Straddled vehicle related ipg

Abstract

The purpose of the present invention is to reduce a load on a hardware resource while improving the well-being of a rider by effectively and efficiently strengthening a feeling of collaboration between the rider and a straddled vehicle. In this straddled vehicle related IPG, customized prompt data is generated by using data for customization and data acquired from an accessory or a portable article of a rider or a straddled vehicle by data acquisition processing. The customized prompt data is supplied to an LLM, and linguistically interpreted data associated with the straddled vehicle is obtained from the LLM. The linguistically interpretated data associated with the straddled vehicle is used to carry out processing for controlling operation of a device. If data for customization of the straddled vehicle is input, the data for customization is updated on the basis of said data.

Description

Straddled vehicle related IPG

[0001] The present invention relates to a saddle-type vehicle-related IPG (Interactive Prompt Generator).

[0002] Patent Literature 1 discloses a processing device for a saddle-ride type vehicle. The processing device includes an input unit that receives information related to a rider's reaction, a calculation unit that learns the rider's reaction tendencies based on the information related to the rider's reaction input from the input unit and generates information to be output based on the learning results, and an output unit that transmits the information generated by the calculation unit. The processing device can learn output rules to match the rider's preferences by obtaining the rider's evaluation of the output information.

[0003] Patent Document 2 discloses an information output device for a saddle-ride type vehicle. The information output device includes a receiving unit that receives input information input by a rider, a learning unit that learns input tendencies of the driver's input information based on the input information received by the receiving unit, a creating unit that creates output information based on the learning content learned by the learning unit, and an output unit that outputs the output information created by the creating unit as voice in natural language from an audio device. The information output device can, for example, output evaluations or suggestions for vehicle settings or driving operations in natural language in accordance with the input tendencies. The information output device also learns rules for generating voice information based on the rider's response to the voice information. Furthermore, the information output device can learn rules for setting the output timing based on the driver's response to the output timing of the voice information.

[0004] Japanese Patent No. 6737875 Japanese Patent No. 6860553

[0005] An object of the present invention is to effectively and efficiently enhance the sense of cooperation between the saddle-type vehicle and the rider, thereby improving the rider's well-being and reducing the load on hardware resources.

[0006] In view of the above problems, the present inventors have conducted extensive research and have obtained the following findings.

[0007] The saddle-type vehicle referred to in the present invention is configured to be able to turn in a lean position. That is, the saddle-type vehicle is equipped with handlebars, and is configured so that the rider leans the vehicle body and turns by shifting his or her weight while gripping the handlebars with both hands. As a result, when the saddle-type vehicle turns, the rider leans together with the vehicle body toward the inside of the curve. In this way, when turning, the rider uses his or her entire body to move the saddle-type vehicle, and the saddle-type vehicle is configured to lean together with the rider in response to the rider's movement. Turning such a saddle-type vehicle can feel to the rider like a collaborative effort between the rider and the saddle-type vehicle. Therefore, compared to vehicles other than saddle-type vehicles that can turn in a lean position, such as ordinary four-wheeled automobiles (hereinafter also referred to as non-lean vehicles), the saddle-type vehicle is a vehicle that is more likely to create a sense of unity with the rider. The stronger the sense of unity the rider feels with the saddle-type vehicle, the more enjoyable the rider's experience of driving the saddle-type vehicle.

[0008] As such, compared to non-lean vehicles, saddle-ride vehicles are vehicles that tend to make the act of driving itself more enjoyable, and by enhancing the sense of collaboration between the saddle-ride vehicle and the rider, the rider's well-being can be improved. The sense of collaboration between the saddle-ride vehicle and the rider can be enhanced not only by the response of the saddle-ride vehicle (vehicle body) to the rider's operations, but also by the provision of information from the saddle-ride vehicle to the rider. However, while providing information from the saddle-ride vehicle to the rider can dramatically enhance the sense of collaboration if done well, there is a risk that the sense of collaboration may be significantly impaired if done poorly. Even if the saddle-ride vehicle responds well to the rider's operations, if the saddle-ride vehicle provides information to the rider poorly, the rider's impression of the saddle-ride vehicle will be negatively affected. Therefore, it is important to consider how information is provided from the saddle-ride vehicle to the rider.

[0009] In order to successfully provide information from a saddle-type vehicle to a rider, the rider's preferences, emotions, personality, and situation must be acquired in greater detail, increasing the number of factors that must be considered as input information. In addition, the output information, such as the content, transmission method, and transmission timing of the information, must also be set in greater detail, increasing the number of factors that must be considered. In other words, in order to achieve a higher level of interaction between the saddle-type vehicle and the rider, the number of factors that must be considered increases.

[0010] Furthermore, as described above, the saddle-type vehicle referred to in the present invention is configured to be able to turn in a lean position. Therefore, in addition to operating the accelerator, brakes, and steering, the rider must also shift his or her own weight to perform a turning operation in conjunction with steering. This weight shift and the resulting vehicle lean are not present in a non-lean vehicle, so compared to a non-lean vehicle, more information can be obtained from a saddle-type vehicle that can turn in a lean position. This can also be said to mean that there is more information available to achieve a higher level of interaction between the saddle-type vehicle and the rider. A notable example is a manual saddle-type vehicle in which different operations are performed with both hands and feet, as follows: Left hand: operates the clutch lever Right hand: operates the throttle (accelerator) and front brake lever Left foot: operates the gear shift pedal (however, gear shifting may also be performed using a manual lever) Right foot: operates the rear brake As the rider shifts his or her own weight, the operating parts corresponding to each of the hands and feet can be operated at different times for different vehicle operations, further increasing the amount of information that can be obtained. Saddle-type vehicles that can turn in a lean position are not limited to this example, but regardless of the type of vehicle, saddle-type vehicles that can turn in a lean position tend to have a greater variety of information that can be obtained compared to non-lean vehicles.

[0011] Furthermore, in a saddle-type vehicle that can turn in a lean position, it is difficult to obtain much information actively input from the rider other than driving operations while driving. Information actively input other than driving operations is likely to reflect the rider's emotions, which is important from the perspective of interaction with the saddle-type vehicle. However, in a saddle-type vehicle that can turn in a lean position, many parts of the body (both hands, both legs, and weight shift) are required for driving operations, and many working areas of the brain are used for driving, leaving little working area available for operations other than driving, making it difficult for sudden changes in emotions to occur. In addition, the installation space for operating parts other than driving operations (such as plywood panels) is smaller than in a non-lean vehicle. Therefore, it is difficult for the rider to actively input a large amount and variety of information other than driving operations while driving. As a result, while the variety and amount of information that can be obtained is large, the variety and amount of information actively input from the rider other than driving operations is limited.

[0012] As described above, in a saddle-type vehicle that can turn in a lean position, there are many factors that must be considered and a large amount of information that can be used to achieve a high level of interaction between the saddle-type vehicle and the rider. To achieve this high level of interaction between the saddle-type vehicle and the rider, it is necessary to take these factors and information into account and provide outputs that are more easily accepted by the rider in a more timely manner. This presents a particular challenge for high-level interaction between the saddle-type vehicle that can turn in a lean position and the rider.

[0013] As the above-mentioned trends of "increasing factors to be considered," "increasing amount of available information," and "higher demands for timeliness and appropriateness of output" become stronger, the load on the hardware resources required for the information output system increases, and more hardware resources are required. In addition, since a large amount of learning data needs to be collected, preparation takes a long time. The devices disclosed in Patent Documents 1 and 2 also have a similar problem. That is, the devices disclosed in Patent Documents 1 and 2 have the problem of requiring enormous hardware resources and learning data in order to achieve high-level interaction between the saddle-riding vehicle and the rider to a degree that can enhance the sense of cooperation between the saddle-riding vehicle and the rider.

[0014] The present invention has been completed based on the above findings. The present invention can provide the following saddle-ride type vehicle-related IPG.

[0015] (1) A saddle-riding type vehicle-related IPG, the saddle-riding type vehicle-related IPG including at least one memory and at least one processor capable of communicating with an LLM (Large Scale Language Model) and capable of communicating with at least one first input device provided on the saddle-riding type vehicle or an accessory or a carried accessory of a rider of the saddle-riding type vehicle, and at least one output device, the processor being connected to the memory and configured to execute at least one program stored in the memory, the at least one program including a data acquisition process for acquiring at least one type of data related to the saddle-riding type vehicle or its rider from the at least one first input device, and / or acquiring CHL (Communicative Human Language) information input by the rider to the at least one first input device as data from the at least one first input device; a linguistic interpretation process that supplies the customized prompt data to the LLM and acquires linguistic interpretation data related to the saddle-ride type vehicle, the linguistic interpretation data being generated by the linguistic interpretation process by the LLM; an output process that uses the linguistic interpretation data related to the saddle-ride type vehicle to produce output for controlling the operation of the at least one output device; and a customization process that receives input of data for customizing the output in the output process for the saddle-ride type vehicle from the at least one first input device or at least one second input device different from the at least one first input device, and updates the customization data based on the data.

[0016] The generator of (1) uses an LLM to provide information from the saddle-type vehicle to the rider in order to effectively and efficiently enhance the sense of cooperation between the saddle-type vehicle and the rider. Additionally, the generator of (1) has a configuration suitable for using the LLM to provide information from the saddle-type vehicle to the rider. That is, the generator of (1) generates customized prompt data using data acquired from at least one first input device by a data acquisition process and customization data. The customization data is data stored in a memory and used to generate a customized prompt related to the saddle-type vehicle. The customized prompt data is data that can be linguistically interpreted by the LLM and has a reduced data volume. The customized prompt data is supplied to the LLM, and linguistic interpretation data related to the saddle-type vehicle is obtained from the LLM. Furthermore, the generator of (1) performs processing to control the operation of a device using the linguistic interpretation data related to the saddle-type vehicle. Additionally, when customization data related to the saddle-type vehicle is input, the generator of (1) updates the customization data based on the input data. This makes it possible to effectively and efficiently achieve a high level of interaction between the saddle-type vehicle and the rider. As a result, the generator (1) effectively and efficiently enhances the sense of cooperation between the saddle-type vehicle and the rider, thereby improving the rider's well-being and reducing the load on hardware resources. In other words, assuming the same hardware resources are used, more advanced processing can be performed, thereby achieving a higher level of interaction. The generator (1) is able to respond at a high level to all of the "increase in factors to be considered," "increase in available information," and "increased demands for timeliness and appropriateness of output," while reducing the load on hardware resources, and can solve the challenges (described above) specific to high-level interaction between a saddle-type vehicle that can turn in a lean position and the rider.From the perspective of achieving the above-mentioned effects (achieving both "reduced load on hardware resources" and "high-level interaction"), a prompt generation process is performed using data acquired from the saddle-type vehicle or the rider, and / or data input by the rider, and customization data to generate customized prompt data that is linguistically interpretable, has a reduced amount of data, and the generated prompt data is then supplied to the LLM. In this context, updating the customization data through a customization process in relation to the prompt generation process has important technical significance.

[0017] The saddle-type vehicle-related IPG includes at least one memory and at least one processor. The at least one processor is communicatively connected to the at least one memory, the at least one first input device, and the at least one output device. These devices may be provided in a single device to form a centralized processing system, or may be provided in multiple devices communicatively connected to each other to form a distributed processing system. The at least one second input device is communicatively connected to the at least one processor. The centralized processing system may be configured to include the at least one second input device. The distributed processing system may be configured to include the at least one second input device. The at least one first input device is provided in the saddle-type vehicle or in equipment or carried by a rider thereof. The at least one memory may be provided in the saddle-type vehicle, in equipment or carried by a rider thereof, a user terminal, or a server. The at least one processor may be provided in the saddle-type vehicle, in equipment or carried by a rider thereof, a user terminal, or a server. The at least one output device may be provided in the saddle-type vehicle, in equipment or carried by a rider thereof, or a user terminal. The at least one second input device may be provided in, for example, a device other than the saddle-riding vehicle and the rider's equipment or personal belongings. A system including a saddle-riding vehicle-related IPG according to the present invention may employ, for example, any of the system configurations (a) to (x) shown in FIGS. 2 and 3 . FIG. 2 illustrates a device in which a first input device (I), a processor (P), a memory (M), and an output device (O) are provided in the system configuration. FIG. 3 illustrates a device in which the first input device, the processor, and the output device are provided. For ease of understanding, FIGS. 2 and 3 use the same reference numerals as those used in the embodiments described below, but these reference numerals are not intended to limit the present invention. In FIG. 2 , the memory is provided in the device in which the processor is provided. In FIG. 3 , the memory is also provided in the device in which the processor is provided, although not shown. However, the present invention is not limited to this example.The memory may be provided in a device different from the device in which the processor is provided (e.g., a device in which the first input device and / or output device is provided). Although a device in which the second input device is provided is not shown in FIGS. 2 and 3 , the second input device may be provided in a device different from the device in which the first input device is provided. Furthermore, there may be multiple first input devices, output devices, memories, and processors. Therefore, if a single system includes multiple devices, the single system may satisfy the requirements of multiple system configurations (a) to (x) shown in FIGS. 2 and 3 . There may also be multiple second input devices. An example of a system configuration will now be described. As a specific example, a smartwatch, which is a rider's personal item, includes at least one memory, at least one processor, at least one first input device, and at least one output device, and therefore the smartwatch may constitute the system (see FIGS. 2(n) and 3(n)). As another specific example, a smartwatch may correspond to the at least one first input device, a meter of the saddle-riding vehicle may correspond to the at least one output device, and a server capable of communicating with the saddle-riding vehicle may include at least one memory and at least one processor (see FIGS. 2(l) and 3(l)). As yet another specific example, a sensor provided in the saddle-riding vehicle may correspond to the at least one first input device, a meter of the saddle-riding vehicle may correspond to the at least one output device, and a server capable of communicating with the saddle-riding vehicle may include at least one memory and at least one processor (see FIGS. 2(d) and 3(d)). In the first example, the smartwatch corresponds to the saddle-riding vehicle-related IPG that generates customized prompt data to be supplied to the LLM and obtains linguistic interpretation data related to the saddle-riding vehicle from the LLM. In the second and third examples, the server corresponds to the saddle-riding vehicle-related IPG. The saddle-riding vehicle-related IPG according to the present invention is a device including at least one processor and at least one memory. In the saddle-ride type vehicle-related IPG according to the present invention, all of the processes may be executed by a single processor, or each process may be executed by a different processor.A system including a saddle-riding vehicle-related IPG according to the present invention may include: at least one first input device and at least one output device, each provided in the saddle-riding vehicle or in a rider's equipment or carried item; and at least one processor and at least one memory, each provided in the saddle-riding vehicle, in the rider's equipment or carried item, a server, or a user terminal ((a) to (p) of FIGS. 2 and 3). In this case, since the output device is provided in the saddle-riding vehicle or in the rider's equipment or carried item, output can be performed at appropriate timing while the saddle-riding vehicle is traveling. A system including a saddle-riding vehicle-related IPG according to the present invention may include: at least one first input device, each provided in the saddle-riding vehicle or in a rider's equipment or carried item; and at least one processor and at least one memory, each provided in the saddle-riding vehicle, in the rider's equipment or carried item, a server, or a user terminal ((q) to (x) of FIGS. 2 and 3). The hardware configuration of the system including the saddle-ride type vehicle-related IPG according to the present invention is not particularly limited.

[0018] As shown in FIGS. 2 and 3 , the output device is provided in the saddle-riding type vehicle, the rider's equipment or portable equipment, or a user terminal. For example, if the output device is the rider's equipment or portable equipment, the rider's equipment or portable equipment may be detachably attached in a position that is easily visible to the rider riding the saddle-riding type vehicle (for example, near the meter of the saddle-riding type vehicle). The output device itself may have a function for communicating with the outside via a network. The output device may be configured to be connected to a control device included in the device in which the output device itself is provided (the saddle-riding type vehicle, the rider's equipment or portable equipment, or the user terminal) and to be controlled by the control device. In this case, the control device may have a function for communicating with the outside via a network. The output device is not particularly limited, and it is desirable that the output device be configured to operate in response to commands input via communication from an outside source while the saddle-riding type vehicle is traveling, without being related to the traveling of the saddle-riding type vehicle. Specific examples of the output device include the following. - Audio system (ON / OFF, volume adjustment, song selection) - FM / AM radio (ON / OFF, volume adjustment, channel selection) - Satellite radio (ON / OFF, volume adjustment, channel selection) - Navigation system (ON / OFF, menu selection, etc.) - Action camera (ON / OFF, start / end of recording, effect selection, etc.) - Heated grips (ON / OFF, temperature adjustment) - Heated seats (ON / OFF, temperature adjustment) - Advanced driver assistance system (ADAS) (turning various functions ON / OFF) ADAS includes, for example, the following:・Quick shift system ・Electronically controlled suspension ・Power delivery control ・Wheelie control ・Front and rear linked brake system ・Brake control based on roll angle ・Engine brake control ・Automatic shift change system ・Anti-lock brake system ・Traction control system ・Slide control system ・Cruise control system ・Sudden acceleration control system ・Setting and changing driving modes

[0019] Furthermore, examples of the output device include a CHL information output device, which outputs CHL information visually or audibly. The CHL information output device is not particularly limited, and examples thereof include the following devices:・Meter (instrument panel) (presents visual output information) ・HMD (Head-Mounted Display) (presents visual output information) ・Speaker (presents auditory output information) ・Intercom (headset) (presents auditory output information) ・Mirror (presents visual output information using lights, etc.) ・Road surface illumination lights (presents visual output information) ・Roadside displays (presents visual output information) ・HUD (Head-Up Display) combiner (presents visual output information) ・HUD screen (presents visual output information) ・Smartphone (presents visual or auditory output information) ・Smartwatch (presents visual or auditory output information) ・Smartglasses (presents visual or auditory output information) ・Earphones (presents auditory output information) ・Bone conduction earphones (presents auditory output information)

[0020] As shown in FIGS. 2 and 3 , the first input device may be provided on the saddle-type vehicle, or on equipment or a portable item of the rider. The first input device is configured, for example, to acquire or generate at least one type of data related to the saddle-type vehicle or its rider over time while the saddle-type vehicle is traveling, and supply the at least one type of data to at least one processor. The at least one type of data related to the saddle-type vehicle or its rider may be, for example, saddle-type vehicle-related data or rider biometric data. The saddle-type vehicle-related data is, for example, data indicating saddle-type vehicle-related parameters that are related to the traveling state of the saddle-type vehicle and change as the saddle-type vehicle travels, detected by the first input device. The saddle-type vehicle-related data may be, for example, parameters that are not related to the traveling state of the saddle-type vehicle or that do not change as the saddle-type vehicle travels. Examples of such saddle-type vehicle-related data include the cumulative on / off period of a switch provided on the saddle-type vehicle, the continuous on / off period of the switch, etc. The lidar biometric data is, for example, data indicating lidar biometric parameters detected by the first input device. The first input device may function as an independent device and have a communication function so as to output data acquired or generated independently. The first input device functioning independently is not particularly limited, and examples thereof include a GPS (Global Positioning System) receiver, a GNSS (Global Navigation Satellite System) receiver, a chest strap equipped with a heart rate sensor, or a smart watch. The GPS receiver or GNSS receiver is provided, for example, in a saddle-type vehicle or in equipment or portable items of the rider. The chest strap or smart watch corresponds to the rider's equipment. The first input device may be configured by a combination of a detection device and a control device. In this case, examples of the detection device include a GPS module, a GNSS module, an IMU (Inertial Measurement Unit), and a heart rate sensor module provided on the handle grip of a saddle-type vehicle.Since riders typically wear gloves as protectors, when acquiring heart rates using a heart rate sensor module attached to a handlebar grip, it may be necessary to devise a method for acquiring heart rates. For example, an optical heart rate sensor module may be employed that can ensure light transmittance even through gloves. By using gloves with a light-transmitting portion, heart rates may be measured using the optical heart rate sensor module through the portion. For example, a pressure-type heart rate sensor configured to detect the pulse of a rider's finger even when the rider is wearing gloves may be employed. A pressure-type heart rate sensor may be employed on the assumption that the rider will wear gloves suitable for detecting finger pulses using the pressure-type heart rate sensor. An example of a control device is an electronic control unit (ECU). In this case, the ECU itself is not a first input device, but in combination with various modules, it functions as a first input device and outputs at least one type of data related to the saddle-type vehicle or its rider. In this way, the first input device, either as an independent device or in combination with the control device, realizes the function of outputting at least one type of data related to the saddle-riding type vehicle or its rider. Note that, hereinafter, unless otherwise specified, the term "first input device" is used to encompass both a method of communicating with the outside world independently and a method of communicating with the outside world via the control device. The first input device may be configured, for example, to generate data related to CHL information input by the rider while the saddle-riding type vehicle is traveling and supply the data to at least one processor. The first input device may be provided, for example, in an apparatus provided with a first input device that acquires or generates at least one type of data related to the saddle-riding type vehicle or its rider. The CHL information input by the rider may be, for example, audio information or text information.The CHL information input by the rider may be, for example, CHL information input by the rider to the first input device in response to CHL information visually or audibly output by the output device (e.g., CHL information corresponding to linguistic interpretation data related to the saddle-riding vehicle), CHL information actively input by the rider to the first input device, or CHL information input by the rider to the first input device independently of the CHL information visually or audibly output by the output device. Examples of such first input devices include a microphone, a touch panel, or a combination of a microphone module with an ECU or a CPU. Examples of devices that may include such first input devices include smartphones, smartwatches, smart glasses, and intercoms (headsets). The first input device may be configured to receive input of data for customizing the output of the output processing for the saddle-riding vehicle and to supply the data to at least one processor. The first input device may be provided in, for example, a device that includes a first input device that acquires or generates at least one type of data related to the saddle-riding vehicle or its rider, or in a device that generates data related to the CHL information input by the rider. The data input by the first input device is performed using, for example, CHL information. The CHL information may be, for example, voice information or text information. Examples of such a first input device include a microphone, a touch panel, and a combination of a microphone module with an ECU or a CPU. Examples of devices equipped with such a first input device include a smartphone, a smart watch, smart glasses, an intercom (headset), and a personal digital assistant (PDA).

[0021] Examples of the first input device and the saddle-riding type vehicle-related data acquired or generated by the first input device are not particularly limited, but include the following: GPS receiver: traveling position information GNSS receiver: traveling position information IMU (6-axis sensor): acceleration in three axes (front / rear, left / right, and up / down) of the saddle-riding type vehicle while traveling, and angular velocity in three axes (pitch, roll, and yaw) Throttle opening sensor: throttle opening Brake position sensor: brake operation ON / OFF or operation amount (operation pressure) Clutch sensor: clutch operation ON / OFF or operation amount Gear position sensor: gear position Steering angle sensor: steering angle Steering torque sensor: steering torque Vehicle speed sensor: vehicle speed Wheel speed sensor: rotation speed of front or rear wheels Engine rotation speed sensor: engine rotation speed

[0022] Examples of the first input device and the lidar biometric data (i.e., lidar biometric parameters) acquired or generated by the first input device include, but are not limited to, the following: The lidar biometric data may be acquired over time while the saddle-riding vehicle is traveling. The lidar biometric data is used to estimate the rider's emotions while the saddle-riding vehicle is traveling, and customized prompt data is generated based on the results. The following are examples of the first input device and the lidar biometric data, but are not limited to these: Heart rate sensor: heart rate Brain wave sensor: brain wave Sweat rate sensor: sweat rate Respiration rate sensor: breathing pattern (rhythm / frequency) Body temperature sensor: body temperature Blood pressure sensor: blood pressure Facial expression camera: recognition of the rider's facial expressions Eye camera: eye movement tracking Oxygen saturation sensor: blood oxygen level Grip pressure sensor: grip pressure Microphone: voice (tone, pitch, speed, volume)

[0023] The at least one second input device is provided, for example, on a device owned by an entity that provides services related to saddle-riding vehicles. The device is, for example, a device different from the device on which the first input device is provided. The device is, for example, a tablet, laptop PC, desktop PC, etc. Examples of services provided related to saddle-riding vehicles include manufacturing saddle-riding vehicles, selling saddle-riding vehicles, and maintaining saddle-riding vehicles. The entity is, for example, a manufacturer of saddle-riding vehicles. The phrase "the second input device is provided on the device" includes cases where the second input device is provided integrally with the device main body and cases where the second input device is provided separably from the device main body. The second input device is configured, for example, to receive input of data for customizing output in output processing related to the saddle-riding vehicle. Data input via the second input device is performed, for example, using CHL information. The CHL information may be, for example, voice information or text information. Examples of the second input device include a microphone, a touch panel, a keyboard, etc. The second input device may function as an independent device and have a communication function so that it can output input data (data for customization) independently. The second input device that functions independently is not particularly limited and may be, for example, a tablet. The second input device may be configured by combining an input module and a control device. In this case, an example of the input module is a keyboard. An example of the control device is a CPU provided in a PC. In this case, the CPU itself is not a second input device, but in combination with the input module, it functions as a second input device and outputs input data (data for customization). In this way, the second input device realizes the function of outputting input data (data for customization) either as an independent device or in combination with a control device. In the following, unless otherwise specified, the term "second input device" is used to encompass both a method of communicating with the outside world independently and a method of communicating with the outside world via a control device.

[0024] The memory includes, but is not limited to, RAM, ROM, non-volatile RAM, PROM, EPROM, EEPROM, flash memory, magnetic data storage, optical data storage, registers, or a combination thereof. There may be one or more memories.

[0025] Processors include central processing units (CPUs), microprocessors, general-purpose processors, digital signal processors (DSPs), graphics processing units (GPUs), controllers, microcontrollers, programmable logic devices (PLDs), field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), etc. Multiple processors can be configured using any combination of these. Execution of a program by at least one processor is not limited to execution of the entire program by a single processor, but may also include execution of the program by parallel processing in a multiprocessor constructed by multiple processors. In a multiprocessor, either symmetric or asymmetric multiprocessing may be performed. A multiprocessor may be tightly coupled or loosely coupled. A processor may be a multi-core processor.

[0026] A large-scale language model (LLM) refers to a language model with a large number of parameters. The large-scale language model is capable of performing natural language processing tasks. The large-scale language model may be a natural language generation model. The natural language generation model is based on the large-scale language model and is capable of creating a sentence consisting of new CHL information from input CHL information. Note that creating a sentence consisting of new CHL information from input CHL information is an example of a natural language processing task. The number of parameters in the large-scale language model may be, for example, 1 billion or more, 10 billion or more, or 100 billion or more. A language model refers to a model of communicative human language using word occurrence probabilities. In one embodiment, the large-scale language model is a language model capable of performing inference using techniques such as zero-shot learning (ZSL), one-shot learning (OSL), or few-shot learning (FSL) without fine-tuning. In one embodiment, the large-scale language model is configured to perform a task and provide output in response to an input prompt. The prompt includes CHL information. The large-scale language model is not particularly limited, and examples thereof include GPT-3, GPT-4, GShard, Switch Transformer, Gopher, HyperCLOVA, etc. The large-scale language model is not included in the saddle-riding type vehicle-related IPG and the system including the saddle-riding type vehicle-related IPG, but is capable of communicating with the saddle-riding type vehicle-related IPG and the system including the saddle-riding type vehicle-related IPG.

[0027] Communicative human language (CHL) information is linguistic information that can be understood, recognized, and memorized by humans. CHL information is based on the linguistic system used by humans in everyday conversation. CHL information is transmitted visually or audibly as text information or audio information.

[0028] A saddle-type vehicle is a vehicle equipped with a saddle-type seat. A saddle-type vehicle is a vehicle configured so that a rider rides the vehicle while straddling a saddle. In the present invention, a saddle-type vehicle is equipped with handlebars and configured so as to be able to turn in a lean position. Examples of saddle-type vehicles include motorcycles, three-wheeled motor vehicles each having a pair of left and right front or rear wheels, and four-wheeled motor vehicles each having a pair of left and right front and rear wheels. Motorcycles are not particularly limited, and examples include scooters, mopeds, off-road vehicles, and on-road vehicles. Saddle-type vehicles that can turn in a lean position have the property of making the rider feel a sense of unity and cooperation with the saddle-type vehicle, and therefore the saddle-type vehicle-related IPG of the present invention is suitable for saddle-type vehicles that can turn in a lean position.

[0029] Rider equipment or personal items refer to devices that are worn or carried by the rider while riding a saddle-type vehicle and are capable of communication. The equipment or personal items are moved along with the rider by the saddle-type vehicle while the saddle-type vehicle is traveling. The rider here refers to a person riding in the saddle-type vehicle. Therefore, the rider includes not only the person driving the saddle-type vehicle but also a passenger. An example of a passenger is a tandem rider. Equipment is not particularly limited, and examples include HMDs, smart glasses, intercoms (headsets), shoes, boots, gloves, helmets, clothing, earphones, and bone conduction earphones. Personal items are not particularly limited, and examples include smartphones, electronic keys, personal digital assistants (PDAs), and smart watches. It is not necessary to strictly distinguish between equipment and personal items; items that fall under either or both are considered "equipment or personal items."

[0030] A user terminal refers to a device that is not part of a rider's equipment or personal belongings and is used by a person who is not a rider (hereinafter also referred to as a user). However, a person may be a rider when riding a saddle-type vehicle and a user when using the user terminal without riding a saddle-type vehicle. The user terminal may, for example, be a device used by a rider after riding the saddle-type vehicle. The user terminal may constitute a saddle-type vehicle-related IPG according to the present invention. The user is not particularly limited, and may, for example, be a rider after riding the saddle-type vehicle. The user terminal is not particularly limited, and may, for example, be a terminal owned by the rider (e.g., a tablet, laptop PC, or desktop PC). When the saddle-type vehicle-related IPG according to the present invention includes a user terminal, the rider can obtain linguistic interpretation data related to the saddle-type vehicle via the user terminal, thereby understanding the rider's emotions during riding and the riding status of the saddle-type vehicle after riding. The user may, for example, be a riding instructor for the saddle-type vehicle or staff at a riding school. In this case, the user terminal may be, for example, a terminal carried by the riding instructor (e.g., a tablet or laptop PC) or a terminal installed in a riding school (e.g., a tablet, laptop PC, or desktop PC). When the saddle-riding-type vehicle-related IPG according to the present invention includes a user terminal, the riding instructor can obtain CHL information indicating the linguistic interpretation result of the riding state of the saddle-riding type vehicle via the user terminal, thereby understanding the riding skill of the rider. Because the information output from the user terminal is CHL information indicating the linguistic interpretation result, the riding instructor can quickly and easily understand the riding skill of the rider. After the rider has ridden the saddle-riding type vehicle, the riding instructor can explain the riding skill to the rider while showing the user terminal displaying the information. Because the saddle-riding-type vehicle-related IPG can quickly generate CHL information indicating the linguistic interpretation result, the information can be used to provide timely instruction to the rider and for discussions with the rider immediately after the ride.

[0031] The server does not fall under the category of equipment or personal belongings of a rider, nor does it fall under the category of a user terminal. The server is not intended to be operated by either a rider or a user. However, the server may be operated by a person for purposes other than processing related to the saddle-type vehicle-related IPG (e.g., maintenance).

[0032] The "at least one program" does not necessarily have to be stored in a single memory, but may be stored separately in each memory of devices that can communicate with each other. Execution of the "at least one program" performs data acquisition processing, prompt generation processing, linguistic interpretation processing, output processing, and customization processing.

[0033] The data acquisition process is a process in which at least one processor acquires at least one type of data related to the saddle-riding vehicle or its rider from a first input device provided on the saddle-riding vehicle or on an accessory or carried by the rider, or a process in which at least one processor acquires CHL information input by the rider to the first input device as data from the first input device. The process in which at least one processor acquires at least one type of data related to the saddle-riding vehicle or its rider from a first input device provided on the saddle-riding vehicle or on an accessory or carried by the rider may be, for example, a process in which at least one processor acquires at least one type of data related to the saddle-riding vehicle or its rider from a first input device provided on the saddle-riding vehicle or on an accessory or carried by the rider over time while the saddle-riding vehicle is traveling. The first input device and the at least one type of data related to the saddle-riding vehicle or its rider are as described above. Acquisition over time refers to repeated acquisition of data over time. The specific manner of time-dependent acquisition is not particularly limited, and may be, for example, periodic or non-periodic acquisition. Multiple types of data may be acquired over time. In this case, the acquisition timing of each data may be the same or different. The data acquisition process may be performed based on an instruction input by a user, or may be performed without input from a user. The timing and trigger for performing the data acquisition process are not particularly limited.

[0034] The prompt generation process is a process in which at least one processor generates customized prompt data using at least one type of data related to the saddle-type vehicle or its rider and customization data. In addition to the at least one type of data related to the saddle-type vehicle or its rider and the customization data, other data may also be used. The other data may include, for example, data obtainable via a network or data stored in a memory. The network is not particularly limited and may be constructed using various wireless networks. The communication method and communication protocol are not particularly limited. Examples of networks include the Internet, an in-vehicle network (e.g., CAN), an OBD-II network, and a mobile network such as LTE / 5G. The other data may include, for example, data used as a template when generating a prompt, history data indicating past interactions, etc. When the at least one type of data related to the saddle-type vehicle or its rider is saddle-type vehicle-related data, the other data may include, for example, rider biometric data. When the at least one type of data related to the saddle-type vehicle or its rider is rider biometric data, the other data may include, for example, saddle-type vehicle-related data. The customized prompt data can be linguistically interpreted by the LLM. The customized prompt data has a smaller amount of data than at least one type of data related to the saddle-type vehicle or its rider. This means that the amount of data in the generated customized prompt data is smaller than the amount of data in the at least one type of data related to the saddle-type vehicle or its rider that was used to generate the customized prompt data. Examples of customized prompt data include the following (i) to (vi).

[0035] (i) CHL information relating to the amount of change over time of a saddle-riding-type vehicle-related parameter indicated by the saddle-riding-type vehicle-related data and the method of evaluating that parameter. Because this customized prompt data is CHL information, it can be directly interpreted linguistically by the LLM. Furthermore, since it also includes data on the evaluation method, evaluation can be performed. Examples of the amount of change over time of the parameter are not particularly limited, and include, for example: - Amount of change over time of bank angle when turning - Amount of change over time of brake operation amount (operation pressure) when turning - Amount of change over time of running position when turning - Amount of change over time of vehicle speed

[0036] (ii) Visual data visually showing the amount of change over time in the saddle-riding-type vehicle-related parameters indicated by the saddle-riding-type vehicle-related data, and CHL information related to the evaluation method for the parameters. The visual data is, for example, data in the form of a graph showing the amount of change over time in the saddle-riding-type vehicle-related parameters. If the LLM is multimodal, the multimodal LLM can also interpret the visual data linguistically. Furthermore, since the evaluation method data is also included, evaluation can be performed. Specific examples are not particularly limited, and include, for example, the same examples as those in (i) above.

[0037] (iii) CHL information relating to a reading method for reading the saddle-riding-type vehicle-related data as the amount of change over time of the saddle-riding-type vehicle-related parameter and a method for evaluating the parameter. The saddle-riding-type vehicle-related data is numerical data. Therefore, the LLM cannot directly interpret the saddle-riding-type vehicle-related data linguistically. However, since the customized prompt data also includes data on the reading method, the LLM can read the saddle-riding-type vehicle-related data based on the reading method. Furthermore, since the customized prompt data also includes data on the evaluation method, the LLM can perform evaluation. Specific examples are not particularly limited, and include the same examples as in (i) above.

[0038] (iv) CHL information relating to the amount of change over time in the lidar biometric parameters indicated by the lidar biometric data and the method of evaluating those parameters. Because this customized prompt data is CHL information, it can be directly interpreted linguistically by the LLM. Furthermore, since it also includes data on the evaluation method, evaluation can be performed. Examples of the amount of change over time in the parameters are not particularly limited and include, for example: - Change in heart rate over time - Change in brain waves over time - Change in sweat rate over time - Change in respiratory rate over time - Change in body temperature over time - Change in blood pressure over time - Change in the rider's facial expression over time - Change in eye movement over time - Change in blood oxygen level over time - Change in grip pressure over time - Change in voice over time.

[0039] (v) Visual data visually showing the amount of change over time in the LIDAR biometric parameter indicated by the LIDAR biometric data, and CHL information related to the evaluation method for that parameter. The visual data is, for example, data that graphically shows the amount of change over time in the LIDAR biometric parameter. If the LLM is multimodal, the multimodal LLM can also interpret the visual data linguistically. Furthermore, since the evaluation method data is also included, evaluation can be performed. Specific examples are not particularly limited, and include, for example, the same examples as those in (iv) above.

[0040] (vi) CHL information relating to a reading method for reading the LIDAR biometric data as a time-dependent change in the LIDAR biometric parameter and a method for evaluating the parameter. The LIDAR biometric data is numerical data. Therefore, the LLM cannot directly interpret the LIDAR biometric data linguistically. However, since the customized prompt data also includes data on the reading method, the LLM can read the LIDAR biometric data based on the reading method. Furthermore, since the customized prompt data also includes data on the evaluation method, evaluation can be performed. Specific examples are not particularly limited, and include the same examples as in (iv) above.

[0041] The customized prompt data is data for performing linguistic interpretation of at least one type of data related to the saddle-type vehicle or its rider, and as shown in (i) to (vi) above, includes, for example, two elements: (I) how to read at least one type of data related to the saddle-type vehicle or its rider, and (II) how to evaluate the read data. Element (I) is, for example, how to obtain characteristics or trends of at least one type of data related to the saddle-type vehicle or its rider. Element (II) is how to communicate the characteristics or trends to the rider. When customized prompt data is generated using at least one type of data related to the saddle-type vehicle or its rider and customization data, elements (I) and (II) are included in the customized prompt data, for example. Furthermore, another element (III) may also be included. Examples of element (III) include, but are not limited to, designating the tone of the output (utterance), designating the creativity or accuracy used when generating the output (utterance), designating continuity or consistency with previous outputs (utterances), and a combination of at least two of these. The customization data may be, for example, data that serves as a template when generating a prompt, at least a portion of the data that serves as the template, or data used to customize at least a portion of the data that serves as the template. The customization data may be, for example, data related to the reading of at least one type of data related to the saddle-type vehicle or its rider, and / or data related to the evaluation of the read data. An example of the customization data related to the reading of data may be, for example, a data reading method. An example of the data reading method may be, for example, a reading method for reading data as a change in a parameter over time. An example of the customization data related to the evaluation of the read data may be, for example, evaluation criteria for the read data. The evaluation may include, for example, advice based on the evaluation.As is apparent from the above description, at least a portion of the customized prompt data may include at least a portion of the customization data.

[0042] The linguistic interpretation process is a process in which at least one processor supplies customized prompt data to the LLM and acquires linguistic interpretation data related to the saddle-type vehicle from the LLM. The linguistic interpretation data related to the saddle-type vehicle is data generated by linguistic interpretation by the LLM. The linguistic interpretation data related to the saddle-type vehicle may be, for example, linguistic interpretation data about the state of the saddle-type vehicle while it is traveling, or linguistic interpretation data about the rider's emotions estimated while the saddle-type vehicle is traveling.

[0043] The output process is a process of using linguistic interpretation data related to the saddle-riding type vehicle acquired from the LLM to perform output for controlling the operation of at least one output device. The output process is performed, for example, while the saddle-riding type vehicle is traveling. The output process is not particularly limited. Examples of the output process include turning on and selecting a song in the audio system, turning on and selecting a station in the FM / AM radio, turning on and selecting a station in the satellite radio, turning on / off the navigation system, starting and ending shooting with an action camera, turning on / off and adjusting the temperature of the heated grips, turning on / off and adjusting the temperature of the heated seat, and turning on / off various functions of the ADAS. As a result, song selection in the audio system and station selection in the FM / AM radio or satellite radio can be performed according to the rider's emotions. The navigation system can also be used according to the rider's emotions. Furthermore, shooting with the action camera can be performed when the rider is feeling excited. Furthermore, the heated grips may be turned on / off and their temperature may be adjusted, and the heated seat may be turned on / off and their temperature may be adjusted, depending on the rider's emotions. Furthermore, a function corresponding to the driving state of the saddle-riding vehicle may be selected and executed from among the various functions possessed by the ADAS. In short, the output processing may be processing that uses linguistic interpretation data related to the saddle-riding vehicle acquired from the LLM while the saddle-riding vehicle is traveling to output information for controlling the operation of at least one output device so as to execute a function from among a plurality of functions possessed by the saddle-riding vehicle that corresponds to the driving state of the saddle-riding vehicle or the rider's emotions. Furthermore, the output processing may be processing that uses linguistic interpretation data related to the saddle-riding vehicle acquired from the LLM while the saddle-riding vehicle is traveling, and outputs CHL information corresponding to the linguistic interpretation data related to the saddle-riding vehicle from at least one output device. The output processing may be performed so that the linguistic interpretation data related to the saddle-riding vehicle acquired from the LLM is output directly from the output device. The linguistic interpretation data related to the saddle-type vehicle acquired from the LLM may be modified, and the modified linguistic interpretation data related to the saddle-type vehicle may be used to perform output processing, which may be performed visually and / or audibly.

[0044] The customization process is a process of receiving input of data for customizing the output of the output process for the saddle-riding type vehicle from at least one first input device or at least one second input device different from the at least one first input device, and updating the customization data based on the input data. The customization data is as described above. The customization process is not particularly limited. Customizing the saddle-riding type vehicle includes, for example, customizing according to the vehicle characteristics of the saddle-riding type vehicle or customizing the vehicle characteristics of the saddle-riding type vehicle in accordance with the entity's policy. Customizing according to the vehicle characteristics of the saddle-riding type vehicle includes, for example, changing the level at which rider fatigue is detected in accordance with the windshield effect of the saddle-riding type vehicle. Customizing the vehicle characteristics of the saddle-riding type vehicle in accordance with the entity's policy includes, for example, changing the settings of various functions of the saddle-riding type vehicle. Updating the customization data may include, for example, changing at least a portion of the data that serves as a template when generating a prompt. If the data used to customize at least a portion of the data that serves as the template is customization data, updating the customization data may include changing at least a portion of the customization data. Updating the customization data may involve, for example, changing at least a portion of the method for reading at least one type of data related to the saddle-riding vehicle or its rider, and / or changing at least a portion of the evaluation criteria for the read data. Updating the customization data includes, for example, changing whether a function of the saddle-riding vehicle is available for use, changing the content of a function of the saddle-riding vehicle, or changing the conditions under which a function of the saddle-riding vehicle is executed. Changing the content of a function of the saddle-riding vehicle includes, for example, changing the degree of intervention of various functions in the driving mode. Data for customizing the output in the output processing for the saddle-riding vehicle includes, for example, data used to update the customization data as described above. This data is used, for example, to change at least a portion of the customization data.

[0045] The present invention can further employ the following configuration.

[0046] (2) The saddle-riding type vehicle-related IPG of (1), wherein the at least one program is further programmed to cause the at least one processor to execute the following in the output process: visually or audibly output CHL information corresponding to the linguistic interpretation data related to the saddle-riding type vehicle by the at least one output device, and output visual information consisting of images and / or video so as to overlap at least partially in time with the CHL information.

[0047] According to the generator (2), CHL information is output visually or audibly. CHL information and visual information are output so as to overlap in time. By using visual information in combination, the efficiency of information transmission to the rider can be improved. It is possible to increase the information transmitted to the rider and improve the impression given to the rider while suppressing the increase in output information. It is possible to achieve a higher level of interaction while suppressing the increase in load on hardware resources. The generator (2) can more effectively solve the above-mentioned unique problems.

[0048] The CHL information according to the linguistic interpretation data related to the saddle-ride type vehicle is, for example, CHL information that indicates the results of a linguistic interpretation of the running state of the saddle-ride type vehicle and / or the rider's feelings.

[0049] The visual information may be stored in at least one memory in advance. The visual information may be received from outside the saddle-type vehicle-related IPG via a communication line such as the Internet. The visual information may be generated within the saddle-type vehicle-related IPG. The visual information may be generated by at least one processor. The visual information may be generated by the LLM. Images are static visual information. Video is dynamic visual information. Images may consist of or include visualizations, or may include non-visualizations such as photo images. Video may be animation or simulation, or may be live-action capture.

[0050] (3) The saddle-type vehicle-related IPG of (2), wherein the at least one program is further programmed to cause the at least one processor to execute a visual information generation process that generates the visual information using the data acquired by the data acquisition process.

[0051] According to the generator of (3), both the CHL information and the visual information are generated based on at least one type of data related to the saddle-type vehicle or its rider, and are output so as to overlap in time with each other. By increasing the correlation between the visual information and the CHL information, the efficiency of information transmission to the rider can be further improved. It is possible to increase the information transmitted to the rider and improve the impression given to the rider while suppressing an increase in the amount of output information. It is possible to achieve a higher level of interaction while suppressing an increase in the load on hardware resources. The generator of (3) can more effectively solve the above-mentioned unique problems.

[0052] (4) The saddle-type vehicle-related IPG of (3), wherein the at least one program is further programmed to cause the at least one processor to execute the following in the visual information generation process: generating the visual information by the LLM using the data acquired by the data acquisition process.

[0053] According to the generator of (4), both the CHL information and the visual information are generated by the LLM based on at least one type of data related to the saddle-type vehicle or its rider, and are output so as to overlap in time with each other. This makes it possible to improve the correlation between the visual information and the CHL information while reducing the load on hardware resources. The generator of (4) can more effectively solve the above-mentioned unique problems.

[0054] (5) The saddle-type vehicle-related IPG according to any one of (2) to (4), wherein in the output process, the CHL information output by the at least one output device includes an explanation about or related to the visual information that is output so as to overlap in time with the CHL information.

[0055] According to the generator (5), the correlation between CHL information and visual information can be further enhanced. It is possible to have the rider recognize multiple types of highly related information in a timely manner. The efficiency of information transmission to the rider can be improved. It is possible to increase the information transmitted to the rider and improve the impression given to the rider while suppressing the increase in output information. It is possible to achieve a higher level of interaction while suppressing the increase in load on hardware resources. The generator (5) can more effectively solve the above-mentioned unique problems.

[0056] A description of or relating to visual information may be a description or explanation of the visual content contained in the visual information itself, or may be a description of how to view the visual content rather than the visual content contained in the visual information itself.

[0057] According to the present invention, by effectively and efficiently enhancing the sense of cooperation between the saddle-type vehicle and the rider, it is possible to build a system that can improve the rider's well-being and reduce the load on the hardware resources that make up the system.

[0058] FIG. 1(a) is a system overview diagram illustrating a system including a saddle-riding-type vehicle-related IPG according to an embodiment of the present invention, and FIG. 1(b) is a flowchart illustrating processing performed by the system. FIGS. 2(a) to 2(x) are diagrams illustrating devices in which an input device (I), a processor (P), a memory (M), and an output device (O) are provided in a system including a saddle-riding-type vehicle-related IPG according to an embodiment of the present invention. FIGS. 3(a) to 3(x) are tables illustrating devices in which an input device, a processor, and an output device are provided in a system including a saddle-riding-type vehicle-related IPG according to the present invention. FIG. 4 is a flowchart illustrating processing performed by a system including a saddle-riding-type vehicle-related IPG according to a first modified embodiment of the present invention.

[0059] FIG. 1A is a system overview diagram for explaining a system 11 including a straddle-type vehicle-related IPG 1 according to an embodiment of the present invention.

[0060] The saddle-riding-type vehicle-related output system 11 (hereinafter simply referred to as the system 11) includes at least one first input device 13, at least one output device 14, and a saddle-riding-type vehicle-related IPG 1. The system 11 also includes at least one second input device 15. The at least one first input device 13 is provided on at least one of a saddle-riding-type vehicle 16, a rider's equipment 17, and a portable item 17. The at least one processor 2 acquires at least one type of data related to the saddle-riding-type vehicle or its rider from the at least one first input device 13. Examples of the first input device 13 illustrated in the figure include a GPS module, a smartwatch, a grip sensor, and an ECU. The GPS module is configured to acquire location information of the saddle-riding-type vehicle 16. The smartwatch may be configured to acquire, for example, heart rate and sweat rate. The grip sensor is configured to acquire, for example, heart rate and grip pressure. Since riders typically wear gloves as protectors, obtaining heart rates using a grip sensor may require some ingenuity depending on the method of obtaining heart rates, as described above. As described above, the ECU does not function as a first input device on its own, but functions as a first input device in combination with a GPS module or a grip sensor. At least one processor 2 obtains at least one type of data related to the saddle-riding vehicle or its rider (saddle-riding vehicle-related data or rider biological data) from the GPS module or the grip sensor via the ECU. The second input device 15 is, for example, a desktop PC owned by the manufacturer of the saddle-riding vehicle 16. The desktop PC is configured to receive input data for customizing the output of the output processing described below for the saddle-riding vehicle 16. Of course, the first input device 13 and the second input device 15 are not limited to these examples.

[0061] The saddle-ride type vehicle-related IPG 1 includes at least one processor 2, at least one memory 3, and at least one communication module 4. The memory 3 stores programs for executing (A) data acquisition processing, (B) prompt generation processing, (C) linguistic interpretation processing, (D) output processing, and (E) customization processing. The at least one processor 2 executes the programs. The number of processors 2, memories 3, and communication modules 4 is not particularly limited, and each may be one or more.

[0062] The hardware configuration of the system 11 is not particularly limited. The output device 14 may also have the functions of the saddle-riding-type vehicle-related IPG 1. If the saddle-riding-type vehicle-related IPG 1 is separate from the output device 14, the saddle-riding-type vehicle-related IPG 1 may be configured by a single server 19 or multiple servers 19 connected to each other so that they can communicate with each other. In this case, the multiple servers 19 may be configured to provide cloud computing services. The communication module 4 enables communication between the processor 2 and each of the LLM (Large Scale Language Model) 6, the first input device 13, the output device 14, and the second input device 15.

[0063] Each of the multiple output devices 14 can communicate with the saddle-riding vehicle-related IPG 1 via the network 12. There is no particular limitation on the number of output devices 14. At least one output device 14 is required. The output device 14 may be provided in the saddle-riding vehicle 16, in rider equipment 17 or portable equipment 17, or in a user terminal 18. Examples of the output device 14 shown in the figure include a meter on the saddle-riding vehicle 16, a helmet HUD, and a smartphone. Of course, the output device 14 is not limited to these examples. Another example of the output device 14 is, for example, an ADAS.

[0064] The network 12 enables communication between the first and second input devices 13, 15, the plurality of output devices 14, the saddle-type vehicle-related IPG 1, and the LLM 6. The network 12 is not particularly limited and can be constructed using various wireless networks. There are also no particular limitations on the communication method or communication protocol.

[0065] The LLM 6 is stored in one server or in multiple servers that are communicatively connected to each other. The LLM 6 can communicate with the system 11. This is the same as the LLM 6 being able to communicate with the saddle-ride type vehicle-related IPG 1 in this embodiment. The LLM 6 outputs to the system 11 in response to input from the system 11. Communication between the LLM 6 and the system 11 is performed using at least CHL information.

[0066] 1(b) is a flowchart for explaining the processing performed by the saddle-riding-type vehicle-related output system 11. In this embodiment, a case will be described in which data related to the rider's heart rate (rider biological data) generated by a smartwatch and a grip sensor is used as at least one type of data related to the saddle-riding-type vehicle or its rider. Note that the processing shown in FIG. 1(b) can be implemented in any of the system configurations shown in FIGS. 2 and 3(a) to 3(x).

[0067] [Data Acquisition Process (A)] At least one processor 2 acquires at least one type of data (rider biological data) over time from a first input device 13 provided on the saddle-riding vehicle 16 or on the rider's equipment 17 or portable item 17 while the saddle-riding vehicle 16 is traveling (step S11). Specifically, the at least one processor 2 acquires data related to the rider's heart rate over time from a smartwatch and a grip sensor.

[0068] [Prompt Generation Process (B)] At least one processor 2 generates customized prompt data using at least one type of data (rider biological data) acquired in step S11 and customization data (step S12). In this embodiment, the customized prompt data is data indicating the following CHL information. The method for evaluating the heart rate includes, for example, providing advice to the rider according to the heart rate: - Transition of the rider's heart rate over time; - Method for evaluating the heart rate that changes over time;

[0069] Linguistic Interpretation Process (C) At least one processor 2 provides the customized prompt data generated in step S12 to the LLM 6 (step S13).

[0070] The LLM 6 linguistically interprets the customized prompt data provided in step S13 (step S21). In this embodiment, the LLM 6 uses the provided customized prompt data to evaluate the rider's heart rate based on the evaluation method and suggests a riding mode according to the evaluation result. For example, if an increase in the rider's fatigue level is detected based on the rider's heart rate, the LLM 6 generates linguistic interpretation data related to the saddle-riding vehicle, such as, "You seem tired. We recommend switching to another riding mode." The other riding mode may be, for example, a riding mode using a quick shift system or an automatic shift change system. Using this riding mode can reduce the burden on the rider of shift change operations. As another example, if an increase in the rider's anxiety is detected based on the rider's heart rate, the LLM 6 may generate linguistic interpretation data related to the saddle-riding vehicle (linguistic interpretation data about the rider's emotions estimated while riding the saddle-riding vehicle), such as, "You seem mentally unstable. Is something wrong?"

[0071] Next, the at least one processor 2 acquires the linguistic interpretation data related to the saddle-ride type vehicle generated in step S21 from the LLM 6 (step S14).

[0072] [Output Process (D)] At least one processor 2 supplies the linguistic interpretation data related to the saddle-ride type vehicle acquired from the LLM 6 in step S14 to the output device 14 (step S15).

[0073] The output device 14 outputs CHL information indicating the linguistic interpretation result of the rider's emotion estimated while riding, based on the linguistic interpretation data related to the saddle-riding type vehicle supplied from at least one processor 2 (step S31). In this embodiment, the meter of the saddle-riding type vehicle displays CHL information such as "You seem tired. We recommend switching to another riding mode." In other words, in this embodiment, the linguistic interpretation data related to the saddle-riding type vehicle is used to output information for controlling the operation of at least one output device 14. The CHL information may be output as audio information from a headset serving as an output device, for example.

[0074] If the rider accepts the output of the output device 14 (e.g., a recommendation to change to another driving mode as described above), the rider may input audio information indicating this via a headset (more specifically, a microphone provided in the headset) serving as the first input device, and the driving mode is changed to the recommended driving mode accordingly. The audio information corresponds to the CHL information input by the rider to the first input device. In other words, the audio information corresponds to the CHL information input by the rider to the first input device in response to a suggestion from the saddle-type vehicle 16.

[0075] [Customization Process (E)] The at least one processor 2 receives input of data for customizing the output in the output process (D) for the saddle-riding vehicle 16 from the at least one second input device 15 (step S41). The at least one processor 2 acquires the data input in step S41 (step S42). The at least one processor 2 updates the customization data based on the data acquired in step S42 (step S43).

[0076] (Variation 1) With reference to FIG. 4 , a saddle-riding-type vehicle-related output system including a saddle-riding-type vehicle-related IPG according to Variation 1 of the embodiment of the present invention will be described. In Variation 1, the memory 3 stores programs for executing (A) data acquisition processing, (B) prompt generation processing, (C) linguistic interpretation processing, (D1) output processing, (E) customization processing, and (F) visual information generation processing. At least one processor 2 executes these programs. In Variation 1, the (A) data acquisition processing, (B) prompt generation processing, (C) linguistic interpretation processing, and (E) customization processing are the same as those in the above embodiment. Therefore, their description will be omitted. The (D1) output processing and (F) visual information generation processing will be described below. In Variation 1, the at least one type of data acquired in step S11 includes data related to the rider's heart rate (rider biometric data) as well as data related to the position information of the saddle-riding-type vehicle 16 (saddle-riding-type vehicle-related data). The data related to the position information of the saddle-riding-type vehicle 16 is acquired, for example, by a GPS module.

[0077] [Visual Information Generation Process (F)] At least one processor 2 generates visual information using at least one type of data acquired in step S11. In Variation 1, at least one processor 2 generates visual information using the at least one type of data acquired in step S11 via the LLM 6 (step S22). More specifically, the process is as follows: At least one processor 2 supplies the at least one type of data acquired in step S11 to the LLM 6 (step S16). The LLM 6 generates visual information using the at least one type of data provided in step S16 (step S22). At least one processor 2 acquires the visual information generated in step S22 from the LLM 6 (step S17). Note that in the example shown in FIG. 4, the visual information generation process (F) is performed after the linguistic interpretation process (C), but the visual information generation process (F) may be performed before the linguistic interpretation process (C) or before the prompt generation process (B).

[0078] The visual information may be an image or a video. In the example shown in Fig. 4, the LLM 6 generates the visual information, but the visual information may be stored in advance in at least one memory 3, or may be received from outside the system 11 via a communication line such as the Internet. The visual information may be generated based on, for example, data relating to the position information of the saddle riding type vehicle 16. The visual information may be, for example, data indicating the positional relationship between the current position of the saddle riding type vehicle 16 and the nearest rest area, together with a map image.

[0079] [Output Process (D1)] At least one processor 2 supplies the linguistic interpretation data related to the saddle-riding type vehicle acquired from the LLM 6 in step S14 and the visual information acquired from the LLM 6 in step S17 to the output device 14 (step S15A). At least one processor 2 outputs the visual information in step S31A so as to at least partially overlap with the CHL information in time. In the example shown in FIG. 4 , the output of the CHL information and the visual information starts at the same time, but, for example, the output of the CHL information may start before the visual information or after the visual information. The same applies to the end of the output of the CHL information and the visual information. In Modification 1, the CHL information may include an explanation about or related to the visual information that is output so as to overlap in time with the CHL information. In Modification 1, for example, audio information such as "You seem tired. We recommend you take a rest" is output from a headset, which is an accessory of the rider, while a positional relationship between the current position of the saddle riding type vehicle 16 and the nearest rest area is displayed together with a map image on a meter provided on the saddle riding type vehicle 16. In other words, in Modification 1, the CHL information and visual information are output so as to overlap in time. Note that in Modification 1, if the rider accepts the suggestion to take a rest, audio information (CHL information) regarding the nearest rest area may be output from the headset while the positional relationship between the current position of the saddle riding type vehicle 16 and the nearest rest area is displayed together with a map image on the meter of the saddle riding type vehicle 16.

[0080] In the present embodiment, data related to the rider's heart rate is used to output advice suggesting a response based on the rider's emotions and a response if the rider accepts the advice from an output device. However, the present invention is not limited to the above embodiment. Other embodiments are possible, and various modifications can be added. For example, data related to the rider's body temperature may be used to adjust the temperature of heated grips or a heated seat as an output device. Alternatively, data related to the rider's heart rate may be used to output music based on the rider's emotions from an output device. When the position information of the saddle-riding vehicle 16 is used to determine that the saddle-riding vehicle 16 is traveling on a highway, the rider may be advised to use a cruise control system. If the rider accepts the advice, the cruise control system may be used. For example, data from the IMU and GPS, i.e., multiple types of data, may be used to understand the state of a saddle-riding vehicle 16 capable of turning in a lean position, and an evaluation of the rider's driving skill may be provided. A saddle-riding vehicle 16 capable of turning in a lean position can obtain a wider variety of information related to driving operations and driving conditions than a non-lean vehicle. Multiple types of data can be used in combination. This makes it easier to understand the state of a saddle-riding vehicle 16 that can turn in a lean position. In other words, a saddle-riding vehicle 16 that can turn in a lean position has more information that can be obtained compared to a non-lean vehicle. Therefore, using multiple types of data in combination to understand the state of the saddle-riding vehicle 16 is suitable for a saddle-riding vehicle 16 that can turn in a lean position. Note that the data used to evaluate the rider's driving skill is not limited to the above data. For example, information on road conditions may be provided using data from the IMU and GPS. In this case, weather information obtained from the Internet may also be used. The data used to provide information on road conditions is not limited to the above data. Road conditions are an example of the environment surrounding the saddle-riding vehicle. In a saddle-riding vehicle that can turn in a lean position, the rider's own weight shifts, which causes the vehicle to lean. Weight shifting is an operation that does not occur in a non-lean vehicle. A manual two-wheeled vehicle requires separate operations with both hands and feet.Not only manual vehicles, but also motorcycles tend to require a greater variety of inputs from the rider while driving. Therefore, compared to non-lean vehicles, riders tend to want to understand the surrounding environment. The surrounding environment can be understood from the state of the saddle-riding vehicle. As described above, the state of the saddle-riding vehicle can be easily understood by using multiple types of data. In other words, compared to non-lean vehicles, more information can be obtained from a saddle-riding vehicle. Therefore, using a combination of multiple types of data to understand the surrounding environment is suitable for saddle-riding vehicles that can turn in a lean position. For example, the rider may inquire of the saddle-riding vehicle 16 about recommended touring routes, and the saddle-riding vehicle 16 may display the recommended touring route on the meter. For example, customization data may be input from the first input device 14 instead of the second input device 15.

[0081] 1: Saddle-ride type vehicle-related IPG (saddle-ride type vehicle-related interactive prompt generator) 2: Processor 3: Memory 4: Communication module 6: LLM 11: Saddle-ride type vehicle-related output system (system) 12: Network 13: Input device 14: First output device 15: Second input device

Claims

1. A saddle-ride type vehicle-related IPG (Interactive Prompt Generator), the saddle-ride type vehicle-related IPG including: at least one memory; and at least one processor capable of communicating with an LLM (Large Scale Language Model), and capable of communicating with at least one first input device and at least one output device provided on the saddle-ride type vehicle or on equipment or carried by a rider of the saddle-ride type vehicle, the processor being connected to the memory and configured to execute at least one program stored in the memory, the at least one program comprising: a data acquisition process for acquiring at least one type of data related to the saddle-ride type vehicle or its rider from the at least one first input device, and / or acquiring CHL (Communicative Human Language) information input by the rider to the at least one first input device as data from the at least one first input device; a linguistic interpretation process that supplies the customized prompt data to the LLM and acquires linguistic interpretation data related to the saddle-ride type vehicle, the linguistic interpretation data being generated by the linguistic interpretation process by the LLM; an output process that uses the linguistic interpretation data related to the saddle-ride type vehicle to produce output for controlling the operation of the at least one output device; and a customization process that receives input of data for customizing the output in the output process for the saddle-ride type vehicle from the at least one first input device or at least one second input device different from the at least one first input device, and updates the customization data based on the data.

2. A saddle-riding type vehicle-related IPG as claimed in claim 1, wherein said at least one program is further programmed to cause said at least one processor to execute the following in said output processing: visually or audibly output CHL information corresponding to the linguistic interpretation data related to said saddle-riding type vehicle by said at least one output device, and output visual information consisting of images and / or video so as to overlap at least partially in time with the CHL information.

3. A saddle-riding type vehicle-related IPG according to claim 2, wherein said at least one program is further programmed to cause said at least one processor to execute a visual information generation process that generates said visual information using said data acquired by said data acquisition process.

4. A saddle-type vehicle-related IPG according to claim 3, wherein the at least one program is further programmed to cause the at least one processor to execute the following in the visual information generation process: generating the visual information by the LLM using the data acquired by the data acquisition process.

5. A saddle-type vehicle-related IPG according to any one of claims 2 to 4, wherein in the output process, the CHL information output by the at least one output device includes an explanation about or related to the visual information that is output so as to overlap in time with the CHL information.

Images