Information processing device, information processing system, information processing method and recording medium

Abstract

An information processing device is provided with an analysis unit, a reference acquisition unit, and an evaluation unit. The analysis unit acquires a relationship between a state of an object based on sensor information including an object outside or inside a vehicle and a state of the vehicle. The reference acquisition unit acquires a driving standard, which is a standard related to vehicle driving and produced through information processing by using, as an input, information on rules for the vehicle driving. The evaluation unit calculates a driving evaluation score obtained by evaluating the vehicle driving on the basis of the driving standard and the relationship.

Description

Information processing device, information processing system, information processing method, and recording medium

[0001] The present disclosure relates to an information processing device, an information processing system, an information processing method, and a recording medium.

[0002] For example, Patent Document 1 describes a technology in which photographed information is input into a computer programmed with artificial intelligence, which analyzes the information for possible traffic violations and reports the information to authorities. Patent Document 1 describes violations that can be detected, such as improper lane changes, improper U-turns, illegal left and right turns, running red lights and stop signs, improper parking, driving with a helmet on for motorcyclists, speeding, and failure to yield to pedestrians.

[0003] Special Publication No. 2023-549983

[0004] However, Patent Document 1 does not disclose a method for determining the above-described detectable violations. With the technology described in Patent Document 1, the number of detectable violations may be limited. Therefore, even if the technology described in Patent Document 1 is used, it may be difficult to accurately evaluate vehicle driving.

[0005] One of the objectives of the present disclosure is to accurately evaluate vehicle driving.

[0006] The information processing device of the present disclosure includes an analysis means for acquiring the relationship between the state of an object based on sensor information including objects outside or inside the vehicle and the state of the vehicle, a standard acquisition means for acquiring driving standards, which are standards for driving the vehicle, created by information processing using information regarding rules for driving the vehicle as input, and an evaluation means for calculating a driving evaluation score that evaluates the driving of the vehicle based on the driving standards and the relationship.

[0007] An information processing system according to the present disclosure includes the information processing device described above, and at least one sensor mounted on the vehicle and configured to generate the sensor information.

[0008] The information processing method disclosed herein includes one or more computers acquiring a relationship between the state of an object based on sensor information including an object outside or inside the vehicle and the state of the vehicle, acquiring a driving standard, which is a standard for driving the vehicle, created by information processing using information regarding rules for driving the vehicle as input, and calculating a driving evaluation score that evaluates the driving of the vehicle based on the driving standard and the relationship.

[0009] The recording medium in the present disclosure is a recording medium having recorded thereon a program for causing one or more computers to execute the following: acquire the relationship between the state of an object based on sensor information including objects outside or inside the vehicle and the state of the vehicle; acquire driving standards, which are standards for driving the vehicle, created by information processing using information regarding rules for driving the vehicle as input; and calculate a driving evaluation score that evaluates the driving of the vehicle based on the driving standards and the relationship.

[0010] According to the present disclosure, it becomes possible to accurately evaluate vehicle driving.

[0011] 1 is a block diagram showing a configuration example of a first information processing device in the present disclosure. FIG. 2 is a block diagram showing a configuration example of a first information processing system in the present disclosure. FIG. 3 is a flowchart showing a processing operation example of a first information processing device in the present disclosure. FIG. 4 is a block diagram showing a detailed configuration example of a first information processing device in the present disclosure. FIG. 5 is a flowchart showing a detailed processing operation example of a first information processing device in the present disclosure. FIG. 6 is a block diagram showing a physical configuration example of a first information processing device in the present disclosure. FIG. 7 is a block diagram showing a configuration example of a second information processing device in the present disclosure. FIG. 8 is a flowchart showing a processing operation example of a second information processing device in the present disclosure. FIG. 9 is a flowchart showing a processing operation example of a second information processing device in the present disclosure. FIG. 10 is a block diagram showing a configuration example of a third information processing device in the present disclosure. FIG. 11 is a flowchart showing a processing operation example of a third information processing device in the present disclosure.

[0012] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings, similar components are denoted by similar reference numerals, and descriptions thereof will be omitted as appropriate. In the present disclosure, the drawings relate to one or more embodiments.

[0013] First Embodiment An information processing device 100 includes an analysis unit 110, a reference acquisition unit 120, and an evaluation unit 140, as shown in FIG.

[0014] The analysis unit 110 acquires the relationship between the state of the object based on sensor information including the object outside or inside the vehicle and the state of the vehicle C.

[0015] The standard acquisition unit 120 acquires driving standards, which are standards for driving a vehicle, created by information processing using information relating to rules for driving a vehicle as input.

[0016] The evaluation unit 140 calculates a driving evaluation score that evaluates the driving of the vehicle C based on the driving criteria and the relationship.

[0017] According to this information processing device 100, it is possible to easily create a driving standard incorporating various rules and evaluate the driving of the vehicle C. It is possible to accurately evaluate the driving of the vehicle C.

[0018] The information processing system S1 includes at least one sensor S and an information processing device 100, as shown in FIG. 2, for example.

[0019] At least one sensor S is mounted on the vehicle C and generates sensor information.

[0020] According to this information processing system S1, it is possible to easily create a driving standard that incorporates various rules and evaluate the driving of the vehicle C. It becomes possible to accurately evaluate the driving of the vehicle C.

[0021] The information processing device 100 executes information processing such as that shown in FIG.

[0022] The analysis unit 110 acquires the relationship between the state of the object based on the sensor information including the object outside or inside the vehicle and the state of the vehicle C (step S110).

[0023] The standard acquisition unit 120 acquires driving standards, which are standards for driving a vehicle, created by information processing using information on rules for driving a vehicle as input (step S120).

[0024] The evaluation unit 140 calculates a driving evaluation score that evaluates the driving of the vehicle C based on the driving standard and the relationship (step S140).

[0025] According to this information processing, it is possible to easily create a driving standard that incorporates various rules and evaluate the driving of the vehicle C. It becomes possible to accurately evaluate the driving of the vehicle C.

[0026] Hereinafter, a detailed example of the information processing system S1, the information processing device 100, and the information processing executed by the information processing device 100 will be described.

[0027] As shown in FIG. 4 , the information processing device 100 may include, in addition to the above-mentioned analysis unit 110, criteria acquisition unit 120, and evaluation unit 140, a driver identification unit 130, an evaluation history storage unit 150, an instruction receiving unit 160, a display control unit 170, and a display unit 180.

[0028] The driver identification unit 130 identifies the driver of the vehicle C based on sensor information from a sensor S that detects an object inside the vehicle.

[0029] The evaluation history storage unit 150 stores the history of the calculated driving evaluation scores.

[0030] The instruction receiving unit 160 receives an instruction from the user to refer to the driving evaluation score.

[0031] The display control unit 170 causes the display unit 180 to display the driving evaluation score in accordance with the user's instruction.

[0032] The information processing device 100 executes information processing such as that shown in FIG.

[0033] The above-described steps S110 and S120 are executed.

[0034] The driver identification unit 130 identifies the driver of the vehicle C based on sensor information from the sensor S that detects an object inside the vehicle (step S130).

[0035] The above-described step S140 is executed.

[0036] The evaluation unit 140 stores the driving evaluation score in the evaluation history storage unit 150 (step S150).

[0037] The information processing device 100 executes information processing such as that shown in FIG.

[0038] The instruction receiving unit 160 receives a user instruction to refer to the driving evaluation score (step S160).

[0039] The evaluation unit 140 calculates a reference evaluation score based on the calculated driving evaluation score in response to an instruction from the user (step S170).

[0040] The display control unit 170 causes the display unit 180 to display at least one of the driving evaluation score and the reference evaluation score in accordance with the user's instruction (step S180).

[0041] (Regarding the sensor S) The sensor S is mounted on the vehicle C and generates sensor information including objects outside or inside the vehicle C. The sensor S may be one or more. For example, when multiple sensors S are mounted on the vehicle C, each sensor S generates sensor information.

[0042] The sensor information may include one or more objects. Each of the at least one sensor S may be, for example, a camera, a LiDAR (Light Detection and Ranging), or the like, but is not limited to these. For example, if the sensor S is a camera, the sensor S generates an image or video including objects outside or inside the vehicle C according to its imaging range. For example, if the sensor S is a LiDAR, the sensor S generates radar information including objects outside or inside the vehicle C according to its detection range.

[0043] Each of the at least one sensor S may be connected to the information processing device 100 via a wireless communication line NT so as to be able to transmit and receive information to and from the information processing device 100. The at least one sensor S may be connected to the information processing device 100 via an appropriate relay device (e.g., an in-vehicle device that communicates with the sensor S and the information processing device 100) or the like (not shown) so as to be able to transmit and receive information to and from the information processing device 100.

[0044] An object external to vehicle C is an object that is outside vehicle C and exists within a predetermined sensing range of sensor S. For example, an object external to vehicle C may include at least one of vehicles other than vehicle C (vehicles other than vehicle C are also referred to as "other vehicles"), the road on which vehicle C is traveling, surrounding roads and sidewalks on which vehicle C is traveling, road signs, boundary lines between the road on which vehicle C is traveling and surrounding roads and sidewalks, crosswalks, pedestrians, buildings, etc. Examples of vehicles include motorcycles, bicycles, kick scooters, etc. Note that the objects external to vehicle C and vehicles are not limited to those exemplified here.

[0045] The objects inside vehicle C may include at least one of the driver of vehicle C, passengers, luggage carried in vehicle C, a terminal device such as a smartphone, a drink, etc., but are not limited to these.

[0046] (Regarding the analysis unit 110) As described above, the analysis unit 110 acquires the relationship between the state of an object based on sensor information and the state of the vehicle C. The object here is an object included in the sensor information. The analysis unit 110 may acquire text information including the relationship between the state of the object and the state of the vehicle C. In other words, the relationship between the state of the object and the state of the vehicle C may be expressed in text.

[0047] The state of the object may include the position of the object. If the object is a road sign or the like, the state of the object may include the object being stationary, being a stationary object that does not move, etc. If the object is a smartphone or the like, the state of the object may include the object being placed or installed in the vehicle C, being held by the driver or passenger, etc., being operated by the driver or passenger, etc. If the object is a movable object such as a person, bicycle, or other vehicle, the state of the object may include the object being stopped, the posture of the object, or being in motion. If the object is in motion, the state of the object may include the moving speed, acceleration, etc. Note that the state of the object may include at least one of the examples given here, but is not limited to the examples given here.

[0048] The state of the vehicle C may include, for example, the current position, traveling speed, acceleration, etc. of the vehicle C as the traveling state of the vehicle C. The state of the vehicle C may include, for example, the driver's drowsiness, the driver's posture, etc. as the state of the driver of the vehicle C. Note that the state of the vehicle C may include at least one of the examples given here, but is not limited to these.

[0049] The relationship between the state of the object and the state of the vehicle C may include, for example, a positional relationship, a movement relationship, etc. between the object and the vehicle C. The positional relationship may include, for example, at least one of distance, direction, etc. The movement relationship may include the vehicle C moving or stopped, and the object moving or stopped. The movement relationship may include the movement speed, acceleration, etc. of the vehicle C or the object when the vehicle C or the object is moving. Note that each of the relationship between the state of the object and the state of the vehicle C, the positional relationship, and the movement relationship may include at least one of the examples given here, but are not limited to these.

[0050] The analysis unit 110 may acquire sensor information from each of at least one sensor S. The analysis unit 110 may, for example, analyze the acquired sensor information to detect an object and acquire the relationship between the state of the object and the state of the vehicle C. An analytical model may be used for this analysis. The analytical model may, for example, be a machine learning model that, when an image is input, detects an object contained in the image. The analytical model may be a machine learning model trained using training data including learning images and correct answers regarding the object contained in the learning images. The analysis unit 110 may include an analytical model and input sensor information into the analytical model to detect the state of the object and the state of the driver of the vehicle C. Furthermore, the analysis unit 110 may detect the running state of the vehicle C using a GPS (Global Positioning System) function, a signal from a control device mounted on the vehicle C, or the like. The analysis unit 110 may then generate (acquire) information indicating the relationship between the state of the object and the state of the vehicle C using the detected state of the object and the state of the vehicle C.

[0051] The analytical model may be a machine learning model for detecting the relationship between the state of the object and the state of the vehicle C. The analysis unit 110 may include an analytical model and input sensor information into the analytical model to (acquire) the relationship between the state of the object and the state of the vehicle C. If the sensor information is radar information, the analysis unit 110 may generate point cloud information indicating the object at each position using the radar information, or may acquire the point cloud information from an external device (not shown). The analysis unit 110 may then use the point cloud information as input to the analytical model. Furthermore, the analysis unit 110 may acquire information indicating the relationship between the state of the object and the state of the vehicle C from an external device (not shown). Furthermore, for example, if the vehicle C is not equipped with a sensor S for detecting an object inside the vehicle C, the driver's state may not need to be acquired. Furthermore, the analytical model may be a machine learning model trained to detect the driving state of the vehicle C, and the driving state of the vehicle C may be detected by inputting sensor information into the analytical model.

[0052] (Regarding the standard acquisition unit 120) As described above, the standard acquisition unit 120 acquires driving standards, which are standards for driving a vehicle, created by information processing using information on rules for driving a vehicle (hereinafter also referred to as "rule information") as input. This information processing may be processing using a machine learning model, for example. Note that the driving standards may also be generated or acquired using general information processing that does not use a machine learning model.

[0053] For example, the standard acquisition unit 120 may include a standard creation model for creating driving standards, and may acquire driving standards using the standard creation model. The standard creation model is a machine learning model trained to create driving standards, and outputs driving standards when, for example, rule information is input. The standard creation model may be, for example, a machine learning model that performs natural language processing, or may be a large-scale language model (LLM) constructed by deep learning using a large amount of data. The driving standards may include, for example, at least one condition related to vehicle driving. The standard creation model may output text information including the driving standards. That is, the driving standards may be expressed in text.

[0054] The rule information may include, for example, at least one of text, graphics, video, etc. related to the rule. The rule information may include, for example, official rules established regarding vehicle driving. Official rules regarding vehicle driving are, for example, rules established by public organizations such as the national government or local governments, and in detail may include at least one of the Road Traffic Act, the Tokyo Metropolitan Road Traffic Regulations, a driving manual, etc. The rule information may include, for example, video of an accident occurring, video of an accident about to occur, etc. Note that the rule information may include at least one of the examples given here, but is not limited to the examples given here.

[0055] The driving standards may include, for example, at least one of recommended driving standards that set standards for recommended driving, illegal driving standards that set standards for illegal driving that violates laws and regulations, and accident occurrence standards that set standards for dangerous driving that may cause an accident.

[0056] An example of a recommended driving criterion may include a driving criterion that includes a first condition that the vehicle is passing a stopped vehicle and a second condition that the vehicle should slow down. This example corresponds to a recommended driving criterion that the vehicle should slow down when passing a stopped vehicle.

[0057] Another example of recommended driving standards is a driving standard that includes a first condition that the vehicle is traveling within a predetermined range from a school, a second condition that the vehicle passes a stopped vehicle on the shoulder of the road, and a third condition that the vehicle should drive slowly. This example corresponds to the recommended driving of driving slowly when passing a parked or stopped vehicle, based on the fact that there have been cases where children have jumped out from behind parked vehicles on the shoulder of a road near a school.

[0058] Yet another example of a recommended driving standard is a driving standard that includes a first condition that the driver is about to cross a crosswalk, a second condition that there are no pedestrians or bicycles attempting to cross ahead in the driver's path, and a third condition that the driver does not slow down to a speed that allows the driver to stop just before the crosswalk. This example corresponds to Article 38 of the Road Traffic Act, which states, "Except when it is clear that there are no pedestrians or bicycles (hereinafter referred to in this Article as "pedestrians, etc.") attempting to cross ahead in the driver's path at the crosswalk, etc." Driving that does not meet this recommended driving standard is not a violation of Article 38 of the Road Traffic Act, but driving that meets this recommended driving standard is considered preferable because it does not impede traffic flow.

[0059] In addition, Article 38, Paragraph 1 of the Road Traffic Act stipulates the following: When a vehicle, etc. approaches a pedestrian crossing or bicycle crossing lane (hereinafter referred to in this Article as a "pedestrian crossing, etc."), it must proceed at a speed that enables it to stop just before the pedestrian crossing, etc. (if a stop line marked by a road sign, etc. is provided, just before that stop line; the same applies hereinafter in this paragraph), unless it is clear that there are no pedestrians or bicycles (hereinafter referred to in this Article as "pedestrians, etc.") attempting to cross ahead of the vehicle's path at the pedestrian crossing, etc. In this case, if there are pedestrians, etc. crossing or attempting to cross ahead of the vehicle's path at the pedestrian crossing, etc., the vehicle must stop temporarily just before the pedestrian crossing, etc., and must not obstruct their passage.

[0060] Examples of illegal driving criteria include driving criteria that include a condition of exceeding the speed limit, and driving criteria that include a first condition of being slower than the acceleration / deceleration rate on a highway and a second condition of exceeding the upper speed limit.

[0061] Other examples of illegal driving criteria include driving criteria that include a condition of looking away from the road for a predetermined percentage of time or more while the vehicle is moving, driving criteria that include a condition of operating a smartphone while the vehicle is moving, and driving criteria that include a condition of falling asleep while the vehicle is moving.

[0062] An example of an accident occurrence criterion may be a driving criterion that includes one or more conditions common to accidents that have occurred or that have nearly occurred, based on accident reports, video footage of the accident, video footage of the nearly occurring accident, etc. Accident occurrence criteria may be developed for specific locations where accidents are likely to occur, and may therefore include information about the location where the accident occurred.

[0063] (Regarding the driver identification unit 130) As described above, the driver identification unit 130 identifies the driver of the vehicle C based on sensor information from the sensor S that detects objects inside the vehicle C. Note that if the sensor S for detecting objects inside the vehicle C is not mounted on the vehicle C, or if the driving of each driver is not evaluated, the driver does not need to be identified.

[0064] For example, the driver identification unit 130 identifies the driver of vehicle C using registration information including pre-registered driver feature amounts and feature amounts extracted from sensor information including the driver of vehicle C. The feature amount may be, for example, a feature vector. In detail, for example, the feature amount may be a feature vector indicating the facial features of the driver. To extract the feature amount (for example, the feature vector), for example, a machine learning model or the like for extracting feature amounts (for example, feature vectors) from video or the like may be used. Such a machine learning model or the like may be a known machine learning model used in face recognition or the like.

[0065] (Regarding the evaluation unit 140) As described above, the evaluation unit 140 calculates a driving evaluation score that evaluates the driving of the vehicle C based on the driving standard and the relationship. The driving standard here may be a driving standard acquired by the standard acquisition unit 120. Furthermore, the relationship may be a relationship between the state of the object and the state of the vehicle C acquired by the analysis unit 110.

[0066] For example, the evaluation unit 140 determines whether the relationship satisfies the driving standard, and calculates, based on the determination result, a driving evaluation score related to the driving of the vehicle C. For example, the evaluation unit 140 may calculate the driving evaluation score by adding or subtracting the score based on the determination result.

[0067] Whether to add or subtract a score may be determined, for example, depending on the type of driving standard satisfied by the relationship. For example, driving that satisfies the above-mentioned recommended driving standard is driving that violates laws and regulations, so the evaluation of driving that satisfies the recommended driving standard is a positive evaluation. Driving that satisfies the above-mentioned illegal driving standard is driving that violates laws and regulations, so the evaluation of driving that satisfies the illegal driving standard is a negative evaluation. Driving that satisfies the above-mentioned accident occurrence standard is driving that has a high risk of causing an accident, so the evaluation of driving that satisfies the accident occurrence standard is a negative evaluation. The evaluation unit 140 may, for example, subtract a score for a negative evaluation and add a score for a positive evaluation.

[0068] The specific magnitude of the score to be added or subtracted may be determined in advance. For example, the specific magnitude of the score to be added or subtracted may be determined according to the level of recommendation in the recommended driving standard, the level of riskiness of driving that corresponds to the illegal driving standard or the accident occurrence standard, etc.

[0069] The method for calculating the evaluation score is not limited to the example given here, and may be, for example, the ratio of the total score related to the positive evaluations to the total score related to the negative evaluations.

[0070] The evaluation unit 140 may, for example, store the calculated driving evaluation score in the evaluation history storage unit 150 .

[0071] The evaluation unit 140 may store history information in which the calculated driving evaluation score is associated with at least one of a vehicle ID and a driver ID in the evaluation history storage unit 150. The vehicle ID (Identification) is information for identifying the vehicle C. The driver ID is information for identifying the driver of the vehicle C. The history information may include the time when the driving of the vehicle C, its evaluation, etc. was performed.

[0072] The history information may further be associated with an evaluation point. The evaluation point is a point where a driving standard is satisfied during driving of the vehicle C, in other words, a point where a positive or negative evaluation is made.

[0073] The historical information may further be associated with at least one of a driving criterion, a score, etc., associated with the evaluation location. The driving criterion associated with the evaluation location may be a driving criterion that was met at the evaluation location. The score associated with the evaluation location may be a score that was added or subtracted at the evaluation location. The added score and the subtracted score may be distinguished by including a plus or minus sign in the score.

[0074] As described above, the evaluation unit 140 may calculate a reference evaluation score based on the calculated driving evaluation score in response to a user instruction. The user instruction may include, for example, at least one of a vehicle ID, a driver ID, and a time period when the driving was performed. The time period when the driving was performed may be specified, for example, by a date or a period.

[0075] For example, the evaluation unit 140 acquires history information in response to a user's instruction from the evaluation history storage unit 150. For example, the evaluation unit 140 acquires driving evaluation scores associated with one or more combinations of a vehicle ID, a driver ID, and a time period when driving was performed from the evaluation history storage unit 150 in response to a user's instruction. Then, for example, the evaluation unit 140 may calculate a reference evaluation score using the acquired driving evaluation score. If there is one acquired driving evaluation score, the evaluation unit 140 may use the acquired driving evaluation score as the reference evaluation score. If there are multiple acquired driving evaluation scores, the evaluation unit 140 may calculate a reference evaluation score by performing statistical processing on the multiple driving evaluation scores. This statistical processing may include calculating at least one of an average value, a mode value, a median value, a minimum value, and a maximum value. Note that the statistical processing is not limited to these.

[0076] (Regarding the instruction receiving unit 160) As described above, the instruction receiving unit 160 receives an instruction from a user to refer to the driving evaluation score. The instruction may include an instruction for one or a combination of a vehicle ID, a driver ID, and a time when the driving was performed.

[0077] (Regarding the display control unit 170) As described above, the display control unit 170 causes the display unit 180 to display, for example, a driving evaluation score and / or a reference evaluation score in accordance with a user's instruction. When the driving evaluation score and the reference evaluation score are displayed, the displayed driving evaluation score may be a plurality of driving evaluation scores used in calculating (statistical processing) the reference evaluation score to be displayed. The display control unit 170 may, for example, superimpose on map information at least one of the travel route of the vehicle C in accordance with a user's instruction, the evaluation points, the driving standards related to the evaluation points, the scores, and the like, and display the superimposed information on the map information on the display unit 180.

[0078] In this way, by displaying at least one of the driving evaluation score and the reference evaluation score, the user can check whether the vehicle C and the driver are driving safely.

[0079] Such a user is preferably a transportation company or the like that manages a large number of vehicles C, but the user is not limited to this. For example, the user may be an individual who is the owner of the vehicle C. Furthermore, for example, the user may be a driver of the transportation company or the like. In this case, the display control unit 170 may transmit the display information to display the display information on a terminal device (not shown) such as a smartphone used by the driver. The display information may be the same as the information displayed on the display unit 180 described above. This allows the driver to check whether he or she is driving safely and to utilize the driving evaluation score, reference evaluation score, etc. for safer driving.

[0080] (Example of Physical Configuration of Information Processing Device 100) The information processing device 100 physically includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, an input interface 1060, and an output interface 1070, as shown in FIG.

[0081] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, network interface 1050, input interface 1060, and output interface 1070. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0082] The processor 1020 is implemented as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

[0083] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0084] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read-only memory (ROM), or the like. The storage device 1040 stores program modules for realizing the functions of the device that includes the storage device 1040. The processor 1020 loads each of these program modules into the memory 1030 and executes them to realize the function corresponding to that program module.

[0085] The network interface 1050 is an interface for connecting a device equipped with it to a communication network.

[0086] The input interface 1060 is an interface for the user to input information, and is configured from, for example, a touch panel, a keyboard, a mouse, and the like.

[0087] The output interface 1070 is an interface for presenting information to the user, and is configured, for example, by a liquid crystal panel, an organic EL (Electro-Luminescence) panel, or the like.

[0088] In this way, the functions of the information processing device 100 can be realized by the physical components cooperating to execute a software program. Therefore, the present invention may be realized as a software program or as a storage medium on which the program is non-temporarily recorded. Note that the information processing device may be physically composed of multiple devices (e.g., computers, etc.).

[0089] (Actions and Effects) As described above, according to this embodiment, the information processing device 100 includes the analysis unit 110, the criterion acquisition unit 120, and the evaluation unit 140. The analysis unit 110 acquires the relationship between the state of the vehicle C and the state of an object based on sensor information including objects outside or inside the vehicle. The criterion acquisition unit 120 acquires driving criteria, which are criteria related to vehicle driving, created by information processing using information related to rules related to vehicle driving as input. The evaluation unit 140 calculates a driving evaluation score that evaluates the driving of the vehicle C based on the driving criteria and the relationship.

[0090] This makes it possible to easily create a driving standard incorporating various rules and evaluate the driving of the vehicle C. It becomes possible to accurately evaluate the driving of the vehicle C.

[0091] According to this embodiment, the information processing is processing using a machine learning model.

[0092] This makes it possible to easily create a driving standard incorporating various rules and evaluate the driving of the vehicle C. It becomes possible to accurately evaluate the driving of the vehicle C.

[0093] According to this embodiment, the standard acquisition unit 120 creates driving standards based on information about rules related to driving the vehicle C.

[0094] This makes it possible to easily create a driving standard incorporating various rules and evaluate the driving of the vehicle C. It becomes possible to accurately evaluate the driving of the vehicle C.

[0095] According to this embodiment, the driving standards include at least one of recommended driving standards that set standards for recommended driving, illegal driving standards that set standards for illegal driving that violates laws and regulations, and accident occurrence standards that set standards for dangerous driving that may cause an accident.

[0096] This makes it possible to incorporate various rules and easily create driving standards including at least one of recommended driving standards, illegal driving standards, and accident occurrence standards, and evaluate the driving of the vehicle C. This makes it possible to accurately evaluate the driving of the vehicle C.

[0097] According to this embodiment, the information processing device 100 further includes a driver identification unit 130 that identifies the driver of the vehicle C based on the sensor information including the object inside the vehicle C.

[0098] This makes it possible to evaluate the driving of the vehicle C for each driver. It becomes possible to accurately evaluate the driving of the vehicle C for each driver.

[0099] [Embodiment 2] In this embodiment, an example will be described in which cautionary location information regarding locations where caution should be exercised when driving a vehicle is generated using at least one of illegal driving criteria and accident occurrence criteria. Note that, in this embodiment, for the sake of simplicity, descriptions that overlap with other embodiments will be omitted as appropriate.

[0100] 8 , the information processing device 200 includes the above-described analysis unit 110, reference acquisition unit 120, driver identification unit 130, evaluation unit 140, and evaluation history storage unit 150. The information processing device 200 further includes, for example, a generation unit 210 and a cautionary location storage unit 220. The information processing device 200 further includes, for example, an instruction receiving unit 260, a display control unit 270, and a display unit 280 in place of the above-described instruction receiving unit 160, display control unit 170, and display unit 180, respectively.

[0101] The generation unit 210 generates caution location information regarding locations where caution should be exercised regarding at least one of illegal driving and dangerous driving, based on at least one of illegal driving criteria and accident occurrence criteria and multiple relationships regarding each of multiple vehicles C.

[0102] The caution place storage unit 220 stores caution place information.

[0103] The instruction receiving unit 260 receives a user instruction to refer to the cautionary place information.

[0104] The display control unit 270 causes the display unit 280 to display the cautionary location information in response to a user instruction.

[0105] The information processing device 200 executes information processing such as that shown in FIG.

[0106] The above-described steps S110 to S150 are executed.

[0107] The generation unit 210 generates caution location information regarding locations where caution should be exercised regarding at least one of illegal driving and dangerous driving, based on at least one of illegal driving criteria and accident occurrence criteria and multiple relationships regarding each of multiple vehicles C (step S210).

[0108] The generating unit 210 stores the generated cautionary place information in the cautionary place storage unit 220 (step S220).

[0109] The information processing device 200 executes information processing such as that shown in FIG.

[0110] The instruction receiving unit 260 receives a user instruction to refer to the cautionary place information (step S260).

[0111] The display control unit 270 causes the display unit 280 to display the cautionary location information in response to a user instruction (step S280).

[0112] The instruction receiving unit 260, the display control unit 270, and the display unit 280 may have the same functions as the instruction receiving unit 160, the display control unit 170, and the display unit 180 described in embodiment 1, respectively. The instruction receiving unit 260, the display control unit 270, and the display unit 280 may then execute steps S160 to S180 described above.

[0113] (Regarding the generation unit 210) The generation unit 210 generates caution location information regarding locations where caution should be exercised regarding at least one of illegal driving and dangerous driving, based on at least one of illegal driving criteria and accident occurrence criteria and multiple relationships regarding each of multiple vehicles C.

[0114] The multiple relationships may be, for example, relationships between the state of an object based on sensor information including an object outside or inside the vehicle, acquired by the analysis unit 110 for each of multiple vehicles C, and the state of the vehicle C.

[0115] For example, the generation unit 210 may identify a location where a plurality of relationships satisfy at least one of the illegal driving criteria and the accident occurrence criteria. Then, the generation unit 210 may identify, among the identified locations, a location or range that satisfies at least one of the illegal driving criteria and the accident occurrence criteria a predetermined number of times or frequency or more within a predetermined range including the identified location as a caution location. A caution location is a location where caution is required when driving a vehicle.

[0116] The predetermined number or frequency may be determined for the total of illegal driving and dangerous driving, or may be determined for each of them, or the same value may be used for each.

[0117] The generating unit 210 may generate caution place information including the identified caution place. The generating unit 210 may store the generated caution place information in the caution place storage unit 220.

[0118] This makes it possible to generate and store caution location information for multiple vehicles C that indicates locations that satisfy at least one of the illegal driving criteria and the accident occurrence criteria, i.e., locations that correspond to locations where caution is required when driving the vehicles.

[0119] (Regarding the instruction receiving unit 260) As described above, the instruction receiving unit 260 receives an instruction from a user to refer to the cautionary place information. This instruction may include, for example, information for specifying the range of the cautionary place information that the user wants to refer to.

[0120] (Regarding the display control unit 270) As described above, the display control unit 270 displays caution place information on the display unit 280 in response to a user instruction. The display control unit 270, for example, acquires caution place information including caution places within a range related to the user instruction from the caution place storage unit 220. The display control unit 270 displays the acquired caution place information on the display unit 280. For example, the display control unit 270 may superimpose caution places on map information indicating the range related to the user instruction and display the map information on the display unit 280.

[0121] This allows the user to know places where caution is required when actually driving the vehicle C. Therefore, the user can utilize the caution place information for safer driving.

[0122] (Actions and Effects) As described above, according to this embodiment, the information processing device 200 is equipped with a generation unit 210 that generates caution location information regarding locations where caution should be exercised regarding at least one of illegal driving and dangerous driving, based on at least one of illegal driving criteria and accident occurrence criteria and multiple relationships regarding each of multiple vehicles C.

[0123] This makes it possible to identify places where caution is required when driving using driving standards incorporating various rules, thereby enabling accurate identification of places where caution is required when driving.

[0124] [Embodiment 3] In this embodiment, an example will be described in which a future state of a vehicle is predicted based on sensor information, and a dangerous state that is predicted to violate a driving standard is detected. Note that, in this embodiment, for the sake of simplicity, description that overlaps with other embodiments will be omitted as appropriate.

[0125] 11 , the information processing device 300 includes the above-mentioned analysis unit 110, reference acquisition unit 120, driver identification unit 130, evaluation history storage unit 150, instruction reception unit 160, display control unit 170, and display unit 180. The information processing device 300 further includes, for example, a prediction unit 310, a danger detection unit 320, and an evaluation unit 340 that replaces the above-mentioned evaluation unit 140.

[0126] The prediction unit 310 predicts the future state (predicted state) of the vehicle C based on the state of the vehicle C.

[0127] The danger detection unit 320 detects a dangerous state that is predicted to violate the driving standard based on a predicted state predicted from the state of the vehicle C and at least one of the illegal driving standard and the accident occurrence standard.

[0128] The evaluation unit 340 calculates a driving evaluation score that evaluates the driving of the vehicle C using the detected dangerous state.

[0129] The information processing device 300 executes information processing such as that shown in FIG.

[0130] The above-described steps S110 to S130 are executed.

[0131] The prediction unit 310 predicts the future state (predicted state) of the vehicle C based on the state of the vehicle C (step S310).

[0132] The danger detection unit 320 detects a dangerous state that is predicted to violate the driving standard based on a predicted state predicted from the state of the vehicle C and at least one of the illegal driving standard and the accident occurrence standard (step S320).

[0133] The evaluation unit 340 calculates a driving evaluation score that evaluates the driving of the vehicle C using the detected dangerous state (step S340).

[0134] The evaluation unit 340 stores the driving evaluation score in the evaluation history storage unit 150 (step S350).

[0135] The information processing device 300 may further execute information processing (steps S160 to S180) as shown in Fig. 6. In this case, the evaluation unit 340 may execute step S170 instead of the evaluation unit 140.

[0136] (Regarding the Prediction Unit 310) As described above, the prediction unit 310 predicts a predicted state based on the state of the vehicle C. Here, the state of the vehicle C may be the same as the state of the vehicle C used by the analysis unit 110 to acquire the relationship, for example. The predicted state is a future state of the vehicle C, and may include at least one of a future position, a future speed, a future acceleration, and the like, for example.

[0137] For example, the prediction unit 310 may predict the predicted state using a prediction model for predicting the future state of the vehicle C. The prediction model is, for example, a machine learning model trained using training data including the state of the vehicle C and the predicted state thereof, and outputs a predicted state when a predicted state is input. The prediction unit 310 may include, for example, a prediction model, and predict the predicted state by inputting the state of the vehicle C into the prediction model and acquiring the predicted state.

[0138] The method used by the prediction unit 310 to predict the predicted state is not limited to the example given here. For example, instead of using a machine learning model, a model that predicts a future speed (after a predetermined time has elapsed) from the current speed and acceleration, assuming that the acceleration is constant, may be used. The predicted state may further include a future state of the object. In this case, the state of the object may also be used to predict the predicted state.

[0139] (Regarding the danger detection unit 320) As described above, the danger detection unit 320 detects a dangerous state that is predicted to violate driving standards based on a predicted state predicted from the state of vehicle C and at least one of the violative driving standards and accident occurrence standards.

[0140] The danger detection unit 320 may detect a dangerous state when the predicted state satisfies at least one of the illegal driving criterion and the accident occurrence criterion, for example. Such a dangerous state can be said to be a state in which the illegal driving criterion or the accident occurrence criterion is not satisfied in the current state, but is likely to be satisfied.

[0141] The danger detection unit 320 may use a condition that the predicted state satisfies a predetermined part of at least one of the illegal driving criteria and the accident occurrence criteria, instead of the condition that the predicted state satisfies at least one of the illegal driving criteria and the accident occurrence criteria. This also makes it possible to detect a dangerous state that does not satisfy the illegal driving criteria or the accident occurrence criteria in the current state, but is likely to satisfy them.

[0142] (Regarding the evaluation unit 340) As described above, the evaluation unit 340 calculates a driving evaluation score that evaluates the driving of the vehicle C using the detected dangerous state. For example, the evaluation unit 340 may subtract a driving evaluation score when a dangerous state is detected. Furthermore, similar to the evaluation unit 140 described above, the evaluation unit 340 may calculate a driving evaluation score that evaluates the driving of the vehicle C based on the driving criteria and relationships. Then, the evaluation unit 340 may calculate a driving evaluation score based on the detected dangerous state and the driving criteria and relationships.

[0143] The evaluation unit 340 may store the driving evaluation score in the evaluation history storage unit 150. Here, the history information stored in the evaluation history storage unit 150 may differ in that it includes the driving evaluation score described in this embodiment instead of the driving evaluation score described in embodiment 1. Except for this point, the history information according to this embodiment may be the same as the history information described in embodiment 1.

[0144] According to the present embodiment, the information processing device 300 includes the danger detection unit 320 that detects dangerous conditions that are predicted to violate driving standards based on a predicted state predicted from the state of the vehicle and at least one of the illegal driving standards and the accident occurrence standards. The driving evaluation score is further calculated using the detected dangerous conditions.

[0145] This makes it possible to evaluate the driving of the vehicle C using the driving standard incorporating various rules and the predicted state. This makes it possible to evaluate the driving of the vehicle C with high accuracy.

[0146] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0147] In addition, although the flowcharts used in the above description show a sequence of steps (processes), the order of steps executed in each embodiment is not limited to the sequence shown in the flowcharts. In each embodiment, the order of steps shown in the diagrams can be changed as long as it does not cause any problems in terms of the content.

[0148] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0149] 1. An information processing device comprising: an analysis means for acquiring the relationship between the state of an object based on sensor information including an object outside or inside the vehicle and the state of the vehicle; a standard acquisition means for acquiring driving standards that are standards for vehicle driving, created by information processing using information on rules related to vehicle driving as input; and an evaluation means for calculating a driving evaluation score that evaluates the driving of the vehicle based on the driving standards and the relationship. 2. The information processing device described in 1., wherein the information processing is processing using a machine learning model. 3. The information processing device described in 1. or 2., wherein the standard acquisition means creates the driving standards based on information on rules related to vehicle driving. 4. The information processing device described in any one of 1. to 3., wherein the driving standards include at least one of: a recommended driving standard that defines standards for recommended driving; a violative driving standard that defines standards for violating driving that violates laws and regulations; and an accident occurrence standard that defines standards for dangerous driving that may result in an accident. 5. The information processing device according to any one of 1. to 6., further comprising: a generation means for generating cautionary location information relating to locations where caution should be exercised regarding at least one of the illegal driving criteria and the accident occurrence criteria, based on at least one of the illegal driving criteria and the accident occurrence criteria, and a plurality of the relationships relating to each of a plurality of vehicles. 6. The information processing device according to 4. or 5., further comprising: a danger detection means for detecting a dangerous state predicted to violate the driving criteria, based on a predicted state predicted from the state of the vehicle and at least one of the illegal driving criteria and the accident occurrence criteria, wherein the driving evaluation score is further calculated using the detected dangerous state. 7. The information processing device according to any one of 1. to 6., further comprising: a driver identification means for identifying a driver of the vehicle based on the sensor information including objects inside the vehicle. 8. An information processing system comprising: the information processing device according to any one of 1. to 7., and at least one sensor mounted on the vehicle and generating the sensor information.9. An information processing method in which one or more computers acquire a relationship between the state of an object based on sensor information including an object outside or inside the vehicle and the state of the vehicle, acquire a driving standard that is a standard for driving the vehicle, created by information processing using information on rules for driving the vehicle as input, and calculate a driving evaluation score that evaluates the driving of the vehicle based on the driving standard and the relationship. 10. The information processing method described in 9., in which the information processing is processing using a machine learning model. 11. The information processing method described in 9. or 10., in which acquiring the driving standard involves creating a driving standard based on information on rules for driving the vehicle. 12. The information processing method described in any one of 9. to 11., in which the driving standard includes at least one of: a recommended driving standard that defines a standard for recommended driving; a violating driving standard that defines a standard for violating driving that violates laws and regulations; and an accident occurrence standard that defines a standard for dangerous driving that has the potential to cause an accident. 13. The information processing method according to 12. further comprises generating cautionary location information relating to locations where caution should be exercised regarding at least one of the illegal driving criteria and the accident occurrence criteria, and a plurality of the relationships relating to each of a plurality of vehicles. 14. The information processing method according to 12. or 13. further comprises detecting a dangerous state predicted to violate the driving criteria based on a predicted state predicted from the state of the vehicle and at least one of the illegal driving criteria and the accident occurrence criteria, and the driving evaluation score is further calculated using the detected dangerous state. 15. The information processing method according to any one of 9. to 14. further comprises identifying the driver of the vehicle based on the sensor information including objects inside the vehicle.16. A program causing one or more computers to execute the following steps: acquire a relationship between the state of an object based on sensor information including an object outside or inside the vehicle and the state of the vehicle; acquire a driving standard that is a standard for driving the vehicle, created by information processing using information on rules for driving the vehicle as input; and calculate a driving evaluation score that evaluates the driving of the vehicle based on the driving standard and the relationship. 17. The program described in 16., in which the information processing is processing using a machine learning model. 18. The program described in 16. or 17., in which acquiring the driving standard involves creating a driving standard based on information on rules for driving the vehicle. 19. The program described in any one of 16. to 18., in which the driving standard includes at least one of: a recommended driving standard that defines standards for recommended driving; a violating driving standard that defines standards for illegal driving that violates laws and regulations; and an accident occurrence standard that defines standards for dangerous driving that may result in an accident. 20. The program described in 19., further causing the program to generate cautionary location information regarding locations where caution should be exercised regarding at least one of the illegal driving criteria and the accident occurrence criteria, based on at least one of the illegal driving criteria and the accident occurrence criteria, and a plurality of the relationships related to each of a plurality of vehicles. 21. The program described in 19. or 20., further causing the program to detect a dangerous state predicted to violate the driving criteria, based on a predicted state predicted from the state of the vehicle and at least one of the illegal driving criteria and the accident occurrence criteria, wherein the driving evaluation score is further calculated using the detected dangerous state. 22. The program described in any one of 16. to 21., further causing the program to identify the driver of the vehicle based on the sensor information including objects inside the vehicle. 23. A recording medium having the program described in any one of 16. to 22. recorded thereon.

[0150] This application claims priority based on Japanese Patent Application No. 2024-110079, filed July 9, 2024, the disclosure of which is incorporated herein by reference in its entirety.

[0151] 100, 200, 300 Information processing device 110 Analysis unit 120 Criterion acquisition unit 130 Driver identification unit 140, 340 Evaluation unit 150 Evaluation history storage unit 160, 260 Instruction reception unit 170, 270 Display control unit 180, 280 Display unit 210 Generation unit 220 Caution location storage unit 310 Prediction unit 320 Hazard detection unit

Claims

1. An information processing device comprising: an analysis means for acquiring the relationship between the state of an object based on sensor information including an object outside or inside the vehicle and the state of the vehicle; a standard acquisition means for acquiring driving standards, which are standards for driving the vehicle, created by information processing using information related to rules for driving the vehicle as input; and an evaluation means for calculating a driving evaluation score that evaluates the driving of the vehicle based on the driving standards and the relationship.

2. The information processing device according to claim 1, wherein the information processing is processing using a machine learning model.

3. The information processing device according to claim 1 or 2, wherein the standard acquisition means creates driving standards based on information relating to rules regarding vehicle driving.

4. An information processing device as described in claim 1 or 2, wherein the driving standards include at least one of: recommended driving standards that set standards for recommended driving; illegal driving standards that set standards for illegal driving that violates laws and regulations; and accident occurrence standards that set standards for dangerous driving that may cause an accident.

5. The information processing device of claim 4, further comprising a generation means for generating caution location information regarding locations where caution should be exercised regarding at least one of the illegal driving criteria and the accident occurrence criteria and a plurality of the relationships regarding each of a plurality of vehicles.

6. The information processing device of claim 4, further comprising a danger detection means for detecting a dangerous state predicted to violate the driving standards based on a predicted state predicted from the state of the vehicle and at least one of the illegal driving standards and the accident occurrence standards, and wherein the driving evaluation score is further calculated using the detected dangerous state.

7. The information processing device according to claim 1 or 2, further comprising a driver identification means for identifying a driver of the vehicle based on the sensor information including an object inside the vehicle.

8. An information processing system comprising: the information processing device according to claim 1 or 2; and at least one sensor mounted on the vehicle and generating the sensor information.

9. An information processing method in which one or more computers acquire the relationship between the state of an object based on sensor information including objects outside or inside the vehicle and the state of the vehicle, acquire driving standards that are standards for driving the vehicle and are created by information processing using information regarding rules for driving the vehicle as input, and calculate a driving evaluation score that evaluates the driving of the vehicle based on the driving standards and the relationship.

10. A recording medium having recorded thereon a program for causing one or more computers to execute the following: acquire the relationship between the state of an object based on sensor information including objects outside or inside the vehicle and the state of the vehicle; acquire driving standards, which are standards for driving the vehicle, created by information processing using information regarding rules for driving the vehicle as input; and calculate a driving evaluation score that evaluates the driving of the vehicle based on the driving standards and the relationship.

Images