JP6688252B2 - Determination device, determination method, and determination program - Google Patents

Description

  The present invention relates to a determination device, a determination method, and a determination program.

  Conventionally, there is a problem of audio collision, that is, it becomes difficult to hear the audio because the audio is overlapped between the automatic broadcast whose schedule is registered in advance and the announcement that is artificially performed at an arbitrary timing. . For example, in a station premises, a voice collision occurs between an automatic broadcast that announces the arrival of a train and an alert announcement issued by a station staff.

  As a technique for preventing such a voice collision, a technique is known in which announced voices are temporarily stored and the stored voices are reproduced in order according to priority. There is also known a technique of avoiding a collision of voices by transmitting a schedule related to automatic broadcasting from a microphone device to a speaker who makes an announcement.

JP-A-6-276600 JP, 2007-67465, A

  However, in the above-described conventional technique, it is difficult to appropriately hold the content of the information to be transmitted while avoiding the collision of voices depending on the situation. For example, with respect to the departure time of a train and the automatic broadcasting for notifying the arrival of the train, since the broadcast time is important, it is not suitable for the process of temporarily storing and reproducing voice. Even if the schedule is transmitted to the speaker who makes the announcement, there is a possibility that the free time during which the voice does not collide is extremely short, for example, in a station yard where trains frequently travel. For this reason, the speaker may not be able to announce all the contents that should be transmitted. In addition, the speaker may have to wait for a long time before the idle time occurs.

  The present application has been made in view of the above, and provides a determination device, a determination method, and a determination program capable of retaining the content of information to be transmitted while appropriately avoiding a collision of voices depending on the situation. The purpose is to

  The determination device according to the present application includes an acquisition unit that acquires audio information, an allocation unit that gives priority to the audio information acquired by the acquisition unit, and a time period during which the audio information does not collide when the audio information is output. Based on the blank time detected by the detection unit, and the priority given by the giving unit, a determination unit that determines the mode for outputting the voice information, It is characterized by having.

  According to the aspect of the embodiment, it is possible to appropriately avoid the collision of voices according to the situation and retain the content of the information to be transmitted.

FIG. 1 is a diagram for explaining an example of the action and effect exhibited by the determination device according to the embodiment. FIG. 2 is a diagram illustrating an example of a functional configuration of the determination device according to the embodiment. FIG. 3 is a diagram showing an example of the automatic voice table according to the embodiment. FIG. 4 is a diagram illustrating an example of the announcement table according to the embodiment. FIG. 5 is a diagram showing an example of the schedule table according to the embodiment. FIG. 6 is a diagram illustrating an example of the output waiting table according to the embodiment. FIG. 7 is a flowchart (1) showing an example of the determination process according to the embodiment. FIG. 8 is a flowchart (2) showing an example of the determination process according to the embodiment. FIG. 9 is a diagram illustrating an example of a functional configuration of the determination device according to the modification.

  Hereinafter, modes (hereinafter, referred to as “embodiments”) for carrying out a determination device, a determination method, and a determination program according to the present application will be described in detail with reference to the drawings. Note that the determination device, the determination method, and the determination program according to the present application are not limited to this embodiment. Also, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicated description will be omitted.

[1. Concept of decision processing]
First, the concept of the determination process executed by the determination device 100 will be described with reference to FIG. FIG. 1 is a diagram for explaining an example of a function and effect exhibited by the determination device 100 according to the embodiment. The decision processing system 1 shown in FIG. 1 includes a decision device 100, a microphone 20A, a microphone 20B, and an output device 30. The number of devices included in the decision processing system 1 is not limited to the illustrated number.

  The determination device 100 according to the embodiment is realized by a single or a plurality of information processing devices such as a server device and a cloud system. The determination device 100 is managed by, for example, a business operator who operates a train, and controls the input / output of audio in the station premises. In addition, the determination device 100 transmits voice information (for example, train operation) from a predetermined external device via a network N (see FIG. 2) such as a mobile communication network, various wired cables, and a wireless LAN (Local Area Network). It is possible to obtain an automatic voice for inputting), and to communicate with an input device (microphone 20A or microphone 20B in the example of FIG. 1) used to input a voice, an output device 30 that outputs a voice, or the like.

  The microphone 20A and the microphone 20B are audio input devices used by station staff. The microphone 20A and the microphone 20B receive the input of the voice uttered by the station staff, and transmit the voice information generated based on the received voice to the determination device 100. In the following, the microphones 20A and 20B are collectively referred to as "microphone 20" unless it is necessary to distinguish between them.

  The output device 30 is an audio output device such as a speaker installed on the platform of the station. The output device 30 may be a directional speaker that has directivity only in a specific home. Further, the microphone 20 and the output device 30 may be connected to an information device such as a predetermined amplifier and a sound adjusting device.

  In the example of FIG. 1, the determination device 100 controls input / output of an automatic voice announcement (hereinafter, referred to as “automatic voice”) that notifies departure and arrival of a train based on schedule information in which train operation is described. The content of the automatic voice is not limited to the notification of arrival / departure of a train, and may include a warning of walking at the platform, a warning of smoking prohibition, and advertising information. In addition, the determination device 100 controls input / output of an announcement input by a station employee via the microphone 20. In the embodiment, the input / output control means a mode of receiving an input of voice, transmitting a voice signal to the output device 30, and outputting (reproducing) when the output device 30 outputs (reproduces) voice information. Including processing such as determination of.

  As described above, various sounds are output from the output device 30 at the platform of the station where the determination device 100 controls the input / output, so that a sound collision may occur. Specifically, the station staff may call the passengers via the microphone 20 at the same time when the automatic voice that notifies the arrival of the train is output. In this case, there is a possibility that the output of one of the sounds will be interrupted, or the sounds will be confused and output. For this reason, the information to be transmitted to the passengers is damaged, or the uncomfortable voice is reproduced, which is not a desirable situation for the passengers in any case. Therefore, the determination device 100 can hold the content of the voice information to be transmitted while appropriately avoiding the collision of voices according to the situation by the determination process described below. Hereinafter, the outline of the determination process according to the embodiment will be described along the flow with reference to FIG. 1.

  FIG. 1 exemplifies a state of a voice collision at a time of 7:00:00 on a platform of a station where the determining apparatus 100 controls voice input / output. For example, for the microphone 20A, the announcement from the station staff A, "Thank you for using this service. Please refrain from smoking because it is a non-smoking area." (Referred to as “voice information 61”) is accepted. Also, based on the train operation schedule information, an automatic voice announcement (hereinafter referred to as "voice information 62") about the operation, such as "A train bound for Shibuya will soon come to Line 1", is about to be output. There is. In addition, the microphone 20B receives an announcement from the station employee B for avoiding danger to passengers at the home (hereinafter referred to as "voice information 63"), such as "Customer, please drop me down!".

  The determination device 100 acquires these audio information (step S11). The determination device 100 stores the acquired voice information in the voice information storage unit 121. Note that the determination device 100 does not necessarily need to acquire voice information in real time. For example, the determining apparatus 100 may acquire the automatic voice such as the voice information 62 in advance.

  Then, the determination device 100 gives a priority to each of the acquired audio information (step S12). Specifically, the determining apparatus 100 gives priority to each audio information, which is a priority represented by a numerical value from 1 to 10, and the smaller the numerical value, the higher the priority.

  In the embodiment, the determination device 100 gives priority to the voice information based on, for example, the priority tagged to the voice information at the time of input. In the embodiment, the microphone 20 is capable of accepting a selection of whether it is an announcement to be sent in “normal time” or an “emergency time” when receiving a voice. For example, the microphone 20 tags an “ordinary time” announcement when one of the buttons included in the microphone 20 is pressed to receive a voice. In addition, the microphone 20 tags the “emergency” announcement when the other button of the microphone 20 is pressed to accept a voice. Thereby, the microphone 20 can tag the priority when transmitting the voice information to the determination device 100.

  In the example of FIG. 1, it is assumed that the station employee A inputs a voice by pressing a button that is tagged with the “normal time” announcement, out of the buttons included in the microphone 20A. In this case, the determination device 100 tags the voice information 61 with a priority of “3”, for example. In addition, it is assumed that the station employee B inputs a voice by pressing a button for tagging an "emergency" announcement among the buttons provided on the microphone 20B. In this case, the determination device 100 tags the voice information 63 with a priority of “1”, for example. The priority may not be selected by a button or the like provided in the microphone 20, but may be set in advance for the individual microphone 20 itself.

  Further, the determination device 100 gives, for example, a priority set in advance by the operation manager to the automatic voice for notifying the train operation. The determination device 100 gives a priority of “2” to the voice information 62 which is an automatic voice for notifying the train operation, for example.

  Then, the determination device 100 detects that the collision of voices has occurred because three pieces of voice information to be output are acquired at the time of 7:00:00. In this case, the determination device 100 performs processing so that the three pieces of audio information can be output in order. First, the determining apparatus 100 determines to preferentially output the audio information having the highest priority among the acquired audio information. At this time, the determining apparatus 100 temporarily records the voice information other than the voice information having the highest priority and the voice information which is not recorded. In the example of FIG. 1, the voice information 62 is an automatic voice and is pre-recorded, so that the determination device 100 does not need to newly record. On the other hand, the voice information 61 is not the recorded voice information. Therefore, the determination device 100 temporarily stores the voice information 61, which is an announcement having a lower priority than the voice information 63, in the output information storage unit 125 (step S13).

  The determining apparatus 100 determines to output the voice information 63 having the highest priority among the three voice information whose outputs collide. In this case, the determination device 100 causes the voice information 63 to be output regardless of the schedule (schedule) in which the voice information 62 that is an automatic voice is output. This means that an announcement or the like issued by a station staff member in an emergency is set to be preferentially output even when the schedule is interrupted. Therefore, the determination device 100 preferentially outputs the interrupt announcement (voice information 63) having the highest priority among the collided voice information (step S14).

  After outputting the voice information 63, the determination device 100 performs a process of detecting a blank time, which is a time period during which the voice information does not collide (step S15). Specifically, the determination device 100 refers to train schedule information that is held in advance in the output information storage unit 125. Then, the determination device 100 detects the blank time until the timing at which the next automatic voice is output after the output of the voice information 63 is completed.

  At this time, the determination device 100 determines a mode in which the voice information is output, based on the detected blank time and the priority given to each voice information. The mode of outputting the audio information includes the order of outputting the audio information and the mode relating to the reproduction when the audio information is output. The mode relating to reproduction includes the speed of reproduction and selection of a portion to be reproduced of audio information.

  First, the determination device 100 orders the audio information that has been waiting for output (hereinafter, may be referred to as “waiting audio”) based on the priority. In the example of FIG. 1, the determination device 100 ranks the voice information 62 having a higher priority than the voice information 61 among the waiting voices.

  Then, the determining apparatus 100 refers to the reproduction time, which is the time required to reproduce the audio information 62. Then, the determining device 100 determines to output the audio information 62 when the detected blank time is longer than the referred reproduction time.

  Note that the determining apparatus 100 may be able to output the audio information 62 even if the detected blank time is shorter than the reproduction time. For example, the determining apparatus 100 holds, for each piece of audio information, information about a reproduction time when the audio information is shortened (hereinafter, referred to as “shortened reproduction time”). The shortened playback time is, for example, a playback time when omitting a portion of the audio information that can be omitted, or a playback time when the audio information is played slightly faster (for example, 1.3 times normal speed). There will be.

  That is, when the detected blank time is shorter than the reproduction time of the audio information 62 interrupted by the audio information 61 and the blank time is longer than the shortened reproduction time, the determining device 100 determines that It is determined to change the voice information 62 to an outputable form (step S16). Specifically, the determining apparatus 100 determines the output mode such that a part of the audio information 62 is omitted and the audio information 62 is output, or the reproduction speed of the audio information 62 is increased and the audio information 62 is output.

  In this way, the determination device 100 outputs the voice information 62 (automatic voice) according to the length of the blank time (step S17). After outputting the voice information 62, the determination device 100 further detects a blank time (step S18). Then, the determining apparatus 100 determines the output timing of the waiting voice (voice information 61) depending on whether or not the blank time during which the voice information 61 can be output is detected (step S19). Then, as in the case of the voice information 62, the determination device 100 outputs the voice information 61 according to the length of the blank time (step S20).

  As described above, the determining apparatus 100 according to the embodiment acquires voice information and gives priority to the acquired voice information. Then, when outputting the voice information, the determination device 100 detects a blank time that is a time period during which the voice information does not collide. Further, the determination device 100 determines the mode of outputting the audio information based on the detected blank time and the given priority. As a result, the determination apparatus 100 can appropriately hold the content of the information to be transmitted while avoiding the collision of voices depending on the situation. Hereinafter, an example of a functional configuration and an operation effect of the determination device 100 that implements the determination process will be described with reference to the drawings.

[2. Example of functional configuration]
First, the configuration of the determination device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of a functional configuration of the information processing apparatus according to the embodiment. As shown in FIG. 2, the determination device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The determination device 100 has an input unit (for example, a keyboard or a mouse) that receives various operations from an administrator of the determination device 100 or the like, and a display unit (for example, a liquid crystal display or the like) for displaying various information. May be.

  The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives various information to and from the microphone 20 and the output device 30.

  The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. The storage unit 120 according to the embodiment has a voice information storage unit 121 and an output information storage unit 125, as shown in FIG. Hereinafter, an example of information registered in the voice information storage unit 121 and the output information storage unit 125 will be described with reference to FIGS. 3 to 6.

  Information regarding voice information is stored in the voice information storage unit 121. As shown in FIG. 2, the voice information storage unit 121 has an automatic voice table 122 and an announcement table 123 as data tables. Hereinafter, each data table will be described in order.

  The automatic voice table 122 stores information regarding automatic voice among the voice information. FIG. 3 is a diagram showing an example of the automatic voice table 122 according to the embodiment. As shown in FIG. 3, the automatic voice table 122 has “automatic voice type”, “schedule”, “automatic voice ID”, “transmission content”, “priority”, “output timing”, “playback time”, “ There is an item such as “shortened playback time”.

  “Automatic voice type” indicates the type of automatic voice. The type of automatic voice is, for example, whether the automatic voice is an operation guide for informing train arrivals and departures, a warning to passengers at the platform, or an advertisement information such as advertisement. Indicates the audio category. The automatic voice may be given a priority according to the automatic voice type. "Schedule" indicates a schedule for which automatic audio reproduction is scheduled.

  The “automatic voice ID” indicates identification information for identifying each automatic voice. “Transmission content” indicates specific transmission content of automatic voice. The “priority” indicates the priority given to the automatic voice. The “output timing” indicates a specific time when the automatic voice output is scheduled. There are two types of automatic voices that are scheduled to be output depending on the time, such as operation guides, and some that are not scheduled to be output depending on the specific time, such as alerts and advertisement information.

  “Playback time” indicates a basic playback time of automatic voice. The “shortened reproduction time” indicates a reproduction time when the automatic voice is reproduced by being shortened.

  Next, the announcement table 123 will be described. The announcement table 123 stores, among the voice information, information about announcements input by the station staff or the like via the microphone 20. FIG. 4 is a diagram showing an example of the announcement table 123 according to the embodiment. As shown in FIG. 4, the announcement table 123 includes “input device ID”, “announce type”, “announce ID”, “acquisition date”, “communication content”, “priority”, “recording time”, and “shortening”. There is an item such as "reproduction time".

  The “input device ID” indicates identification information for identifying the device into which the voice information related to the announcement has been input. “Announcement type” indicates the type of announcement. As described above, the announcement type may be set by a selection operation when input to the microphone 20, or may be preset for each microphone 20. The normal announcement indicates an announcement that is set and input as normal time. The urgent announcement indicates an announcement that has been set and entered as an emergency. The recording announcement is not an announcement that is output immediately, but an announcement that a station employee or the like inputs to prerecord an advertisement or the like. “Announce ID” indicates identification information for identifying voice information related to the announcement.

  The “acquisition date and time” indicates the date and time when the announcement was acquired. “Communication content” indicates the content of the announcement. The content of the announcement may be, for example, content tagged by the station staff by a function provided in the microphone 20 at the timing of input, or the content analyzed by analyzing the voice of the announcement (for example, text. It may be automatically given from the content of data, etc.).

  The “priority” indicates the priority of the voice information related to the announcement. The “recording time” indicates the time when the announcement was recorded, that is, the reproduction time of the voice information related to the announcement. The “shortened playback time” indicates the playback time when the voice information related to the announcement is shortened and played back.

  Next, the output information storage unit 125 will be described. The output information storage unit 125 stores a schedule for outputting automatic voice and voice information that has been output. As shown in FIG. 2, the output information storage unit 125 has a schedule table 126 and an output waiting table 127 as data tables. Hereinafter, each data table will be described in order.

  The schedule table 126 stores an automatic audio schedule. FIG. 5 is a diagram showing an example of the schedule table 126 according to the embodiment. As shown in FIG. 5, the schedule table 126 has items such as “voice output schedule”, “automatic voice ID”, “playback time”, and “blank time”.

  “Voice output schedule” indicates a scheduled time at which the automatic voice is output. "Automatic voice ID" indicates identification information for identifying automatic voice. The "reproduction time" indicates the reproduction time of the automatic voice. “Blank time” is the time from the end of the reproduction of one automatic voice to the start of the reproduction of the next automatic voice in the schedule, and indicates the time when the output is blank in the output device 30. The blank time may be appropriately updated according to the delayed time when the output of the automatic voice is delayed due to an interrupt announcement or the like.

  The output waiting table 127 stores information about waiting voices waiting for output. FIG. 6 is a diagram illustrating an example of the output waiting table 127 according to the embodiment. As shown in FIG. 6, the output wait table 127 has items such as “voice collision date / time”, “waiting voice ID”, “priority”, “playback time”, and “output mode”.

  “Voice collision date and time” indicates the date and time when the voice information collision occurred. The “waiting voice ID” indicates identification information for identifying voice information that is in a state of not being output and waiting for output when a voice information collision is uttered. The identification information shown as the waiting voice ID is common to the automatic voice ID in FIG. 3 and the announcement ID in FIG. The “priority” indicates the priority given to the waiting voice. The “reproduction time” indicates the reproduction time of the waiting voice. The “output mode” indicates an output mode scheduled when the waiting voice is output. The waiting voice may be played after waiting for the blank time to be detected, or may be played back after the original schedule, so that the waiting voice may be output in such a manner that the playback ends earlier than usual. Specifically, as the output mode, the reproduction time may be shortened by reproducing a part of the audio information, or the reproduction speed may be increased to shorten the reproduction time. For example, the determining apparatus 100 compares the total playback time of the waiting voice with the length of the detected blank time, and determines that the output mode of the waiting voice can be played back shorter if the blank time is shorter. Then, adjust so that the waiting voice is output as quickly as possible.

  Returning to FIG. 2, the description will be continued. The control unit 130 is a controller, and includes, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), and the like inside the determination device 100. Various programs stored in the storage device (for example, the determination program according to the embodiment) are implemented by executing a storage area such as a RAM as a work area. In the example illustrated in FIG. 2, the control unit 130 includes the acquisition unit 131, the addition unit 132, the detection unit 133, the determination unit 134, and the transmission unit 135 (hereinafter, collectively referred to as the processing units 131 to 135). There is a case).

  The connection relationship between the processing units 131 to 135 included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 2 and may be another connection relationship. Further, each processing unit 131 to 135 realizes and executes a function / action (for example, FIG. 1) of the determination processing as described below, but these are functional units arranged for explanation, It does not matter whether it matches the actual hardware element or software module. That is, if the function / action of the following determination process can be realized / executed, the determination device 100 may realize / execute the guidance process in arbitrary function units.

[3. Example of action and effect in decision processing]
Hereinafter, the contents of the determination process executed / implemented by the respective processing units 131 to 135 will be described using the flowcharts shown in FIGS. 7 and 8. FIG. 7 is a flowchart (1) showing an example of the determination process according to the embodiment. It should be noted that FIG. 7 shows an example of a processing procedure of a determination process when voice information other than automatic voice such as an announcement collides.

  First, the acquisition unit 131 determines whether audio information has been acquired (step S101). The acquisition unit 131 acquires voice information by receiving a voice input from a speaker such as a station staff via an input device such as the microphone 20. When the acquisition unit 131 has not acquired the voice information (step S101; No), it waits until the acquisition. When the acquisition unit 131 has acquired the voice information (step S101; Yes), the adding unit 132 adds a priority to the acquired voice information. For example, the giving unit 132 gives a priority to the voice information based on the setting of the microphone 20 or the like (selection of "normal time" or "emergency time") (step S102).

  At this time, the detection unit 133 determines whether a voice collision has occurred when the voice information is acquired (step S103). Note that the detection unit 133 does not determine as a collision only when some audio information is currently output, but determines, for example, a situation in which an automatic audio is scheduled to be output after a few seconds as a collision. Good.

  When the voice collision has not occurred (step S103; No), the acquisition unit 131 continues the process of acquiring the voice information. Although not shown in FIG. 7, the deciding unit 134 may decide to output the audio information acquired in step S101 as it is to the output device 30 when the audio collision does not occur.

  When a sound collision has occurred (step S103; Yes), the acquisition unit 131 determines whether or not there is unrecorded sound in the collision sound information (step S104). When there is unrecorded voice (step S104; Yes), the acquisition unit 131 records the unrecorded voice (step S105). For example, when the acquisition unit 131 acquires two or more pieces of voice information that are separately input from a plurality of speakers and the voice information to which the priority has been given by the addition unit 132, the acquisition unit 131 has the highest priority. Temporarily record anything other than audio information. In other words, the acquisition unit 131 stores the acquired voice information in the voice information storage unit 121. If the voice information that has collided is recorded (step S104; No), the acquisition unit 131 does not need to record the voice information.

  Then, the determination unit 134 determines to output the voice with the highest priority among the voice information that has collided (step S106). Subsequently, the determination unit 134 changes the order of the waiting voices (step S107). That is, the determining unit 134 outputs the voice information with the highest rank (high priority), and then changes the waiting voice with the next highest rank to the highest rank of the waiting voice.

  Then, the detection unit 133 determines whether or not a blank time period during which the waiting voice can be output is detected (step S108). The blank time during which the waiting voice can be output means, for example, a blank time that is longer than the shortened reproduction time of the waiting voice so that the waiting voice can be reproduced when the waiting voice is shortened. When the blank time that can be output is not detected (step S108; No), the detection unit 133 waits until the blank time is detected. On the other hand, when the blank time that can be output is detected (step S108; Yes), the detection unit 133 further determines whether the detected blank time is longer than the next audio information to be output (step S108). Step S109).

  When the detected blank time is longer than the next audio information to be output (step S109; Yes), the determination unit 134 determines to output the audio information to be output (step S110). On the other hand, when the detected blank time is not longer than the next audio information to be output (step S109; No), the determination unit 134 determines the output mode so as to match the blank time (step S111).

  For example, the determination unit 134 determines the reproduction speed of the audio information to be output, according to the length of the blank time. Alternatively, the determination unit 134 selects a reproduction portion in the audio information according to the length of the blank time and determines to output only the selected reproduction portion.

  Then, the determination unit 134 outputs the audio information to be output in the determined mode (step S112). That is, the transmission unit 135 transmits the audio information to the output device 30 in the mode determined by the determination unit 134.

  Here, after the transmitting unit 135 transmits the voice information to the output device 30, the determining unit 134 determines whether or not more waiting voice exists (step S113). Further, when there is a waiting voice (step S113; Yes), the determining unit 134 changes the order of the waiting voice (step S107). On the other hand, when there is no waiting voice (step S113; No), the determination unit 134 ends the processing that has occurred after step S103.

  Next, with reference to FIG. 8, the contents of the determination process executed and realized by the respective processing units 131 to 135 will be described. FIG. 8 is a flowchart (2) showing an example of the determination process according to the embodiment. Note that FIG. 8 illustrates an example of a processing procedure of a determination process when the automatic voice and the voice information such as the announcement collide with each other.

  In the case of the example in FIG. 8, the acquisition unit 131 holds in advance audio information regarding automatic audio and schedule information for outputting (reproducing) automatic audio. The determination unit 134 refers to the schedule information held in the output information storage unit 125 and determines whether or not the timing for reproducing the automatic voice has come (step S201). When the timing for reproducing the automatic voice has not come (step S201; No), the determination unit 134 waits until the timing comes.

  On the other hand, when the timing to reproduce the automatic voice arrives (step S201; Yes), the determining unit 134 reproduces the automatic voice (step S202). The acquisition unit 131 determines whether new audio information is acquired during the reproduction of the automatic audio (step S203). Specifically, the acquisition unit 131 determines whether or not the input of voice information such as an announcement via the microphone 20 has been accepted as new voice information. That is, the acquisition unit 131 determines whether or not a voice collision has occurred. When new voice information is not acquired during the reproduction of the automatic voice (step S203; No), the determination unit 134 waits until the timing of reproducing the next automatic voice comes.

  On the other hand, when new voice information is acquired during the reproduction of the automatic voice (step S203; Yes), the adding unit 132 gives a priority to the new voice information. Then, the determination unit 134 determines whether or not the acquired voice information has a higher priority than the automatic voice being reproduced (step S204).

  When the priority of the acquired audio information is higher than that of the automatic audio being reproduced (step S204; Yes), the determination unit 134 stores the current reproduction position of the automatic audio and stops the automatic audio reproduction. (Step S205). Then, the determining unit 134 determines to output the acquired voice to the output device 30 (step S206).

  This means that when the giving unit 132 gives the voice information a priority higher than a predetermined threshold, the deciding unit 134 decides to preferentially output the voice information regardless of the blank time. Means that. Further, this means that when the voice information having a higher priority than the automatic voice is acquired, the determining unit 134 determines to output the voice information having a higher priority regardless of the schedule. . Specifically, when an emergency announcement for danger avoidance, which has a higher priority than the automatic voice, is input, the determination unit 134 is playing the automatic voice or the blank time is short ( Even if it is a few seconds before the next automatic voice is output), the announcement is interrupted and output.

  As shown in step S205, when the determination unit 134 determines to output the voice information having a higher priority than the automatic voice, when the other voice information including the automatic voice is being output. Determines that the voice information with the higher priority is preferentially output and the output of the other voice information is stopped. Then, the determination unit 134 stores the location where the sound is stopped. Accordingly, the deciding unit 134 can start the reproduction from the stopped position or the vicinity of the stopped position when the audio information in which the collision has occurred is reproduced again. The vicinity of the stopped location is, for example, a location that is a few seconds before the stopped location. That is, when the stopped audio information is reproduced again, the determination unit 134 may determine the output mode such that the audio information is reproduced for a few seconds before the stopped audio information.

  After that, the determination unit 134 determines whether or not the output of the acquired voice information is completed (step S207). When the output of the acquired voice information is not completed (step S207; No), the determination unit 134 continues to output the voice information of high priority. On the other hand, when the output of the acquired voice information is completed (step S207; Yes), the detection unit 133 determines whether or not a blank time period for replaying the stopped automatic voice is detected (step S208).

  For example, when the acquisition unit 131 acquires the automatic voice that is the voice information in which the output timing based on the schedule is preset, the detection unit 133 indicates the schedule information indicating the timing when the automatic voice is output. Refer to. Then, the detection unit 133 detects the blank time based on the schedule set for the automatic voice. Specifically, the detection unit 133 refers to the current time and the blank time described in the schedule table 126 as shown in FIG. 5, and blanks for replaying the stopped automatic voice. Detect time. In addition, in this process, the detection unit 133 may appropriately update the information stored in the schedule table 126. For example, the detection unit 133 appropriately updates the audio output schedule according to the delayed time when the timing of outputting the automatic audio is delayed due to the interruption of the urgent announcement.

  When the blank time that can be output is not detected (step S208; No), the detection unit 133 waits until the blank time is detected. On the other hand, when the outputable blank time is detected (step S208; Yes), the detection unit 133 further detects the detected blank time for a predetermined time (for example, the original reproduction time of the stopped automatic voice or the stopped automatic sound). It is determined whether it is longer than the remaining reproduction time of the sound) (step S209).

  When the detected blank time is longer than the predetermined time (step S209; Yes), specifically, when the detected blank time is longer than the original reproduction time of the stopped automatic voice, the determination unit 134 determines. The mode for deciding to reproduce the stopped automatic voice from the beginning is determined (step S210). This is because it is possible to reliably convey the information to be transmitted to the passengers by reproducing the automatic voice from the beginning, if possible, rather than reproducing the automatic voice from the stopped position.

  Note that the determining unit 134 does not necessarily have to reproduce the automatic voice from the beginning even when the detected blank time is longer than the original reproduction time of the stopped automatic voice. For example, originally, when a predetermined time (for example, several tens of seconds) or more has passed from the timing of reproducing the automatic voice, the automatic voice for which the timing of the operation information and the like is set in detail is quickly terminated. May be preferable. That is, the determining unit 134 may determine the output mode of the automatic voice according to the automatic voice type shown in FIG. 3, for example. Specifically, regarding the automatic voice related to the operation guide, the determination unit 134 does not reproduce the automatic voice again from the beginning when the predetermined time or more has elapsed from the timing of reproducing the automatic voice, and the stop location You may decide to reproduce from. Alternatively, the determination unit 134 outputs an automatic voice such as an alert or advertisement information so that the automatic voice is reproduced again from the beginning even if a predetermined time or more has elapsed from the timing of reproducing the automatic voice. The aspect may be determined.

  When the detected blank time is not longer than the predetermined time (for example, the original reproduction time of the stopped automatic voice or the remaining reproduction time of the stopped automatic voice) (step S209; No), The determination unit 134 determines the mode of outputting the automatic voice (step S211). For example, when the detected blank time is shorter than the reproduction time from the beginning of the stopped automatic voice but is longer than the remaining reproduction time of the stopped automatic voice, the determination unit 134 determines that the audio information with high priority is selected. After the output is finished, it is decided to output the automatic voice again from the vicinity of the reproduction position where the output of the automatic voice is stopped.

  Alternatively, although the deciding unit 134 does not compare the detected blank time with the remaining reproduction time of the stopped automatic voice, the determination unit 134 outputs the automatic voice (for example, the reproduction speed of the automatic voice or the reproduction position). If the automatic audio can be reproduced by the adjustment of, the output is determined in the adjusted manner. In this way, the determination unit 134 outputs the stopped automatic voice again in the determined mode (step S212).

  On the other hand, when the newly acquired voice information has a lower priority than the automatic voice (step S204; No), the acquisition unit 131 temporarily records the acquired voice information (step S221).

  In this case, the determination unit 134 continues the reproduction of the automatic voice (step S222). Then, the determination unit 134 determines whether or not the reproduction of the automatic voice has ended (step S223). When the reproduction of the automatic voice is not completed (step S223; No), the determination unit 134 continues to reproduce the automatic voice. On the other hand, when the reproduction of the automatic voice is completed (step S223; Yes), the detection unit 133 determines whether or not the blank time for reproducing the recorded voice information is detected (step S224).

  Specifically, the detection unit 133 refers to the schedule information and detects a blank time. When the blank time is not detected (step S224; No), the detection unit 133 waits until it is detected. When the blank time is detected (step S224; Yes), the detection unit 133 further determines whether the detected blank time is longer than a predetermined time (for example, the recording time of the acquired voice information) (step S225). ). When the detected blank time is longer than the predetermined time (step S225; Yes), the determination unit 134 determines the mode in which the acquired voice information is reproduced at the normal speed (step S226).

  On the other hand, when the detected blank time is not longer than the predetermined time (step S225; No), the determination unit 134 determines the output mode of the acquired voice information so as to match the blank time (step S227). Then, the determination unit 134 outputs the audio information acquired in the determined mode (step S228). After that, the transmission unit 135 transmits the information regarding the mode determined by the determination unit 134 and the voice information to the output device 30.

[4. Modification example)
The determination device 100 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. Therefore, other embodiments of the determination device 100 described above will be described below. Note that, in the following, description of the same points as those in the embodiment will be appropriately omitted.

[4-1. Generation of notification information]
The determination device 100 may have a configuration for generating notification information for notifying a speaker (for example, a station staff) of information such as a schedule such as an automatic voice, a blank time, and a recorded announcement. For example, FIG. 9 shows a configuration example of the determination device 200 according to the modification. FIG. 9 is a diagram illustrating an example of a functional configuration of the determination device 200 according to the modification. The determination device 200 further includes a generation unit 136 with respect to the determination device 100.

  The generation unit 136 notifies the information about the blank time detected by the detection unit 133, the reproduction time of the predetermined audio information scheduled to be output after the lapse of the blank time, and the reproduction content of the predetermined audio information. Generate notification information.

  For example, the notification information generated by the generation unit 136 is displayed on, for example, the microphone 20 or an information device installed in the vicinity of the microphone 20 when the station staff tries to make an announcement using the microphone 20. Specifically, the notification information includes the length of the blank time until the next automatic voice is output (for example, the number of seconds remaining until the automatic voice is output) and the next automatic voice to be output. The information is tagged, and includes information indicating the transmission contents of the automatic voice, the length of the reproduction time of the automatic voice, and the like. The information included in the notification information is not limited to the information related to the automatic voice, but may include, for example, the information related to the voice information that is temporarily recorded and becomes the standby voice.

  That is, the station staff can avoid the collision between the automatic voice and the announcement by checking the notification information. In addition, the station staff can recognize that the announcement he / she intends to make overlaps with the content of the automatic voice that is output next. That is, the notification information generated by the generation unit 136 can prevent a collision with an automatic voice or recorded voice information.

[4-2. Variation of output mode]
In the above-described embodiment, the determination unit 134 has shown an example in which the output mode is determined by adjusting the speed of the audio information and the reproduction portion. Here, the determination unit 134 may adopt an output mode of a different method.

  For example, the acquisition unit 131 acquires an automatic voice that is given a priority for each phrase. Then, the determining unit 134 extracts the clauses in the descending order of the reproduction order from the clauses included in the voice information and having the reproduction order set in advance, and outputs the extracted clauses in combination. To decide. The phrase may be arbitrarily set by, for example, a person who creates the automatic voice. Specifically, the acquisition unit 131 is an automatic voice that has the content that “a train bound for Shibuya will soon come to Line 1”, and has phrases such as “To Line 1”, “To Shibuya”, and “Visit” The automatic voice having a relatively high priority and the relatively low priority of the phrases “soon” and “no train ga” are acquired. In this case, the deciding unit 134 decides to output an automatic voice in which a clause with a low priority is omitted, for example, when the blank time is shorter than the predetermined time. In this example, the determination unit 134 omits the phrases “soon” and “no train”, and determines to output an automatic voice with the content “I'm going to Shibuya on line 1.”.

  In this way, the determination unit 134 may determine the reproduction point according to the priority of each clause. As a result, the determining unit 134 can shorten the reproduction time and output the audio information without damaging the transmission content. The omitted clause does not necessarily have to be set in advance. For example, the deciding unit 134 may perform a machine learning process on the automatic voice, and may automatically perform a process of setting the priority to a low place even if omitted, which does not impair the meaning.

  Further, the determining unit 134 may determine whether or not to shorten and reproduce the voice based on the entire occupation rate indicated by the automatic voice. Taking the platform of a station as shown in FIG. 1 as an example, it is assumed that the occupancy rate of automatic voice in the time zone is high in the morning and evening hours. In other words, it is assumed that the blank time tends to become shorter as a whole in the morning and evening hours. Therefore, for example, the determining unit 134 may determine to shorten and reproduce the entire voice during a time period when the automatic voice occupies a large proportion. As a result, the deciding unit 134 can secure a large amount of blank time, so that it is possible to prevent the audio information from colliding with each other as a whole.

[4-3. Application of decision processing]
In the above embodiment, an example of preventing the collision of voice information on the platform of the station has been shown. However, the determination process shown in the above embodiment can be applied to various situations.

  For example, the determination process according to the embodiment can be used for a conference in which a plurality of people participate. For example, in a conference, a speaker speaks using a microphone, and the uttered voice is heard by participants through earphones, speakers, or the like. For example, the determination device 100 gives the chairperson the highest priority, and when another speaker speaks, the determination device 100 sequentially outputs the voices with higher priority according to the priority of each speaker. Mode is determined. Further, the determination device 100 may dynamically change the priority of each speaker. For example, the determining apparatus 100 may dynamically change and assign the priority according to the number of utterances. For example, the determining apparatus 100 may gradually reduce the priority of a speaker who has a large amount of utterances, and may make an adjustment so that the utterance is not concentrated on one speaker.

  In addition, the determination process according to the embodiment may be used for a telephone call or the like in which a plurality of people participate online. According to the determination process according to the embodiment, even if a plurality of speakers input voices to the terminal device at the same time, the uttered contents are sequentially output. That is, according to the determination processing according to the embodiment, the collision of voices is prevented, and thus the participant can easily hear the voice. Further, according to the determination process according to the embodiment, since the content uttered by the speaker is recorded, the speaker can utter without waiting for the timing of utterance. The speaker may select the priority by himself / herself.

  Further, the determination process according to the embodiment may be used, for example, for utterance process of an IoT (Internet of Things) device, a smart device, a robot, or the like. For example, when the robot is used for utterance, the robot holds information such as regular maintenance with low priority as an automatic voice that is uttered periodically. Further, the robot holds notification information with high priority (such as notification of failure) as an automatic voice spoken in an emergency. Then, the robot delays the timing of uttering the periodic maintenance information if the conversation has a higher priority even if the timing of uttering the periodic maintenance information comes during some conversation, for example. On the other hand, the robot interrupts the conversation and utters a notification of the failure when the high-priority information such as the failure interrupts even during some conversation.

  Further, the determination process according to the embodiment may be applied to, for example, an automatic announcement used at home. For example, when the determination process according to the embodiment is applied to an automatic announcement used at home, a high priority is set when an emergency situation such as a dish burned is announced. Also, set low priority for non-urgent announcements, such as the delivery of luggage within a few hours. Then, according to the determination process according to the embodiment, even when two announcements collide with each other, an urgent announcement is automatically selected and is preferentially output.

  Further, the determination process according to the embodiment may be used in navigation software such as a car navigation application, for example. For example, when the determination process according to the embodiment is used in the car navigation application, the priority is set to be high when an emergency situation is announced, such as turning right at the next intersection or running out of gasoline. Also, set a low priority for non-urgent announcements, such as a delicious restaurant nearby. In this case, even if the setting is such that two announcements are output when passing through a certain point, according to the determination process according to the embodiment, a voice that announces an emergency situation such as turning right at the next intersection is output. It is output with priority.

  Further, in the determination process according to the embodiment, for example, in a relatively large place such as an airport, the priority is set according to whether the content to be transmitted is for the whole or personal. May be. For example, announcements for all passengers may be set to a high priority, and announcements to be notified to an individual may be set to a relatively low priority.

[5. Other Embodiments]
Note that the above-described embodiment is merely an example, and the present invention also includes the following exemplified embodiments and other embodiments. For example, the functional configuration, the data structure, the order and contents of the processes shown in the flowchart in the present application are merely examples, and the presence or absence of each element, the arrangement and order of the process execution, and the specific contents can be appropriately changed. . For example, the determination process described above can be realized as a device, a method, or a program in a cloud system, in addition to being realized by the determination device 100 as illustrated in the above embodiment.

  In addition, it is general that each of the processing units 131 to 135 included in the determination device 100 and each of the processing units 131 to 136 included in the determination device 200 are realized by independent devices. Similarly, by calling an external platform or the like by API (application program interface) or network computing (so-called cloud, etc.), the respective means shown in the above embodiments are realized, and the configuration of the present invention is flexible. Can be changed. Further, each element such as the means related to the present invention may be realized not only by the arithmetic and control unit of the computer but also by another information processing mechanism such as a physical electronic circuit.

[6. effect〕
As described above, the determination device 100 acquires voice information. Further, the determination device 100 gives priority to the acquired voice information. Further, the determination device 100 detects a blank time, which is a time period during which the respective pieces of audio information do not collide, when outputting the audio information. In addition, the determining apparatus 100 determines a mode in which the audio information is output, based on the detected blank time and the given priority. As a result, the determination device 100 can appropriately hold the content of the information to be transmitted while avoiding the collision of voices depending on the situation.

  Further, the determining apparatus 100 determines the reproduction speed of the audio information to be output according to the length of the blank time. As a result, the determining apparatus 100 can output the voice information without causing a collision even when the blank time is shorter than the voice information to be output.

  Further, the determining apparatus 100 selects a reproduction part in the audio information according to the length of the blank time and determines to output only the selected reproduction part. As a result, the determining apparatus 100 can output the voice information without causing a collision even when the blank time is shorter than the voice information to be output.

  Further, the determining apparatus 100 determines, from the clauses included in the voice information and having the reproduction order set in advance, the clauses in descending order of the reproduction order, and outputs the combined clauses. As a result, the determination device 100 can output the voice information without causing the voice information to collide with each other and without damaging the content to be transmitted, even when the blank time is shorter than the voice information to be output. it can.

  Further, when the priority higher than the predetermined threshold is given to the voice information, the determination device 100 determines to preferentially output the voice information regardless of the blank time. As a result, the determination device 100 can preferentially output urgent announcements and other immediacy contents without causing a collision with other audio information even when a situation occurs in which the audio collides. it can.

  Further, the determination device 100 acquires an automatic voice, which is voice information whose timing to be output based on the schedule is preset. Further, the determination device 100 detects the blank time based on the schedule set to the automatic voice. Thereby, the determining apparatus 100 can accurately grasp the blank time, and thus can appropriately determine the mode in which the acquired voice information is output.

  Further, when the voice information having a higher priority than the automatic voice is acquired, the determination device 100 determines to output the voice information having a high priority regardless of the schedule. Accordingly, the determination device 100 can prevent a situation in which the content having immediacy such as an urgent announcement becomes difficult to hear due to a collision of voices.

  Further, when the decision device 100 decides to output the voice information having a higher priority than the automatic voice, and when other voice information is being output, the determination device 100 outputs the voice information having a higher priority. It is determined that the output of other audio information is stopped while the output of the audio information is given priority. Accordingly, the determination device 100 can prevent a situation in which a content having immediacy such as an urgent announcement becomes difficult to hear due to a collision.

  Further, when the output of the other audio information is stopped, the determination device 100, after the output of the audio information of high priority is finished, from the vicinity of the reproduction point where the output of the other audio information is stopped, Alternatively, it is decided to output the other voice information again from the beginning of the other voice information. Thus, the determining apparatus 100 can output the interrupted automatic voice without impairing the content to be originally transmitted even when there is an interrupt such as an urgent announcement.

  Further, the determination device 100 acquires voice information by accepting a voice input from a speaker via the input device. Further, the determination device 100 gives priority to the voice information based on the setting in the input device. As a result, the determining apparatus 100 can appropriately give priority to voice information that is randomly obtained instead of automatic voice.

  Further, the determination device 100 stores, in the storage unit 120, the voice information input by the speaker and given the priority. In addition, the determination device 100 determines a mode of outputting the audio information stored in the storage unit 120 based on the priority when the blank time is detected. As described above, the determination device 100 can temporarily output the voices to output the voice information in an appropriate order even when the voices collide.

  In addition, the determination device 100, when acquiring voice information to which priority is given, which is two or more voice information input separately from a plurality of speakers, determines other than the voice information with the highest priority. Store in the storage unit. Further, the determination device 100 outputs the voice information with the highest priority among the two or more voice information, and outputs the voice information stored in the storage unit after the output of the voice information with the highest priority is completed. Decide to output one of them. As described above, the determining apparatus 100 may immediately output the voice information with high priority and record the remaining voice information. Thereby, the determination device 100 can output the voice information in an appropriate order.

  Further, the determination apparatus 200 notifies the information about the detected blank time, the reproduction time of the predetermined audio information that is scheduled to be output after the lapse of the blank time, and the reproduction content of the predetermined audio information. Generate information. Accordingly, the determination device 200 can prevent the speaker from making an announcement or the like of the duplicated content in advance, and thus can avoid the occurrence of a collision with the automatic voice or the recorded voice information.

  Further, of the processes described in the above-described embodiment and modified examples, all or part of the processes described as being automatically performed may be manually performed, or described as manually performed. It is also possible to automatically carry out all or part of the processing performed by a known method. In addition, the processing procedures, specific names, information including various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various kinds of information shown in each drawing are not limited to the illustrated information.

  Further, each component of each device shown in the drawings is functionally conceptual, and does not necessarily have to be physically configured as shown. That is, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part of the device may be functionally or physically distributed / arranged in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

  Further, the above-described embodiments and modified examples can be appropriately combined within a range in which the processing content is not inconsistent.

  Also, the above-mentioned "section (module, unit)" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition unit or an acquisition circuit.

1 determination processing system 100 determination device 121 voice information storage unit 122 automatic voice table 123 announcement table 125 output information storage unit 126 schedule table 127 output waiting table 130 control unit 131 acquisition unit 132 addition unit 133 detection unit 134 determination unit 135 transmission unit 136 Generator N Network

Claims (14)

An acquisition unit that acquires audio information including automatic audio with preset timing output based on a schedule ,
An assigning unit that assigns a priority to the voice information acquired by the acquiring unit,
In outputting the voice information, a detection unit that detects a blank time, which is a time period in which the voice information does not collide , based on the schedule set for the automatic voice ,
A blanking time detected by the detection unit, and a determination unit that determines a mode for outputting the voice information based on the priority assigned by the assignment unit,
A determining device, comprising: The determination unit is
According to the length of the blank time, to determine the playback speed of the audio information to be output,
The determination device according to claim 1, wherein The determination unit is
In accordance with the length of the blank time, select a playback portion in the audio information, and determine to output only the selected playback portion,
The determination device according to claim 1 or 2, characterized in that. The determination unit is
Of the clauses included in the voice information, of which the reproduction order is set in advance, the clauses are extracted in descending order of reproduction order, and the extracted clauses are combined to be output.
The determination device according to claim 3, wherein The determination unit is
When a priority higher than a predetermined threshold is given to the voice information by the giving unit, it is determined that the voice information is preferentially output regardless of the blank time.
The determination device according to any one of claims 1 to 4, characterized in that. The determination unit is
When voice information having a higher priority than the automatic voice is acquired, it is determined to output the voice information having a high priority regardless of the schedule.
The determination device according to any one of claims 1 to 5 , characterized in that. The determination unit is
When it is decided to output the voice information having a higher priority than the automatic voice, if other voice information is being output, the voice information having a higher priority is preferentially output. At the same time, it is decided to stop outputting the other audio information.
The determination device according to claim 6 , wherein The determination unit is
When the output of the other audio information is stopped, after the output of the audio information of the higher priority is finished, from the vicinity of the reproduction position where the output of the other audio information is stopped, or the other From the beginning of the voice information of, it is determined to output the other voice information again,
The determination device according to claim 7 , wherein The acquisition unit is
Obtaining the voice information by accepting voice input from the speaker via the input device,
The adding unit is
Assigning a priority to the voice information based on the setting in the input device,
Determining apparatus according to any one of claims 1-8, characterized in that. The acquisition unit is
The voice information input from the speaker, the voice information to which priority is given by the giving unit is stored in a storage unit,
The determination unit is
When the blank time is detected, a mode of outputting the voice information stored in the storage unit is determined based on the priority.
The determination device according to claim 9 , wherein The acquisition unit is
When two or more voice information input separately from a plurality of speakers and the voice information to which the priority is assigned by the assigning unit is acquired, the storage unit saves the voice information other than the highest priority voice information. Stored in
The determination unit is
Of the two or more audio information, the audio information with the highest priority is output, and after the output of the audio information with the highest priority is completed, any of the audio information stored in the storage unit is output. Decide to let
The determination device according to claim 10 , wherein Information about the blank time detected by the detection unit, a playback time of predetermined audio information scheduled to be output after the lapse of the blank time, and a notification notifying the playback content of the predetermined audio information A generator that generates information,
Determining apparatus according to any one of claims 1 to 11, characterized in that it further comprises a. A computer-implemented decision method,
An acquisition step of acquiring voice information including an automatic voice whose output timing is preset based on a schedule ;
An assigning step of assigning priority to the voice information acquired by the acquiring step,
In the output of the voice information, a detection step of detecting a blank time, which is a time period in which each voice information does not collide , based on the schedule set for the automatic voice ,
A deciding step of deciding a mode of outputting the voice information based on the blank time detected by the detecting step and the priority given by the giving step;
A determination method characterized by including. An acquisition procedure for acquiring audio information including automatic audio whose timing output based on a schedule is preset ,
An assigning procedure for assigning a priority to the voice information acquired by the acquiring procedure,
In outputting the voice information, a detection procedure for detecting a blank time, which is a time zone in which the voice information does not collide , based on the schedule set to the automatic voice ,
Based on the blank time detected by the detection procedure and the priority given by the giving procedure, a decision procedure for deciding a mode of outputting the voice information,
A decision program characterized by causing a computer to execute.

Images