Information processing programs, information processing methods, storage media, and application devices

Abstract

To enable the appropriate transmission of necessary information to the driver of a moving vehicle. [Solution] The information processing program is an information processing program that causes a computer to execute the following steps: an intent generation step of generating intent information including string information indicating a string of words or phrases that constitute a notification message to be output audibly to the driver of a mobile vehicle, and intent information indicating the type of notification set for each string; and a transmission step of transmitting intent information to an information processing device that generates a notification message based on the intent information, wherein the intent generation step generates intent information that further includes application priority information indicating the application priority set for each application that generates the intent information.

Description

Technical Field

[0001] The present invention relates to an information processing program, an information processing method, a storage medium, and an application device.

Background Art

[0002] Conventionally, in the case where there are multiple types of voice outputs simultaneously, a technique for controlling the multiple types of voice outputs is known. For example, according to the temporal relationship based on the scheduled time when the significant content of the prior voice information is to be transmitted and the allowable time of delay from the occurrence time of the output request of the subsequent voice information until the output starts, it is determined whether the output of the subsequent voice information can be waited. And a technique is known in which, on the condition that it is determined that waiting is possible, the output of the subsequent voice information is waited, the output of the prior voice information is preferentially performed, and then the output of the subsequent voice information is performed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the above prior art, since only the output of the prior voice information is preferentially performed and then the output of the subsequent voice information is performed, it is not always possible to output both the prior voice information and the subsequent voice information within a desired time. That is, in the above prior art, it is not always possible to convey all the necessary information to the user within a desired time.

[0005] In addition, in the above prior art, there are problems such as the content becoming difficult to understand due to voice interruptions and the problems that the case where a user's response is required is not considered.

[0006] The present invention has been made in view of the above, and aims to provide an information processing program, an information processing method, a storage medium, and an application device that enable the appropriate transmission of necessary information to the driver of a mobile vehicle. [Means for solving the problem]

[0007] The information processing program according to claim 1 is an information processing program for causing a computer to perform the following steps: an intent generation step of generating intent information including string information indicating a string of words or phrases that constitute a notification sentence that is output audibly to the driver of a mobile vehicle, and intent information indicating the type of notification set for each string; and a transmission step of transmitting the intent information to an information processing device that generates the notification sentence based on the intent information, wherein the intent generation step generates intent information that further includes application priority information indicating the application priority set for each application that generates the intent information. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of the configuration of an information processing system according to an embodiment. [Figure 2] Figure 2 shows an example of the configuration of an application device according to an embodiment. [Figure 3] Figure 3 shows an example of the configuration of an information processing device according to the embodiment. [Figure 4] Figure 4 is a diagram illustrating the overview of the information processing according to the embodiment. [Figure 5] Figure 5 shows an example of intent information according to the embodiment. [Figure 6] Figure 6 shows an example of intent information according to the embodiment. [Figure 7] Figure 7 shows an example of intent information according to the embodiment. [Figure 8] Figure 8 is a flowchart showing the information processing procedure according to the embodiment. [Figure 9] Figure 9 is a hardware configuration diagram showing an example of a computer that implements the functions of an application device or information processing device. [Modes for carrying out the invention]

[0009] The embodiments for carrying out the present invention (hereinafter referred to as "embodiments") will be described below with reference to the drawings. However, the present invention is not limited to the embodiments described below. Furthermore, in the drawings, the same parts are denoted by the same reference numerals.

[0010] (Embodiment) [1. Configuration of the Information Processing System] First, the configuration of the information processing system according to the embodiment will be described using Figure 1. Figure 1 is a diagram showing an example configuration of the information processing system according to the embodiment. As shown in Figure 1, the information processing system 1 includes an application device 10 (hereinafter also referred to as the application device 10) and an information processing device 100. The application device 10 and the information processing device 100 are connected to each other via a predetermined network N, either by wired or wireless communication. Note that the information processing system 1 shown in Figure 1 may include multiple application devices 10 and multiple information processing devices 100.

[0011] The application device 10 is an information processing device that executes an application that provides information to the driver of a vehicle (an example of a mobile body), and can be implemented by, for example, a server device or a cloud system. Figure 1 shows an example where the application device 10 is implemented by a cloud system. In the following description, the mobile body is described as a vehicle, but the mobile body is not limited to a vehicle. The technology related to this disclosure can be applied to various products. For example, the technology related to this disclosure may be implemented as a device mounted on any type of mobile body such as an automobile, electric vehicle, hybrid electric vehicle, motorcycle, bicycle, personal mobility device, airplane, drone, ship, or robot.

[0012] Also, hereinafter, the application device 10 will be described as application devices 10-1 and 10-2 according to the type of application executed by the application device 10. For example, the application device 10-1 is the application device 10 on which application #1 (hereinafter also referred to as app #1) is executed. Also, for example, the application device 10-2 is the application device 10 on which application #2 (hereinafter also referred to as app #2) is executed. Also, hereinafter, when the application devices 10-1 and 10-2 are described without particular distinction, they will be referred to as the application device 10.

[0013] The information processing device 100 is, for example, a stationary navigation device or a drive recorder installed in a vehicle. Note that the information processing device 100 is not limited to a navigation device or a drive recorder, and a portable terminal such as a smartphone used by a vehicle occupant may be adopted.

[0014] [2. Configuration of the Application Device] Next, the configuration of the application device according to the embodiment will be described with reference to FIG. 2. FIG. 2 is a diagram showing a configuration example of the application device according to the embodiment. As shown in FIG. 2, the application device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0015] (Communication Unit 11) The communication unit 11 is realized, for example, by a NIC (Network Interface Card) or the like. Also, the communication unit 11 is connected to the network N (see FIG. 1) by wire or wirelessly.

[0016] (Storage Unit 12) The storage unit 12 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. For example, the storage unit 12 stores information regarding a machine learning model used to generate intent information. Further, the storage unit 12 stores app priority information indicating the app priority set for each application.

[0017] Also, the storage unit 12 stores state information including sensor information such as vehicle position information, guidance route information including a search route and a destination, user interest information, user schedule information, etc. in a form linked to the ID of the information processing device 100 (an example of identification information for identifying the information processing device 100 mounted on each vehicle).

[0018] (Control unit 13) The control unit 13 is a controller, and is realized, for example, by a CPU (Central Processing Unit), MPU (Micro Processing Unit), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), etc., when various programs (corresponding to an example of an information processing program) stored in an internal storage device of the application device 10 are executed using a storage area such as a RAM as a work area. In the example shown in FIG. 2, the control unit 13 includes an acquisition unit 131, an intent generation unit 132, and a transmission unit 133.

[0019] (Acquisition unit 131) The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires a machine learning model that takes an app notification text as an input and outputs intent information. For example, the acquisition unit 131 acquires a machine learning model learned based on learning data including a combination of an app notification text and intent information. When the acquisition unit 131 acquires a machine learning model, it stores information regarding the acquired machine learning model in the storage unit 12.

[0020] Furthermore, the acquisition unit 131 acquires sensor information, including the location information of the information processing device 100, and the results of voice recognition of users riding in the vehicle, from the information processing device 100 via the communication unit 11.

[0021] (Intent generation unit 132) The intent generation unit 132 generates intent information, which is metadata information relating to a notification message that is output audibly to the driver of a mobile vehicle. Here, the intent information according to the embodiment will be explained using Figures 5 to 7. Figures 5 to 7 show an example of intent information according to the embodiment.

[0022] The intent generation unit 132 generates an app notification message related to the notification. In the example shown in Figure 5, the intent generation unit 132 generates app notification message #13, which reads, "Turn right at the next intersection. Convenience store A is a landmark. Please drive in the innermost lane." based on the guidance route information and location information from the information processing device 100. After generating app notification message #13, the intent generation unit 132 generates intent information T1 based on the generated app notification message #13.

[0023] For example, the intent generation unit 132 extracts a string from the app notification message #13. Next, the intent generation unit 132 generates intent information T1 containing the extracted string. In the example shown in Figure 5, the intent generation unit 132 refers to the storage unit 12 to obtain a machine learning model #1 that takes the app notification message as input and outputs a string indicating the notification content. For example, the intent generation unit 132 obtains a machine learning model #1 that has been trained on training data that includes combinations of app notification messages and strings indicating the notification content. Once the intent generation unit 132 obtains the machine learning model #1, it inputs the app notification message #13 into the obtained machine learning model #1 and obtains strings indicating the notification content, such as "next intersection," "turn right," "convenience store," and "innermost," output from the machine learning model #1. The intent generation unit 132 generates intent information T1 containing the obtained string.

[0024] Alternatively, instead of using a machine learning model, the intent generation unit 132 may use natural language processing techniques such as morphological analysis to extract strings from the app notification text. For example, the intent generation unit 132 performs morphological analysis on the app notification text ##13 to extract words such as "ahead," "intersection," "turn right," "convenience store A," "number one," and "inside" from the app notification text #1. Next, the intent generation unit 132 compares the extracted words with predetermined dictionary information to determine the part of speech, conjugation type, synonyms, etc. Subsequently, based on the results of comparing the extracted words with predetermined dictionary information, the intent generation unit 132 generates intent information T1 that includes strings indicating the notification content, such as "next intersection," "turn right," "convenience store," and "insidemost."

[0025] Furthermore, the intent generation unit 132 generates intent information that includes intent information indicating the type of notification set for each string. For example, the intent generation unit 132 refers to the storage unit 12 to obtain machine learning model #2, which takes an app notification text as input and outputs intent information indicating the type of notification for each string. For example, the intent generation unit 132 obtains machine learning model #2 that has been trained based on training data that includes combinations of app notification texts and intent information set for each string. For example, the intent generation unit 132 obtains machine learning model #3 that has been trained to output a string indicating the type of notification for each string as output information when an app notification text is input.

[0026] When the intent generation unit 132 obtains machine learning model #2, it inputs the app notification text #1 into the obtained machine learning model #2 and obtains intent information for each string output from machine learning model #2. In Figure 5, the intent generation unit 132 obtains intent information for the strings "next intersection" and "turn right" as the string "route," which indicates the type of notification. The intent generation unit 132 also obtains intent information for the string "convenience store," as the string "landmark," which indicates the type of notification. Furthermore, the intent generation unit 132 obtains intent information for the string "innermost," as the string "driving lane," which indicates the type of notification. The intent generation unit 132 generates intent information T1, which includes the intent information for each obtained string.

[0027] Furthermore, the intent generation unit 132 generates intent information that includes content priority information indicating the content priority set for each string. For example, the intent generation unit 132 refers to the storage unit 12 to obtain machine learning model #3, which takes an app notification text as input and outputs content priority information indicating the content priority for each string. For example, the intent generation unit 132 obtains machine learning model #3 that has been trained based on training data that includes combinations of app notification texts and content priority information set for each string. For example, the intent generation unit 132 obtains machine learning model #3 that has been trained to output numbers indicating the content priority for each string (for example, numbers such as 1, 2, 3, ... in order from highest priority) as output information when an app notification text is input.

[0028] When the intent generation unit 132 obtains machine learning model #3, it inputs the app notification message #1 into the obtained machine learning model #3 and obtains content priority information for each string output from machine learning model #3. In Figure 5, the intent generation unit 132 obtains content priority information for the strings "next intersection" and "turn right," which is the number "1" indicating content priority. The intent generation unit 132 also obtains content priority information for the string "convenience store," which is the number "3" indicating content priority. Furthermore, the intent generation unit 132 obtains content priority information for the string "innermost," which is the number "2" indicating content priority. The intent generation unit 132 generates intent information T1, which includes the obtained content priority information for each string.

[0029] Furthermore, the intent generation unit 132 generates intent information that also includes notification priority information indicating the notification priority set for each intent information. For example, the intent generation unit 132 refers to the storage unit 12 to obtain machine learning model #4, which takes an app notification text as input and outputs notification priority information. For example, the intent generation unit 132 obtains machine learning model #4 that has been trained based on training data that includes combinations of app notification texts and notification priority information. For example, the intent generation unit 132 obtains machine learning model #4 that, when an app notification text is input, outputs a number indicating the notification priority of the notification related to the app notification text (for example, numbers such as 1, 2, 3, ... in order from highest priority).

[0030] When the intent generation unit 132 obtains machine learning model #4, it inputs app notification message #1 into the obtained machine learning model #4 and obtains notification priority information output from machine learning model #4. In Figure 5, the intent generation unit 132 obtains notification priority information (In priority), which is the number "1" indicating the notification priority, for the notification related to app notification message #1. The intent generation unit 132 generates intent information T1, which includes the obtained notification priority information.

[0031] Furthermore, the intent generation unit 132 generates intent information that also includes application priority information, which indicates the application priority set for each application generating intent information. Although not shown in the diagram, in Figure 5, the intent generation unit 132 refers to the storage unit 12 and obtains application priority information, which indicates the application priority set for application #1. For example, the intent generation unit 132 obtains a number indicating the application priority set for each application (for example, numbers such as 1, 2, 3, ... in order from highest priority). In Figure 5, the intent generation unit 132 obtains application priority information, which is the number "1" indicating the application priority. The intent generation unit 132 generates intent information T1, which includes the obtained application priority information.

[0032] Furthermore, the intent generation unit 132 may determine overall priority information indicating the overall priority of the intent information based on the notification priority information and the application priority information. For example, the intent generation unit 132 may calculate an average value by adding the number indicating the notification priority and the number indicating the application priority, and use the calculated average value as overall priority information indicating the overall priority of the intent information. Although not shown in the diagram, in Figure 5, the intent generation unit 132 uses an average value "1" obtained by adding the number "1" indicating the notification priority and the number "1" indicating the application priority as overall priority information indicating the overall priority of intent information T1.

[0033] In the example shown in Figure 6, the intent generation unit 132 generates an app notification message #24 based on the location information of the information processing device 100, which reads, "After turning right at the next intersection, you will find the cake shop "XXX" that has recently been featured on TV 400m ahead. We recommend the Mont Blanc, which is not too sweet." Subsequently, the intent generation unit 132 generates intent information T2 based on the app notification message #24, in the same manner as in the case of Figure 5 described above. Specifically, the intent generation unit 132 generates intent information T2 that includes strings indicating the notification content, such as "next intersection," "turn right," "400m ahead," "cake shop," "shop name "XXX"," "featured on TV," "Mont Blanc," and "not too sweet."

[0034] Furthermore, in Figure 6, the intent generation unit 132 acquires intent information, which is the string "route" indicating the type of notification, for the strings "next intersection", "turn right", and "400m ahead". The intent generation unit 132 also acquires intent information, which is the string "recommended" indicating the type of notification, for the strings "cake shop", "shop name "XXX"", and "popular on TV". The intent generation unit 132 also acquires intent information, which is the string "recommended" indicating the type of notification, for the strings "Mont Blanc" and "not too sweet". The intent generation unit 132 generates intent information T2, which includes the intent information for each acquired string.

[0035] Furthermore, in Figure 6, the intent generation unit 132 acquires content priority information, which is the number "1" indicating content priority, for the strings "next intersection", "turn right", "400m ahead", and "cake shop". The intent generation unit 132 also acquires content priority information, which is the number "3" indicating content priority, for the string "store name "XXX"". The intent generation unit 132 also acquires content priority information, which is the number "4" indicating content priority, for the strings "popular on TV" and "not too sweet". The intent generation unit 132 also acquires content priority information, which is the number "2" indicating content priority, for the string "Mont Blanc". The intent generation unit 132 generates intent information T2, which includes the content priority information for each acquired string.

[0036] Furthermore, in Figure 6, the intent generation unit 132 obtains notification priority information (In priority), which is the number "2" indicating the notification priority, for the notification related to app notification message #2. The intent generation unit 132 then generates intent information T2, which includes the obtained notification priority information.

[0037] Although not shown in the diagram, in Figure 6, the intent generation unit 132 refers to the storage unit 12 and obtains application priority information, which is the number "2" indicating the application priority set for application #2. The intent generation unit 132 then generates intent information T2, which includes the obtained application priority information.

[0038] Although not shown in the diagram, in Figure 6, the intent generation unit 132 adds the number "2" indicating notification priority and the number "2" indicating application priority, and uses the average value "2" to represent the overall priority of intent information T2 as overall priority information.

[0039] In the example shown in Figure 7, the intent generation unit 132 generates an app notification message #34 that reads, "A passing shower is forecast near your home in one hour. Are you sure you want to bring in your laundry? (If the user responds 'No',) I will connect you to your home via video call. / (If the user responds 'Yes', end)." Subsequently, the intent generation unit 132 generates intent information T3 based on the app notification message #34, in the same manner as in the case of Figure 5 described above. Specifically, the intent generation unit 132 generates intent information T3 that includes strings indicating the notification content, such as "passing shower," "near home," "one hour later," "laundry," "Yes / No," and "Yes: end, No: video call."

[0040] Furthermore, in Figure 7, the intent generation unit 132 acquires intent information, which is the string "weather forecast," for the strings "passing shower," "near home," and "1 hour later," indicating the type of notification. The intent generation unit 132 also acquires intent information, which is the string "information," for the string "laundry," indicating the type of notification. Furthermore, the intent generation unit 132 acquires intent information, which is the string "user response," for the strings "Yes / No" and "Yes: End, No: Video call," indicating the type of notification. The intent generation unit 132 generates intent information T3, which includes the intent information for each acquired string.

[0041] Furthermore, in Figure 7, the intent generation unit 132 acquires content priority information, which is the number "1" indicating content priority, for the strings "passing shower" and "near home". The intent generation unit 132 also acquires content priority information, which is the number "2" indicating content priority, for the string "1 hour later". The intent generation unit 132 also acquires content priority information, which is the number "3" indicating content priority, for the string "laundry". The intent generation unit 132 also acquires content priority information, which is the number "4" indicating content priority, for the strings "Yes / No" and "Yes: finished, No: video call". The intent generation unit 132 generates intent information T3, which includes the content priority information for each acquired string.

[0042] Furthermore, in Figure 7, the intent generation unit 132 obtains notification priority information (In priority), which is the number "3" indicating the notification priority, for the notification related to app notification message #3. The intent generation unit 132 then generates intent information T3, which includes the obtained notification priority information.

[0043] Although not shown in the diagram, in Figure 7, the intent generation unit 132 refers to the storage unit 12 and obtains application priority information, which is the number "3" indicating the application priority set for application #3. The intent generation unit 132 then generates intent information T3, which includes the obtained application priority information.

[0044] Although not shown in the diagram, in Figure 7, the intent generation unit 132 adds the number "3" indicating notification priority and the number "3" indicating application priority, and uses the average value "3" as the overall priority information for intent information T3.

[0045] (Transmitter 133) The transmitting unit 133 transmits intent information to the information processing device 100, which generates a notification message based on the intent information. For example, when intent information is generated by the intent generation unit 132, the transmitting unit 133 transmits the intent information to the information processing device 100. For example, when intent information T1 to T3 is generated by the intent generation unit 132, the transmitting unit 133 transmits intent information T1 to T3 to the information processing device 100.

[0046] [3. Configuration of the Information Processing Device] Next, the configuration of the information processing device according to the embodiment will be described using Figure 3. Figure 3 is a diagram showing an example of the configuration of the information processing device according to the embodiment. As shown in Figure 3, the information processing device 100 includes a communication unit 110, a storage unit 120, a sensor unit 130, an audio output unit 140, an audio recognition unit 150, and a control unit 160.

[0047] (Communications Department 110) The communication unit 110 is implemented by, for example, a NIC, a modem chip, and an antenna module. The communication unit 110 is also connected to the network N (see Figure 1) by wire or wireless connection.

[0048] (Storage unit 120) The memory unit 120 is implemented by, for example, semiconductor memory elements such as RAM and flash memory, or storage devices such as hard disks and optical discs.

[0049] (Sensor unit 130) The sensor unit 130 is equipped with various sensors. For example, the sensor unit 130 is equipped with a GNSS (Global Navigation Satellite System). The GNSS sensor uses GNSS to receive radio waves containing positioning data transmitted from navigation satellites. This positioning data is used to detect the absolute position of the vehicle from latitude and longitude information, etc. The GNSS used may be, for example, GPS (Global Positioning System) or another system. The sensor unit 130 also outputs the positioning data generated by the GNSS sensor to the control unit 160.

[0050] Furthermore, the sensor unit 130 includes a vehicle speed sensor. The vehicle speed sensor detects the vehicle's speed and generates vehicle speed data corresponding to that speed. The sensor unit 130 also outputs the vehicle speed data generated by the vehicle speed sensor to the control unit 160.

[0051] Furthermore, the sensor unit 130 includes an acceleration sensor. The acceleration sensor detects the acceleration of the vehicle and generates acceleration data corresponding to the acceleration. The sensor unit 130 outputs the acceleration data generated by the acceleration sensor to the control unit 160. The sensor unit 130 may also calculate the speed based on the acceleration data.

[0052] The sensor unit 130 also includes a camera. Under the control of the control unit 160, the camera takes pictures of the area around the vehicle and generates captured images. The sensor unit 130 also outputs the captured images generated by the camera to the control unit 160.

[0053] (Audio output unit 140) The audio output unit 140 includes a speaker and converts the digital audio signal input from the control unit 160 into an analog audio signal by D / A (Digital / Analog) conversion, and outputs audio corresponding to the analog audio signal from the speaker.

[0054] Furthermore, the audio output unit 140 outputs the notification text generated by the generation unit 163 to the driver as an audio message. Specifically, the audio output unit 140 outputs multiple application notification texts in the order determined by the generation unit 163, one by one.

[0055] (Voice recognition unit 150) The speech recognition unit 150 is implemented by the control unit 160 executing a speech recognition application stored in the memory unit 120. The speech recognition unit 150 also recognizes the driver's speech. Furthermore, the speech recognition unit 150 converts the driver's speech received by the microphone, which is part of the voice input unit (not shown), into text data. Note that the text data conversion process may be performed on a dedicated server (not shown).

[0056] Furthermore, the voice recognition unit 150 is equipped with a barge-in function. The voice recognition unit 150 enables the barge-in function when the decision unit 164 determines that it should be enabled. On the other hand, the voice recognition unit 150 disables the barge-in function when the decision unit 164 determines that it should not be enabled.

[0057] (Control unit 160) The control unit 160 is a controller, and is realized by executing various programs (corresponding to an example of an information processing program) stored in the internal memory of the information processing device 100 using a memory area such as RAM as a working area, for example, by a CPU, MPU, ASIC, FPGA, etc. In the example shown in Figure 3, the control unit 160 has an acquisition unit 161, a calculation unit 162, a generation unit 163, and a determination unit 164.

[0058] (Acquisition part 161) The acquisition unit 161 acquires various types of information. Specifically, the acquisition unit 161 acquires situational information, including driving information regarding the driving status of a moving object and driving information regarding the driver's driving status. For example, the acquisition unit 161 acquires from the sensor unit 130 information such as the driving speed of the moving object, the density of vehicles, congestion information, road type (expressway, city street, residential road, suburban road, mountain road, straight road, intersection, curve, etc.), time, and weather (daytime, nighttime, sunny, rainy, snowy, snowy, icy, etc.) as an example of driving information. The acquisition unit 161 may also acquire information such as congestion information, road type (expressway, city street, residential road, suburban road, mountain road, straight road, intersection, curve, etc.), time, and weather (daytime, nighttime, sunny, rainy, snowy, snowy, icy, etc.) from an external information provider.

[0059] Furthermore, the acquisition unit 161 acquires, as an example of driving information, the driver's attribute information, the presence or absence of passengers, and the passengers' attribute information. For example, the acquisition unit 161 acquires the driver's attribute information and passengers' attribute information that have been pre-registered in a predetermined database. Alternatively, the acquisition unit 161 may acquire information from the driver regarding the presence or absence of passengers based on the driver's self-declaration.

[0060] Furthermore, the acquisition unit 161 acquires intent information from each of the multiple applications. Here, the overview of information processing by the information processing device 100 will be explained using Figure 4. Figure 4 is a diagram showing an overview of information processing according to the embodiment. In the example shown in Figure 4, the acquisition unit 161 of the information processing device 100 simultaneously acquires intent information T1 to T3 from each of the three applications #1 to #3.

[0061] For example, the acquisition unit 161 acquires intent information from the application, which includes string information indicating the strings that make up the notification message to be voice-output to the driver of the mobile vehicle, and intent information indicating the type of notification set for each string. The acquisition unit 161 also acquires intent information which further includes content priority information indicating the content priority set for each string. The acquisition unit 161 also acquires intent information which further includes notification priority information indicating the notification priority set for each intent information. The acquisition unit 161 also acquires intent information which further includes application priority information indicating the application priority set for each application.

[0062] Furthermore, the acquisition unit 161 acquires an output grace period timing that indicates when the notification of the notification message should be completed. Here, the output grace period timing may be either the time when the notification of the notification message should be completed or the location where the notification of the notification message should be completed. For example, the acquisition unit 161 acquires the output grace period timing based on intent information acquired from the application. For example, based on intent information T1, the acquisition unit 161 acquires the information "next intersection" as the output grace period timing for the notification message related to intent information T1. Also, based on intent information T2, the acquisition unit 161 acquires the information "next intersection" and "cake shop" as the output grace period timing for the notification message related to intent information T2. ​​Also, based on intent information T3, the acquisition unit 161 acquires the information "1 hour later" as the output grace period timing for the notification message related to intent information T3.

[0063] (Calculation section 162) The calculation unit 162 calculates the output grace period, which is the remaining time until the output grace period timing is reached. Specifically, the calculation unit 162 calculates the output grace period based on the output grace period timing acquired by the acquisition unit 161. For example, if the output grace period timing is a predetermined time, the calculation unit 162 calculates the remaining time from the current time to the predetermined time, which is the output grace period, as the output grace period. Also, if the output grace period timing is a predetermined position, the calculation unit 162 calculates the estimated arrival time from the current position to the predetermined position, which is the output grace period, as the output grace period. For example, the calculation unit 162 calculates the estimated arrival time based on the distance to the predetermined position and the expected average speed of the moving object.

[0064] Furthermore, the calculation unit 162 calculates a safety level, which indicates the degree of safety of the vehicle's driving conditions or the driver's driving conditions, based on the situation information acquired by the acquisition unit 161. For example, the calculation unit 162 calculates a higher safety level the lower the vehicle speed. Also, for example, the calculation unit 162 calculates a higher safety level when driving on suburban roads than on urban roads.

[0065] Furthermore, the calculation unit 162 calculates a margin of safety, which indicates the degree to which the driver has the capacity to pay attention to matters other than driving the moving object, based on the situational information acquired by the acquisition unit 161. For example, the calculation unit 162 calculates a higher margin of safety when driving on a straight road than on a road that is not straight. Also, for example, the calculation unit 162 calculates a lower margin of safety when it is raining than when the weather is sunny.

[0066] Next, the calculation unit 162 calculates the safety level and margin level, and then calculates the output grace period based on the calculated safety level and margin level. Specifically, the calculation unit 162 calculates a longer output grace period the higher the safety level. For example, the calculation unit 162 calculates a longer output grace period than the estimated arrival time the higher the safety level. Also, the calculation unit 162 calculates a longer output grace period the higher the margin level. For example, the calculation unit 162 calculates a longer output grace period than the estimated arrival time the higher the safety level.

[0067] (Generation unit 163) The generation unit 163 generates a notification message to be output audibly to the driver based on the intent information. For example, the generation unit 163 generates a notification message to be output audibly to the driver based on the string information and intent information included in the intent information. More specifically, the generation unit 163 generates a notification message containing a string based on the string information and intent information, and modifies the expression of the notification message so that the timing of the completion of the audible output of the generated notification message is before the output grace period. By modifying the expression of the notification message, the generation unit 163 generates a notification message that can be played back within the output grace period.

[0068] For example, the generation unit 163 generates a temporary notification message containing a string, and if the playback time of the temporary notification message does not exceed the output grace period, it changes the expression of the notification message to a more polite expression compared to the temporary notification message. For example, the generation unit 163 generates a temporary notification message, "Turn right at the next intersection," with a playback time of 2 seconds, based on the strings "next intersection" and "turn right" contained in the intent information T1 shown in Figure 5, and the string "route," which is intent information corresponding to the strings "next intersection" and "turn right." In this case, if the output grace period is 3 seconds, the generation unit 163 changes the expression of the notification message to "Turn right at the next intersection" (playback time 2.5 seconds), which is a more polite expression compared to the temporary notification message, because the playback time of the temporary notification message (2 seconds) does not exceed the output grace period (3 seconds).

[0069] Furthermore, the generation unit 163 generates a provisional notification text containing strings, and if the playback time of the provisional notification text exceeds the output grace period, it changes the expression of the notification text to a style that does not include auxiliary verbs at the end of sentences. For example, the generation unit 163 generates a provisional notification text, "Turn right at the next intersection," with a playback time of 2.5 seconds, based on the strings "next intersection" and "turn right" contained in the intent information T1 shown in Figure 5, and the string "route," which is intent information corresponding to the strings "next intersection" and "turn right." In this case, assuming the output grace period is 2 seconds, the generation unit 163 changes the expression of the notification text to "Turn right at the next intersection" (playback time 2 seconds), as the playback time of the provisional notification text (2.5 seconds) exceeds the output grace period (2 seconds). Note that if the playback time of the provisional notification text exceeds the output grace period, the generation unit 163 may change the expression of the notification text to a style that ends with a noun.

[0070] Furthermore, the generation unit 163 generates a notification message to be output as voice to the driver based on the string information, intent information, and content priority information. Specifically, the generation unit 163 generates a notification message containing strings based on content priority so that the voice output of the notification message is completed before the output grace period. More specifically, the generation unit 163 generates a temporary notification message containing multiple strings with different content priorities, and if the playback time of the temporary notification message exceeds the output grace period, it deletes the strings in the temporary notification message in order from the lowest content priority to generate a notification message that can be played within the output grace period.

[0071] For example, the generation unit 163 generates a provisional notification message that includes all of the strings "next intersection" and "turn right" with a content priority of "1" included in the intent information T1 shown in Figure 5, the string "innermost lane" with a content priority of "2", and the string "convenience store" with a content priority of "3", which is "turn right at the next intersection. Convenience store A is a landmark. Please drive in the innermost lane." Next, the generation unit 163 estimates the playback time of the provisional notification message to be 8 seconds.

[0072] At this point, assuming the output grace period is 7 seconds, the generation unit 163 determines that the playback time of the provisional notification message (8 seconds) exceeds the output grace period (7 seconds), and therefore deletes the string "convenience store" which has a low content priority of "3" among the multiple strings included in the provisional notification message. Next, the generation unit 163 generates a provisional notification message, "Turn right at the next intersection. Drive in the innermost lane," which includes the strings "next intersection" and "turn right" with a content priority of "1," and the string "innermost" with a content priority of "2." Next, the generation unit 163 estimates the playback time of the provisional notification message to be 6 seconds. Since the playback time of the provisional notification message (6 seconds) does not exceed the output grace period (7 seconds), the generation unit 163 adopts the generated provisional notification message as the notification message.

[0073] Furthermore, the generation unit 163 generates multiple different app notification messages based on multiple different intent information obtained from multiple different applications, and, based on the notification priority information obtained by the acquisition unit 161, decides to output the app notification messages in order from the ones generated based on intent information with the highest notification priority.

[0074] For example, the generation unit 163 generates three different app notification messages #1´ to #3´ based on intent information #1 to #3 obtained from each of three different applications #1 to #3. Next, the generation unit 163 obtains information from the notification priority information contained in each of the intent information #1 to #3 that the notification priority of application #1 is "1", the notification priority of application #2 is "2", and the notification priority of application #3 is "3". Subsequently, when outputting a notification message containing the three app notification messages #1´ to #3´ as voice, the generation unit 163 decides to output the app notification message #1´, which is generated based on intent information #1 with the highest notification priority, first, the app notification message #2´, which is generated based on intent information #2 with the next highest notification priority, second, and the app notification message #3´, which is generated based on intent information #3 with the lowest notification priority, last.

[0075] Alternatively, the generation unit 163 may determine the order in which to output multiple app notification messages based on app priority instead of notification priority. Specifically, the generation unit 163 generates multiple different app notification messages based on multiple different intent information obtained from multiple different applications, and then, based on the app priority information obtained by the acquisition unit 161, decides to output the app notification messages from the application with the highest app priority first.

[0076] For example, the generation unit 163 obtains information from the app priority information contained in intent information #1 to #3 that the app priority of application #1 is "1", the app priority of application #2 is "2", and the app priority of application #3 is "3". Subsequently, when outputting a notification message containing the three app notification messages #1' to #3', the generation unit 163 decides to output the app notification message #1', which is generated based on intent information #1, the app priority of which is highest, first, the app notification message #2', which is generated based on intent information #2, the app priority of which is second, and the app notification message #3', which is generated based on intent information #3, the app priority of which is lowest, last.

[0077] Furthermore, the generation unit 163 may determine the order in which to output multiple app notification messages by voice based on an overall priority, which indicates an overall priority, instead of notification priority or app priority. Specifically, the generation unit 163 generates multiple different app notification messages based on multiple different intent information obtained from multiple different applications, and based on the overall priority information obtained by the acquisition unit 161, it decides to output the app notification messages from the application with the highest overall priority first.

[0078] For example, the generation unit 163 obtains information from the overall priority information contained in each of the intent information #1 to #3 that the overall priority of application #1 is "1", the overall priority of application #2 is "2", and the overall priority of application #3 is "3". Subsequently, when outputting a notification message containing the three app notification messages #1' to #3' as audio, the generation unit 163 decides to output the app notification message #1', which is generated based on intent information #1, which has the highest overall priority, as the first, the app notification message #2', which is generated based on intent information #2, which has the next highest overall priority, as the second, and the app notification message #3', which is generated based on intent information #3, which has the lowest overall priority, as the last.

[0079] Furthermore, the generation unit 163 generates all possible app notification messages based on the intent information obtained from each application. For example, based on the intent information T1 shown in Figure 5 obtained from application #1, the generation unit 163 generates two app notification messages #11' and #11, "Turn right at the next intersection" (playback time 2 seconds) and "Turn right at the next intersection" (playback time 2.5 seconds), which contain only strings with a content priority of "1". The generation unit 163 also generates app notification message #12, "Turn right at the next intersection. Please drive in the innermost lane." (playback time 6 seconds), which contains strings with a content priority of "2" or lower. The generation unit 163 also generates app notification message #13, "Turn right at the next intersection. Convenience store A is a landmark. Please drive in the innermost lane.", which contains strings with all notification priorities. In this way, the generation unit 163 generates all possible app notification messages #11', #11, #12, and #13 based on the intent information T1.

[0080] Furthermore, based on the intent information T2 shown in Figure 6 obtained from application #2, the generation unit 163 generates two app notification messages #21' and #21, which contain only strings with a content priority of "1": "Turn right at the next intersection, and the cake shop is 400m ahead" and "Turn right at the next intersection, and the cake shop is 400m ahead." The generation unit 163 also generates app notification message #22, which contains strings with a content priority of "2" or lower: "Turn right at the next intersection, and the cake shop is 400m ahead. Mont Blanc is recommended." The generation unit 163 also generates app notification message #23, which contains strings with a content priority of "3" or lower: "Turn right at the next intersection, and the cake shop "XXX" is 400m ahead. Mont Blanc is recommended." Furthermore, the generation unit 163 generates app notification message #24, which includes the string for all notification priorities: "After turning right at the next intersection, you will find the cake shop "XXX" that has recently been featured on TV 400m ahead. We recommend the Mont Blanc, which is not too sweet." In this way, the generation unit 163 generates all of the possible app notification messages #21', #21, #22, #23, and #24 based on the intent information T2.

[0081] Furthermore, the generation unit 163 generates an app notification message #31 containing only strings with a content priority of "1," which reads, "A passing shower is forecast near your home.", based on the intent information T3 shown in Figure 7 obtained from application #3. The generation unit 163 also generates an app notification message #32 containing strings with a content priority of "2" or lower, which reads, "A passing shower is forecast near your home in one hour." The generation unit 163 also generates an app notification message #33 containing strings with a content priority of "3" or lower, which reads, "A passing shower is forecast near your home in one hour. Are you sure you want to bring in your laundry?" The generation unit 163 also generates an app notification message #34 containing strings of all notification priorities, which reads, "A passing shower is forecast near your home in one hour. Are you sure you want to bring in your laundry? (If the user responds "No,") We will connect you to a video call at home. / (If the user responds "Yes," end)." In this way, the generation unit 163 generates all of the possible application notification sentences #31, #32, #33, and #34 based on the intent information T3.

[0082] Next, the generation unit 163 generates all possible app notification messages and then estimates the playback time for each app notification message. For example, the generation unit 163 estimates the playback time for each of the possible app notification messages #11', #11, #12, #13, #21', #21, #22, #23, #24, #31, #32, #33, and #34.

[0083] Next, the generation unit 163 estimates the playback time of each app notification message and selects the app notification message with the longest playback time from among the app notification messages. For example, the generation unit 163 selects app notification message #13, which is the longest among the notification messages related to app #1, app notification message #24, which is the longest among the notification messages related to app #2, and app notification message #34, which is the longest among the notification messages related to app #3.

[0084] Next, the generation unit 163 selects the app notification message with the longest playback time from among the app notification messages, and then estimates the total playback time of the notification message containing all of the selected app notification messages. For example, the generation unit 163 estimates the total playback time of the notification message containing all of the selected app notification messages #13, #24, and #34. Next, the generation unit 163 determines whether the total playback time of the notification message is less than or equal to the output grace period.

[0085] The generation unit 163 determines that the total playback time of the notification messages is less than or equal to the output grace period, and decides to output the selected app notification messages. Once the generation unit 163 decides to output the selected app notification messages, it generates a notification message that includes all of the selected app notification messages.

[0086] On the other hand, if the generation unit 163 determines that the total playback time of the notification messages is not less than or equal to the output grace period, it selects the next shortest app notification message in order from the app with the lowest priority (or notification priority or overall priority). For example, if the generation unit 163 determines that the total playback time of the notification message containing all of the selected app notification messages #13, #24, and #34 is not less than or equal to the output grace period, it selects the next shortest app notification message #33 instead of app notification message #34, in order from the app with the lowest priority, app #3. Subsequently, the generation unit 163 selects the next shortest app notification message in order from the app with the lowest priority, and then estimates the total playback time of the notification message containing all of the selected app notification messages.

[0087] In this way, the generation unit 163 generates a temporary notification message containing multiple app notification messages with different app priorities (or notification priorities or overall priorities). If the total playback time of the temporary notification message exceeds the output grace period, the generation unit shortens the length of the app notification messages in the temporary notification message, starting with the app notification message with the lowest app priority (or notification priority or overall priority), to generate a notification message that can be played back within the output grace period.

[0088] (Decision Section 164) Based on the situation information acquired by the acquisition unit 161, the decision unit 164 determines the reception time for receiving a response from the driver to the notification text when outputting a notification text to the driver that requires a response from the driver. Specifically, the decision unit 164 determines the reception time based on a comparison of the playback time of the notification text generated by the generation unit 163 and the output grace period calculated by the calculation unit 162. More specifically, the decision unit 164 determines that the reception time is short if the total playback time of the provisional notification text including the string generated by the generation unit 163 is less than a predetermined time longer than the output grace period.

[0089] If the decision unit 164 determines that the acceptance time is short, the generation unit 163 generates a notification message that includes only the option number and the option item for the driver to select. For example, the generation unit 163 generates a notification message that includes only the option numbers "1", "2", and "3" and the option items "Italian", "Chinese", and "Japanese", such as "There are three recommended restaurants ahead: 1. Italian, 2. Chinese, and 3. Japanese. Which would you prefer?"

[0090] Furthermore, the decision unit 164 determines that there is no time for reception if the total playback time of the provisional notification message is longer than a predetermined time than the output grace period. If the decision unit 164 determines that there is no time for reception, the generation unit 163 generates a notification message that does not include notification content requiring a response from the driver. For example, if the decision unit 164 determines that there is no time for reception, the generation unit 163 generates an app notification message #34' which includes a user response, such as "A passing shower is forecast near your home in one hour. Is it okay to bring in your laundry? (If the user's response is "No",) I will connect you to your home via video call. / (If the user's response is "Yes", end)", but removes the user response and subsequent information.

[0091] Furthermore, the determination unit 164 determines the acceptance time based on the safety level and margin calculated by the calculation unit 162. For example, the higher the safety level calculated by the calculation unit 162, the longer the acceptance time determined by the determination unit 164. Also, the higher the margin calculated by the calculation unit 162, the longer the acceptance time determined by the determination unit 164.

[0092] Furthermore, the decision unit 164 determines whether or not to enable the barge-in function of the speech recognition unit 150 based on the situation information acquired by the acquisition unit 161. Specifically, the decision unit 164 determines whether or not to enable the barge-in function of the speech recognition unit 150 based on the safety level and margin level calculated by the calculation unit 162. For example, the decision unit 164 decides to enable the barge-in function if the safety level calculated by the calculation unit 162 exceeds a first threshold. Also, the decision unit 164 decides to enable the barge-in function if the margin level calculated by the calculation unit 162 exceeds a second threshold.

[0093] (Transmitter 165) The transmitting unit 165 transmits the information acquired by the acquiring unit 161 to the application device 10. Specifically, the transmitting unit 165 transmits status information to the application device 10, including driving information regarding the driving status of the moving object and driving information regarding the driving status of the driver, which has been acquired by the acquiring unit 161. For example, the transmitting unit 165 transmits the status information to the application device 10 in real time. Alternatively, for example, the transmitting unit 165 may transmit the status information to the application device 10 at predetermined intervals (for example, every 30 seconds or every minute).

[0094] [4. Information Processing Flow] Next, the procedure for information processing according to the embodiment will be described using Figure 8. Figure 8 is a flowchart of an example of information processing according to the embodiment. In the example shown in Figure 8, the calculation unit 162 of the information processing device 100 calculates the output grace period, which is the remaining time until the output grace period timing is reached (step S101).

[0095] The generation unit 163 of the information processing device 100 generates all possible application notification sentences based on the intent information obtained from each application (step S102). Once the generation unit 163 has generated all possible application notification sentences, it estimates the playback time for each application notification sentence (step S103).

[0096] The generation unit 163 estimates the playback time of each app notification message and selects the app notification message with the longest playback time from among the app notification messages (step S104). After selecting the app notification message with the longest playback time from among the app notification messages, the generation unit 163 estimates the total playback time of all notification messages, including the selected app notification message (step S105). Next, the generation unit 163 determines whether the total playback time of the notification messages is less than or equal to the output grace period (step S106).

[0097] If the generation unit 163 determines that the total playback time of the notification messages is less than or equal to the output grace period (step S106; Yes), it decides to output the selected app notification messages (step S107). Once the generation unit 163 decides to output the selected app notification messages, it generates a notification message that includes all of the selected app notification messages.

[0098] On the other hand, if the generation unit 163 determines that the total playback time of the notification messages is not less than or equal to the output grace period (step S106; No), it selects the next shortest app notification message in order of app priority (step S108). After selecting the next shortest app notification message in order of app priority, the generation unit 163 estimates the total playback time of the notification message that includes all of the selected app notification messages (step S105).

[0099] [5. Variations] [5-1. Adding information based on priority] In the embodiment described above, the generation unit 163 generates a temporary notification text containing multiple strings with different content priorities, and if the playback time of the temporary notification text exceeds the output grace period, it deletes the strings with lower content priorities from among the multiple strings contained in the temporary notification text in order to generate a notification text that can be played back within the output grace period. However, the method of generating the notification text is not limited to this.

[0100] Specifically, the generation unit 163 generates a temporary notification text that prioritizes the string with the higher content priority among multiple strings with different content priorities. If the total playback time of the temporary notification text does not exceed the output grace period, it adds a string with a lower content priority than the strings included in the temporary notification text to generate a notification text that can be played back within the output grace period.

[0101] For example, the generation unit 163 generates two application notification messages #11' and #11, "Turn right at the next intersection" (playback time 2 seconds) and "Turn right at the next intersection" (playback time 2.5 seconds), which contain only strings with a content priority of "1", based on the intent information T1 shown in Figure 5 obtained from application #1. In this case, assuming the output grace period is 7 seconds, the generation unit 163 determines that the total playback time of the provisional notification message does not exceed the output grace period, so it adds a string with a lower content priority of "2" than the strings included in the provisional notification message to generate a notification message that can be played back within the output grace period. For example, the generation unit 163 adds a string with a lower content priority of "2" to a string with a content priority of "1" to generate a notification message that can be played back within the output grace period, "Turn right at the next intersection. Please drive in the innermost lane." (playback time 6 seconds).

[0102] Furthermore, in the embodiment described above, the generation unit 163 generates a provisional notification statement containing multiple app notification statements with different app priorities (or notification priorities or overall priorities), and if the total playback time of the provisional notification statement exceeds the output grace period, the length of the app notification statements is shortened in order from the app notification statement with the lowest app priority (or notification priority or overall priority) among the multiple app notification statements included in the provisional notification statement, in order to generate a notification statement that can be played back within the output grace period. However, the method of generating notification statements is not limited to this.

[0103] Specifically, the generation unit 163 generates a temporary notification message that prioritizes the app notification message with the higher app priority (or notification priority or overall priority) among multiple app notification messages with different app priorities (or notification priority or overall priority). If the total playback time of the temporary notification message does not exceed the output grace period, it adds an app notification message with a lower app priority (or notification priority or overall priority) than the app notification message included in the temporary notification message to generate a notification message that can be played back within the output grace period.

[0104] For example, the generation unit 163 generates a temporary notification message that prioritizes app notification messages #1 to #3 with app priorities of "1" to "3" from among app notification message #1 with app priority "1", app notification message #2 with app priority "2", app notification message #3 with app priority "3", app notification message #4 with app priority "4", ... Next, if the total playback time of the temporary notification message containing all of app notification messages #1 to #3 does not exceed the output grace period, the generation unit 163 adds app notification message #4 with an app priority of "4", which has a lower app priority than the app notification messages included in the temporary notification message, to the temporary notification message to generate a notification message that can be played back within the output grace period.

[0105] [5-2. Deletion of information based on priority] Furthermore, in the embodiment described above, the generation unit 163 generates a provisional notification statement containing multiple app notification statements with different app priorities (or notification priorities or overall priorities), and if the total playback time of the provisional notification statement exceeds the output grace period, the length of the app notification statements is shortened in order from the app notification statement with the lowest app priority (or notification priority or overall priority) among the multiple app notification statements included in the provisional notification statement, in order to generate a notification statement that can be played back within the output grace period. However, the method of generating notification statements is not limited to this.

[0106] Specifically, the generation unit 163 generates a temporary notification message containing multiple app notification messages with different app priorities (or notification priorities or overall priorities). If the total playback time of the temporary notification message exceeds the output grace period, the unit deletes the app notification messages included in the temporary notification message, starting with those with lower app priorities (or notification priorities or overall priorities), to generate a notification message that can be played within the output grace period.

[0107] For example, the generation unit 163 generates a temporary notification message that includes app notification message #1 with an app priority of "1", app notification message #2 with an app priority of "2", app notification message #3 with an app priority of "3", and app notification message #4 with an app priority of "4". Subsequently, if the total playback time of the temporary notification message exceeds the output grace period, the generation unit 163 deletes the app notification messages included in the temporary notification message in order, starting with app notification message #4 with the lowest app priority, to generate a notification message that can be played back within the output grace period.

[0108] [5-3. Intent Information Generation Process] Furthermore, in the embodiments described above, the case in which the intent generation unit 132 generates an application notification text and generates intent information based on the generated application notification text was explained, but the method of generating intent information is not limited to this. Specifically, the intent generation unit 132 may generate intent information based on situation information obtained from the information processing device 100. For example, the intent generation unit 132 generates intent information T1 to T3 shown in Figures 5 to 7 based on situation information including guidance route information and location information obtained from the information processing device 100. Then, the transmission unit 133 transmits the intent information generated by the intent generation unit 132 to the information processing device 100.

[0109] [5-4. Processing to change priority information] Furthermore, while the above-described embodiment illustrates an example in which the information processing device 100 generates a notification text based on content priority information, notification priority information, application priority information, or overall priority information acquired from the application device 10, the invention is not limited to this. Specifically, when generating a notification text, the generation unit 163 of the information processing device 100 may modify the content priority, notification priority, application priority, or overall priority based on past notification history, user attribute information, interest information, passenger information, and situation information. For example, the generation unit 163 may assign weights to information that is likely to be of high interest to the user (e.g., strings) based on past notification history, user attribute information, interest information, passenger information, and situation information, so that it has a higher priority. Also, for example, the generation unit 163 may assign weights to notifications for which there was no response in the past, based on a history of no response to notifications (no visit to the facility, no response within the response time), so that the notification priority for notifications for which there was no response in the past is lower. The generation unit 163 generates a notification text based on the weighted content priority, notification priority, application priority, or overall priority.

[0110] [6. Effects] As described above, the application device 10 according to the embodiment comprises an intent generation unit 132 and a transmission unit 133. The intent generation unit 132 generates intent information which includes string information indicating a string that constitutes a notification message to be output audibly to the driver of a mobile vehicle, and intent information indicating the type of notification set for each string. The transmission unit 133 transmits the intent information to an information processing device 100 that generates a notification message based on the intent information.

[0111] Thus, the application device 10 does not provide the information processing device 100, which generates the notification text, with a fixed notification text, but rather provides intent information, which is metadata information related to the notification text. This enables the application device 10 to generate a notification text that allows the information processing device 100 to convey the necessary information to the driver of the moving vehicle within a desired time, according to the situational information. Therefore, the application device 10 can appropriately convey the necessary information to the driver of the moving vehicle.

[0112] Furthermore, the intent generation unit 132 generates intent information that also includes content priority information indicating the content priority set for each string.

[0113] This enables the application device 10 to generate notification messages that allow the information processing device 100 to appropriately convey necessary information to the driver of the mobile vehicle according to content priority.

[0114] Furthermore, the intent generation unit 132 generates intent information that also includes notification priority information indicating the notification priority set for each intent piece of information.

[0115] This enables the application device 10 to generate notification messages that appropriately convey necessary information to the driver of a moving vehicle, according to the notification priority.

[0116] Furthermore, the intent generation unit 132 generates intent information that also includes application priority information indicating the application priority set for each application that generates intent information.

[0117] This enables the application device 10 to generate notification messages that appropriately convey necessary information to the driver of the mobile vehicle, according to the application priority.

[0118] Furthermore, the intent generation unit 132 generates an app notification text related to the notification, and generates intent information based on the generated app notification text. For example, the intent generation unit 132 generates intent information that includes a string extracted from the app notification text.

[0119] This enables the application device 10 to generate intent information by effectively utilizing application notification messages generated by existing applications.

[0120] The application device 10 also includes an acquisition unit 131. The acquisition unit 131 takes an application notification text as input and acquires a machine learning model that outputs intent information. For example, the acquisition unit 131 acquires a machine learning model that has been trained on training data including combinations of application notification texts and the intent information. The intent generation unit 132 generates intent information by inputting the application notification text into the machine learning model.

[0121] As a result, the application device 10 can generate appropriate intent information from the application notification message without human intervention.

[0122] [7. Program] The processing performed by the application device 10 described above is realized by the information processing program according to the present invention. For example, the intent generation unit 132 of the application device 10 is realized by the CPU, MPU, etc. of the application device 10 executing the processing procedures related to the information processing program, with the RAM as the working area. For example, the intent generation unit 132 of the application device 10 is realized by the CPU, MPU, etc. of the application device 10 executing the information processing procedures related to the generation of intent information, etc., with the RAM as the working area. Other parts of the application device 10 are similarly realized by the execution of each procedure by the information processing program.

[0123] [8. Hardware Configuration] Furthermore, the application device 10 or information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration such as that shown in Figure 9. Figure 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the application device 10 or information processing device 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0124] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, controlling various components. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0125] The HDD1400 stores programs executed by the CPU1100, as well as data used by such programs. The communication interface1500 receives data from other devices via a predetermined communication network and sends it to the CPU1100, and transmits data generated by the CPU1100 to other devices via the predetermined communication network.

[0126] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the generated data to output devices via the input / output interface 1600. Note that an MPU (Micro Processing Unit) or, given the significant computing power required, a GPU (Graphics Processing Unit) may be used instead of the CPU 1100.

[0127] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0128] For example, when computer 1000 functions as an application device 10 or an information processing device 100, the CPU 1100 of computer 1000 implements the functions of control unit 13 or control unit 160 by executing programs loaded onto RAM 1200. The CPU 1100 of computer 1000 reads and executes these programs from a recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0129] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0130] [9. Other] Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0131] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0132] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0133] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of symbols]

[0134] 1. Information Processing System 10 Application Devices 11 Communications Department 12 Storage section 13 Control Unit 131 Acquisition Department 132 Intent generation unit 133 Transmitter 100 Information Processing Devices 110 Communications Department 120 Storage section 130 Sensor section 140 Audio output section 150 Voice Recognition Unit 160 Control Unit 161 Acquisition Department 162 Calculation Section 163 Generation part 164 Decision Section 165 Transmitter

Claims

1. An intent generation step that generates intent information including string information indicating a string of words or phrases that constitute a notification message to the driver of a mobile vehicle, and intent information indicating the type of notification set for each string, A transmission step of transmitting the intent information to an information processing device that generates the notification text based on the intent information, An information processing program that causes a computer to execute, The intent generation step is, The intent information is generated which further includes application priority information indicating the application priority set for each application that generates the intent information. An information processing program characterized by the following features.

2. The intent generation step is, The intent information is generated which further includes content priority information indicating the content priority set for each of the aforementioned strings. The information processing program according to feature 1.

3. The intent generation step is, The intent information is generated, further including notification priority information that indicates the notification priority set for each intent information. The information processing program according to claim 1 or 2.

4. The intent generation step is, Generate an app notification text related to the notification, and generate the intent information based on the generated app notification text. An information processing program according to any one of features 1 to 3.

5. The intent generation step is, The intent information is generated, which includes the string extracted from the aforementioned app notification text. The information processing program according to feature 4.

6. An acquisition step to obtain a machine learning model that takes the aforementioned app notification text as input and outputs the aforementioned intent information. Let's execute it further, The intent generation step is, The intent information is generated by inputting the aforementioned app notification text into the machine learning model. The information processing program according to feature 4 or 5.

7. The acquisition step described above is: The machine learning model is acquired based on training data that includes the combination of the aforementioned app notification text and the aforementioned intent information. The information processing program according to feature 6.

8. An information processing method performed by an information processing device, An intent generation step that generates intent information including string information indicating a string of words or phrases that constitute a notification message to the driver of a mobile vehicle, and intent information indicating the type of notification set for each string, A transmission step of transmitting the intent information to an information processing device that generates the notification text based on the intent information, An information processing method including, The intent generation step is, The intent information is generated which further includes application priority information indicating the application priority set for each application that generates the intent information. An information processing method characterized by the following:

9. An intent generation step that generates intent information including string information indicating a string of words or phrases that constitute a notification message to the driver of a mobile vehicle, and intent information indicating the type of notification set for each string, A transmission step of transmitting the intent information to an information processing device that generates the notification text based on the intent information, A storage medium characterized by storing an information processing program for causing a computer to execute, The intent generation step is, The intent information is generated which further includes application priority information indicating the application priority set for each application that generates the intent information. A storage medium characterized by the following features.

10. An intent generation unit generates intent information including string information that indicates a string of words or phrases that constitute a notification message to the driver of a mobile vehicle, and intent information that indicates the type of notification set for each string, A transmission unit that transmits the intent information to an information processing device that generates the notification text based on the intent information, An application device characterized by comprising, The intent generation unit, The intent information is generated which further includes application priority information indicating the application priority set for each application that generates the intent information. An application device characterized by the following features.

Images