration example will be described with reference to FIGS. Then, a simulator control device 21b as a second configuration example will be described with reference to FIG. 12 and FIG.

The functional configuration of the simulator control device 21a will be described with reference to FIG.

The simulator control device 21a includes an operation input control unit 51, a simulator control unit 52, a control device output control unit 53, a simulator operation input acquisition control unit 54, a display screen generation unit 55, a video data storage unit 56, and a simulator screen display control unit. 57, a voice acquisition control unit 58, a voice recognition processing unit 59, an operator situation recording unit 60, a keyword storage unit 61, an expert utterance information storage unit 62, and an utterance content evaluation unit 63. ..

The operation input control unit 51 (hereinafter, referred to as the input control unit 51) controls the acquisition of the operation input of the user (the instructor related to train operation) supplied from the operation input device 22, and acquires the acquired operation input information from the simulator. It is supplied to the control unit 52.

The simulator control unit 52 controls the operation of the simulator control device 21a based on the operation input supplied from the input control unit 51. Specifically, the simulator control unit 52 causes the display device 23 to display information for prompting the user to input an operation by the operation input device 22 (an instructor related to train driving, etc.), and the controller output control unit 53. (Hereinafter, referred to as the output control unit 53) is controlled. Further, the simulator control unit 52 causes the simulation screen display device 31 to display a display screen that matches the route, weather, etc. corresponding to the simulation scenario selected by the user based on the operation input supplied from the input control unit 51. Therefore, the display screen generation unit 55 is controlled.

The simulator control unit 52 controls the display screen generation unit 55 based on the information supplied from the simulator operation input acquisition control unit 54 (hereinafter, referred to as the operation acquisition control unit 54) and executes it from the video data storage unit 56. The image data corresponding to the scene of the inside scenario is read out, and the image data displayed on the simulation screen display device 31 is generated. For example, when the driving operation simulator 32 performs a driving operation for departure at the start of the simulation, the simulator control unit 52 controls the display screen generation unit 55 based on the information supplied from the operation acquisition control unit 54. The image displayed on the simulation screen display device 31 is controlled to be a moving image corresponding to the actual departure. Further, when an operation input for driving such as speed change or braking is made in the driving operation simulator 32 during the execution of the simulation, the simulator control unit 52 changes the information supplied from the operation acquisition control unit 54. Based on this, the display screen generation unit 55 is controlled so that the image displayed on the simulation screen display device 31 corresponds to the driving operation executed by the simulator operator. Further, the simulator control unit 52 notifies the utterance content evaluation unit 63 (hereinafter referred to as the evaluation unit 63) of the timing at which an abnormal event occurs in the scenario being executed.

In addition, the simulator control unit 52 causes the display device 23 to display and outputs the information corresponding to the result of the simulation to the printer 24 or the printer 24 to print out the information, and thus the operator situation recording unit 60 (hereinafter, referred to as the recording unit 60). The information about the operator's situation during the simulation recorded in (4) and the evaluation result of the utterance content by the evaluation unit 63 are supplied and supplied to the output control unit 53. The simulator control unit 52 also controls the display screen generation unit 55 to generate display data corresponding to the result of the simulation and supply the display data to the display control unit 57.

Based on the control of the simulator control unit 52, the output control unit 53 causes the display device 23 to display information for prompting a user (an instructor or the like regarding train driving) to input an operation using the operation input device 22. The information for prompting the operation input includes, for example, information for selecting a simulation condition such as a simulation route name and weather. Further, the output control unit 53 generates output data corresponding to the result of the simulation based on the control of the simulator control unit 52, and corresponds to the result of the simulation including the evaluation of the utterance content on the display device 23 or the printer 24. Output information.

The operation acquisition control unit 54 acquires information regarding the operation input of the simulator operator, which is supplied from the driving operation simulator 32 via the network 13, and supplies the information to the simulator control unit 52, the recording unit 60, and the evaluation unit 63. ..

The display screen generation unit 55 reads out the image data stored in the video data storage unit 56 under the control of the simulator control unit 52, and generates the image data for simulation to be displayed on the simulation screen display device 31, It is supplied to the simulator screen display control unit 57 (hereinafter referred to as the display control unit 57). Further, the display screen generation unit 55 generates display data corresponding to the result of the simulation based on the control of the simulator control unit 52 and supplies it to the display control unit 57.

The video data storage unit 56 stores video data for generating simulation image data to be displayed on the simulation screen display device 31.

The display control unit 57 supplies the image data generated by the display screen generation unit 55 to the simulation screen display device 31 via the network 13 and controls the display thereof.

The voice acquisition control unit 58 (hereinafter, referred to as a voice acquisition unit 58) acquires the voice uttered by the simulator operator from the sound collection device 33 via the network 13 and supplies the voice to the voice recognition processing unit 59.

The voice recognition processing unit 59 performs voice recognition of the voice uttered by the simulator operator supplied from the voice acquisition unit 58, converts the voice data into text data, and supplies the voice data as a simulation result to the recording unit 60 for recording. It is supplied to the evaluation unit 63. Further, the voice recognition processing unit 59 digitizes the pitch of the utterance voice of the simulator operator supplied from the voice acquisition unit 58 and the speed of the utterance, supplies the digitized voice to the recording unit 60, and records the digitized voice. Supply to 63.

The recording unit 60 records the simulation result supplied from the operation acquisition control unit 54 and the voice recognition processing unit 59.

The keyword storage unit 61 stores, as the first information used by the evaluation unit 63 to evaluate the utterance content of the simulator operator, the keywords used for reporting to the transportation command for each predetermined classification.

FIG. 3 shows an example of keywords stored in the keyword storage unit 61. Keywords are classified according to their contents, for example, location, accident content, own train, passengers/passengers, other trains, ground facilities, surrounding conditions, and others. Keywords stored in the category of place include, for example, A station (A has a name), B station and C station (B and C have a name), after departure, before arrival, inside station , 10km300m (approx. kilometer: any number is acceptable), No. 0 block traffic light (numerals are entered in No. 0), special signal lighter, relay traffic light, inward, outward, D crossing (D There is a name), E bridge (E has a name), F tunnel (F has a name) and so on. The keywords stored in the classification of the accident content include, for example, a car, a passenger car, a light passenger car, a truck, a bus, and a motorcycle. Also, the keywords stored in the classification of the own train are, for example, 200M (train number), traveling speed X km/h (where X is a numerical value, etc.), protection radio notification, protection radio reception, vehicle Ignition of a signal flame tube for portable use, ignition of a portable signal flame tube, etc.

The keywords stored in the classification of passengers/passengers include injured persons, injuries, passengers, evacuation guidance, customers, drivers, pedestrians, pedestrians, and shelters. The keywords stored in the classification of other trains include, for example, oncoming lanes, following trains, other trains, restraint arrangements, rescue trains, and line-of-sight distances. Further, the keywords stored in the classification of the ground equipment include, for example, the ATS ground wire, the switch machine, the wayside telephone, and the breaker. Further, the keywords stored in the classification of the surrounding situation include railroad tracks, railroad crossings, inside railroad crossings, outside railroad crossings, overhead lines, rockfalls, avalanches, strong winds, heavy fog, and deer. In addition, keywords that do not belong to each category are stored in the other categories. The classification of keywords may be other than this. In addition, keywords other than these may be registered in each category.

Returning to FIG. 2, the expert utterance information storage unit 62 reports the report to the expert's transportation command as the second information, which is the reference utterance content used by the evaluation unit 63 to evaluate the utterance content of the simulator operator. The utterance content example is stored for each predetermined scene of the simulation. The predetermined scene of the simulation is a scene in which an abnormal event occurs and the simulator operator makes an emergency stop and reports to a transportation command. Specifically, during a simulation scenario, for example, a person or a passenger vehicle has entered the railroad crossing, there is an obstacle on the overhead line or track, an emergency stop signal is lit, or a passenger at the home When a scene such as an abnormality occurs in the simulator, the simulator operator needs to perform an emergency stop operation and report to the transportation command. Therefore, the expert utterance information storage unit 62 stores an example of utterance contents of a report to the transportation command of the expert corresponding to those scenes.

FIG. 4 shows an example of the utterance contents of the expert stored in the expert utterance information storage unit 62. FIG. 4 shows an example of the utterance content of a skilled person in a scene where a light vehicle has entered the railroad crossing and has come into contact with the railroad crossing. In the example of the utterance content of the expert, the word corresponding to each keyword described with reference to FIG. 3 or the wording including a plurality of words is associated with each classification. For example, words such as “Hikarimachi Station”, “first block traffic light”, “second block traffic light” are associated with the “place” classification, and words such as “light car” and “contact” are associated with “accident”. The classification of "content" is associated. Then, the wording including a word or a plurality of words such as "200M", "protection radio is issued", "vehicle signal flame tube is ignited" is associated with the classification of "own train", and "driver" "passenger" The words “passengers, passers-by, etc.” are associated with words such as “injury”. Then, the words "other train", "deterrent arrangement", and "oncoming lane" are associated with the classification of "other train", and the words "outside the railroad crossing" and "ambulance" are classified as "surroundings". It is associated.

In the example of the utterance contents of the expert shown in FIG. 4, many categories of keywords are efficiently included in large numbers. It should be noted that in this example of the utterance content of the expert, the keyword of the ground equipment is not included, but depending on the content of the abnormal event generated by the simulation, there is a classification that is not necessary. In the scenes other than the example shown in FIG. 4, the expert utterance information storage unit 62 stores the utterance content examples of the expert in association with the classifications corresponding to the keywords described with reference to FIG. ..

Returning to FIG. 2 again, the evaluation unit 63 evaluates the speech content of the simulator operator using the voice recognition result supplied from the voice recognition processing unit 59. Specifically, the evaluation unit 63 can evaluate the utterance content of the simulator operator using the information stored in the keyword storage unit 61 and the expert utterance information storage unit 62. In addition, the evaluation unit 63 extracts quantitative words (for example, words indicating distance, number of people, number of units, etc.) from the voice recognition result supplied from the voice recognition processing unit 59 to determine the utterance content of the simulator operator. Can be evaluated. In addition, the evaluation unit 63 evaluates the utterance content of the simulator operator based on the information of the pitch of the utterance voice of the simulator operator and the quantized speed of the utterance supplied from the voice recognition processing unit 59. can do.

The evaluation unit 63 starts evaluation of the utterance content at the timing when an abnormal event occurs in the simulation and the trainee starts reporting to the transportation command in response to the abnormal event. Specifically, for example, when the evaluation unit 63 is supplied with the information indicating that the operation input of the emergency stop is performed from the operation acquisition control unit 54, the evaluation unit 63 can start the evaluation of the utterance content. Further, when the evaluation unit 63 receives, for example, information from the simulator control unit 52 indicating that it is the timing at which an abnormal event occurs in the simulation scenario being executed, the evaluation unit 63 starts the evaluation of the utterance content. You can In addition, for example, when the voice recognition result supplied from the voice recognition processing unit 59 is “transport command, transport command”, which is a fixed word indicating the start of communication to the transport command, the evaluation unit 63 indicates the utterance content. The evaluation can start. The evaluation unit 63 determines whether or not information indicating that an emergency stop operation input has been performed, whether or not information indicating that an abnormal event has occurred is supplied, or voice recognition. All conditions are judged whether the result is a fixed word indicating the start of communication to the transportation command, and if any of the conditions is met, it is determined that it is the timing to start the evaluation of the utterance content. Alternatively, it may be determined that it is the start timing of the evaluation of the utterance content by performing any condition determination.

The evaluation of the utterance content of the simulator operator by the evaluation unit 63 will be described with reference to FIGS. 5 and 6.

FIG. 5 shows an example of the voice recognition result of the utterance content of the simulator operator when the same abnormal event occurs in the same scene as the utterance content example of the expert described in FIG. In the example of the utterance content shown in FIG. 5, among the keywords described with reference to FIG. 3, the keywords “car” and “contact” of the accident content classification and “200M” “stop” “of the own train classification” The keywords "damaged" and "derailment" are included, but the keywords of other categories are not included. That is, in the example of the utterance content of the simulator operator shown in FIG. 5, only the keywords included in the biased classification are used among the keywords described with reference to FIG. Further, as compared with the example of the utterance content of the expert using FIG. 4, it can be seen that the information about the place where the accident occurred, passengers, passers-by, other trains, and surrounding conditions are missing.

The evaluation unit 63 refers to the keywords stored in the keyword storage unit 61 and the utterance content example of the expert in the same scene stored in the expert utterance information storage unit 62, and supplies from the voice recognition processing unit 59. Based on the voice recognition result, the number of matching keywords in the utterance content of the simulator operator and the utterance content example of the expert is detected, and the detection result is supplied to the simulator control unit 52. For example, in the case of the voice recognition result described with reference to FIG. 5, the number of keywords that match the example of the utterance content of the expert described with reference to FIG. 4 is 6. The evaluation unit 63 may count the number of overlapping keywords as one. Further, the evaluation unit 63 also calculates the number of keywords included in the utterance content example of the expert in the same scene, thereby calculating the number of keywords matching the utterance content example of the expert as 6/28, for example. It may be done.

Further, the evaluation unit 63 refers to the keyword stored in the keyword storage unit 61 and the example of the utterance content of the expert in the same scene stored in the expert utterance information storage unit 62, and the voice recognition processing unit 59. Based on the voice recognition result supplied from the simulator operator, the voice recognition result of the utterance content of the simulator operator and the classification ratio of the keywords included in the utterance content example of the expert in the same scene are calculated, and the calculation result is calculated by the simulator. It is supplied to the control unit 52. For example, when the voice recognition result is described with reference to FIG. 5 and the example of the utterance content of the expert in the same scene is described with reference to FIG. 4, the rate of keyword classification depends on the simulator operator. Own train 80%, accident content is 20%, in the example of utterance content of skilled person, own train is 38%, location is 18%, accident content and passengers, passers by 14%, other trains 11% and surrounding situation is 7%. Further, the evaluation unit 63 may count the overlapping keywords as one and calculate the classification ratio.

The evaluation unit 63 also refers to an example of the utterance content of the expert in the same scene stored in the expert utterance information storage unit 62, and based on the voice recognition result supplied from the voice recognition processing unit 59, the simulator operation is performed. The matching rate between the voice recognition result of the utterance content of the person and the example of the utterance content of the expert in the same scene is calculated, and the calculation result is supplied to the simulator control unit 52.

In addition, the evaluation unit 63 determines, based on the voice recognition result supplied from the voice recognition processing unit 59, a quantitative word (for example, distance, number of persons, number of units, etc.) included in the voice recognition result of the utterance content of the simulator operator. The number of words shown) is detected, and the detection result is supplied to the simulator control unit 52.

In addition, the evaluation unit 63 evaluates the easiness of communication of the utterance based on the voice recognition result supplied from the voice recognition processing unit 59, using the speed of the utterance of the simulator operator, the pitch of the voice, and the like. The result is supplied to the simulator control unit 52. Specifically, the evaluation unit 63 compares the information obtained by quantifying the utterance speed or the voice pitch of the simulator operator with one or more threshold values, and by leveling or indexing the information, Evaluate the ease of communication of speech.

The simulator control unit 52 uses the information supplied from the evaluation unit 63 to control the output control unit 53 to supply the evaluation result as shown in FIG. 6 to the display device 23 or the printer 24 and output it. Let The simulator control unit 52 also controls the display screen generation unit 55 to generate display image data corresponding to the evaluation result as shown in FIG. 6 and supply the display image data to the display control unit 57. The display control unit 57 supplies the image data generated by the display screen generation unit 55 to the simulation screen display device 31 via the network 13 and controls the display thereof.

By confirming this evaluation result, the utterance content of the simulator operator is lacking in keywords and the keyword classification is biased compared with the utterance example of the expert, that is, the utterance example of the expert is compared. Then, the report contents are biased and other trains, passengers, passersby, etc., and the surrounding situation reports are missing, and it can be seen that the report contents are generally insufficient.

The evaluation unit 63 performs at least one of the evaluation methods described above, and preferably performs all the processes. Further, the evaluation unit 63 may perform the evaluation method selected by the user among the above-described evaluation methods based on the control by the simulator control unit 52.

Next, with reference to the flowchart of FIG. 7, the simulation process 1 executed in the train operation simulation system 1 including the simulator control device 21a will be described.

In step S1, the operation input device 22 receives an operation input from a user (an instructor or the like regarding train driving) and supplies it to the simulator control device 21a. The simulator control device 21a performs preparation for starting a simulation that matches conditions such as a route and weather based on a user's operation input. The simulator control unit 52 of the simulator control device 21a controls the display screen generation unit 55 to start image generation according to the simulation scenario. The image generated by the display screen generation unit 55 is displayed on the simulation screen display device 31 of the train driving simulator unit 12 via the display control unit 57.

In step S2, the operation acquisition control unit 54 of the simulator control device 21a determines whether the information regarding the operation input from the driving operation simulator 32 is acquired via the network 13. When it is determined in step S2 that the information regarding the operation input has not been acquired, the process of step S2 is repeated until it is determined that the information regarding the operation input has been acquired.

When it is determined in step S2 that the information regarding the operation input is acquired, the operation acquisition control unit 54 supplies the information regarding the acquired operation input to the simulator control unit 52 and the evaluation unit 63 in step S3. .. The simulator control unit 52 controls the display screen generation unit 55 based on the information supplied from the operation acquisition control unit 54 to read the image data corresponding to the scene of the scenario being executed from the video data storage unit 56. Then, the image data displayed on the simulation screen display device 31 is generated, and the simulation based on the operation input is executed. For example, when the driving operation simulator 32 performs a driving operation for departure at the start of the simulation, the simulator control unit 52 controls the display screen generation unit 55 based on the information supplied from the operation acquisition control unit 54. The image displayed on the simulation screen display device 31 is controlled to be a moving image corresponding to the actual departure. After that, the simulator control unit 52 controls the display screen generation unit 55 based on the information supplied from the operation acquisition control unit 54, for example, when an operation input such as speed change or braking is made. Then, the simulation based on the operation input is performed such that the image displayed on the simulation screen display device 31 corresponds to the driving operation executed by the simulator operator.

In step S4, the voice acquisition unit 58 acquires the voice uttered by the simulator operator supplied from the sound collection device 33 via the network 13 and supplies the voice to the voice recognition processing unit 59.

In step S5, the voice recognition processing unit 59 voice-recognizes the voice uttered by the simulator operator supplied from the voice acquisition unit 58, converts the voice data into text data, and supplies the voice data to the recording unit 60 as a simulation result. It is recorded and supplied to the evaluation unit 63.

In step S6, the evaluation unit 63 is supplied with information indicating that the operation input of the emergency stop is performed from the operation acquisition control unit 54, or the simulator control unit 52 causes an abnormality in the simulation scenario being executed. Whether it receives information indicating that it is the time when the event occurs, or whether the voice recognition result is a fixed word indicating the start of communication to a transportation command such as "transportation command, transportation command", It is determined whether or not it is time to evaluate the utterance content. When it is determined in step S6 that it is not the timing for evaluating the utterance content, the process returns to step S3, and the subsequent processes are repeated.

When it is determined in step S6 that it is time to evaluate the utterance content, in step S7, at least one of utterance content evaluation processes 1 to 4 described later with reference to FIGS. 8 to 11, preferably, All the utterance content evaluation processes 1 to 4 are executed.

In step S8, the simulator control unit 52 causes the display device 23 to display the information corresponding to the result of the simulation, the information about the operator situation during the simulation recorded in the recording unit 60, and the evaluation unit 63. The evaluation result of the utterance content is supplied to the output control unit 53. The output control unit 53 generates display data corresponding to the result of simulation. The simulator controller 52 also controls the display screen generator 55 to generate display data corresponding to the result of the simulation.

In step S9, the display screen generation unit 55 supplies the display control unit 57 with the display data corresponding to the result of the simulation, and supplies the display data to the simulation screen display device 31 via the network 13 to display the display data. Then, the display device 23 or the printer 24 is caused to output the information corresponding to the result of the simulation, and the processing ends.

In this way, the uttered voice of the operator is acquired, the uttered voice of the operator is voice-recognized, and the keyword stored in the keyword storage unit 61 and the expert stored in the expert utterance information storage unit 62 are acquired. As the evaluation of the voice recognition result is started at a predetermined timing using the example of the utterance contents of, the utterance contents of the trainees can be evaluated correctly without the time and effort of the user (trainer related to train driving). can do. Further, the evaluation start timing should be the timing at which the information indicating that the operation input for the emergency stop is input is supplied or the abnormal event occurs in the simulation scenario being executed from the simulator control unit 52. Is received, or the voice recognition result is either a fixed word indicating the start of communication to a transportation command such as "transportation command, transportation command". It is possible to execute a portion requiring utterance evaluation without making an error and performing unnecessary processing.

Next, the utterance content evaluation process 1, which is the first process executed in step S7 of FIG. 7, will be described with reference to the flowchart of FIG.

In step S21, the evaluation unit 63 reads the keyword information stored in the keyword storage unit 61, for example, as described with reference to FIG.

In step S22, the evaluation unit 63 acquires the scene information of the simulation currently in progress from the simulator control unit 52.

In step S23, the evaluation unit 63 reads, from the expert utterance information storage unit 62, the expert utterance information described with reference to FIG. 4, which corresponds to the scene information of the simulation.

In step S24, the evaluation unit 63 extracts a keyword from the voice recognition result supplied from the voice recognition processing unit 59.

In step S25, the evaluation unit 63 determines whether the number of matches between the extracted keyword and the keyword included in the expert utterance information or the comparison result of the ratio of the classified attributes of the extracted keyword and the expert utterance information. At least any one of them, preferably all of them, is calculated and supplied to the simulator control unit 52, and the process proceeds to step S8 of FIG.

In this way, since the speech recognition result is evaluated using the classified keywords and the expert utterance information that matches the scene of the simulation currently in progress, the utterance content of the operator is compared with the utterance example of the expert. It can be compared and evaluated accurately.

Next, the utterance content evaluation process 2, which is the second process executed in step S7 of FIG. 7, will be described with reference to the flowchart of FIG.

In step S31, the evaluation unit 63 extracts, from the voice recognition result supplied from the voice recognition processing unit 59, a quantitative word indicating, for example, the distance, the number of persons, the number of units, or the like.

In step S32, the evaluation unit 63 calculates the number of extracted quantitative words and supplies the calculated number to the simulator control unit 52, and the process proceeds to step S8 in FIG.

In this way, it is possible to evaluate whether or not the speech recognition result includes a quantitative word. Thereby, it is possible to perform an evaluation to encourage the trainee to use the quantitative word as needed.

Next, the utterance content evaluation processing 3, which is the third processing executed in step S7 of FIG. 7, will be described with reference to the flowchart of FIG.

In step S51, the evaluation unit 63 acquires the scene information of the simulation currently in progress from the simulator control unit 52.

In step S52, the evaluation unit 63 reads the expert utterance information corresponding to the simulation scene information from the expert utterance information storage unit 62.

In step S53, the evaluation unit 63 calculates the concordance rate between the voice recognition result and the expert utterance information and supplies it to the simulator control unit 52, and the process proceeds to step S8 in FIG.

In this way, since the voice recognition result is evaluated by using the expert utterance information that matches the scene of the simulation that is currently proceeding, the operator's utterance content is evaluated with high accuracy by comparing with the expert utterance example. can do.

Next, the utterance content evaluation process 4, which is the fourth process executed in step S7 of FIG. 7, will be described with reference to the flowchart of FIG.

In step S61, the evaluation unit 63 compares the numerical information corresponding to the tone (pitch) of the operator's voice and the utterance speed supplied from the voice recognition processing unit 59 with a predetermined threshold value.

In step S62, the evaluation unit 63 calculates the easiness of transmitting the utterance of the operator based on the comparison result and supplies the utterance to the simulator control unit 52, and the process proceeds to step S8 in FIG. 7.

In this way, since the voice recognition result is compared with the predetermined threshold value, the numerical information corresponding to the tone (pitch) of the voice and the speed of the utterance is compared, so that the easiness of transmitting the utterance of the operator is evaluated. be able to.

In the processing described above, the evaluation unit 63 of the simulator control device 21a is supplied with information indicating that the operation input for the emergency stop has been performed, or the simulator control unit 52 causes an abnormality in the simulation scenario being executed. Whether it receives information indicating that it is the time when the event occurs, or whether the voice recognition result is a fixed word indicating the start of communication to a transportation command such as "transportation command, transportation command", When it came time to evaluate the utterance content, evaluation of the voice recognition result was started. On the other hand, when the predetermined timing comes, the voice recognition may be started and the evaluation of the voice recognition result may be started.

Next, the functional configuration of the simulator control device 21b as the second configuration example will be described with reference to FIG.

In the simulator control device 21b of FIG. 12, parts having the same functions as those of the simulator control device 21a described with reference to FIG. 2 are designated by the same reference numerals, and detailed description thereof will be omitted.

That is, the simulator control device 21b of FIG. 12 is provided with the function of the simulator control unit 71 in place of the simulator control unit 52, and replaces the simulator operation input acquisition control unit 54 with the simulator operation input acquisition control unit 72 (hereinafter, The operation acquisition control unit 72) is provided, the voice recognition processing unit 59 is replaced by the voice recognition processing unit 73, and the utterance content evaluation unit 63 is replaced by the utterance content evaluation unit 74 (hereinafter, referred to as an utterance content evaluation unit 74). , Evaluation unit 74). The simulator control device 21b of FIG. 12 has the same functions as the simulator control device 21a except for the above-mentioned portions.

The simulator control unit 71 notifies the voice recognition processing unit 59 that it is a timing at which an abnormal event occurs in the scenario being executed. The other functions of the simulator control unit 71 are the same as those of the simulator control unit 52 described above.

The operation acquisition control unit 72 acquires the information regarding the operation input of the simulator operator, which is supplied from the driving operation simulator 32 via the network 13, and supplies the information to the simulator control unit 71, the recording unit 60, and the voice recognition processing unit 73. Supply.

The voice recognition processing unit 73 performs voice recognition of the voice uttered by the simulator operator supplied from the voice acquisition unit 58, converts the voice data into text data, and supplies the voice data to the recording unit 60 as a simulation result for recording. It is supplied to the evaluation unit 74. The voice recognition processing unit 73 starts voice recognition processing at the timing when an abnormal event occurs in the simulation and the trainee starts reporting to the transportation command in response to the abnormal event. Specifically, the voice recognition processing unit 73 can start the voice recognition process when, for example, the information indicating that the operation input for the emergency stop has been input is received from the operation acquisition control unit 54. .. Further, the voice recognition processing unit 73 starts the voice recognition process, for example, when it is supplied from the simulator control unit 52 with information indicating that it is the timing at which an abnormal event occurs in the simulation scenario being executed. be able to. The voice recognition processing unit 73 determines whether or not information indicating that an emergency stop operation input has been performed, or whether or not information indicating that an abnormal event has occurred is supplied. It may be possible to determine that it is the start timing of the voice recognition process if any of the conditions are satisfied, and if any of the conditions are met, the voice recognition process is started by making any of the condition determinations. It may be determined that it is timing.

The evaluation unit 74 evaluates the speech content of the simulator operator using the voice recognition result supplied from the voice recognition processing unit 59. The method of evaluating the utterance content by the evaluation unit 74 is the same as that of the evaluation unit 63 described above, but the evaluation start timing is when the voice recognition result is supplied from the voice recognition processing unit 59.

Next, with reference to the flowchart of FIG. 13, a simulation process 2 executed in the train operation simulation system 1 including the emulator controller 21b will be described.

In step S71, the operation input device 22 receives an operation input from a user (a trainer-related instructor or the like) and supplies it to the simulator control device 21b. The simulator control device 21b performs preparation for starting a simulation that matches conditions such as a route and weather based on a user's operation input. The simulator control unit 71 of the simulator control device 21b controls the display screen generation unit 55 to start image generation according to the simulation scenario. The image generated by the display screen generation unit 55 is displayed on the simulation screen display device 31 of the train driving simulator unit 12 via the display control unit 57.

In step S72, the operation acquisition control unit 72 of the simulator control device 21b determines whether the information regarding the operation input from the driving operation simulator 32 is acquired via the network 13. When it is determined in step S72 that the information regarding the operation input has not been acquired, the process of step S72 is repeated until it is determined that the information regarding the operation input has been acquired.

When it is determined in step S72 that the information related to the operation input is acquired, the operation acquisition control unit 72 transfers the acquired information related to the operation input to the simulator control unit 71 and the voice recognition processing unit 73 in step S73. Supply. The simulator control unit 71 controls the display screen generation unit 55 based on the information supplied from the operation acquisition control unit 72 to read the image data corresponding to the scene of the scenario being executed from the video data storage unit 56. Then, the image data displayed on the simulation screen display device 31 is generated, and the simulation based on the operation input is executed. For example, when the driving operation simulator 32 performs a driving operation for departure at the start of the simulation, the simulator control unit 71 causes the display screen generation unit 55 to operate based on the information supplied from the operation acquisition control unit 72. The image displayed on the simulation screen display device 31 is controlled to be a moving image corresponding to the actual departure. After that, the simulator control unit 71 controls the display screen generation unit 55 based on the information supplied from the operation acquisition control unit 72, for example, when an operation input such as speed change or braking is made. Then, the simulation based on the operation input is executed, such as the image displayed on the simulation screen display device 31 corresponding to the driving operation executed by the simulator operator.

In step S74, the voice recognition processing unit 73 receives the information indicating that the operation input for the emergency stop has been input from the operation acquisition control unit 72, or the simulator control unit 71 notifies of the simulation being executed. In the scenario, it is determined whether or not it is the start timing of the voice recognition process, such as whether or not the information indicating that it is the timing at which an abnormal event occurs is supplied. When it is determined in step S74 that the start timing of the voice recognition process has not come, the process returns to step S73, and the subsequent processes are repeated.

When it is determined in step S74 that the start timing of the voice recognition process has come, in step S75, the voice recognition processing unit 73 acquires the utterance voice of the simulator operator supplied from the voice acquisition unit 58.

In step S76, the voice recognition processing unit 73 voice-recognizes the utterance voice of the simulator operator acquired from the voice acquisition unit 58, converts the voice data into text data, and supplies the voice data to the recording unit 60 as a simulation result for recording. The evaluation unit 74 is supplied with it.

When it is determined in step S76 that it is time to evaluate the utterance content, in step S77, at least one of the utterance content evaluation processes 1 to 4 described with reference to FIGS. 8 to 11, preferably, All the utterance content evaluation processes 1 to 4 are executed.

In step S78, the simulator control unit 71 causes the display device 23 to display the information corresponding to the result of the simulation, the information about the operator situation during the simulation recorded in the recording unit 60, and the evaluation unit 74. The evaluation result of the utterance content is supplied to the output control unit 53. The output control unit 53 generates display data corresponding to the result of simulation. The simulator controller 71 also controls the display screen generator 55 to generate display data corresponding to the result of the simulation.

In step S79, the display screen generation unit 55 supplies the display control unit 57 with the display data corresponding to the result of the simulation, and supplies the display data to the simulation screen display device 31 via the network 13 to display the display data. Then, the display device 23 or the printer 24 is caused to output the information corresponding to the result of the simulation, and the processing ends.

In this way, the uttered voice of the operator is acquired, the voice recognition of the uttered voice of the operator is started at a predetermined timing, and the voice recognition result is evaluated. Therefore, the utterance content of the trainee can be correctly evaluated. .. Further, the timing of the start of the voice recognition process is the timing at which the information indicating that the operation input for the emergency stop has been input is received, or the timing at which the abnormal event occurs in the simulation scenario being executed from the simulator control unit 52. Since it is either supplied with information indicating that it is, it is possible to reduce the number of execution points of voice recognition processing as much as possible, without the user's (training staff etc.) time and effort, operator The utterance evaluation of can be performed.

As described above, in the simulator control device 21 according to the embodiment of the present invention, the utterance voice of the operator who is executing the train driving simulation is acquired (for example, step S4 in FIG. 7 or step S73 in FIG. 13). Processing), the acquired utterance voice of the operator is voice-recognized (for example, the processing of step S5 of FIG. 7 or step S74 of FIG. 13), and the utterance content of the operator obtained by the voice recognition and the train In the driving simulation, the operator's utterance content is evaluated by comparing with the reference utterance content to be uttered by the operator (for example, the expert utterance information shown in FIG. 4 stored in the expert utterance information storage unit 62). (For example, the process of step S7 of FIG. 7 or the process of step S77 of FIG. 13), the evaluation of the utterance of the operator can be executed without the trouble and time of the user (instructor or the like regarding train driving). ..

Further, for each scene of the train driving simulation, the reference utterance content corresponding to the scene (for example, the processing of step S23 of FIG. 8 or the processing of step S52 of FIG. 10), and the operation obtained by voice recognition of the corresponding scene Since the utterance contents of the operator are compared and the utterance contents of the operator are evaluated, the utterance contents of the operator can be evaluated for each scene. As a result, the operator's uttered content can be evaluated more accurately.

In addition, a keyword (for example, the information shown in FIG. 3 stored in the keyword storage unit 61) is extracted from the voice recognition result obtained by the processing of the voice recognition processing unit 59 or the voice recognition processing unit 73 (for example, FIG. 8 processing of step S24), the extracted keyword and the keyword included in the reference utterance content (for example, expert utterance information stored in the expert utterance information storage unit 62) are compared, and based on the comparison result. Since the voice recognition result is evaluated (for example, the process of step S25 of FIG. 8), the utterance content of the operator can be evaluated based on the keyword. Since the words (keywords) used in the content to be verbally reported according to the scene are specified to some extent, the keywords included in the utterance content of the operator can be examined to appropriately evaluate the utterance content.

Further, the ratio of the extracted keyword classification to the utterance content and the ratio of the keyword classification included in the reference utterance content (for example, the expert utterance information stored in the expert utterance information storage unit 62) to the reference utterance content Since the operator's utterance content is evaluated (for example, the process of step S25 of FIG. 8), the operator's utterance content can be evaluated even if the keywords used vary. .. For example, “car” and “passenger car” are classified as “accident content” (FIG. 3 ), so even if the words do not match exactly in the comparison with the reference utterance content, the words that are intended to be the same. Therefore, it can be determined that the standard utterance content is supported.

The series of processes described above can be executed by hardware or software. When a series of processes is executed by software, a program that constitutes the software can execute various functions by installing a computer in which dedicated hardware is installed or various programs. It is installed from a program recording medium into a possible general-purpose personal computer or the like.

The program executed by the computer may be a program in which processing is performed in time series in the order described in this specification, or in parallel, or at a necessary timing such as when a call is made. It may be a program in which processing is performed.

The embodiments of the present invention are not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the present invention.

DESCRIPTION OF SYMBOLS 1... Train operation simulation system, 11... Simulator control unit, 12... Train operation simulator unit, 13... Network, 21 (21a, 21b)... Simulator control device, 22... Operation input device, 23... Display device, 24... Printer, 31... Simulation screen display device, 32... Driving operation simulator, 33... Sound collecting device, 51... Operation input control unit, 52, 71... Simulator control unit, 53... Control device output control unit, 54, 72... Simulator operation input Acquisition control unit, 55... Display screen generation unit, 56... Video data storage unit, 57... Simulator screen display control unit, 58... Voice acquisition control unit, 59, 73... Voice recognition processing unit, 60... Operator situation recording unit, 61... Keyword storage unit, 62... Expert utterance information storage unit, 63, 74... Utterance content evaluation unit

Claims (12)

A simulation evaluation device for evaluating a training result by a train driving simulator for carrying out train driving training,
A voice acquisition control unit that controls the acquisition of the voice uttered by the operator of the train driving simulator being executed by the train driving simulator.
A voice recognition processing unit for voice-recognizing the voice uttered by the operator acquired by the control of the voice acquisition control unit;
An evaluation unit that compares the utterance content of the operator obtained by the voice recognition by the voice recognition processing unit with a reference utterance content that the operator should utter in the train driving simulation, and evaluates the utterance content of the operator. And a simulation evaluation device. The simulation evaluation device according to claim 1, wherein
The evaluation unit, for each scene of the train driving simulation, compares the reference utterance content corresponding to the scene, the utterance content of the operator of the scene obtained by the processing of the voice recognition processing unit, the A simulation evaluation device that evaluates the content of the operator's speech. The simulation evaluation device according to claim 1 or 2, wherein
The evaluation unit extracts a keyword from the voice recognition result obtained by the process of the voice recognition processing unit, compares the extracted keyword and the keyword included in the reference utterance content, and based on the comparison result. A simulation evaluation device characterized by evaluating the utterance content of the operator. The simulation evaluation device according to claim 3,
The evaluation unit evaluates the utterance content of the operator by comparing a ratio in the utterance content of the extracted keyword classification with a ratio in the reference utterance content of the keyword classification included in the reference utterance content. A simulation evaluation device characterized by: The simulation evaluation device according to any one of claims 1 to 4,
The simulation evaluation device, wherein the evaluation unit evaluates the utterance content of the operator based on the matching rate between the voice recognition result obtained by the processing of the voice recognition processing unit and the reference utterance content. .. The simulation evaluation device according to any one of claims 1 to 5,
The evaluation unit further evaluates the utterance content of the operator based on whether or not the speech recognition result obtained by the processing of the speech recognition processing unit has a quantitative word. apparatus. The simulation evaluation device according to any one of claims 1 to 6,
The voice recognition processing unit digitizes at least one of the pitch of the utterance voice of the operator whose acquisition is controlled by the voice acquisition control unit, or the speed,
The simulation evaluation device, wherein the evaluation unit further evaluates the utterance content of the operator based on the height or speed of the uttered voice digitized by the processing of the voice recognition processing unit. .. The simulation evaluation device according to any one of claims 1 to 7,
An operation acquisition control unit that controls acquisition of operation input to the train driving simulator,
An image data generation control unit for controlling generation of image data to be displayed and output to the train driving simulator,
The evaluation unit, when the operation acquisition control unit controls the acquisition of the operation input for the emergency stop, when the image data generation control unit controls the generation of the simulation image that requires the emergency stop, or If the voice recognition result obtained by the process of the voice recognition processing unit is a predetermined wording indicating the start of communication, after that timing, the utterance of the operator obtained by the process of the voice recognition processing unit Simulation evaluation device characterized by starting evaluation of contents. The simulation evaluation device according to any one of claims 1 to 7,
An operation acquisition control unit that controls acquisition of operation input to the train driving simulator,
An image data generation control unit for controlling generation of image data to be displayed and output to the train driving simulator,
The voice recognition processing unit, when the operation acquisition control unit controls the acquisition of the operation input for the emergency stop, or the image data generation control unit controls the generation of the simulation image that requires the emergency stop. In that case, after that timing, the voice evaluation of the voice of the operator whose acquisition is controlled by the voice acquisition control unit is started, and the simulation evaluation apparatus. A train operation simulation system including a train operation simulator for performing train operation training and a simulation evaluation device for controlling the train operation simulator,
The train driving simulator,
A simulation screen display unit that displays a display screen corresponding to each scene of the scenario that is progressed in the simulation,
Trainees who perform the driving training, with reference to the image displayed by the simulation screen display unit, a driving operation simulator that performs the operation,
And a sound collection unit that collects a voice uttered by the operator of the driving operation simulator,
The simulation evaluation device,
A voice acquisition control unit that controls the acquisition of the voice uttered by the operator of the train driving simulator collected by the sound collection unit,
A voice recognition processing unit for voice-recognizing the voice uttered by the operator acquired by the control of the voice acquisition control unit;
An evaluation unit that compares the utterance content of the operator obtained by the voice recognition by the voice recognition processing unit with a reference utterance content that the operator should utter in the train driving simulation, and evaluates the utterance content of the operator. And a train driving simulator system. A train operation simulation evaluation method executed by a simulation evaluation device for controlling a train operation simulator for train operation training, comprising:
A voice acquisition control step for controlling the acquisition of the voice uttered by the operator of the train driving simulator being executed by the train driving simulator.
A voice recognition processing step of recognizing the voice uttered by the operator acquired by the processing of the voice acquisition control step,
Evaluation for comparing the utterance content of the operator obtained by the voice recognition processing of the voice recognition processing step and the reference utterance content to be uttered by the operator in the train driving simulation, and evaluating the utterance content of the operator A train operation simulation evaluation method comprising: A computer that controls a train driving simulator for train driving training,
A voice acquisition control step for controlling the acquisition of the voice uttered by the operator of the train driving simulator being executed by the train driving simulator.
A voice recognition processing step of recognizing the voice uttered by the operator acquired by the processing of the voice acquisition control step,
Evaluation for comparing the utterance content of the operator obtained by the voice recognition processing of the voice recognition processing step and the reference utterance content to be uttered by the operator in the train driving simulation, and evaluating the utterance content of the operator A program that executes processing including steps and.

Images