Information processing device and information processing method

Abstract

To achieve personal optimization of a notification with respect to a driver.SOLUTION: An information processing device according to the present invention is the information processing device including a controller. The controller performs: issuing a notification at a frequency or timing of a notification mode selected by a driver from the plurality of notification modes related to a driving support; collecting state information related to a state of the driver in issuing the notification; and adding the new notification mode at the frequency or timing corresponding to the state information as a selection choice.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The disclosed embodiments relate to an information processing device and an information processing method. [Background technology]

[0002] Conventionally, there is an in-vehicle device that determines the preferences of a driver of a vehicle. For example, Patent Document 1 discloses a technology that determines the following distance preferred by the driver from the driving tendency of the driver, and controls the vehicle with an option that is close to the following distance preferred by the driver from among preset options. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-162523 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, there were cases where the parameters of the preset options were different from the parameters actually preferred by the driver. In addition, when notifying the driver of information regarding parameter optimization, individual optimization of each parameter, such as notification frequency and notification timing, is required. In other words, in the conventional technology, there was a problem that the notification to the driver was difficult to optimize for the driver.

[0005] An object of the present invention is to provide an information processing device and an information processing method that can individually optimize notifications for a driver. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objective, the controller of the present invention provides notification at a frequency or timing of a notification mode selected by the driver from a plurality of notification modes related to driving assistance, collects status information related to the driver's state at the time of the notification, and adds as an option a new notification mode with a frequency or timing according to the status information. Effect of the Invention

[0007] According to the present invention, a new notification mode that reflects the frequency or timing preferred by each driver is presented to the driver, so that notification for each driver can be individually optimized. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system. [Diagram 2] FIG. 2 is a diagram showing an example of a notification mode setting screen. [Diagram 3] FIG. 3 is a block diagram of the in-vehicle device. [Figure 4] FIG. 4 is an explanatory diagram of learning data related to preference parameters. [Diagram 5] FIG. 5 is a diagram showing a specific example of the notification frequency. [Figure 6] FIG. 6 is an explanatory diagram of notification timing. [Figure 7] FIG. 7 is a diagram showing the relationship between the notification frequency and the criteria for alerting. [Figure 8] FIG. 8 is a block diagram of the server device. [Figure 9] FIG. 9 is a flowchart showing a process performed by the in-vehicle device. [Figure 10] FIG. 10 is a flowchart showing a processing procedure executed by the server device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, a detailed description will be given of an embodiment (hereinafter, referred to as an "embodiment") for carrying out an information processing device and an information processing method according to the present application with reference to the drawings. Note that the information processing device and the information processing method according to the present application are not limited to the embodiment.

[0010] First, an overview of an information processing system according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing a configuration example of the information processing system. As shown in Fig. 1, an information processing system S according to an embodiment includes a plurality of in-vehicle devices 1 and a server device 100.

[0011] The multiple vehicle-mounted devices 1 and the server device 100 are connected by a network N and communicate with each other through the network N. The vehicle-mounted devices 1 are, for example, drive recorders installed in each vehicle.

[0012] The in-vehicle device 1 is mounted on each vehicle and notifies the driver of the vehicle of driving support information. The driving support information is information for supporting the driver in driving, and is information for alerting the driver to things such as going out of the driving lane, inattentive driving, and insufficient distance between vehicles. The driving support information may include information on traffic congestion, weather, and the like.

[0013] The in-vehicle device 1 can detect lane deviation, insufficient distance between vehicles, etc. by analyzing image data captured around the vehicle, and can detect distracted driving by the driver by analyzing image data captured inside the vehicle. The in-vehicle device 1 may transmit the image data to the server device 100 and request the server device 100 to analyze the image data. The in-vehicle device 1 also obtains information on traffic congestion and weather from an external device (for example, the server device 100) and notifies the information as driving support information.

[0014] Regarding the notification of driving assistance information, multiple notification modes are set as defaults in the in-vehicle device 1, and the driver can select a notification mode from the multiple notification modes. Then, the in-vehicle device 1 notifies the driving assistance information according to the notification mode selected by the driver. For example, in such a case, it is assumed that the setting parameters preset for each notification mode may deviate from the parameters actually preferred by the driver. In other words, it is assumed that the notification to the driver may not be optimized for the driver.

[0015] Therefore, in the information processing system S according to the embodiment, a new notification mode in which the driver's preferred parameters are set is added to the notification mode options for the notification of driving support information. The parameters here include the notification frequency, notification timing, notification method, etc., which will be described later.

[0016] In the information processing system S, the server device 100 learns the driver's preferred parameters based on the information transmitted from the in-vehicle device 1. The server device 100 corresponds to an example of an information processing device according to the embodiment.

[0017] Specifically, in the information processing system S, the in-vehicle device 1 notifies the driver of driving support information in a notification mode selected by the driver, and acquires status information indicating the state of the driver when the driving support information is notified. The status information is, for example, photographed data of the driver, but may also include information regarding the driving operation of the driver.

[0018] The in-vehicle device 1 estimates the driver's emotions from the image data of the driver using an emotion estimation AI (Artificial Intelligence) stored inside the in-vehicle device 1. The emotion estimation AI is an AI trained using teacher data that links the subject's face shown in the image data with the subject's emotions, and is a model trained to estimate the subject's emotions shown in the image data from the image data.

[0019] In this embodiment, the emotion estimation AI estimates whether the emotion of the driver captured in the captured data is unpleasant or not from the captured data. For example, the in-vehicle device 1 notifies the driver of driving assistance information in a notification mode selected by the driver, and collects information on the user's emotion when notified of the driving assistance information, i.e., whether the driver is unpleasant or not in response to the notification of the driving assistance information.

[0020] Then, the in-vehicle device 1 transmits the information to the server device 100. The server device 100 learns the driver's preferred parameters (hereinafter, referred to as preference parameters) based on the information. The server device 100 learns the preference parameters based on the driver's tolerance to notifications of driving support information.

[0021] In other words, the server device 100 can learn the preference parameter according to the driver's tolerance by learning the preference parameter based on the driver's emotion when the driving support information is notified. A specific example of learning the preference parameter will be described later.

[0022] Then, when the server device 100 finishes learning the preference parameters, it generates a new notification mode of the preference parameters and transmits it to the in-vehicle device 1. The in-vehicle device 1 adds the new notification mode received from the server device 100 to the notification mode options. Note that, hereinafter, the new notification mode may be referred to as a new notification mode.

[0023] Fig. 2 is a diagram showing an example of a setting screen for a notification mode. The upper part of Fig. 2 illustrates an example of the setting screen before the new notification mode is added, and the lower part of Fig. 2 illustrates an example of the setting screen after the new notification mode is added.

[0024] As shown in the upper part of Fig. 2, a setting menu for notification of driving assistance information is displayed on the setting screen. In the example of Fig. 2, the driver can set parameters such as "notification frequency", "notification timing", and "notification method" from the setting menu.

[0025] "Notification frequency" indicates the notification frequency of driving assistance information, that is, the number of notifications per unit time. As shown in FIG. 2, the driver can select "high," "medium," "low," or "none" for "notification frequency." For example, a "high" notification frequency means 10 notifications per unit time, a "medium" notification frequency means 5 notifications per unit time, and a "low" notification frequency means 1 notification per unit time. Also, a "none" notification frequency means 0 notifications per unit time.

[0026] The "notification timing" indicates the notification timing from the occurrence of an event that is the subject of the notification of the driving support information to the notification. To give a more specific example, it is assumed that the subject of the notification of the driving support information is "insufficient distance between vehicles."

[0027] For example, if the notification timing is "late," the notification will be made one second after the reference notification timing, and if the notification timing is "early," the notification will be made one second before the reference notification timing.

[0028] Furthermore, the "notification method" shown in Fig. 2 indicates the method of notifying the driving support information, and for example, as shown in Fig. 2, indicates the type of voice when notifying the driving support information. The example shown in Fig. 2 shows a case where "buzzer" or "voice" can be selected as the notification method. Note that the notification method here corresponds to an example of the type of voice.

[0029] When the server device 100 finishes learning the above-mentioned preference parameters, it transmits this information to the in-vehicle device 1. As a result, after the preference parameters have been learned, an option of "AI Auto" is added for each parameter on the setting screen, as shown in the lower part of FIG.

[0030] Here, AI Auto is a notification mode in which driving assistance information is notified with the preference parameters preferred by the driver. That is, in the information processing system S, after learning the preference parameters, a new notification mode is added as an option. Then, the driver can set the notification mode in which driving assistance information is notified with the preference parameters by selecting "AI Auto" from the setting menu. In addition, when "AI Auto" is added to the options, the in-vehicle device 1 may notify the driver of this through voice or image. This allows the driver to recognize that "AI Auto" has been added. In addition, in the information processing system S, after the "AI mode" is added, the notification mode may be automatically set to "AI Auto".

[0031] In this manner, the information processing system S according to the embodiment learns the driver's preference parameters regarding notification of driving assistance information, and adds AI Auto (new notification mode) having the preference parameters to the selection of notification modes.

[0032] Therefore, in the information processing system S according to the embodiment, the parameters preferred by each driver are learned and information reflecting the learned parameters is presented to the driver, so that notifications to the driver can be individually optimized.

[0033] Next, a configuration example of the in-vehicle device 1 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram of the in-vehicle device 1. As shown in Fig. 3, the in-vehicle device 1 is connected to an exterior camera 50, an interior camera 51, a speaker 52, and a display 53.

[0034] The exterior camera 50 is a camera installed to capture an image of the area in front of the vehicle. The exterior camera 50 is not limited to a camera that captures an image of the area in front of the vehicle, and may include a camera that captures an image of the area behind the vehicle or in all directions.

[0035] The in-vehicle camera 51 is a camera installed so as to capture the inside of the vehicle, more specifically, the face of the driver while driving the vehicle. The speaker 52 generates the sound output from the in-vehicle device 1 inside the vehicle. The display 53 displays the image output from the in-vehicle device 1.

[0036] 3, the in-vehicle device 1 includes a communication unit 2, a control unit 3, and a storage unit 4. The communication unit 2 is realized, for example, by a network interface card (NIC) or the like. The communication unit 2 is connected to a predetermined communication network so as to be capable of two-way communication, and transmits and receives information to and from a server device 100 or the like.

[0037] The storage unit 4 includes a non-volatile storage medium such as a non-volatile memory, a flash memory, a hard disk drive, etc. For example, the storage unit 4 stores information about the notification mode, an emotion estimation AI, and image data captured by the exterior camera 50 or the interior camera 51.

[0038] The control unit 3 includes a microcomputer having a CPU (Central Processing Unit), ROM (Read Only Memory), RAM, etc., and various circuits. The control unit 3 controls the operation of the entire in-vehicle device 1 by the CPU executing a program stored in the ROM using the RAM as a working area. Note that the control unit 3 may be partially or entirely configured with hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0039] The control unit 3 executes various processes related to the notification of driving assistance. The control unit 3 notifies the driving assistance information in a notification mode selected by the driver. The control unit 3 notifies the driving assistance information using setting parameters of the notification mode selected by the driver of the vehicle from among multiple notification modes.

[0040] Here, the driving support information notified to the driver includes information of various types such as deviation from the driving lane, inattentive driving, insufficient distance between vehicles, etc. The control unit 3 detects deviation from the driving lane and insufficient distance between vehicles by analyzing the photographed data captured by the exterior camera 50. The control unit 3 also detects inattentive driving by analyzing the photographed data captured by the interior camera 51.

[0041] When the control unit 3 detects an event that requires notification of driving support information, the control unit 3 generates the driving support information in accordance with the currently set mode, and notifies the driver of the driving support information through the speaker 52.

[0042] In addition, the control unit 3 collects state information indicating the state of the driver when the driving support information is notified, and generates learning data of the preference parameters. First, when the vehicle is powered on, the control unit 3 authenticates (identifies) the driver from the photographed data captured by the in-vehicle camera 51.

[0043] In other words, the control unit 3 generates learning data of the preference parameters for each driver. Next, while the vehicle is being driven, the control unit 3 generates learning data of the preference parameters while notifying the driver of the driving assistance information in the notification mode selected by the driver.

[0044] The control unit 3 estimates the driver's emotion from the photographed data of the driver for a predetermined period (e.g., 5 seconds) after the notification of the driving support information. For example, the control unit 3 inputs the photographed data to the emotion estimation AI stored in the storage unit 4, and estimates the driver's emotion from the output result.

[0045] Here, a specific example of the learning data will be described by taking the case where the preference parameter is the notification frequency as an example with reference to Fig. 4. Fig. 4 is an explanatory diagram of the learning data related to the preference parameter.

[0046] In FIG. 4, the horizontal axis indicates the time lapse of one cycle, and the case where the notification frequency in the notification mode set by the driver is five times is shown. Note that one cycle here is the cycle when counting the notification frequency. In addition, the lower part of FIG. 4 indicates the state of the driver when the driving support information is notified by a flag, with "1" indicating that the driver was uncomfortable and "0" indicating that the driver was not uncomfortable.

[0047] For example, the control unit 3 generates information on the flags shown in FIG.

[0048] In the example of Fig. 4, the flags for the first, second and fifth notifications are "0", and the flags for the third and fourth notifications are "1". In other words, this indicates that the driver allows three notifications out of a total of five notifications.

[0049] Therefore, it is assumed from Fig. 4 that three notifications of driving support information in one period is optimal for the driver. From this result, it is estimated that the driver will tolerate notifications of driving support information up to three times, but will become uncomfortable if the notifications are more than three times.

[0050] In the learning data collection stage, the control unit 3 provisionally sets the optimal notification frequency to three times, and notifies the driving assistance information at a different notification frequency in the next and subsequent cycles. Then, the control unit 3 continues to collect the learning data until the optimal notification frequency converges to a certain value.

[0051] For example, in the learning data collection stage, the control unit 3 collects the learning data while changing the notification frequency so that the notification frequency differs for each period. Note that the control unit 3 may determine the notification frequency from the next time onwards based on an instruction from the server device 100, or may determine the notification frequency from the next time onwards based on a predetermined rule or the like.

[0052] By the way, if the driver does not feel uncomfortable with all notifications (say five times) in one cycle, the notification frequency of "five times" may be learned as the optimal notification frequency. On the other hand, it is also possible that the optimal notification frequency for the driver is more than five times.

[0053] Therefore, for example, if the driver does not feel uncomfortable after five notifications, i.e., if all of the flags are "0", the notification frequency may be set higher than the current frequency in the next and subsequent cycles.

[0054] Here, a specific example of the notification frequency will be described with reference to Fig. 5. Fig. 5 is a diagram showing a specific example of the notification frequency. In the example of Fig. 5, since the driver did not feel uncomfortable with any of the five notifications, the control unit 3 sets the notification to six or more times in any of the following cycles. This enables the server device 100, which will be described later, to appropriately learn the optimal notification frequency for the driver.

[0055] Furthermore, the control unit 3 collects learning data by combining parameters related to notification timing, voice type, volume, etc. in addition to notification frequency. That is, the control unit 3 collects learning data with notification frequency, notification timing, voice type, volume, etc. as variables.

[0056] Here, the notification timing will be described with reference to Fig. 6. Fig. 6 is an explanatory diagram of the notification timing. In Fig. 6, the horizontal axis indicates the passage of time, and indicates the notification timing from the occurrence of an event that is the subject of the notification of driving support information (e.g., deviation from a driving lane) to the actual notification of the driving support information.

[0057] 6 shows that in the setting mode, the driver can select one of the notification timings from "early," "normal," and "late" from the occurrence of the event. In the learning data collection stage, the control unit 3 collects the learning data by shifting these notification timings little by little.

[0058] In other words, in addition to the notification timings of "early," "normal," and "slow," the control unit 3 notifies driving assistance information at a notification timing that does not fall into any of the categories of "early," "normal," and "slow," and collects the driver's reaction at that time as learning data.

[0059] In this way, the control unit 3 collects learning data when the notification timing is shifted, so that the server device 100, which will be described later, can learn the notification timing appropriate for the driver.

[0060] The control unit 3 also changes parameters of the voice type and volume in addition to the notification frequency and notification timing described above, and collects learning data. Here, the voice type is the type of voice used when notifying the driving support information, and includes buzzer and voice, and further, the voice includes male voice and female voice.

[0061] That is, the control unit 3 collects learning data of items according to “notification frequency”דnotification timing”דaudio type”דvolume” and transmits the learning data to the server device 100 .

[0062] In this case, the control unit 3 may generate learning data using, for example, the information type of the driving support information as a variable. Here, the information type is classified into, for example, "distracted driving," "varying from the lane," and "insufficient distance between vehicles."

[0063] In this way, the control unit 3 generates learning data with the information type as a variable, thereby making it possible to learn the optimum preference parameter for each information type. Note that the control unit 3 continues to collect learning data even after the server device 100 generates the preference parameters, and transmits the learning data to the server device 100. The server device 100 then continues to learn the preference parameters based on the learning data.

[0064] In this way, the server device 100 can make the preference parameters closer to the parameters that the driver actually prefers by continuously learning the preference parameters.

[0065] After that, when the server device 100 finishes learning the preference parameters, the control unit 3 notifies the driver that the "AI AUTO" notification mode has been added. Then, when the "AI AUTO" notification mode is selected by the driver, the control unit 3 notifies the driver of the driving assistance information by using the preference parameters.

[0066] Here, a specific example of the process by the control unit 3 when the notification frequency is the preference parameter will be described with reference to Fig. 7. Fig. 7 is a diagram showing the relationship between the notification frequency and the criteria for calling attention.

[0067] The horizontal axis of Figure 7 shows the warning standard, and shows that as the warning standard becomes stricter, the notification frequency becomes relatively lower, and as the warning standard becomes looser, the notification frequency becomes relatively higher.

[0068] As described above, the driving assistance information is information that alerts the driver to "drowsy driving," "distracted driving," "veering out of the lane," "insufficient distance between vehicles," etc. For example, the control unit 3 adjusts the notification frequency by setting a standard for alerting the driver based on, for example, a preference parameter for the notification frequency.

[0069] Specifically, when the control unit 3 wishes to reduce the frequency of notifications for "lane departure" or "insufficient distance between vehicles," the control unit 3 sets the warning criteria to a stricter value, and when the control unit 3 wishes to increase the frequency of notifications, the control unit 3 sets the warning criteria to a lenient value.

[0070] This allows the control unit 3 to optimize the notification frequency. At this time, the control unit 3 does not change the standards for alerts for items for which alerts are highly important, such as "drowsy driving" and "distracted driving."

[0071] That is, the information processing system S according to the embodiment sets an allowable range of the preference parameter for each information type of the driving assistance information, and then generates the preference parameter within the range of the allowable range.

[0072] As a result, the information processing system S according to the embodiment can notify the driver of driving assistance information with optimal parameters while appropriately calling the driver's attention.

[0073] Next, a configuration example of the server device 100 according to the embodiment will be described with reference to Fig. 8. Fig. 8 is a block diagram of the server device 100. As shown in Fig. 8, the server device 100 includes a communication unit 20, a control unit 30, and a storage unit 40.

[0074] The communication unit 20 is realized, for example, by a NIC etc. The communication unit 20 is connected to a predetermined communication network so as to be capable of two-way communication, and transmits and receives information to and from each of the in-vehicle devices 1.

[0075] The storage unit 40 includes a non-volatile storage medium such as a non-volatile memory, a flash memory, a hard disk drive, etc. The storage unit 40 stores information related to the learning data collected by the in-vehicle device 1, for example.

[0076] The control unit 30 includes a microcomputer having a CPU, ROM, RAM, etc., and various circuits. The control unit 30 controls the operation of the entire in-vehicle device 1 by the CPU executing a program stored in the ROM using the RAM as a working area. Note that the control unit 30 may be partially or entirely configured with hardware such as an ASIC or an FPGA.

[0077] The control unit 30 learns preference parameters preferred by the driver of each vehicle based on the learning data transmitted from each in-vehicle device 1. The control unit 30 acquires, in each in-vehicle device 1, state information on the state of the driver when the driving assistance information is notified in a notification mode selected by the driver of the vehicle from among a plurality of notification modes.

[0078] For example, the control unit 30 acquires the driver's emotion when the driving support information is notified as state information from the in-vehicle device 1. Specifically, the control unit 30 collects learning data from each in-vehicle device 1 in which the state information is linked to information related to the setting parameters of the driving support information.

[0079] Then, the control unit 30 learns the preference parameters for each driver based on the learning data acquired from each in-vehicle device 1. For example, the control unit 30 learns the preference parameters depending on whether the driver feels uncomfortable with the notification of the driving support information.

[0080] That is, the control unit 30 learns the preference parameters according to the driver's tolerance for the notification of the driving support information. As described above, the setting parameters include the notification frequency, notification timing, voice type, volume, etc. Then, the control unit 30 learns the preference parameters for each type of driving support information.

[0081] The control unit 30 learns the preference parameter by various machine learning methods using learning data for each driver. For example, when the value of the preference parameter converges as a result of learning, the control unit 30 sets the value as the preference parameter. In other words, if the value of the preference parameter does not converge, the control unit 30 continues learning the preference parameter.

[0082] This allows the control unit 30 to avoid providing preference parameters that deviate from the parameters that the driver actually prefers.

[0083] As described in Fig. 5, in the learning stage of the preference parameters, if the number of times the driver feels uncomfortable when the driving assistance information is notified at the notification frequency of the set parameters does not reach the threshold, the control unit 30 increases the notification frequency to a value higher than the notification frequency of the set parameters. Note that, in the example shown in Fig. 5, the threshold for the number of times the driver feels uncomfortable is "0 times", but it may be "1 time" or "2 times", etc.

[0084] In this case, the control unit 30 refers to the storage unit 40, identifies the learning data that meets the above-mentioned conditions, and requests the in-vehicle device 1 to collect the learning data with a higher notification frequency. Furthermore, when there is a shortage of learning data in the learning stage of the preference parameters, the control unit 30 may request the in-vehicle device 1 to collect the missing learning data.

[0085] In this case, the control unit 30 specifies the parameters to be collected and then requests the in-vehicle device 1 to collect learning data. This allows the control unit 30 to efficiently acquire learning data that is insufficient for learning preference parameters.

[0086] Then, when the control unit 30 finishes learning the preference parameters, that is, when the preference parameters have converged, the control unit 30 generates a preference mode, which is a notification mode having the preference parameters, and transmits the preference mode to the in-car device 1.

[0087] As a result, in the in-car device 1, a new notification mode option "AI Auto" is added, as shown in the lower part of FIG.

[0088] Furthermore, for example, when setting the notification frequency as the preference parameter, the control unit 30 may set a criterion for calling attention as the preference parameter as shown in FIG.

[0089] In addition, even after "AI Auto" is added, the control unit 30 continues to collect learning data and learn the preference parameters. In other words, the control unit 30 updates the preference parameters from time to time. This allows the control unit 30 to optimize the preference parameters, that is, to individually optimize notifications to the driver.

[0090] Next, a process procedure executed by the in-vehicle device 1 according to the embodiment will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the process procedure executed by the in-vehicle device 1. Note that the process described below is repeatedly executed by the control unit 3 of the in-vehicle device 1 after the vehicle is powered on.

[0091] 9, the control unit 3 first identifies the driver (step S101). The control unit 3 identifies the driver based on image data captured by the in-vehicle camera 51, for example.

[0092] Next, the control unit 3 determines the notification setting (notification mode) of the driving support information (step S102). If the driver selects a new notification setting, the control unit 3 determines the notification setting, and if the driver does not select a new notification setting, the control unit 3 determines the current notification setting.

[0093] Next, when driving of the vehicle is started, the control unit 3 judges whether or not notification of driving assistance information is necessary (step S103). The control unit 3 judges whether or not notification of driving assistance information is necessary based on the analysis result of the photographed data taken by the exterior camera 50 and the interior camera 51. More specifically, when the control unit 3 detects an event such as "drowsy driving", "distracted driving", "veering out of the lane", "insufficient distance between vehicles", etc., it judges that notification of driving assistance information is necessary, and when the control unit 3 does not detect the above events, it judges that notification of driving assistance information is not necessary.

[0094] When the control unit 3 determines that the notification of the driving support information is necessary (step S103, Yes), the control unit 3 determines whether the notification count is within the notification range (step S104). That is, the control unit 3 determines whether the current notification is within the range of the currently set notification frequency (i.e., equal to or less than the upper limit number of times).

[0095] When the control unit 3 determines that the notification count is within the notification range (step S104, Yes), the control unit 3 notifies the driver of the driving support information (step S105). The control unit 3 notifies the driver of the driving support information through the speaker 52 and the display 53.

[0096] Next, the control unit 3 estimates the driver's emotion when the driving support information is notified (step S106). The control unit 3 estimates the driver's emotion by inputting the image data of the driver when the driving support information is notified to the emotion estimation AI.

[0097] Next, the control unit 3 determines whether or not the cycle of the notification frequency has ended (step S107). The control unit 3 determines whether or not the cycle of the notification frequency has ended by measuring the time since the start of the current cycle.

[0098] When the control unit 3 determines that the cycle has ended (step S107, Yes), it transmits the learning data to the server device 100 (step S108). After that, the control unit 3 determines whether or not the driver has finished driving (step S109), and when it determines that the driver has finished driving (step S109, Yes), it ends the process.

[0099] Furthermore, if the control unit 3 determines in step S109 that the operation is continuing (step S109, No), or if the control unit 3 determines in step S107 that the cycle has not ended (step S107, No), the control unit 3 returns to the processing of step S103.

[0100] In addition, if the control unit 3 determines in step S103 that notification of driving assistance information is unnecessary, or if the control unit 3 determines in step S104 that the number of notifications is outside the notification range (step S103 / step S104, No), the control unit 3 proceeds to processing in step S107.

[0101] Next, a process procedure executed by the server device 100 will be described with reference to Fig. 10. Fig. 10 is a flowchart showing the process procedure executed by the server device 100. Note that the process procedure shown below is repeatedly executed by the control unit 30 every time learning data is acquired.

[0102] 10, the control unit 30 first acquires learning data from the in-vehicle device 1 (step S201). The control unit 30 acquires various parameters related to the driving support information and information related to the user's emotions when the driving support information is notified as the learning data.

[0103] Next, the control unit 30 learns preference parameters based on the acquired learning data (step S202). The control unit 30 learns the preference parameters by various machine learning methods.

[0104] Next, the control unit 30 determines whether the learned preference parameters have converged (step S203). If the control unit 30 determines that the preference parameters have converged (step S203, Yes), the control unit 30 adds an AI mode having the preference parameters to the notification mode options of the target in-vehicle device 1 (step S204), and ends the process.

[0105] Furthermore, when the control unit 30 determines in step S203 that the preference parameters have not converged (step S203, No), the control unit 30 omits the process in step S204 and ends the process. That is, in this case, the control unit 30 acquires new learning data and learns the preference parameters again.

[0106] In the above-described embodiment, the case where the information processing device is the server device 100 has been described, but the present invention is not limited to this. The information processing device may be the in-vehicle device 1. That is, learning of preference parameters may be completed within the in-vehicle device 1. Furthermore, the processing by the information processing device may be appropriately distributed between the in-vehicle device 1 and the server device 100.

[0107] In the above embodiment, the state information indicating the state of the driver is the driver's emotion, but the state information is not limited to this. The state information may include information regarding the driving operation by the driver and information regarding the voice of the driver.

[0108] For example, in this case, when the server device 100 notifies the driving assistance information, the server device 100 may learn the preference parameters by replacing the driver's rough driving operation with the user's feeling of discomfort.

[0109] The parameters of the learning data are not limited to the above examples. For example, various data such as the vehicle's running speed, weather, time, etc. may be included in the learning parameters when learning the preference parameters, and the preference parameters may be learned.

[0110] Further advantages and modifications may readily occur to those skilled in the art. Thus, the invention in its broader aspects is not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and equivalents thereof. [Explanation of symbols]

[0111] 1 In-vehicle device 2. Communications Department 3. Control Unit 4 Storage section 20 Communications Department 30 Control section 40 Storage section 50 Exterior Camera 51 In-car camera 52 Speaker 53 Display 100 Server device S Information Processing System

Claims

1. An information processing device having a controller, The controller: The driver is notified at the frequency or timing of a notification mode selected by the driver from multiple notification modes related to driving assistance, collecting status information regarding the state of the driver at the time of the notification, and adding a new notification mode having a frequency or timing according to the status information as an option; Information processing device.

2. The controller: acquiring photographed data of the driver as the status information; adding the new notification mode with a frequency or timing set based on the driver's emotion estimated from the photographed data; The information processing device according to claim 1 .

3. The controller: adding the new notification mode with a frequency or timing set depending on whether the driver feels uncomfortable at the time of the notification; The information processing device according to claim 2 .

4. The controller: performing the notification at a frequency or timing different from the notification mode selected by the driver, and adding the new notification mode of a frequency or timing according to the state information at the time of the notification; The information processing device according to claim 3 .

5. The controller: When the number of times that the driver feels uncomfortable when the notification is performed at the frequency of the notification mode selected by the driver does not reach a threshold value, the state information is collected at a higher frequency. The information processing device according to claim 4.

6. The notification regarding the driving assistance is Including information to alert the driver, The controller: setting a criterion for issuing the warning depending on the frequency of the new notification mode; The information processing device according to claim 1 .

7. The controller: adding the new notification mode, in which the timing from the occurrence of an event requiring attention to the notification is set based on the state information, to the options; The information processing device according to claim 1 .

8. The controller: Adding the new notification mode in which a sound type or a sound volume is set when making the notification; The information processing device according to claim 1 .

9. The controller: Adding the new notification mode for each information type when performing the notification. The information processing device according to claim 1 .

10. An information processing method executed by a controller, comprising: The driver is notified at the frequency or timing of a notification mode selected by the driver from multiple notification modes related to driving assistance, collecting status information regarding the state of the driver at the time of the notification, and adding a new notification mode having a frequency or timing according to the status information as an option; Information processing methods.

Images