Passenger recognition device mounted in vehicle, and method by which passenger recognition device performs calibration

Abstract

A passenger recognition device for recognizing a passenger in a vehicle, and a method by which the passenger recognition device performs calibration are provided. The passenger recognition device can perform a calibration operation in which an available frequency region is determined by acquiring frequency response characteristics related to ultrasonic signals in an inaudible frequency band for each of a plurality of speakers, volume values output by each of the plurality of speakers are adjusted for each frequency within the available frequency region, and thus offset data for adjusting the output volume of each of the plurality of speakers is acquired so that ultrasonic signals having signal level values greater than or equal to a reference volume is received by a microphone, and offset data about the available frequency region and the output volume for each frequency are stored for each of the plurality of speakers.

Description

A passenger recognition device mounted in a vehicle and a method for the passenger recognition device to perform calibration

[0001] The present disclosure relates to an occupant recognition system for recognizing an occupant in a vehicle and a method of operating the same. Specifically, the present disclosure relates to an occupant recognition system and a method for the occupant recognition system to perform calibration to recognize an occupant in a vehicle.

[0002] There is an increasing demand for recognizing whether passengers inside a vehicle—such as the driver, front passenger, or rear passengers—have entered or exited the vehicle. In particular, legislation is currently underway to mandate the installation of passenger recognition systems in vehicles to prevent passengers from being left unattended inside the vehicle after the driver has exited. Traditionally, Occupant Monitoring Systems (OMS) have been utilized. These systems use cameras to capture images of drivers or passengers, recognize the driver's face to perform actions such as detecting drowsy driving or issuing driver status warnings, or to be used in intelligent speed assist systems, reverse assist systems, event data recorders (EDRs), or emergency braking systems. However, since OMS systems rely on cameras to capture and acquire images of drivers or passengers' faces, there have been privacy infringement issues due to the potential leakage of personal information.

[0003] To prevent the possibility of personal information leakage and avoid privacy infringement issues, a passenger recognition device is needed that can identify occupants inside the vehicle without using a camera.

[0004] One aspect of the present disclosure provides a method for a occupant recognition device mounted in a vehicle to perform calibration. A calibration method for an occupant recognition device according to one embodiment of the present disclosure may include the step of determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of a plurality of speakers. A calibration method for an occupant recognition device according to one embodiment of the present disclosure may include the step of obtaining offset data for adjusting the output volume of each of a plurality of speakers by adjusting the volume value output by each of the plurality of speakers for each frequency within the available frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by a microphone. A calibration method for an occupant recognition device according to one embodiment of the present disclosure may include the step of storing offset data regarding the available frequency range and the output volume for each of the plurality of speakers.

[0005] One aspect of the present disclosure provides a passenger recognition device mounted in a vehicle. A passenger recognition device according to one embodiment of the present disclosure may include a plurality of speakers that output an ultrasonic signal in an inaudible frequency band; a microphone that receives the ultrasonic signal; a memory that stores one or more instructions; and at least one processor including a processing circuit. As the one or more instructions are executed individually or collectively by the at least one processor, the passenger recognition device may determine an available frequency range for each of the plurality of speakers by acquiring frequency response characteristics for each of the plurality of speakers through a frequency sweep. As the one or more instructions are executed individually or collectively by the at least one processor, the passenger recognition device may acquire offset data for adjusting the output volume of each of the plurality of speakers by adjusting the volume value output by each of the plurality of speakers by frequency within the available frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by the microphone. As the above one or more instructions are executed individually or collectively by the at least one processor, the occupant recognition device can store offset data for the available frequency range and frequency-specific output volume for each of the plurality of speakers in the storage space of memory.

[0006] One aspect of the present disclosure provides a computer program product comprising a computer-readable storage medium. The storage medium may include instructions readable by a passenger recognition device for recognizing a passenger in a vehicle, for performing the following operations: determining a usable frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of a plurality of speakers; obtaining offset data for adjusting the output volume of each of a plurality of speakers by adjusting the volume value output by each of a plurality of speakers by frequency within the usable frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by a microphone; and storing offset data regarding the usable frequency range and the output volume by frequency for each of a plurality of speakers.

[0007] The present disclosure can be easily understood from the combination of the following detailed description and the accompanying drawings, where reference numerals denote structural elements.

[0008] Figure 1 is a conceptual diagram illustrating the components of a passenger recognition device installed in a vehicle and the operation of the components.

[0009] FIG. 2 is a flowchart illustrating a method for a passenger recognition device to perform calibration according to one embodiment of the present disclosure.

[0010] FIG. 3 is a block diagram illustrating the components of an occupant recognition device according to one embodiment of the present disclosure.

[0011] FIG. 4 is a flowchart illustrating a method for determining a usable frequency range for a plurality of speakers using an occupant recognition device according to one embodiment of the present disclosure.

[0012] FIG. 5 is a graph illustrating frequency response characteristics to explain the operation of a passenger recognition device according to one embodiment of the present disclosure determining an available frequency range.

[0013] FIG. 6 is a flowchart illustrating a method for an occupant recognition device according to one embodiment of the present disclosure to acquire offset data for adjusting the output volume of a speaker.

[0014] FIG. 7 is a flowchart illustrating a method for a passenger recognition device according to one embodiment of the present disclosure to obtain a gain of a signal level value of an input signal based on a recognition result regarding whether a vehicle window is open or closed.

[0015] FIG. 8 is a flowchart illustrating a method for determining an available frequency range when a single ultrasonic signal is output by a plurality of speakers in a passenger recognition device according to one embodiment of the present disclosure.

[0016] FIG. 9 is a diagram illustrating the connection relationship between an amplifier and speakers in a passenger recognition device according to one embodiment of the present disclosure.

[0017] FIG. 10 is a graph illustrating frequency response characteristics to explain the operation of determining an available frequency range when a single ultrasonic signal is output by a plurality of speakers in a passenger recognition device according to one embodiment of the present disclosure.

[0018] FIG. 11 is a diagram illustrating the operation of a passenger recognition device displaying calibration information according to one embodiment of the present disclosure.

[0019] FIG. 12 is a diagram illustrating the operation of a passenger recognition device according to one embodiment of the present disclosure displaying calibration information through an external device.

[0020] FIG. 13 is a diagram illustrating the operation performed by the occupant recognition device of the present disclosure using artificial intelligence technology.

[0021] FIG. 14 is a drawing illustrating a disclosed embodiment in which the occupant recognition device of the present disclosure operates in conjunction with a server.

[0022] FIG. 15 is a drawing for explaining FIG. 14 in detail.

[0023] The terms used in the embodiments of this specification have been selected to be as widely used as possible, taking into account the functions of the present disclosure; however, these terms may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the description section of the relevant embodiments. Therefore, terms used in this specification should be defined not merely by their names, but based on their meanings and the overall content of the present disclosure.

[0024] Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art as described in this specification.

[0025] Throughout this disclosure, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "...part," "...module," etc., as used in this specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software.

[0026] As used in this disclosure, the expression “configured to” may be replaced, depending on the context, with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of.” The term “configured to” may not necessarily mean only “specifically designed to” in hardware. Instead, in some situations, the expression “system configured to” may mean that the system is “capable of” in conjunction with other devices or components. For example, the phrase “processor configured to perform A, B, and C” may mean a dedicated processor for performing the said operations (e.g., an embedded processor), or a generic-purpose processor (e.g., a CPU or an application processor) capable of performing said operations by executing one or more software programs stored in memory.

[0027] In addition, when a component is described in the present disclosure as being "connected" or "connected" to another component, it should be understood that the component may be directly connected to or directly connected to the other component, but unless otherwise specifically stated, it may also be connected or connected through another component in between.

[0028] In the present disclosure, a "vehicle" is a means of transportation that travels on a road or a track. A vehicle may be a concept that includes an internal combustion engine vehicle equipped with an engine as a power source, a hybrid vehicle equipped with an engine and an electric motor as a power source, an electric vehicle equipped with an electric motor as a power source, and the like. In one embodiment of the present disclosure, a vehicle may include at least one of an automobile, a train, and a motorcycle.

[0029] In the present disclosure, the "occupant recognition device" refers to a device configured to recognize whether a driver, front passenger, and / or rear passenger is in or out of a vehicle without a camera, as well as to recognize the passenger's actions, movements, or breathing. In one embodiment of the present disclosure, the occupant recognition device outputs an ultrasonic signal in the inaudible frequency band through a speaker and receives an ultrasonic signal reflected by the passenger through a microphone, and can recognize the passenger by utilizing the time difference and frequency difference between the transmitted signal (the output ultrasonic signal) and the received signal. The occupant recognition device may be implemented, for example, as a Human Presents Detection (HPD) system.

[0030] In the present disclosure, 'inaudible sound frequency' means a frequency that cannot be heard by the human ear. Inaudible sound frequency may refer, for example, to a frequency of 18 kHz or higher.

[0031] Embodiments of the present disclosure are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein.

[0032] Embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0033] FIG. 1 is a conceptual diagram for explaining the components of a passenger recognition device (100) mounted in a vehicle (10) and the operation of the components.

[0034] Referring to FIG. 1, the occupant recognition device (100) is positioned within a vehicle (10) and may be implemented as an electronic device comprising a plurality of speakers (110-1 to 110-5), a microphone (120), and a processor (130). The number and placement locations of the plurality of speakers (110-1 to 110-5) and the placement location of the microphone (120) shown in FIG. 1 are exemplary for convenience of explanation, and the components of the occupant recognition device (100) of the present disclosure are not limited to those shown in FIG. 1. The components of the occupant recognition device (100) will be described in detail in FIG. 3.

[0035] The passenger recognition device (100) can be implemented as a system that recognizes whether a passenger (20) in a vehicle (10) has boarded or disembarked. In one embodiment of the present disclosure, the passenger recognition device (100) can recognize not only whether the passenger (20) has boarded or disembarked, but also the passenger's (20) movements, actions, or breathing. The passenger recognition system can be implemented, for example, as a Human Presents Detection (HPD) system.

[0036] In one embodiment of the present disclosure, the occupant recognition device (100) outputs an ultrasonic signal in an inaudible frequency band using a plurality of speakers (110-1 to 110-5), receives an ultrasonic signal reflected by an occupant (20) through a microphone (120), and can recognize the occupant (20) by using the time difference and frequency difference between the transmitted signal (output ultrasonic signal) and the received signal. Each of the plurality of speakers (110-1 to 110-5) is positioned differently within the vehicle (10) and may include a high-frequency speaker (e.g., tweeter), a mid-frequency speaker (e.g., mid-range), and a low-frequency speaker (e.g., woofer) depending on the frequency band of the output volume. A microphone (120) can receive an ultrasonic signal that is output by each of the plurality of speakers (110-1 to 110-5), and an ultrasonic signal that is reflected by the occupant (20), and can provide information regarding the reception time and frequency of the ultrasonic signal to a processor (130). For example, in the case of the fifth speaker (110-5) among the plurality of speakers (110-1 to 110-5), the ultrasonic signal output by the fifth speaker (110-5) can be received directly by the microphone (120) (path 1 in FIG. 1), reach an object inside the vehicle (10) and be reflected from the object to reach the microphone (120) (2-1, 2-2 in FIG. 1), or reach the occupant (20) and be reflected from the occupant (20) to reach the microphone (120) (3-1, 3-2 in FIG. 1). The processor (130) can measure the time difference and frequency difference between the ultrasonic signal output by each of the plurality of speakers (110-1 to 110-5) and the signal received by the microphone (120), and can recognize the occupant (20) based on the measurement results. In one embodiment of the present disclosure, the processor (130) can measure the time difference between the transmitted signal and the received signal based on the time of flight of the ultrasonic signal.Additionally, the processor (130) can measure the frequency difference between the transmitted signal and the received signal based on the Doppler effect of the ultrasonic signal.

[0037] In order for the passenger recognition device (100) to improve the accuracy of the passenger (20) recognition result, it is necessary to perform calibration. In the present disclosure, 'calibration' refers to the operation of correcting (or adjusting) the frequency and / or output volume value for accurate passenger (20) recognition. During the calibration process of the passenger recognition device (100), a moving object (e.g., a passenger) must not be in the space (in-cabin) of the vehicle (10). In one embodiment of the present disclosure, 'calibration' may include operations of determining an available frequency range for each of the plurality of speakers (110-1 to 110-5), obtaining offset data for adjusting the volume value output by each of the plurality of speakers (110-1 to 110-5) for each frequency within the available frequency range, and storing the available frequency range and offset data.

[0038] The passenger recognition device (100) can automatically perform initial calibration when the vehicle (10) or the passenger recognition device (100) is purchased and operated for the first time, or when the application for passenger recognition is run for the first time.

[0039] In one embodiment of the present disclosure, the occupant recognition device (100) tracks the frequency of an ultrasonic signal output by each of a plurality of speakers (110-1 to 110-5) through a microphone (120) in real time, and if a change greater than a preset value is detected in the frequency as a result of tracking, it determines that a change has occurred in the environment inside the vehicle (10), and can perform real-time calibration according to the result of determination. However, it is not limited thereto, and in one embodiment of the present disclosure, the occupant recognition device (100) may display a UI (user interface) for executing a calibration operation through a CID (center information display) inside the vehicle (10), and may perform manual calibration when user input is received through the UI.

[0040] In one embodiment of the present disclosure, the occupant recognition device (100) recognizes a physical change (e.g., a change in vehicle seat position, or the opening of a sunroof, etc.) in the environment (in-cabin) of the vehicle (10), and can perform calibration as the change in the environment (in-cabin) of the vehicle (10) is recognized.

[0041] A specific method for the occupant recognition device (100) to perform calibration will be explained with reference to FIG. 2.

[0042] FIG. 2 is a flowchart illustrating a method in which a passenger recognition device (100) according to one embodiment of the present disclosure performs calibration.

[0043] In step S210, the occupant recognition device (100) determines an available frequency range by obtaining the frequency response characteristics of an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of the plurality of speakers. Referring together to FIG. 1, the occupant recognition device (100) can obtain a frequency response by generating and outputting an ultrasonic signal through each of the plurality of speakers (110-1 to 110-5) while changing the frequency by performing a frequency sweep, and by receiving the ultrasonic signal through a microphone (120). The processor (130) of the occupant recognition device (100) can analyze the characteristics of the obtained frequency response and detect a frequency at which the signal level value of the signal input through the microphone (120) drops by a preset value compared to the signal level value at the initial frequency. The 'preset value' may be, for example, 3dB or 6dB, but is not limited thereto. The processor (130) can determine the ultrasonic band between the initial frequency and the detected frequency as an available frequency range.

[0044] The usable frequency range may be determined differently for each of the plurality of speakers (110-1 to 110-5). For example, among the plurality of speakers (110-1 to 110-5), the usable frequency range of a high-frequency reproduction speaker (e.g., tweeter) may be determined to be in the range of 18 kHz to 28 kHz, the usable frequency range of a mid-frequency reproduction speaker (e.g., mid-range) may be determined to be in the range of 18 kHz to 24 kHz, and the usable frequency range of a low-frequency reproduction speaker (e.g., woofer) may be determined to be in the range of 18 kHz to 21 kHz. However, the above-mentioned usable frequency range is merely exemplary, and the usable frequency range of the present disclosure is not limited to the above-mentioned frequency range.

[0045] In step S220, the occupant recognition device (100) obtains offset data for adjusting the output volume of each of the plurality of speakers by adjusting the volume value output by each of the plurality of speakers for each frequency within the available frequency range so that a signal level value greater than or equal to the reference volume is received by the microphone. The distance between the speakers and the microphone within the vehicle (10) varies depending on the position of the speakers. Referring together to the embodiment illustrated in FIG. 1, when the position of the microphone (120) is fixed, the distance between the plurality of speakers (110-1 to 110-5) and the microphone (120) is determined by the position where each of the plurality of speakers (110-1 to 110-5) is placed. For accurate analysis of the ultrasonic signal, it is necessary to input a signal of a certain magnitude or greater into the microphone (120). In one embodiment of the present disclosure, the occupant recognition device (100) can adjust the output volume value of an ultrasonic signal output by each of a plurality of speakers (110-1 to 110-5) through an output volume sweep at a specific frequency within a usable frequency range, and can receive the ultrasonic signal through a microphone (120) to obtain an input signal. The processor (130) can identify an output volume value in which the signal level value of the input signal obtained by the microphone (120) is greater than or equal to a preset threshold. The threshold may be preset to, for example, -30dB, but is not limited thereto. The processor (130) can obtain offset data for adjusting the default volume value for each of the plurality of speakers (110-1 to 110-5) to the identified output volume value.

[0046] In one embodiment of the present disclosure, the occupant recognition device (100) can identify a speaker among a plurality of speakers whose signal level value of an input signal received through a microphone is below a threshold value even when the output volume value is adjusted. In this case, the occupant recognition device (100) can exclude the identified speaker so that it does not operate when recognizing an occupant in the vehicle. For example, the occupant recognition device can disable the identified speaker.

[0047] In step S230, the occupant recognition device (100) stores offset data regarding the available frequency range and the output volume per frequency for each of the plurality of speakers. Referring together to the embodiment illustrated in FIG. 1, the processor (130) of the occupant recognition device (100) determines the available frequency range for each of the plurality of speakers (110-1 to 110-5) and can store information regarding the determined available frequency range for each of the plurality of speakers (110-1 to 110-5). The processor (130) can store offset data regarding the output volume of the speakers per frequency.

[0048] Although not illustrated in FIGS. 1 and 2, the occupant recognition device (100) may display information regarding the progress or completion of a calibration operation, including a step of determining the usable frequency range of each of the plurality of speakers (110-1 to 110-5) (S210), a step of acquiring frequency-specific offset data (S220), and a step of storing the usable frequency range and offset data (S230). In one embodiment of the present disclosure, the occupant recognition device (100) may display calibration information through a center information display (CID) in the vehicle (10). However, it is not limited thereto, and the occupant recognition device (100) may transmit calibration information to an external device via a wireless communication network and display calibration information through the external device. Specific embodiments of how the occupant recognition device (100) displays calibration information will be described in detail in FIGS. 11 and 12.

[0049] There is an increasing demand for recognizing whether a passenger (20) inside a vehicle (10), such as a driver, a passenger in the front seat, or a passenger in the rear seat, is boarding or disembarking. In particular, legislation is currently being enacted to mandate the installation of a passenger recognition system in vehicles for the purpose of preventing passengers from being left unattended inside the vehicle after the driver has disembarked. Conventional occupant monitoring systems (OMS) recognize the driver or passenger from images obtained by photographing the driver or passenger using a camera, but this raises privacy infringement issues due to the potential leakage of personal information. To prevent the potential leakage of personal information and to avoid privacy infringement issues, it is necessary to recognize the passenger (20) inside the vehicle (10) without using a camera.

[0050] The passenger recognition device (100) according to the present disclosure generates and outputs an ultrasonic signal in the inaudible frequency band through a plurality of speakers (110-1 to 110-5), receives a signal reflected by a passenger (20) through a microphone (120), and can recognize the passenger (20) by comparing the output ultrasonic signal with the received signal. In order to improve the accuracy of passenger (20) recognition, it is necessary to perform calibration of the passenger recognition device (100).

[0051] The present disclosure aims to provide a passenger recognition device (100) that recognizes a passenger (20) in a vehicle (10) using an ultrasonic signal in the inaudible frequency band. Specifically, the present disclosure aims to provide a passenger recognition device (100) and a calibration method that perform calibration to improve the accuracy of recognizing a passenger (20) in a vehicle (10).

[0052] The passenger recognition device (100) according to the embodiment illustrated in FIGS. 1 and 2 determines the usable frequency range of each of the plurality of speakers (110-1 to 110-5), obtains offset data of output volume values ​​such that each of the plurality of speakers (110-1 to 110-5) outputs a volume that satisfies the reference value of the input signal of the microphone (120) for each frequency, and performs calibration to store the usable frequency range and the offset data of the output volume values, thereby providing a technical effect of improving the accuracy of passenger (20) recognition. In addition, the passenger recognition device (100) according to one embodiment of the present disclosure does not include a camera, so there is no possibility of personal information such as the face of the driver or passenger being leaked, and since speakers, microphones, etc. already existing inside the vehicle (10) can be utilized, additional costs, space constraints, and design problems associated with the addition of electronic devices can be resolved.

[0053] FIG. 3 is a block diagram illustrating the components of a passenger recognition device (100) according to one embodiment of the present disclosure.

[0054] Referring to FIG. 3, the occupant recognition device (100) may be implemented as an electronic device comprising a speaker (110), a microphone (120), a processor (130), a memory (140), and a display (150). The speaker (110), microphone (120), processor (130), memory (140), and display (150) may each be electrically and / or physically connected to one another. FIG. 3 illustrates only the essential components for explaining the operation of the occupant recognition device (100), and the components included in the occupant recognition device (100) are not limited to those illustrated in FIG. 3. In one embodiment of the present disclosure, the occupant recognition device (100) may further include a communication interface (160, see FIG. 15) configured to perform data transmission and reception with a server (300, see FIG. 14 and FIG. 15) or an external device.

[0055] In one embodiment of the present disclosure, the occupant recognition device (100) may not include some of the components shown in FIG. 3. For example, the occupant recognition device (100) may not include a display (150).

[0056] A speaker (110) is a device configured to output an acoustic signal. In one embodiment of the present disclosure, the speaker (110) may output an ultrasonic acoustic signal in the inaudible sound frequency band. The inaudible sound frequency is a frequency that cannot be heard by the human ear, and may refer, for example, to a frequency of 18 kHz or higher.

[0057] The speaker (110) may be composed of a plurality of speakers including a first speaker (110-1), a second speaker (110-2), a third speaker (110-3), ..., an nth speaker (110-n). Each of the plurality of speakers (110-1 to 110-n) may be placed at different locations within the vehicle. Each of the plurality of speakers (110-1 to 110-n) may have different output volume bands. The plurality of speakers (110-1 to 110-n) may be classified, for example, into high-frequency speakers (e.g., tweeters), mid-frequency speakers (e.g., mid-ranges), and low-frequency speakers (e.g., woofers) according to the output volume band.

[0058] A microphone (120) is a device configured to receive an acoustic signal and convert it into an electrical signal. In one embodiment of the present disclosure, the microphone (120) can receive an ultrasonic signal that is output by a plurality of speakers (110-1 to 110-n) and reflected by a passenger in the vehicle. The microphone (120) can convert the received ultrasonic signal into an electrical signal and provide information regarding the signal level value of the converted electrical signal to a processor (130).

[0059] The processor (130) can execute one or more instructions of a program stored in memory (140). The processor (130) may be composed of hardware elements that perform arithmetic, logic, and input / output operations and image processing. Although the processor (130) is depicted as a single element in FIG. 3, it is not limited thereto. In one embodiment of the present disclosure, the processor (130) may be composed of one or more elements.

[0060] The processor (130) may include a processing circuit. The processor (130) may include one or more processors. For example, the term "processor" as used in the present disclosure, including in the claims, may include at least one processor and various processing circuits. In at least one processor, one or more processors may be configured to perform the various functions and / or operations described in the present disclosure in a distributed manner, individually and / or collectively. As used herein, "processor," "at least one processor," and "one or more processors" may be configured to perform various functions. However, these terms cover, without limitation, situations where one processor performs some of the functions and other processor(s) perform other parts of the functions, and situations where a single processor can perform all functions. Additionally, at least one processor may include a combination of processors performing various functions of the disclosed functions in a distributed manner. At least one processor may execute program code or instructions to achieve or perform various functions.

[0061] One or more processors included in the processor (120) may be circuitry such as a system on chip (SoC) or an integrated circuit (IC). The processor (130) may be implemented as a general-purpose processor such as a CPU (Central Processing Unit), AP (Application Processor), or DSP (Digital Signal Processor), a graphics-dedicated processor such as a GPU (Graphic Processing Unit) or VPU (Vision Processing Unit), or an artificial intelligence-dedicated processor such as an NPU (Neural Processing Unit). The processor (130) may be controlled to process input data according to predefined operation rules or an artificial intelligence model. Alternatively, if the processor (130) is an artificial intelligence-dedicated processor, the artificial intelligence-dedicated processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0062] The memory (140) may be composed of at least one type of storage medium, such as a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), or an optical disk.

[0063] The memory (140) may store instructions executed by the processor (130) for the occupant recognition device (100) to perform a calibration operation. In one embodiment of the present disclosure, the instructions stored in the memory (140) may include, for example, at least one of an algorithm, a data structure, program code, and an application program. The instructions stored in the memory (140) may be implemented in a programming or scripting language such as, for example, C, C++, Java, assembler, etc.

[0064] Instructions regarding a calibration module (142) may be stored in the memory (140). The 'module' included in the memory (140) refers to a unit that processes a function or operation performed by the processor (130), and may be implemented as software such as instructions, algorithms, data structures, or program code. In one embodiment of the present disclosure, the memory (140) may include a calibration data storage (144) that stores data obtained as a calibration result.

[0065] The processor (130) can perform a calibration operation by executing instructions stored in memory (140) to determine an available frequency range for each of the plurality of speakers (110-1 to 110-n), acquire offset data for adjusting the output volume value of each of the plurality of speakers (110-1 to 110-n) by frequency, and store the available frequency range and offset data. Below, the functions and / or operations performed by the processor (130) by executing instructions or program codes stored in memory (140) will be described in detail.

[0066] The calibration module (142) is composed of instructions for executing a calibration operation that determines an available frequency range for each of the plurality of speakers (110-1 to 110-n), obtains offset data for adjusting the output volume value of each of the plurality of speakers (110-1 to 110-n) for each frequency, and stores the available frequency range and offset data. The processor (130) can perform calibration of the occupant recognition device (100) by executing the instructions of the calibration module (142).

[0067] The processor (130) can obtain the frequency response of a plurality of speakers (110-1 to 110-n) based on the signal level of an input signal received by the microphone (120), and can determine the usable frequency range for each of the plurality of speakers (110-1 to 110-n) by analyzing the characteristics of the frequency response. In one embodiment of the present disclosure, the processor (130) controls the plurality of speakers (110-1 to 110-5) to generate and output an ultrasonic signal in an inaudible frequency band while changing the frequency for each of the plurality of speakers (110-1 to 110-n) through a frequency sweep, and can obtain the response characteristics of the ultrasonic signal by receiving the signal output and reflected by the plurality of speakers (110-1 to 110-n) through the microphone (120). The processor (130) can analyze frequency response characteristics to detect a frequency at which the signal level of a signal input through the microphone (120) drops by a preset value relative to the signal level at the initial frequency. The 'preset value' may be, for example, 3 dB or 6 dB, but is not limited thereto. The processor (130) can determine the ultrasonic band between the initial frequency and the detected frequency as the usable frequency range. Specific embodiments in which the processor (130) determines the usable frequency range for each of the plurality of speakers (110-1 to 110-n) will be described in detail with reference to FIGS. 4 and FIGS. 5.

[0068] The processor (130) obtains offset data for adjusting the output volume of each of the plurality of speakers (110-1 to 110-n) by adjusting the volume value output by each of the plurality of speakers (110-1 to 110-n) by frequency within the available frequency range so that a signal level value greater than or equal to the reference volume is received by the microphone (120). In one embodiment of the present disclosure, the processor (130) can adjust the output volume value of the ultrasonic signal output by each of the plurality of speakers (110-1 to 110-n) through an output volume sweep at a specific frequency within the available frequency range, and can obtain an input signal by receiving the ultrasonic signal through the microphone (120). The processor (130) can identify an output volume value in which the signal level value of the input signal obtained by the microphone (120) is greater than or equal to a preset threshold. The threshold may be preset to, for example, -30dB, but is not limited thereto. The processor (130) can obtain offset data for adjusting the default volume value to the identified output volume value for each of the plurality of speakers (110-1 to 110-n). A specific embodiment of how the processor (130) obtains offset data for the output volume value by frequency will be described in detail with reference to FIG. 6.

[0069] The processor (130) may store calibration data in memory (140) that includes an available frequency range for each of the plurality of speakers (110-1 to 110-n) and offset data for output volume by frequency. In one embodiment of the present disclosure, the processor (130) may determine an available frequency range for each of the plurality of speakers (110-1 to 110-n) and store information regarding the determined available frequency range in memory (140) for each of the plurality of speakers (110-1 to 110-n). The processor (130) may store offset data regarding the output volume of the speakers in memory (140) by frequency.

[0070] In one embodiment of the present disclosure, the processor (130) may store calibration data in a calibration data storage (144) within the memory (140). The calibration data storage (144) may be composed of non-volatile memory. Non-volatile memory refers to a storage medium that stores and maintains information even when power is not supplied, and can use the stored information again when power is supplied. Non-volatile memory may include, for example, at least one of flash memory, hard disk, SSD (Solid State Drive), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), ROM (Read Only Memory), magnetic memory, magnetic disk, and optical disk.

[0071] In FIG. 3, the calibration data storage (144) is depicted as a component included within the memory (140), but the present disclosure is not limited to what is depicted in the drawings. In one embodiment of the present disclosure, the calibration data storage (144) may be configured as a database within the passenger recognition device (100), which is a component separate from the memory (140). However, it is not limited thereto, and in one embodiment of the present disclosure, the calibration data storage (144) may be implemented as a web storage or cloud server that is accessible via a network and performs a storage function. In this case, the passenger recognition device (100) further includes a communication interface (160, see FIG. 15) configured to perform wired or wireless data communication, and can perform data transmission and reception by establishing a communication connection with the web storage or cloud server through the communication interface (160). The processor (130) can transmit calibration data to the web storage or cloud server and store the calibration data in the web storage or cloud server.

[0072] The display (150) is configured to display calibration information of the occupant recognition device (100) under the control of the processor (130). In one embodiment of the present disclosure, the 'calibration information' may include information regarding the progress or completion of the calibration operation of the occupant recognition device (100). For example, the display (150) may display information regarding the progress or completion of each operation of determining the available frequency range, obtaining offset data of the output volume value, and storing the available frequency range and the offset data. For example, the display (150) may display information regarding the date or time when the most recent calibration was performed.

[0073] In one embodiment of the present disclosure, the display (150) may be implemented as a Center Information Display (CID) placed in a vehicle. However, it is not limited thereto, and the display (150) may be composed of at least one of, for example, an instrument cluster display, a Head Up Display (HUD), a navigation device, or a passenger seat display.

[0074] The display (150) may include a screen composed of at least one of, for example, a liquid crystal display, a thin film transistor-liquid crystal display, an organic light-emitting diode display, a flexible display, a 3D display, or an electrophoretic display.

[0075] FIG. 4 is a flowchart illustrating a method for determining a usable frequency range for a plurality of speakers using a passenger recognition device (100) according to one embodiment of the present disclosure.

[0076] Steps S410 to S430 illustrated in FIG. 4 are steps that embody the operation of step S210 of FIG. 2. After the operation of step S430 illustrated in FIG. 4 is performed, step S220 of FIG. 2 may be performed.

[0077] FIG. 5 is a graph illustrating frequency response characteristics (500) to explain the operation of determining an available frequency range by a passenger recognition device (100) according to one embodiment of the present disclosure.

[0078] Hereinafter, with reference to FIGS. 4 and FIGS. 5, the function and / or operation of the passenger recognition device (100) determining the usable frequency range will be described in detail.

[0079] In step S410, the occupant recognition device (100) obtains a frequency response by receiving an ultrasonic signal output by each of a plurality of speakers through a microphone while changing the frequency through a frequency sweep. In one embodiment of the present disclosure, the occupant recognition device (100) can obtain a frequency response by generating and outputting an ultrasonic signal while changing the frequency from a low frequency to a high frequency through each of a plurality of speakers, receiving the ultrasonic signal through a microphone, and obtaining a signal level value of the received ultrasonic signal. The frequency response characteristic (500) illustrated in FIG. 5 is a graph showing the frequency-specific signal level value (510) of an input signal obtained by receiving an ultrasonic signal output by one of a plurality of speakers through a microphone.

[0080] In step S420, the occupant recognition device (100) analyzes the characteristics of the frequency response and detects a second frequency in which an input signal is received having a signal level value that is reduced by a preset value relative to the signal level value of the input signal at the first frequency. Referring together with FIG. 5, the processor (130, see FIG. 3) of the occupant recognition device (100) analyzes the frequency-specific signal level value (510) of the frequency response to identify a signal level value that is reduced by a preset threshold (α dB) relative to the signal level value of the input signal received through the microphone at the initial frequency of the frequency sweep, i.e., the first frequency (f1), and can detect a second frequency (f2) in which the identified signal level value is measured. The threshold (α dB) may be, for example, 3 dB or 6 dB. However, it is not limited thereto.

[0081] The first frequency (f1) may be, for example, 18 kHz. The second frequency (f2), which is the frequency at which the signal level value drops by a preset threshold (α dB), may be measured differently depending on the multiple speakers. For example, in the case of a high-frequency speaker (e.g., a tweeter), the second frequency (f2) may be detected as 28 kHz, in the case of a mid-range speaker (e.g., a mid-range), the second frequency (f2) may be detected as 24 kHz, and in the case of a low-frequency speaker (e.g., a woofer), the second frequency (f2) may be detected as 21 kHz.

[0082] In step S430, the occupant recognition device (100) determines a frequency range between a first frequency and a second frequency as the available frequency range. Referring together with the frequency response characteristics (500) illustrated in FIG. 5, the processor (130) may determine frequencies having a range from the first frequency (f1) to the second frequency (f2) as the available frequency range (520). The available frequency range (520) may be determined differently depending on the output volume band of a plurality of speakers. For example, the available frequency range of a high-frequency reproduction speaker may be determined to be a range from 18 kHz to 28 kHz, the available frequency range of a mid-frequency reproduction speaker may be determined to be a range from 18 kHz to 24 kHz, and the available frequency range of a low-frequency reproduction speaker may be determined to be a frequency range from 18 kHz to 21 kHz. However, the aforementioned available frequency range is merely exemplary, and the available frequency range of the present disclosure is not limited to the aforementioned frequency range.

[0083] FIG. 6 is a flowchart illustrating a method for an occupant recognition device (100) according to one embodiment of the present disclosure to acquire offset data for adjusting the output volume of a speaker.

[0084] Steps S610 to S660 illustrated in FIG. 6 are steps that embody the operation of step S220 of FIG. 2. Step S610 illustrated in FIG. 6 can be performed after the operation of step S210 of FIG. 2 has been performed. After the operation of step S640 illustrated in FIG. 6 has been performed, the operation of step S230 of FIG. 2 can be performed.

[0085] In step S610, the occupant recognition device (100) adjusts the output volume value of the ultrasonic signal output by each of the plurality of speakers according to the frequency. In one embodiment of the present disclosure, the output volume value of the ultrasonic signal output by the speakers can be increased or decreased through an output volume sweep at a specific frequency within a determined usable frequency range for each of the plurality of speakers. The occupant recognition device (100) can receive the ultrasonic signal output by the speakers through a microphone (120) to obtain an input signal.

[0086] In step S620, the occupant recognition device (100) compares the signal level value of the input signal received through the microphone with a reference volume value. The reference volume value refers to a signal level value above a certain level that must be input to the microphone for smooth signal analysis. The reference volume value may be, for example, -30 dB. However, the reference volume value is not limited to -30 dB.

[0087] When the signal level value of the input signal is greater than or equal to the reference volume value of the microphone (step S630), the occupant recognition device (100) identifies an output volume value that satisfies the reference volume value. In one embodiment of the present disclosure, the occupant recognition device (100) can identify an output volume value of a speaker that causes an input signal greater than or equal to the reference volume value to be received by the microphone.

[0088] In step S640, the occupant recognition device (100) obtains offset data for adjusting the default volume value for each of the plurality of speakers to the output volume value identified in step S630. In one embodiment of the present disclosure, the 'offset data' represents the difference between the initial default volume value and the output volume value satisfying the reference volume value identified in step S630 during the output volume sweep of the speakers. That is, the offset data may be data regarding the value to which the output volume value of the speakers must be adjusted to satisfy the reference volume value of the microphone. The occupant recognition device (100) can obtain the offset data by calculating the difference between the output volume value identified in step S630 and the default volume value. The occupant recognition device (100) can obtain the offset data for the output volume value for each frequency.

[0089] If, in step S620, the signal level value of the input signal is less than the reference volume value of the microphone (step S650), the occupant recognition device (100) adds 1 to the counter. The 'counter' refers to the number of times the default volume value is adjusted in the output volume sweep.

[0090] In step S660, the passenger recognition device (100) compares the counter with a threshold (N).

[0091] If the counter is less than the threshold (N), the occupant recognition device (100) can return to step S610 and adjust the output volume value of the ultrasonic signal output by the speaker. If 1 is added to the counter, the volume value output by the speaker can be adjusted (increased or decreased) by a preset value.

[0092] When the counter exceeds the threshold (N), that is, when the signal level value of the input signal does not satisfy the reference volume value of the microphone even though the output volume value has been adjusted beyond a preset number of times (step S670), the occupant recognition device (100) determines that the corresponding frequency is unusable. The occupant recognition device (100) can control the speaker so as not to generate and output an ultrasonic signal of the frequency determined to be unusable when performing an occupant recognition operation in the vehicle.

[0093] FIG. 7 is a flowchart illustrating a method in which a passenger recognition device (100) according to one embodiment of the present disclosure obtains a compensation value (gain) of a signal level value of an input signal based on a recognition result regarding whether a vehicle window is open or closed.

[0094] In step S710, the occupant recognition device (100) recognizes whether the vehicle window is open or closed. In one embodiment of the present disclosure, the occupant recognition device (100) may obtain information regarding the opening or closing of the vehicle window from the vehicle's ECU (electronic control unit). However, it is not limited thereto, and the occupant recognition device (100) according to one embodiment of the present disclosure may further include a sensor and recognize whether the window is open or closed through the sensor.

[0095] In step S720, when the window is recognized as being open, the occupant recognition device (100) measures a change in the signal level value of the input signal received through the microphone due to a change in the reflection path of the ultrasonic signal. In one embodiment of the present disclosure, the occupant recognition device (100) determines the input signal obtained by receiving the reflected signal of the ultrasonic signal through the microphone while the window is closed as a reference value, and measures the change value by calculating the difference between the signal level value of the input signal received through the microphone while the window is open and the reference value.

[0096] In step S730, the occupant recognition device (100) obtains a gain of the signal level value based on the measurement result. In one embodiment of the present disclosure, the occupant recognition device (100) may determine the gain as the change value measured in step S720.

[0097] In step S740, the occupant recognition device (100) stores a compensation value. In one embodiment of the present disclosure, the occupant recognition device (100) may store the compensation value as calibration data in a calibration data storage (144, see FIG. 3).

[0098] The occupant recognition device (100) according to the embodiment illustrated in FIG. 7 can add a stored compensation value to the signal level value of an input signal received through a microphone when recognizing an occupant while the window of the vehicle is open. By adjusting the signal level value of the input signal using the compensation value, the occupant recognition device (100) can recognize an occupant using the same signal level value as when the window is closed, even when the window is open, thereby maintaining a constant accuracy of occupant recognition regardless of changes in the internal environment of the vehicle.

[0099] FIG. 8 is a flowchart illustrating a method for determining an available frequency range when a single ultrasonic signal is output by a plurality of speakers in a passenger recognition device (100) according to one embodiment of the present disclosure.

[0100] Steps S810 to S830 illustrated in FIG. 8 are steps that embody the operation of step S210 of FIG. 2. After the operation of step S830 of FIG. 8 is performed, step S220 of FIG. 2 may be performed.

[0101] FIG. 9 is a diagram illustrating the connection relationship between an amplifier (amp) (910, 920) and speakers (110-1 to 110-9) in a passenger recognition device (100) according to one embodiment of the present disclosure.

[0102] FIG. 10 is a graph illustrating a frequency response characteristic (1000) to explain the operation of determining an available frequency range when a single ultrasonic signal is output by a plurality of speakers in a passenger recognition device according to one embodiment of the present disclosure.

[0103] Hereinafter, with reference to FIG. 8 together with FIG. 9 and FIG. 10, the function and / or operation of the passenger recognition device (100) determining the usable frequency range will be described in detail.

[0104] In step S810, the occupant recognition device (100) obtains the frequency response characteristics of two or more speakers through a frequency sweep when a single ultrasonic signal is simultaneously output by two or more speakers. The occupant recognition device (100) includes a plurality of speakers, and the plurality of speakers can receive a signal in the inaudible frequency band from the output terminal of an amplifier and output an ultrasonic signal. Each of the plurality of speakers is connected to a single output terminal of the amplifier, but is not limited thereto. One or more speakers may be connected to a single output terminal of the amplifier, and the same signal may be simultaneously output through one or more of the plurality of speakers by the single output terminal.

[0105] Referring together with the embodiment illustrated in FIG. 9, the occupant recognition device (100) may include a plurality of speakers (110-1 to 110-9) positioned at different locations within the vehicle (10), and a plurality of amplifiers (910, 920) connected to the plurality of speakers (110-1 to 110-9). The positions, shapes, and number of the plurality of speakers (110-1 to 110-9) and the plurality of amplifiers (910, 920) illustrated in FIG. 9 are exemplary for convenience of explanation and the embodiments of the present disclosure are not limited to those illustrated in the drawings. In FIG. 9, the first amplifier (910) may be connected to the first speaker (110-1) to the third speaker (110-3). For example, the first speaker (110-1) is connected to the second output terminal (912) of the first amplifier (910), the second speaker (110-2) is connected to the first output terminal (911), and the third speaker (110-3) is connected to the third output terminal (913), and can receive ultrasonic signals in the inaudible range from the output terminals. The first speaker (110-1) to the third speaker (110-3) are connected one-to-one (1:1) to each of the output terminals (911, 912, 913) of the first amplifier (910), receive different ultrasonic signals, and can output different ultrasonic signals. The fourth speaker (110-4) to the ninth speaker (110-9) can be connected to the second amplifier (920). For example, the fourth speaker (110-4) and the sixth speaker (110-6) are connected to the second output terminal (922) of the second amplifier (920), and the fifth speaker (110-5) is connected to the first output terminal (921), and can receive ultrasonic signals in the inaudible range from the output terminals.

[0106] In the embodiment illustrated in FIG. 9, the fourth speaker (110-4) and the sixth speaker (110-6) are connected to a single output terminal (e.g., 'second output terminal (922)') of the second amplifier (920) and can receive the same signal. In this case, the fourth speaker (110-4) and the sixth speaker (110-6) output the same ultrasonic signal, and as the same ultrasonic signal is received through a microphone, signal interference may occur. In particular, if the fourth speaker (110-4) and the sixth speaker (110-6) are different types of speakers that output volumes of different bands, signal interference may occur in a specific frequency band. Similarly, in FIG. 9, the seventh speaker (110-7) and the ninth speaker (110-9) are also connected to the fourth output terminal (924) of the second amplifier (920), and accordingly, the same signal can be output simultaneously by the two speakers.

[0107] In the case where two or more speakers are connected to a single output terminal of an amplifier and the same ultrasonic signal is output from two or more speakers, for example, in the case of the fourth speaker (110-4) and the sixth speaker (110-6) of the embodiment shown in FIG. 9, the occupant recognition device (100) can output an ultrasonic signal while changing the frequency through a frequency sweep and obtain frequency response characteristics by receiving the output signal through a microphone. The frequency response characteristic (1000) shown in FIG. 10 is a graph of two signal level values ​​regarding an ultrasonic signal output by two speakers, including a first signal level value (1001) and a second signal level value (1002) according to frequency. For example, if the fourth speaker (110-4) is a high-frequency reproduction speaker (e.g., a tweeter) and the sixth speaker (110-6) is a low-frequency reproduction speaker (e.g., a woofer), in the frequency response characteristic (1000), the first signal level value (1001) represents a signal level value obtained by receiving an ultrasonic signal output by the fourth speaker (110-4) through a microphone, and the second signal level value (1002) represents a signal level value obtained by receiving an ultrasonic signal output by the sixth speaker (110-6) through a microphone.

[0108] Referring again to FIG. 8, in step S820, the occupant recognition device (100) analyzes the frequency response characteristics and detects a frequency in which the difference in the signal level value of the input signal is greater than or equal to a preset threshold. In one embodiment of the present disclosure, the occupant recognition device (100) can analyze the frequency response characteristics to detect the maximum response characteristic difference of the signal level values ​​of a plurality of input signals. The occupant recognition device (100) can measure the difference value of the signal level values ​​between a plurality of input signals and detect a frequency in which the measured difference value is greater than or equal to a preset threshold. Referring together to the frequency response characteristics (1000) illustrated in FIG. 10, the processor (130, see FIG. 3) of the occupant recognition device (100) calculates the difference value between a first signal level value (1001) and a second signal level value (1002), compares the calculated difference value with a preset threshold (βdB), and, according to the comparison result, detects a frequency (f) in which the difference value exceeds the threshold (βdB). k ) can be detected. The threshold (βdB) can be predetermined, for example, to 20dB, but is not limited thereto.

[0109] In step S830, the occupant recognition device (100) determines the usable frequency range of one of two or more speakers based on the detected frequency. In one embodiment of the present disclosure, the occupant recognition device (100) may select only one of two or more speakers in a frequency band greater than the detected frequency to minimize signal interference between ultrasonic signals output by two or more speakers, and determine the usable frequency range of the selected speaker. Referring together with FIG. 10, the processor (130) of the occupant recognition device (100) detects the frequency (f kIn a frequency band greater than ), a speaker that outputs an ultrasonic signal having a first signal level value (1001) (e.g., the 'fourth speaker (110-4)' of FIG. 9) is selected, and only the selected speaker can be used to recognize occupants in the vehicle. The processor (130) detects the frequency range of the selected speaker as the available frequency range (f k It can be determined as a frequency band greater than ). Frequency (f k ) can be, for example, 22kHz, but is not limited thereto.

[0110] A passenger recognition device (100) according to the embodiment illustrated in FIGS. 8 to 10 has two or more speakers connected to a single output terminal, and when the same ultrasonic signal is output by two or more speakers, analyzes the frequency response characteristics (1000) and determines a frequency (f) in which the difference value between signal level values ​​(1001, 1002) is greater than or equal to a preset threshold (βdB). k Detects ) and the usable frequency range of any one of two or more speakers is the detected frequency (f k It can be determined to be a frequency band greater than ). Through this, the occupant recognition device (100) according to one embodiment of the present disclosure provides a technical effect of minimizing signal interference when the same ultrasonic signal is output by two or more speakers and improving the accuracy of occupant recognition.

[0111] FIG. 11 is a diagram illustrating the operation of a passenger recognition device (100) according to one embodiment of the present disclosure displaying calibration information.

[0112] Referring to FIG. 11, the occupant recognition device (100) can display calibration information through a display (150) inside the vehicle. In one embodiment of the present disclosure, the 'calibration information' may include information regarding the progress or completion of a calibration operation of the occupant recognition device (100), which includes determining an available frequency range, acquiring offset data, and storing the available frequency range and offset data. In one embodiment of the present disclosure, the display (150) is implemented as a center information display (CID) inside the vehicle, and the occupant recognition device (100) can display calibration information through the CID.

[0113] In the embodiment illustrated in FIG. 11, the occupant recognition device (100) may display a notification message (1100) indicating calibration information on the CID. The notification message (1100) may consist of text indicating, for example, "Calibration of the occupant recognition system has been completed." However, the calibration information is not limited to the notification message (1100) illustrated in FIG. 11. The occupant recognition device (100) may also display calibration information through at least one of, for example, an instrument cluster display, a Head-Up Display (HUD), a navigation device, or a passenger seat display. In one embodiment of the present disclosure, the occupant recognition device (100) may display information regarding the date or time when the most recent calibration was performed on the CID.

[0114] Although an embodiment in FIG. 11 is illustrated in which calibration information is displayed through a display (150), the embodiment of the present disclosure is not limited to displaying a notification message (1100) in the form of text. In one embodiment of the present disclosure, the occupant recognition device (100) may identify at least one speaker among a plurality of speakers for which the acquisition and storage of available frequency range and offset data is completed, that is, for which the calibration operation is completed, and may output an acoustic signal indicating the completion of calibration through the identified at least one speaker.

[0115] FIG. 12 is a diagram illustrating the operation of a passenger recognition device (100) according to one embodiment of the present disclosure displaying calibration information through an external device (200).

[0116] Referring to FIG. 12, the passenger recognition device (100) can transmit calibration information to an external device (200). Since the 'calibration information' is the same as that described in FIG. 11, a redundant description is omitted. The 'external device' refers to a device or device separate from the vehicle, not an electronic device mounted or installed in the vehicle. In one embodiment of the present disclosure, the external device may be a mobile device such as a smartphone. However, it is not limited thereto, and the external device may be, for example, a tablet PC, a laptop computer, a digital camera, an e-book terminal, a digital broadcasting terminal, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a navigation system, or an MP3 player. For example, the external device may be implemented as a wearable device such as a smart watch, an augmented reality device (e.g., AR glasses), a head-mounted device (HMD), or a body-attached device (e.g., a skin pad).

[0117] In one embodiment of the present disclosure, the passenger recognition device (100) may further include a communication interface configured to perform data transmission and reception with an external device via a wireless communication network. The communication interface may include, for example, a hardware communication device that performs short-range wireless data communication such as Wi-Fi, Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), WiFi-Direct, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), or Bluetooth™. However, it is not limited thereto, and the communication interface may include a hardware communication device that performs data communication using a mobile communication network such as CDMA, WCDMA, 3G, 4G LTE, 5G Sub 6, 5G NR, or millimeter wave (mmWave).

[0118] The external device (200) can display calibration information received from the passenger recognition device (100). In the embodiment illustrated in FIG. 12, the external device (200) can display a notification message (1200) indicating calibration information on the display. The notification message (1200) may consist of text indicating, for example, "Calibration of the passenger recognition system has been completed." However, the calibration information is not limited to the notification message (1200) illustrated in FIG. 12. The external device (200) may also output a voice message through a speaker indicating the progress or completion of the calibration.

[0119] The occupant recognition device (100) according to the embodiment illustrated in FIGS. 11 and 12 provides a notification message (1100, 1200) to the user regarding the progress or completion of the calibration operation of the occupant recognition device (100) in the vehicle, thereby enabling the user to easily determine whether the calibration is currently in progress or has been completed, and thereby improving user convenience.

[0120] FIG. 13 is a diagram illustrating an operation performed by an occupant recognition device (100) according to one embodiment of the present disclosure using artificial intelligence technology.

[0121] Specifically, at least one of the following operations performed by the passenger recognition device (100) is: i) determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of the multiple speakers; ii) obtaining offset data for adjusting the output volume of each of the multiple speakers by adjusting the volume value output by each of the multiple speakers for each frequency within the available frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by the microphone; and iii) storing offset data for the available frequency range and the output volume for each of the multiple speakers for each frequency, can be performed using artificial intelligence (AI) technology that performs calculations through a neural network.

[0122] Artificial intelligence technology (hereinafter referred to as 'AI technology') is a technology that obtains desired results by processing input data, such as analyzing and / or classifying it, based on computations through neural networks.

[0123] Such AI technology can be implemented by utilizing algorithms. Here, an algorithm or a set of algorithms for implementing AI technology is referred to as a neural network. A neural network receives input data, performs the aforementioned operations for analysis and / or classification, and can output result data. In order for a neural network to accurately output result data corresponding to the input data, it is necessary to train the neural network. Here, 'training' can refer to training the neural network so that it can independently discover or learn methods for analyzing input data, methods for classifying input data, and / or methods for extracting features necessary for generating result data from input data. Specifically, through the training process, the neural network can optimize its internal weight values ​​by training on training data (e.g., multiple different images). Then, by processing the input data through a neural network with optimized weight values, it outputs the desired result.

[0124] A neural network can be classified as a deep neural network when the number of hidden layers, which are internal layers that perform computations, is multiple—that is, when the depth of the neural network performing computations increases. Neural networks include, for example, Convolutional Neural Networks, Recurrent Neural Networks, Restricted Boltzmann Machines, Deep Belief Networks, Bidirectional Recurrent Deep Neural Networks, and Deep Q-Networks, but are not limited to the examples mentioned above. Additionally, neural networks can be subdivided. For example, a Convolutional Neural Network can be subdivided into a Deep Convolutional Neural Network (D-CNN) or a Capsnet neural network (not shown).

[0125] "AI model" may refer to a neural network comprising at least one layer that operates to receive input data and output a desired result. Additionally, "AI model" may refer to an algorithm that performs computations through a neural network to output a desired result, a set of multiple algorithms, a processor for executing an algorithm (or set of algorithms), software for executing an algorithm (or set of algorithms), or hardware for executing an algorithm (or set of algorithms).

[0126] At least one of the above-described operations—i) determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of the multiple speakers; ii) obtaining offset data for adjusting the output volume of each of the multiple speakers by adjusting the volume value output by each of the multiple speakers for each frequency within the available frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by a microphone; and iii) storing offset data for the available frequency range and the output volume for each of the multiple speakers—can be performed based on an AI model.

[0127] Referring to FIG. 13, a neural network (1300) can be trained by receiving training data. Then, the trained neural network (1300) receives input data (1310) through an input terminal (1320), and the input terminal (1320), hidden layer (1330), and output terminal (1340) can perform operations to output output data (1350) by analyzing the input data (1310) and data transmitted from the previous layer. Although FIG. 13 shows the hidden layer (1330) as a single layer, this is merely an example, and the hidden layer (1330) may consist of multiple layers.

[0128] In the disclosed embodiment, the neural network (1300) can be trained to i) analyze frequency response characteristics to detect a second frequency in which an input signal is received having a signal level value that is lowered by a preset value relative to the signal level value of an input signal received by a microphone at a first frequency, which is an initial frequency, and ii) determine a frequency range between the first frequency and the second frequency as a usable frequency range.

[0129] In the disclosed embodiment, the neural network (1300) can be trained to i) identify an output volume value in which the signal level value of an input signal obtained through a microphone is greater than or equal to a preset threshold, and ii) acquire offset data for adjusting a default volume value for each of the plurality of speakers to the identified output volume value.

[0130] In the disclosed embodiment, data or program code related to a neural network (1300) that performs at least one of the following operations is stored in a memory (140, see FIG. 3): i) determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of the aforementioned multiple speakers; ii) obtaining offset data for adjusting the output volume of each of the multiple speakers so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by a microphone by adjusting the volume value output by each of the multiple speakers for each frequency; and iii) storing offset data regarding the available frequency range and the output volume for each of the multiple speakers. Learning using the neural network (1300) can be performed by a processor (130, see FIG. 3). In this case, the processor (130) may include an artificial intelligence dedicated processor such as a Neural Processing Unit (NPU).

[0131] In the disclosed embodiment, data or program code related to a neural network (1300) that performs at least one of the following operations is stored in a memory (140): i) determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of the aforementioned multiple speakers; ii) obtaining offset data for adjusting the output volume of each of the multiple speakers so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by a microphone by adjusting the volume value output by each of the multiple speakers for each frequency; and iii) storing offset data regarding the available frequency range and the output volume for each of the multiple speakers. Learning using the neural network (1300) can be performed by a processor (130).

[0132] However, the neural network (1300) that performs at least one of the following operations may be implemented in a separate device (not shown) or processor (not shown) distinct from the passenger recognition device (100).

[0133] The computation through the aforementioned neural network (1300) may be performed by a server (300, see FIG. 14 and FIG. 15) capable of communicating with a passenger recognition device (100) according to one embodiment via a wireless communication network. Communication between the passenger recognition device (100) and the server (300) is described with reference to FIG. 14 and FIG. 15.

[0134] FIG. 14 is a drawing illustrating a passenger recognition device (100) according to a disclosed embodiment that operates in conjunction with a server (300).

[0135] FIG. 15 is a drawing for explaining FIG. 14 in detail.

[0136] The passenger recognition device (100) may include a speaker (110), a microphone (120), a processor (130), a memory (140), and a display (150). Referring to FIG. 15, the passenger recognition device (100) may further include a communication interface (160). Since the speaker (110), microphone (120), processor (130), memory (140), and display (150) shown in FIG. 15 are identical to the speaker (110, see FIG. 3), microphone (120, see FIG. 3), processor (130, see FIG. 3), memory (140, see FIG. 3), and display (150, see FIG. 3) shown and described in FIG. 3, redundant descriptions are omitted.

[0137] The server (300) can transmit and receive data with the passenger recognition device (100) and process data through the communication network (400).

[0138] Referring to FIG. 14 and FIG. 15 together, the server (300) may include a communication interface (310) that communicates with a passenger recognition device (100), a processor (320) that performs at least one instruction, and a memory (330).

[0139] The server (300) may train an AI model and store the trained AI model. The server (300) may use the trained AI model to perform at least one of the following operations: i) determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of the multiple speakers; ii) obtaining offset data for adjusting the output volume of each of the multiple speakers by adjusting the volume value output by each of the multiple speakers for each frequency within the available frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by the microphone; and iii) storing offset data regarding the available frequency range and the output volume for each of the multiple speakers.

[0140] Generally, the passenger recognition device (100) may have limited storage capacity of memory (140, see FIG. 3), computational processing speed of processor (130, see FIG. 3), and ability to collect training data sets compared to the server (300). Therefore, operations requiring the storage of large amounts of data and large amounts of computation can be performed on the server (300), and then the necessary data and / or AI models can be transmitted to the passenger recognition device (100) through the communication network (400). The passenger recognition device (100) can perform necessary operations quickly and easily by receiving and utilizing the necessary data and / or AI models through the server (300), even without a processor having large amounts of memory and fast computational capabilities.

[0141] In the disclosed embodiment, the server (300) may include the neural network (1300) described in FIG. 13.

[0142] In FIG. 15, the components of the server (300) will be described in detail. Referring to FIG. 15, the server (300) may include a communication interface (310), a processor (320), and a memory (330).

[0143] The communication interface (310) communicates with an external device through a wireless communication network (400). Here, the external device (not shown) may include a server capable of performing at least one of the operations required by the passenger recognition device (100) or transmitting data required by the passenger recognition device (100).

[0144] The communication interface (310) includes at least one communication module, such as a short-range communication module, a wired communication module, a mobile communication module, a broadcast reception module, etc. Here, at least one communication module refers to a communication module capable of transmitting and receiving data through a network that follows a communication standard such as a tuner that performs broadcast reception, Bluetooth, Wi-Fi, Wibro (Wireless broadband), WiMAX (World Interoperability for Microwave Access), CDMA, WCDMA, the Internet, 3G, 4G, 5G and / or a communication method using millimeter wave (mmWave).

[0145] A mobile communication module included in the communication interface (310) can communicate with another device located at a distance (e.g., a passenger recognition device (100)) through a communication network according to communication standards such as 3G, 4G (LTE), and / or 5G. In one embodiment of the present disclosure, the passenger recognition device (100) further includes a communication interface (160), and the communication interface (310) of the server (300) can transmit and receive data via wired or wireless connection with the communication interface (160) of the passenger recognition device (100).

[0146] The processor (320) controls the overall operation of the server (300). For example, the processor (320) can perform required operations by executing at least one of the instructions and programs of the server (300).

[0147] The memory (330) can store at least one of at least one instruction, program, and data required for the server (300) to perform a predetermined operation. Additionally, the memory (330) can store data required for the server (300) to perform operations according to a neural network.

[0148] In the disclosed embodiment, the server (300) may store the neural network (1300) described in FIG. 13. The neural network (1300) may be stored in at least one of the processor (320) and memory (330). The neural network (1300) included in the server (300) may be a trained neural network.

[0149] Additionally, the server (300) can transmit the trained neural network (1300, see FIG. 13) to the communication interface (160) of the passenger recognition device (100) through the communication interface (310). The passenger recognition device (100) can acquire and store the trained neural network (1300) and acquire the desired output data through the neural network (1300).

[0150] The present disclosure provides a method for performing calibration of a passenger recognition device (100) mounted in a vehicle (10). A calibration method of a passenger recognition device (100) according to one embodiment of the present disclosure may include a step (S210) of determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of a plurality of speakers (110). A calibration method of a passenger recognition device (100) according to one embodiment of the present disclosure may include a step (S220) of obtaining offset data for adjusting the output volume of each of the plurality of speakers (110) by adjusting the volume value output by each of the plurality of speakers (110) for each frequency within the available frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by a microphone (120). A calibration method for an occupant recognition device (100) according to one embodiment of the present disclosure may include a step (S230) of storing offset data for an available frequency range and output volume per frequency for each of a plurality of speakers (110).

[0151] In one embodiment of the present disclosure, the step of determining the usable frequency range (S210) may include: a step of obtaining a frequency response by receiving an ultrasonic signal output by each of a plurality of speakers (110) through a microphone (120) while changing the frequency through a frequency sweep (S410); a step of detecting a second frequency in which an input signal having a signal level value lowered by a preset value relative to the signal level value of an input signal received by the microphone (120) at a first frequency, which is an initial frequency, is received by analyzing the characteristics of the frequency response (S420); and a step of determining the frequency range between the first frequency and the second frequency as the usable frequency range (S430).

[0152] In one embodiment of the present disclosure, the step of acquiring offset data (S220) may include: a step (S610) of adjusting the output volume value of an ultrasonic signal output by each of a plurality of speakers (110) according to frequency; and a step (S630) of receiving an ultrasonic signal through a microphone (120) and identifying an output volume value such that the signal level value of the acquired input signal is greater than or equal to a preset threshold. The step of acquiring offset data (S220) may include a step (S640) of acquiring offset data for adjusting the default volume value for each of the plurality of speakers (110) to the identified output volume value.

[0153] In one embodiment of the present disclosure, the calibration method of the occupant recognition device (100) may further include the step of excluding from the occupant recognition device any speaker among a plurality of speakers (110) whose signal level value of an input signal received through a microphone (120) is below a threshold value even when the output volume value is adjusted.

[0154] In one embodiment of the present disclosure, the calibration method of the occupant recognition device (100) may further include: a step of recognizing whether the window of the vehicle is open or closed (S710); a step of measuring a change in the signal level value of an input signal received through a microphone (120) by a change in the reflection path of an ultrasonic signal when the window is recognized as being open according to the recognition result (S720); a step of obtaining a compensation value (gain) of the signal level value based on the measurement result (S730); and a step of storing the compensation value (S740).

[0155] In one embodiment of the present disclosure, the step of determining the usable frequency range (S210) may include: a step of obtaining the frequency response characteristics of the two or more speakers through a frequency sweep when one ultrasonic signal is simultaneously output by two or more speakers (S810); a step of detecting a frequency in which the difference in the signal level value of the input signal is greater than or equal to a preset threshold by analyzing the frequency response characteristics of the two or more speakers (S820); and a step of determining the usable frequency range of one of the two or more speakers based on the detected frequency (S830).

[0156] In one embodiment of the present disclosure, the calibration method of the occupant recognition device (100) may further include the step of displaying calibration information on a center information display (CID) in a vehicle, the calibration information including information regarding the progress or completion of the calibration operation of the occupant recognition device (100), which includes determining an available frequency range, acquiring offset data, and storing the available frequency range and offset data.

[0157] In one embodiment of the present disclosure, the calibration method of the occupant recognition device (100) may further include the step of transmitting calibration information to an external device, the calibration information including information regarding the progress or completion of the calibration operation of the occupant recognition device (100), which includes determining an available frequency range, acquiring offset data, and storing the available frequency range and offset data. The calibration information may be displayed through a display of the external device.

[0158] In one embodiment of the present disclosure, the calibration method of the occupant recognition device (100) may further include the step of identifying at least one speaker among a plurality of speakers (110) for which the acquisition and storage of available frequency range and offset data is completed; and the step of outputting an acoustic signal indicating the completion of calibration through the identified at least one speaker.

[0159] The present disclosure provides a passenger recognition device (100) mounted in a vehicle. A passenger recognition device (100) according to one embodiment of the present disclosure may include a plurality of speakers (110) that output an ultrasonic signal in an inaudible frequency band; a microphone (120) that receives the ultrasonic signal; a memory (140) that stores one or more instructions; and at least one processor (130) that includes a processing circuit. As the one or more instructions are executed individually or collectively by the at least one processor (130), the passenger recognition device (100) can determine an available frequency range for each of the plurality of speakers (110) by obtaining frequency response characteristics for each of the plurality of speakers (110) through a frequency sweep. As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can obtain offset data for adjusting the output volume of each of the plurality of speakers (110) by adjusting the volume value output by each of the plurality of speakers (110) by frequency within the available frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by the microphone (120). As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can store offset data regarding the available frequency range and the output volume by frequency for each of the plurality of speakers (110) in the storage space of the memory (140).

[0160] In one embodiment of the present disclosure, as one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can obtain a frequency response by receiving an ultrasonic signal output by each of a plurality of speakers (110) through a microphone (120) while changing the frequency through a frequency sweep. As one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can analyze the characteristics of the frequency response to detect a second frequency in which an input signal having a signal level value lowered by a preset value relative to the signal level value of the input signal received by the microphone (120) at a first frequency, which is an initial frequency, and determine the frequency range between the first frequency and the second frequency as a usable frequency range.

[0161] In one embodiment of the present disclosure, as the one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can adjust the output volume value of an ultrasonic signal output by each of the plurality of speakers (110) according to frequency, identify an output volume value in which the signal level value of the input signal obtained by receiving the ultrasonic signal through the microphone (120) is greater than or equal to a preset threshold, and obtain offset data for adjusting the default volume value for each of the plurality of speakers (110) to the identified output volume value.

[0162] In one embodiment of the present disclosure, as the one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can recognize a speaker among a plurality of speakers (110) for which the signal level value of an input signal received through a microphone (120) is below a threshold value even when the output volume value is adjusted. As the one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can disable the recognized speaker during the operation of the occupant recognition device (100).

[0163] In one embodiment of the present disclosure, as one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) recognizes whether the window of the vehicle is open or closed, and if the window is recognized as being open according to the recognition result, measures the change in the signal level value of the input signal received through the microphone (120) by the change in the reflection path of the ultrasonic signal, obtains a gain of the signal level value based on the measurement result, and can store the gain value in memory (140).

[0164] In one embodiment of the present disclosure, as the one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can obtain the frequency response characteristics of two or more speakers through a frequency sweep when one ultrasonic signal is simultaneously output by two or more speakers. As the one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can analyze the frequency response characteristics of two or more speakers to detect a frequency at which the difference in the signal level value of the input signal is greater than or equal to a preset threshold, and determine the usable frequency range of one of the two or more speakers based on the detected frequency.

[0165] In one embodiment of the present disclosure, the occupant recognition device (100) may further include a display (150). As one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) may display calibration information through the display (150), including information regarding the progress or completion of a calibration operation, which includes determining an available frequency range, acquiring offset data, and storing the available frequency range and offset data.

[0166] In one embodiment of the present disclosure, the occupant recognition device (100) may further include a communication interface (160) configured to perform data transmission and reception with an external device (200) via a wireless communication network. As one or more of the instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) may transmit calibration information to the external device (200) via the communication interface (160), the calibration information including information regarding the progress or completion of a calibration operation of the occupant recognition device (100), which includes determining an available frequency range, acquiring offset data, and storing the available frequency range and offset data.

[0167] In one embodiment of the present disclosure, the calibration information may be displayed through a display of an external device (200).

[0168] In one embodiment of the present disclosure, as the one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can identify at least one speaker among a plurality of speakers (110) for which the acquisition and storage of available frequency range and offset data is completed. As the one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) can output an acoustic signal indicating the completion of calibration through the identified at least one speaker.

[0169] The present disclosure provides a computer program product comprising a computer-readable storage medium. The storage medium may include instructions readable by a passenger recognition device (100) for recognizing a passenger in a vehicle (10) to perform the following operations: determining a usable frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of a plurality of speakers (110); obtaining offset data for adjusting the output volume of each of the plurality of speakers (110) by adjusting the volume value output by each of the plurality of speakers (110) by frequency within the usable frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by a microphone (120); and storing offset data regarding the usable frequency range and the output volume by frequency for each of the plurality of speakers (110).

[0170] The program executed by the occupant recognition device (100) described herein may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. The program may be executed by any system capable of executing computer-readable instructions.

[0171] Software may include a computer program, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively.

[0172] Software can be implemented as a computer program containing instructions stored on a computer-readable storage medium. Examples of computer-readable recording media include magnetic storage media (e.g., ROM (read-only memory), RAM (random-access memory), floppy disks, hard disks, etc.) and optical reading media (e.g., CD-ROMs, DVDs (Digital Versatile Discs)). Computer-readable recording media can be distributed across networked computer systems, allowing computer-readable code to be stored and executed in a distributed manner. The medium is readable by a computer, stored in memory, and can be executed by a processor.

[0173] Computer-readable storage media may be provided in the form of non-transitory storage media. Here, 'non-transitory' means only that the storage medium does not contain a signal and is tangible, and does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium. For example, a 'non-transitory storage medium' may include a buffer in which data is stored temporarily.

[0174] In addition, the program according to the embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product.

[0175] A computer program product may include a software program and a computer-readable storage medium on which the software program is stored. For example, a computer program product may include a product in the form of a software program (e.g., a downloadable application) that is distributed electronically through a manufacturer of an electronic device or an electronic market (e.g., Samsung Galaxy Store™, Google Play Store™). For electronic distribution, at least a portion of the software program may be stored on a storage medium or temporarily created. In this case, the storage medium may be a cloud server of the manufacturer of the vehicle (10), a server of the manufacturer of the occupant recognition device (100), a server of an electronic market, or a storage medium of a relay server that temporarily stores the software program.

[0176] A computer program product may include a storage medium of the server (300) or a storage medium of another electronic device in a system composed of a passenger recognition device (100), a server (300, see FIG. 14 and FIG. 15), and another electronic device. Alternatively, if there is a third device (e.g., a mobile device such as a smartphone) that is connected to the passenger recognition device (100) in communication, the computer program product may include a storage medium of the third device. Alternatively, the computer program product may include a software program itself that is transmitted from the passenger recognition device (100) to another electronic device or the third device, or transmitted from the third device to the passenger recognition device (100).

[0177] In this case, one of the passenger recognition device (100), other electronic device, and third device (e.g., a mobile device such as a smartphone) may execute a computer program product to perform the method according to the disclosed embodiments. Alternatively, two or more of the passenger recognition device (100), other electronic device, and third device may execute a computer program product to perform the method according to the disclosed embodiments in a distributed manner.

[0178] For example, the passenger recognition device (100) can execute a computer program product stored in memory (140, see FIG. 3) to control another electronic device that is communicationally connected to the passenger recognition device (100) to perform a method according to the disclosed embodiments.

[0179] As another example, a third device may execute a computer program product to control an electronic device connected to the third device in communication to perform the method according to the disclosed embodiment.

[0180] When the third device executes a computer program product, the third device may download the computer program product from the passenger recognition device (100) and execute the downloaded computer program product. Alternatively, the third device may execute a computer program product provided in a pre-loaded state to perform the method according to the disclosed embodiments.

[0181] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, appropriate results can be achieved even if the described techniques are performed in a different order than described, and / or components such as the described computer system or module are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

Claims

1. A method for a occupant recognition device (100) mounted in a vehicle to perform calibration, A step (S210) of determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of the multiple speakers (110); A step (S220) of obtaining offset data for adjusting the output volume of each of the plurality of speakers (110) by adjusting the volume value output by each of the plurality of speakers (110) by frequency within the above-mentioned usable frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by the microphone (120); and A step (S230) of storing offset data for the available frequency range and the frequency-specific output volume for each of the plurality of speakers (110); A method including 2. In Paragraph 1, The step (S210) of determining the above-mentioned available frequency range is, A step (S410) of obtaining the frequency response by receiving the ultrasonic signal output by each of the plurality of speakers (110) through the microphone (120) while changing the frequency through a frequency sweep; A step (S420) of analyzing the characteristics of the above frequency response to detect a second frequency in which an input signal is received having a signal level value that is lowered by a preset value compared to the signal level value of the input signal received by the microphone (120) at the first frequency, which is the initial frequency; and A step (S430) of determining the frequency range between the first frequency and the second frequency as the available frequency range; A method including 3. In Paragraph 1 or 2, The step of acquiring the above offset data (S220) is, A step (S610) of adjusting the output volume value of the ultrasonic signal output by each of the plurality of speakers (110) according to the frequency; A step (S630) of identifying an output volume value in which the signal level value of the input signal obtained by receiving the ultrasonic signal through the microphone (120) is greater than or equal to a preset threshold; and A step (S640) of obtaining offset data for adjusting the default volume value to the identified output volume value for each of the plurality of speakers (110); A method including 4. In any one of paragraphs 1 to 3, The step (S210) of determining the above-mentioned available frequency range is, When a single ultrasonic signal is simultaneously output by two or more speakers, a step (S810) of obtaining the frequency response characteristics of the two or more speakers through a frequency sweep; A step (S820) of analyzing the frequency response characteristics of the two or more speakers to detect a frequency in which the difference in signal level values ​​of the input signal is greater than or equal to a preset threshold; and A step (S830) of determining the usable frequency range of any one of the two or more speakers based on the detected frequency; A method including 5. In any one of paragraphs 1 through 4, A step of displaying calibration information on a center information display (CID) in the vehicle, the calibration information including information regarding the progress or completion of a calibration operation of the occupant recognition device (100), which includes determining the available frequency range, acquiring the offset data, and storing the available frequency range and the offset data; A method that further includes.

6. In any one of paragraphs 1 through 4, A step of transmitting calibration information to an external device, the calibration information including information regarding the progress or completion of a calibration operation of the occupant recognition device (100), which includes determining the available frequency range, acquiring the offset data, and storing the available frequency range and the offset data; Includes more, A method in which the above calibration information is displayed through the display of the external device.

7. In any one of paragraphs 1 through 6, A step of identifying at least one speaker among the plurality of speakers (110) for which the acquisition and storage of the available frequency range and offset data is completed; and A step of outputting an acoustic signal indicating the completion of calibration through at least one identified speaker; A method that further includes.

8. In a passenger recognition device (100) installed in a vehicle, A plurality of speakers (110) that output ultrasonic signals in the inaudible frequency band; A microphone (120) that receives the above ultrasonic signal; Memory (140) for storing one or more instructions; and At least one processor (130) including a processing circuit; Includes, As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) is, By obtaining frequency response characteristics for each of the plurality of speakers (110) through a frequency sweep, a usable frequency range for each of the plurality of speakers (110) is determined, and Offset data is obtained to adjust the output volume of each of the plurality of speakers (110) by adjusting the volume value output by each of the plurality of speakers (110) according to frequency within the above usable frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by the microphone (120). A passenger recognition device (100) that stores offset data for the available frequency range and the frequency-specific output volume for each of the plurality of speakers (110) in the storage space of the memory (140).

9. In Paragraph 8, As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) is, The frequency response is obtained by receiving the ultrasonic signal output by each of the plurality of speakers (110) through the microphone (120) while changing the frequency through a frequency sweep, and By analyzing the characteristics of the above frequency response, a second frequency is detected in which an input signal is received having a signal level value that is lowered by a preset value compared to the signal level value of the input signal received by the microphone (120) at the first frequency, which is the initial frequency. A passenger recognition device (100) that determines a frequency range between the first frequency and the second frequency as a usable frequency range.

10. In Paragraph 8 or 9, As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) is, The output volume value of the ultrasonic signal output by each of the plurality of speakers (110) is adjusted according to the frequency, and Identifying an output volume value in which the signal level value of the input signal obtained by receiving the ultrasonic signal through the microphone (120) is greater than or equal to a preset threshold, and A passenger recognition device (100) for acquiring offset data to adjust the default volume value to the identified output volume value for each of the plurality of speakers (110).

11. In any one of paragraphs 8 through 10, As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) is, When a single ultrasonic signal is simultaneously output by two or more speakers, the frequency response characteristics of the two or more speakers are obtained through a frequency sweep, and By analyzing the frequency response characteristics of the two or more speakers mentioned above, a frequency is detected in which the difference in signal level values ​​of the input signal is greater than or equal to a preset threshold, and A passenger recognition device (100) that determines the usable frequency range of any one of the two or more speakers based on the detected frequency.

12. In any one of paragraphs 8 through 11, Display (150); Includes more, As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) is, A passenger recognition device (100) that displays calibration information through the display (150), the calibration information including information regarding the progress or completion of a calibration operation of the passenger recognition device (100), which includes determining the available frequency range, acquiring the offset data, and storing the available frequency range and the offset data.

13. In any one of paragraphs 8 through 12, A communication interface (160) configured to perform data transmission and reception with an external device (200) via a wireless communication network; Includes more, As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) is, Calibration information including information regarding the progress or completion of a calibration operation of the occupant recognition device (100), which includes determining the available frequency range, acquiring the offset data, and storing the available frequency range and the offset data, is transmitted to the external device (200) through the communication interface (160). The above calibration information is displayed through the display of the external device (200), and the occupant recognition device.

14. In any one of paragraphs 8 through 13, As the above one or more instructions are executed individually or collectively by the at least one processor (130), the occupant recognition device (100) is, Identify at least one speaker among the plurality of speakers (110) for which the acquisition and storage of the usable frequency range and offset data is completed, and A passenger recognition device (100) that outputs an acoustic signal indicating completion of calibration through at least one identified speaker.

15. In a computer program product comprising a computer-readable storage medium, The above storage medium is, Operation of determining an available frequency range by obtaining frequency response characteristics regarding an ultrasonic signal in an inaudible frequency band through a frequency sweep for each of the plurality of speakers (110); The operation of obtaining offset data for adjusting the output volume of each of the plurality of speakers (110) by adjusting the volume value output by each of the plurality of speakers (110) according to frequency within the above usable frequency range so that an ultrasonic signal having a signal level value greater than or equal to a reference volume is received by the microphone (120); and An operation of storing offset data for the available frequency range and the frequency-specific output volume for each of the plurality of speakers (110); A computer program product comprising instructions executed by said electronic device (100) to perform the electronic device (100) mounted on the vehicle.

Images