Information processing system and vehicle
The system objectively evaluates passenger comfort by using sensors and predictive models to analyze vehicle vibrations and passenger attributes, improving ride comfort through personalized feedback.
Patent Information
- Application Number
- JP2023080443
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-15
- Publication Date
- 2024-11-27
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing methods lack the ability to objectively evaluate passenger comfort in vehicles, making it difficult to quantify and improve ride comfort based on individual passenger feedback.
An information processing system and vehicle equipped with sensors to detect vibrations, a processing unit to analyze data, and a transmission unit to send data to a server for evaluation, utilizing a predictive model that considers passenger attributes to objectively assess ride comfort.
Enables objective evaluation of passenger comfort, allowing for personalized ride comfort improvements based on individual passenger feedback, enhancing the driving experience.
Smart Images

Figure 2024164744000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing system and a vehicle. [Background technology]
[0002] There are known techniques for evaluating the ride comfort of a vehicle. Patent Document 1 discloses a "ride comfort evaluation method for evaluating ride comfort, the ride comfort being evaluated from head acceleration response data." [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2012-251913 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, it is considered to be difficult to evaluate the ride comfort of the passenger more objectively, and therefore there is a need to provide a technique for evaluating the ride comfort of the passenger more objectively. [Means for solving the problem]
[0005] According to the present invention, there is provided the following information processing system. This information processing system includes a sensor unit, a processing unit, a transmission unit, and a server. The sensor unit is used to detect vibrations acting on the body of an occupant seated in a vehicle seat. The processing unit processes data obtained from the sensor unit. The transmission unit is used to transmit the data processed by the processing unit. The server accumulates the data transmitted from the transmission unit.
[0006] According to the present invention, the following vehicle is provided. This vehicle includes a sensor unit, a processing unit, and a transmission unit. The sensor unit is disposed in at least one of the back part, the seating surface part, and the floor part on which the occupant places their feet of the seat on which the occupant sits, and is used to detect vibrations acting on the occupant sitting in the seat. The processing unit processes data obtained from the sensor unit. The transmission unit is used to transmit the data processed by the processing unit. Furthermore, according to the present invention, the following vehicle is provided. This vehicle includes a first sensor, a processing unit, and a transmission unit. The first sensor is used to detect vibrations acting on the occupant sitting in the seat. The processing unit processes data obtained from the sensor. The transmission unit is used to transmit the data processed by the processing unit. And the first sensor is disposed in the seating surface part of the seat on which the occupant sits. Effect of the Invention
[0007] According to the present invention, a technique for evaluating the ride comfort of a passenger more objectively is provided. Note that problems, configurations, and effects other than those described above will become apparent from the following description of the preferred embodiment of the invention. [Brief description of the drawings]
[0008] [Figure 1] FIG. 1 is a diagram showing an example of a configuration of a vehicle. [Diagram 2] FIG. 13 is a diagram showing an example of a process for storing passenger attributes and the acceleration at the time of boarding the passenger as a data set. [Diagram 3] FIG. 1 is a diagram showing an example of a ride comfort evaluation system. [Figure 4] FIG. 4 is a diagram showing an example of information provided by the ride comfort evaluation system. [Diagram 5] FIG. 4 is a diagram showing an example of an arrangement of an acceleration sensor. [Figure 6] FIG. 4 is a diagram showing an example of data acquired by the control unit. [Figure 7] FIG. 4 is a diagram showing an example of a formula used to calculate a value based on acceleration data. [Figure 8] 5 is a diagram showing an example of data for each acceleration band acquired by the control unit; [Figure 9]FIG. 13 is a diagram for explaining an example of a prediction model. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The embodiment is an example for explaining the present invention, and appropriate omissions and simplifications are made for clarity of explanation. The present invention can be implemented in various other forms. Unless otherwise specified, each component may be singular or plural.
[0010] The position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc., in order to facilitate understanding of the invention. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings. As examples of various information, expressions such as "table", "list", and "queue" may be used, but various information may be expressed in other data structures. For example, various information such as "XX table", "XX list", and "XX queue" may be expressed as "XX information". When describing identification information, expressions such as "identification information", "identifier", "name", "ID", and "number" are used, but these are mutually interchangeable. When there are multiple components having the same or similar functions, they may be described by adding different subscripts to the same symbol. In addition, when there is no need to distinguish between these multiple components, the subscripts may be omitted.
[0011] In the embodiment, a process performed by executing a program may be described. Here, a computer executes the program using a processor (e.g., CPU, GPU), and performs the process defined by the program while using a storage resource (e.g., memory) and an interface device (e.g., communication port), etc. Therefore, the subject of the process performed by executing the program may be the processor. Similarly, the subject of the process performed by executing the program may be a controller, device, system, computer, or node having a processor. The subject of the process performed by executing the program may be a calculation unit, and may include a dedicated circuit that performs a specific process. Here, the dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), or a CPLD (Complex Programmable Logic Device), etc.
[0012] The program may be installed in the computer from a program source. The program source may be, for example, a program distribution server or a computer-readable storage medium. When the program source is a program distribution server, the program distribution server may include a processor and a storage resource for storing the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other computers. In addition, in an embodiment, two or more programs may be realized as one program, or one program may be realized as two or more programs.
[0013] In this embodiment, a ride comfort evaluation system that can objectively evaluate the ride comfort of passengers (occupants) in a vehicle will be described. This system can also link the evaluation results to information about the driver of the vehicle and present the linked information.
[0014] First, a vehicle that acquires vehicle information will be described with reference to FIG. 1. As shown in FIG. 1, the vehicle 101 includes, as an example, a steering wheel 103, a control unit 104, a front camera 105, a seat camera 106, monitors (107a, 107b), seats (108a, 108b), acceleration sensors (109a, 109b, 109c), and a windshield 110. The steering wheel 103 is used by a driver who sits in the front seat 108a to drive the vehicle. The front camera 105 is disposed at the front of the vehicle and acquires image data in front of the vehicle 101. The windshield 110 is provided in front of the driver. With respect to the vehicle 101 and the driver or the driver, the horizontal direction X is the left-right direction, the lateral direction of the vehicle, or the width direction of the vehicle, the vertical direction Z is the up-down direction or the longitudinal direction of the vehicle, and the horizontal direction Y perpendicular to the lateral direction of the vehicle is the front-rear direction of the vehicle or the traveling direction of the vehicle.
[0015] The seat camera 106 is positioned so as to be able to capture image data of a passenger (crew member) seated in the rear seat 108b. In this example, the seat camera 106 is positioned on the rear side of the seat 108a in which the driver sits. The monitors (107a, 107b) display various information. The monitor 107a presents the driver with, for example, route information, fare information, and information regarding passenger comfort levels (described below). The monitor 107b presents passengers with, for example, route information, fare information, and appropriate advertising information.
[0016] The acceleration sensors (109a, 109b, 109c) are disposed on a seat 108b on which a passenger sits and on the floor of the vehicle 101. A specific example of the arrangement of the acceleration sensors (109a, 109b, 109c) will be described in detail later with reference to FIG.
[0017] The vehicle 101 may be provided with, for example, a GPS receiver and an input device for the driver to input various information. The vehicle 101 may also be provided with known sensors such as a temperature sensor, an illuminance sensor, and a distance measurement sensor as appropriate.
[0018] The control unit or control unit 104 (processing unit) can execute data processing. The control unit 104 can be, for example, an ECU (Electronic Control Unit), and may also be configured to include a processing device that processes data, a storage device that stores various data, a communication device used for communication with the outside of the vehicle 101, and the like. The control unit 104 is connected to an appropriate component of the vehicle 101 via a bus (not shown) and inputs and outputs data.
[0019] Furthermore, the control unit 104 controls the vehicle 101 based on the input and output of data. The control unit 104 and devices connected to the control unit 104 constitute an in-vehicle system 100. That is, the in-vehicle system 100 is a system in which the control unit 104 can control the vehicle 101 using the vehicle information 102.
[0020] The vehicle information 102 includes, for example, speed information, gear information, steering wheel angle information, lamp illumination information, external light information, distance information, infrared information, engine ON / OFF information, camera image information (inside / outside the vehicle), GPS information, navigation information, vehicle-to-vehicle communication information, road-to-vehicle communication information, and vehicle body identification information. The control unit 104 can appropriately acquire the vehicle information 102 from various sensors, communication devices, and the like provided in the vehicle 101.
[0021] Next, a data set acquired by the vehicle 101 will be described. This data set is data related to acceleration and passenger attributes, and can be used, for example, as data for calculating an evaluation value of ride comfort and constructing a prediction model used for ride comfort evaluation. In this embodiment, the control unit 104 is connected to the seat camera 106 and acceleration sensors (109a, 109b, 109c). The control unit 104 then stores data acquired from the three acceleration sensors (109a, 109b, 109c) in association with an input from the seat camera 106. Furthermore, the control unit 104, for example, executes person attribute determination using image recognition AI for the video from the seat camera 106.
[0022] An example of a process for acquiring a data set will be described with reference to Fig. 2. First, the seat camera 106 detects that a passenger (occupant) is getting on the vehicle 101 (S201). Then, the control unit 104 acquires image data of the passenger.
[0023] For example, the control unit 104 may determine that a passenger has boarded the vehicle based on face recognition of video data acquired by the seat camera 106, and start acquiring image data of the passenger. Alternatively, for example, the seat camera 106 may be a camera that automatically switches ON / OFF in response to detection of a passenger, and the control unit 104 may start acquiring image data of the passenger in response to switching the seat camera 106 to ON. Alternatively, for example, the driver may use an input device to input an instruction to acquire image data, and the control unit 104 may start acquiring image data of the passenger.
[0024] The control unit 104 acquires the attributes of the passenger (S202). The attributes of the passenger include the age, nationality, and sex of the passenger.
[0025] The control unit 104 acquires the attributes of the passengers by performing AI inference of the attributes of the passengers using, for example, the acquired image data (i.e., the camera image) and a model for inferring the attributes of the passengers from the camera image. The control unit 104 acquires (infers) the attributes of the passengers based on, for example, an image recognition AI using face recognition information. Here, the model for inferring the attributes of the passengers is stored in advance. Note that, in S202, for example, the driver may input the attributes of the passengers using an input device, and the control unit 104 may acquire the attributes of the passengers input by the driver.
[0026] When the driver starts the vehicle 101 toward the passenger's destination, the control unit 104 starts accumulating data from the acceleration sensors (109a, 109b, 109c) (S203).
[0027] After that, the vehicle arrives at the destination, and the seat camera 106 detects the passengers getting off (S204). The control unit 104 stops storing data from the acceleration sensors (109a, 109b, 109c) (S205).
[0028] For example, the control unit 104 may determine that a passenger has disembarked based on the absence of input to the seat camera 106, and may end data accumulation from the acceleration sensors (109a, 109b, 109c). Also, for example, the seat camera 106 may be a camera that automatically switches ON / OFF in response to the detection of a passenger, and the control unit 104 may end data accumulation from the acceleration sensors (109a, 109b, 109c) in response to the switching of the seat camera 106 to OFF.
[0029] While the vehicle is traveling to the passenger's destination, acceleration data is constantly acquired by the acceleration sensors (109a, 109b, 109c). The acceleration data is then accumulated in the control unit 104, which then organizes the acceleration data. An example of the organized acceleration data will be described in detail later with reference to FIGS. 6 and 8.
[0030] The control unit 104 stores the passenger attributes and the acceleration data for each time as a data set (S206). When a new passenger gets on, the same process as above is performed. Therefore, the control unit 104 obtains a new data set and stores the data set. By repeating S201 to S206, data sets are accumulated.
[0031] Next, an overview of the ride comfort evaluation system (information processing system) will be described with reference to FIG. 3. As shown in FIG. 3, the vehicle 101 wirelessly communicates with the dedicated server 203 via a communication device (transmitter). In this embodiment, the control unit 104 is connected to the Internet and can transmit data to the dedicated server 203 via wireless communication 202 such as Wi-Fi. The dedicated server 203 posts information related to the ride comfort evaluation on a dedicated site 205. An example of the information posted on the dedicated site 205 will be described in detail later with reference to FIG. 4. The dedicated server 203 is configured as an appropriate computer and includes, for example, a processor, a storage device, and a communication device.
[0032] In the operation of the system, first, when a registered driver 200 gets in the vehicle, the vehicle 101 is identified by an ID or the like, and individual information of the driver 200 is linked to the vehicle 101. After this synchronization, data acquired by the vehicle 101 is used to evaluate the ride comfort of the driver 200.
[0033] In this embodiment, the control unit 104 of the vehicle 101 stores a prediction model that receives acceleration data and passenger attributes as input and outputs (estimates) an evaluation value of the ride comfort.
[0034] Then, the passenger gets on board the vehicle 101, the driver 200 drives the vehicle 101 to the passenger's destination, and the passenger gets off at the destination. After the passenger gets off, the acceleration data accumulated during the travel is organized on the control unit 104. Then, the control unit 104 receives the organized acceleration data and the acquired attributes of the passenger 201 who got on the vehicle 101 as input, and outputs an evaluation value of the ride comfort (ride comfort score) using the input ride comfort evaluation algorithm (i.e., prediction model). The control unit 104 transmits the evaluation value of the ride comfort (ride comfort score) to the dedicated server 203 via a communication device (transmission unit).
[0035] Furthermore, after getting off, passenger 201b can transmit user evaluation 207 via an internet site or a smartphone app. Here, passenger 201b can use a personal computer, smartphone 206, or the like. As will be described later, dedicated server 203 can obtain data 208 related to user evaluation 207 and perform data processing using the data 208.
[0036] In this embodiment, the dedicated server 203 performs HTTP communication 204 and provides a dedicated site 205 on which the score based on the input ride comfort evaluation algorithm or the evaluation value of the ride comfort is posted. Here, an example of information displayed on the dedicated site 205 will be described with reference to FIG. 4.
[0037] 4, the attributes of the driver 200 and the evaluation value of the ride comfort (ride comfort in FIG. 4) are linked and posted on the dedicated site 205 by the dedicated server 203. The attributes of the driver 200 include the company he / she belongs to, his / her name, his / her age, his / her gender, and the languages he / she can speak, and the attributes of the driver 200 are registered in advance in the dedicated server 203 as information about the driver 200.
[0038] 4, the dedicated site 205 may basically display the evaluation values of the ride comfort in descending order, starting with the driver 200 with the highest score. The dedicated site 205 may also be a user interface that allows filtering according to each column according to user settings.
[0039] In this example, the average evaluation score of the driver is posted in the column of ride comfort. That is, every time a passenger gets on or off, an evaluation value of ride comfort based on the prediction model is transmitted from the vehicle 101 to the dedicated server 203, and the dedicated server 202 counts up the evaluation values of ride comfort and posts the average value on the dedicated site 205. Therefore, in this example, the evaluation value of ride comfort (ride comfort) is updated every time a passenger gets on or off.
[0040] Furthermore, the dedicated site 205 may post, for example, the distance from the current location. That is, the dedicated server 203 may acquire, for example, the location information input by a user browsing the dedicated site 205 and the location information of the vehicle 101. Then, the dedicated server 203 may post, on the dedicated site 205, the distance from the location input by the user to the vehicle 101.
[0041] A user browsing the dedicated site 205 can refer to various information such as the evaluation value of the ride comfort visualized by the prediction model and select, for example, which driver's service to use. Also, a user of a service provider that dispatches vehicles 101 can browse the dedicated site 205 and select which driver's vehicle 101 or the vehicle 101 driven by that driver to dispatch.
[0042] Next, a specific arrangement of the acceleration sensor 109 will be described with reference to FIG. b Direction, y b direction, and z b That is, the acceleration sensor 109a is used to detect acceleration in three axial directions, and b The direction is the front-rear direction of the vehicle 101, and the y b The direction is the width direction of vehicle 101, z b The direction corresponds to the height direction of the vehicle 101. The acceleration sensor 109a is provided to detect vibrations transmitted from the back side of the seat 108b to the passenger 201 seated in the seat 108b while the vehicle 101 is traveling. In this example, the acceleration sensor 109a is disposed on the back of the seat 108b, at the height of the backrest of the passenger 201 seated in the seat 108b.
[0043] The acceleration sensor 109b is orthogonal to the x S Direction, y S direction, and z S That is, the acceleration sensor 109b is used to detect acceleration in three axial directions, and sThe direction is the front-rear direction of the vehicle 101, and the y s The direction is the width direction of vehicle 101, z s The x direction corresponds to the height direction of the vehicle 101. S Rotation direction r around the direction x , y S Rotation direction r around the direction y , and z S Rotation direction r around the direction z The acceleration sensor 109b is used to detect the acceleration of the passenger 201 seated in the seat 108b. The acceleration sensor 109b is provided to detect vibrations transmitted from the seat surface side of the seat 108b to the passenger 201 seated in the seat 108b while the vehicle 101 is traveling. In this example, the acceleration sensor 109b is disposed on the seat surface portion of the seat 108b on which the passenger 201 is seated.
[0044] The acceleration sensor 109c has x t Direction, y t direction, and z t That is, the acceleration sensor 109c is used to detect acceleration in three axial directions, and t The direction is the front-rear direction of the vehicle 101, and the y t The direction is the width direction of vehicle 101, z t The direction corresponds to the height direction of vehicle 101. Acceleration sensor 109c is provided to detect vibrations transmitted from the floor of vehicle 101 to the legs of passenger 201 seated in seat 108b while vehicle 101 is traveling. In this example, acceleration sensor 109c is provided on the floor of vehicle 101 at a position where the feet of passenger 201 are placed when passenger 201 is seated in seat 108b.
[0045] Next, an example of data that the control unit organizes and acquires by sorting the accumulated data will be described with reference to FIGS. 6 to 8. As shown in FIG. 6, the control unit 104 organizes the above-mentioned components (x b , y b , z b , x s , y s , z s , r x , r y , rz , x t , y t , z t ) acceleration data. The control unit 104 acquires acceleration data at an arbitrary or predetermined measurement interval (0.5 s in this example). The control unit 104 also calculates a seat Calculate.
[0046] Above a seat is a value for evaluating vibration based on acceleration data, and in this embodiment, is a value related to the frequency characteristics of the human body in ISO2631-1. In this embodiment, the control unit 104 calculates a based on the formula shown in FIG. seat Calculate the following: seat The evaluation of the ride comfort based on the above can be expressed as (0) to (5) below, for example.
[0047] In this example, as shown in FIG. 9 described later, the initial values of the ride comfort evaluation coefficients k0=0, k1=100, k2=150, k3=200, k4=250, and k5=300 are preset according to the acceleration bands given by (0) to (5) below, and the ride comfort score felt by the passengers is calculated and evaluated. (0)a seat is 0.315 [m / s 2 ], the ride is "not uncomfortable." (1)a seat 0.315~0.6[m / s 2 ], the ride is "slightly uncomfortable." (2)a seat 0.6~1.0[m / s 2 ], the ride is "somewhat uncomfortable." (3)a seat is 1.0 to 1.6 [m / s 2 ], the ride is "uncomfortable." (4)a seat 1.6~2.5[m / s 2 ], the ride is "very uncomfortable." (5)a seat is 2.5 [m / s 2] and the ride is "extremely uncomfortable."
[0048] The control unit 104 determines a seat The control unit 104 determines which of the above acceleration bands (divisions) (0) to (5) the passenger 201 is classified into. Furthermore, the control unit 104 calculates the duration of each acceleration band during the total riding time of the passenger 201 from the measurement interval and the number of measurements, and obtains the data shown in FIG.
[0049] As shown in FIG. 8, the control unit 104 acquires data classified into measurement interval, number of measurements, total riding time, duration, and duration / total riding time for each acceleration band. Here, the measurement interval is the interval at which the control unit 104 acquires acceleration data. The number of measurements is a seat The total ride time corresponds to the time from the acquisition of acceleration data to the end of the ride. The duration corresponds to the number of times that the seat Duration / Total Ride Time is the duration divided by the total ride time.
[0050] Next, a prediction model for evaluating ride comfort will be described in detail. As an example, the prediction model is generated by machine learning using a data set accumulated by the control unit 104. In this embodiment, the prediction model shown in FIG. 9, which will be described later, is used.
[0051] Here, as an example, the dedicated server 203 may transmit a prediction model to the vehicle 101. That is, the dedicated server 203 acquires an accumulated data set from the vehicle 101 and generates a prediction model to be transmitted to the vehicle 101. Then, the vehicle 101 may acquire the prediction model via communication.
[0052] However, there may be cases where the output value of the prediction model and the evaluation of the actual user (passenger) who rode in the vehicle deviate from each other, and the evaluation of the actual user (passenger) cannot be output appropriately. Therefore, a prediction model that can perform a more appropriate ride comfort evaluation may be obtained.
[0053] Therefore, in this embodiment, a process is performed to obtain a more appropriate prediction model based on the ride comfort score s based on the data of each acceleration band acquired by the control unit 104 and the evaluation of the actual passengers (i.e., the user evaluation 207). This process will be specifically described while explaining an example of calculating the ride comfort score.
[0054] First, an example of calculation of the ride comfort score s will be described. In the prediction model shown in FIG. n are discomfort indices based on vibration acceleration when seated (i.e., evaluation coefficients of ride comfort according to acceleration ranges), and are set in advance as provisional values (initial values). In this example, k0=0, k1=100, k2=150, k3=200, k4=250, and k5=300 are assumed to be input initially. Note that the maximum score (100 in this example) corresponds to the maximum score of the user evaluation 207.
[0055] For example, when the data shown in FIG. 8 is input, the passenger ride comfort score s for this data can be calculated as 100-(0x0.524+100x0.352+150x0.088+200x0.024+250x0.011+300x0.001)=43.75.
[0056] If the average score of the user evaluation 207 actually obtained on the dedicated site 205 for the driver regarding this data is 68.0 points, this is taken as the answer, k n (i.e., k0, k1, k2, k3, k4, k5) can be adjusted (learned) to obtain a more appropriate prediction model. Note that, since parameters such as k0, k1, k2, k3, k4, and k5 exist for each passenger, with the average score of the user ratings 207 being the answer, the parameters for bringing the calculation result in the formula closer to the answer are determined almost uniquely by the gradient descent method.
[0057] That is, the score (a seatA more appropriate prediction model can be obtained by repeating the learning process to minimize the difference between the ride comfort score s based on the vehicle's characteristics and the average score of the 207 user ratings. By repeating this learning process, a unique algorithm that approaches the sensory evaluation of the human body can be constructed.
[0058] Note that this algorithm may be set separately for each passenger attribute recognized by, for example, the seat camera 106. Local updates based on attributes are also possible. In this case, however, it is necessary to perform separate learning for each passenger attribute. Then, the ride comfort is evaluated using a prediction model according to the passenger attributes.
[0059] The dedicated server 203 may execute the above learning and transmit the obtained more appropriate prediction model to the vehicle 101. Then, the algorithm enhanced by the dedicated server 203 (i.e., the more appropriate prediction model) may be overwritten in the control unit 104 of the vehicle 101.
[0060] From the above explanation, a technology is provided that allows the ride comfort to be objectively evaluated, even though the driving characteristics differ depending on the driver. Also, a technology is provided that allows universal quantification, even though the index may change depending on the attributes of the occupants.
[0061] The control unit 104 may input data acquired from the acceleration sensor during the journey to the destination into the prediction model to obtain a discomfort index that quantifies the discomfort of the passengers. Here, the discomfort index can be obtained, for example, by converting the ride comfort score estimated using the prediction model.
[0062] For example, an algorithm for evaluating ride comfort during driving may be incorporated into the control unit 104, so that the control unit 104 may obtain the discomfort index at an appropriate timing during driving. Here, the control unit 104 may obtain the discomfort index in real time or at preset time intervals. The control unit 104 may also obtain the discomfort index based on the distribution of accumulated acceleration data, for example, based on the acceleration distribution over one minute.
[0063] The control unit 104 may be connected to the driver's monitor 107a and display information on passenger comfort levels (in other words, information according to the passenger discomfort index) on the driver's monitor 107a. By receiving this notification, the driver 200 can improve his driving. The control unit 104 may, for example, obtain the discomfort index in real time and display information on the passenger comfort levels based on the discomfort index on the monitor 107a in real time. In this case, the driver 200 can improve his driving in real time.
[0064] Furthermore, the control unit 104 may display, on the driver's monitor 107a, information according to the difference between the discomfort index obtained in real time and the discomfort index obtained a certain time ago. That is, when the difference in the discomfort index indicates that driving has improved, the control unit 104 may display, on the driver's monitor 107a, information indicating that driving has improved. Conversely, when the difference in the discomfort index indicates that driving has deteriorated, the control unit 104 may display, on the driver's monitor 107a, information indicating that driving has deteriorated. Here, the certain time is a time that is appropriately set from the viewpoint of evaluating driving. The certain time may be, for example, in units of several minutes.
[0065] The control unit 104 may be connected to a monitor 107b for passengers and customize advertisement display on the monitor 107b according to the acquired passenger attributes. The control unit 104 may change the content and size of the advertisement display according to, for example, the age and sex of the passenger.
[0066] Although the embodiments have been described above, the present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the spirit of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those having all of the configurations described. In addition, for example, other configurations may be added, deleted, or replaced with respect to part of the configuration of the embodiment.
[0067] In the above embodiment, the acceleration sensors (109a, 109b, 109c) are used. However, other sensors may be used as long as a sensor unit is configured to detect vibrations acting on the body of a passenger (crew member). Note that other sensors may be known sensors such as a gyro sensor and a motion sensor. The control unit 104 may also acquire acceleration data based on a known calculation method using data from the sensor unit.
[0068] In the above embodiment, an example of obtaining a predictive model that takes attributes into account has been described, but a predictive model that evaluates ride comfort without taking passenger attributes into account may also be obtained.
[0069] In the above embodiment, an example has been described in which the prediction model is stored in the control unit 104, and the control unit 104 calculates the evaluation value of the ride comfort using the prediction model. However, the dedicated server 203 may calculate the ride comfort score. That is, the prediction model may be stored in the dedicated server 203, and the dedicated server 203 may calculate the ride comfort score using data acquired from the vehicle 101 as an input.
[0070] In this specification, "body" means the body excluding the head.
[0071] According to this specification, as an example, the following prediction model generation method is provided. That is, the prediction model generation method includes the steps of: generating a prediction model used for evaluating passenger ride comfort using acceleration data during travel acquired from the vehicle 101 as an input; and generating a new prediction model (a more appropriate prediction model) by machine learning the prediction model based on the prediction model and an evaluation of the ride comfort actually acquired by a user, so that an output value of the prediction model approaches the evaluation of the ride comfort actually acquired by a user.
[0072] In addition, in the predictive model generation method, the predictive model may have parameters (ride comfort evaluation coefficients) according to acceleration bands, and the new predictive model may be generated by resetting the parameters in the machine learning.
[0073] The prediction model generation method may also generate a prediction model for each passenger attribute. [Explanation of symbols]
[0074] 101 vehicles 104 Control Unit 106 Seat Camera 107a Monitor 107b Monitor 109 Acceleration Sensor 200 Driver 201 passengers 202 Wireless Communications 203 Dedicated Server 204 HTTP communication 205 Dedicated Site 206 Smartphone 207 User Ratings 208 User Rating Data
Claims
1. A sensor unit used to detect vibration acting on the body of an occupant seated in a vehicle seat; A processing unit that processes data obtained from the sensor unit; a transmission unit used for transmitting data processed by the processing unit; a server that accumulates the data transmitted from the transmission unit; An information processing system comprising:
2. 2. The information processing system according to claim 1, using a prediction model for estimating an evaluation by an occupant that has been machine-learned using data obtained from the sensor unit on the server, the evaluation by the occupant is estimated using data obtained from the sensor unit as an input; An information processing system comprising:
3. 3. The information processing system according to claim 2, estimating the evaluation according to the attributes of the occupant using the prediction model generated using the attributes of the occupant; An information processing system comprising:
4. 2. The information processing system according to claim 1, The processing unit includes: A discomfort index that quantifies the discomfort of the occupant is calculated based on the data from the sensor unit by using a prediction model that estimates an evaluation by the occupant that has been machine-learned using the data obtained from the sensor unit on the server. An information processing system comprising:
5. 5. The information processing system according to claim 4, The processing unit includes: Notifying the driver of information corresponding to the discomfort index. An information processing system comprising:
6. 5. The information processing system according to claim 4, The processing unit includes: notifying the driver of information corresponding to a difference between the discomfort index obtained in real time and the discomfort index obtained a certain time ago; An information processing system comprising:
7. 2. The information processing system according to claim 1, The server, The information on the passenger's evaluation based on the data is linked to information on the driver of the vehicle that has been registered in advance, and the linked information is displayed in a list on the website. and rearranging the information according to the occupant's evaluation based on the data acquired thereafter. An information processing system comprising:
8. 2. The information processing system according to claim 1, Further equipped with a camera for photographing the occupants, After the occupant is detected by the camera, the processing unit processes data obtained from the sensor unit. An information processing system comprising:
9. 9. The information processing system according to claim 8, When the camera detects that the occupant has dismounted, the processing unit stops acquiring data from the sensor unit. An information processing system comprising:
10. a sensor unit that is disposed in at least one of a back surface portion, a seat surface portion, and a floor portion on which the occupant places his / her feet of the seat on which the occupant sits, and that includes a sensor used to detect vibration acting on the occupant sitting in the seat; A processing unit that processes data obtained from the sensor unit; a transmission unit used for transmitting data processed by the processing unit; A vehicle comprising:
11. 11. The vehicle according to claim 10, The processing unit includes: Using a prediction model that estimates an evaluation by an occupant, which is machine-learned using data obtained from the sensor unit, an evaluation by an occupant is estimated using data obtained from the sensor unit as an input; generating data that can be input to the prediction model based on the data obtained from the sensor unit; A vehicle characterized by:
12. 11. A vehicle as claimed in claim 10, the sensors disposed on the back surface and the floor surface are sensors used to acquire acceleration data in three-axis directions, The sensor disposed in the seat portion is a sensor used to acquire acceleration data in three axial directions and in a rotational direction of each of the three axial directions. A vehicle characterized by:
13. A first sensor used to detect vibration acting on the occupant seated in the seat; A processing unit for processing data obtained from the sensor; a transmission unit used for transmitting data processed by the processing unit; Equipped with The first sensor is It is placed on the seat surface of the seat on which the passenger sits. A vehicle characterized by:
14. 14. A vehicle as claimed in claim 13, a second sensor for detecting vibration acting on the occupant seated in the seat; The second sensor is Located on the back of the seat on which the passenger sits, A vehicle characterized by:
15. 14. A vehicle as claimed in claim 13, a second sensor for detecting vibration acting on the occupant seated in the seat; The second sensor is The seat is disposed on a floor portion on which the feet of the occupant sitting in the seat are placed. A vehicle characterized by:
16. 15. A vehicle as claimed in claim 14, a third sensor for detecting vibration acting on the occupant seated in the seat; The third sensor is The seat is disposed on a floor portion on which the feet of the occupant sitting in the seat are placed. A vehicle characterized by:
Citation Information
Patent Citations
Method and device for evaluating riding comfort
JP2012251913A
Cited By
Intelligent seat automatic adjusting method and device combined with navigation system and vehicle
CN120135026A
