Vehicle and control method thereof

Abstract

The present invention relates to a vehicle and a control method thereof. The vehicle selects various sound sources based on information received from a navigation system and outputs a driving sound. A database stores sound sources classified into a first emotion and a second emotion. A controller outputs a landmark name based on a route guidance text and outputs a first emotion ratio and a second emotion ratio corresponding to the landmark name. The controller selects a first sound source from among the sound sources classified into the first emotion based on the first emotion ratio, selects a second sound source from among the sound sources classified into the second emotion based on the second emotion ratio, and determines a first play period and a second play period based on the first emotion ratio and the second emotion ratio. The controller outputs a first sound generated based on the first sound source during the first play period and outputs a second sound generated based on the second sound source during the second play period.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Korean Patent Application No. 10-2020-0077390 filed on Jun. 24, 2020, which is hereby incorporated by reference in its entirety for all purposes. Technical Field

[0003] The present invention relates to a vehicle and a control method thereof for changing driving sound based on data received from a navigation system. Background Art

[0004] In modern society, cars are the most commonly used form of transportation, and their numbers are increasing. In the past, they existed solely as a means of transportation, but in modern society, vehicles are widely used as tools for self-expression and driving pleasure, not just for transportation. Accordingly, many people enjoy the thrill of speed, as seen in motorcycles and racing cars. Those who enjoy speed experience a thrill not only from the speed of their vehicles, but also from the sounds and vibrations generated by their engines. Consequently, some drivers are adapting their engines to achieve the desired driving sound.

[0005] Specifically, for electric vehicles, since there is no operating sound or vibration sound generated by the vehicle engine, artificial driving sounds are output through speakers. However, since the driving sounds provided to the vehicle are pre-designed by the manufacturer, it is difficult to meet the needs of drivers. Summary of the Invention

[0006] A vehicle and a control method thereof are provided, the vehicle being configured to select various sound sources based on information received from a navigation system and output driving sounds.

[0007] According to one aspect of the present invention, a vehicle may include: a database, a speaker, and a controller, wherein the database is configured to store multiple sound sources classified as a first emotion and multiple sound sources classified as a second emotion; the controller is configured to output a landmark name based on a route guidance text included in driving route information calculated by a navigation system; output a first emotion ratio and a second emotion ratio corresponding to the landmark name based on the landmark name; select a first sound source from multiple sound sources classified as the first emotion based on the first emotion ratio; select a second sound source from multiple sound sources classified as the second emotion based on the second emotion ratio; determine a first playback period and a second playback period based on the first emotion ratio and the second emotion ratio; output a first sound generated based on the first sound source during the first playback period; and output a second sound generated based on the second sound source during the second playback period.

[0008] The controller may be configured to use natural language processing (NLP) to output landmark names included in the route guidance text. The controller may be configured to use the landmark names as input data for a long short-term memory (LSTM) network to output a first sentiment ratio and a second sentiment ratio corresponding to the landmark names.

[0009] The controller can be configured to: during a first playback period for outputting a first sound, determine a plurality of first target engine sound levels based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure, and synthesize the first sound based on the first sound source and the plurality of first target engine sound levels; during a second playback period for outputting a second sound, determine a plurality of second target engine sound levels based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure, and synthesize the second sound based on the second sound source and the plurality of second target engine sound levels.

[0010] The controller can be configured to: select some first target engine sound levels from multiple first target engine sound levels based on the first emotion ratio and the second emotion ratio, and synthesize the first sound based on the first sound source and the selected part of the first target engine sound levels; select some second target engine sound levels from multiple second target engine sound levels based on the first emotion ratio and the second emotion ratio, and synthesize the second sound based on the second sound source and the selected part of the second target engine sound levels.

[0011] In addition, the controller may be configured to determine the volume of the first sound and the second sound based on at least one of the output torque, speed, and accelerator pedal pressure of the vehicle. The first emotion and the second emotion may be one of happiness, joy, sadness, excitement, fear, anger, or calmness.

[0012] According to one aspect of the present invention, a vehicle may include: a database, a speaker, and a controller, the database being configured to store a plurality of sound sources classified as a first terrain and a plurality of sound sources classified as a second terrain; the controller being configured to receive a map image output from a navigation system; outputting a first color ratio and a second color ratio forming the map image by processing the map image; selecting a first sound source from a plurality of sound sources classified as the first terrain based on the first color ratio; selecting a second sound source from a plurality of sound sources classified as the second terrain based on the second color ratio; determining a first playback period and a second playback period based on the first color ratio and the second color ratio; outputting a first sound generated based on the first sound source by the speaker during the first playback period; and outputting a second sound generated based on the second sound source during the second playback period.

[0013] The controller may be configured to compress a map image and cluster the compressed map image by color using a K-means algorithm. The controller may be configured to match a first color to a first terrain and a second color to a second terrain. The controller may be configured to: during a first playback period in which a first sound is output, determine a plurality of first target engine sound levels based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure, and synthesize the first sound based on the first sound source and the plurality of first target engine sound levels; and during a second playback period in which a second sound is output, determine a plurality of second target engine sound levels based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure, and synthesize the second sound based on the second sound source and the plurality of second target engine sound levels.

[0014] The controller can be configured to: select some first target engine sound levels from a plurality of first target engine sound levels based on the first color ratio and the second color ratio, and synthesize the first sound based on the first sound source and the selected part of the first target engine sound levels; select some second target engine sound levels from a plurality of second target engine sound levels based on the first color ratio and the second color ratio, and synthesize the second sound based on the second sound source and the selected part of the second target engine sound levels.

[0015] The controller may be configured to determine the volume of the first sound and the second sound based on at least one of the output torque, speed, and accelerator pedal pressure of the vehicle.The first terrain and the second terrain may be one of a city, a mountain, a river, a road, a beach, or a tunnel.

[0016] According to one aspect of the present invention, a control method for a vehicle includes a database storing multiple sound sources classified as a first emotion and multiple sound sources classified as a second emotion. The method may include: outputting a landmark name based on a route guidance text included in driving route information calculated by a navigation system; outputting a first emotion ratio and a second emotion ratio corresponding to the landmark name based on the landmark name; selecting a first sound source from multiple sound sources classified as the first emotion based on the first emotion ratio; selecting a second sound source from multiple sound sources classified as the second emotion based on the second emotion ratio; determining a first playback period and a second playback period based on the first emotion ratio and the second emotion ratio; outputting a first sound generated based on the first sound source during the first playback period; and outputting a second sound generated based on the second sound source during the second playback period.

[0017] Outputting a landmark name based on route guidance text included in driving route information calculated by the navigation system may include: outputting the landmark name included in the route guidance text using natural language processing (NLP). Additionally, outputting a first emotion ratio and a second emotion ratio corresponding to the landmark name based on the landmark name may include: outputting the first emotion ratio and the second emotion ratio corresponding to the landmark name using the landmark name as input data of a long short-term memory network (LSTM).

[0018] According to one aspect of the present invention, a control method for a vehicle includes a database storing a plurality of sound sources classified as a first terrain and a plurality of sound sources classified as a second terrain. The method may include: receiving a map image output from a navigation system; outputting a first color ratio and a second color ratio forming the map image by processing the map image; selecting a first sound source from a plurality of sound sources classified as the first terrain based on the first color ratio; selecting a second sound source from a plurality of sound sources classified as the second terrain based on the second color ratio; determining a first playback period and a second playback period based on the first color ratio and the second color ratio; and outputting, by a speaker, a first sound generated based on the first sound source during the first playback period and a second sound generated based on the second sound source during the second playback period.

[0019] Outputting the first color ratio and the second color ratio of the map image by processing the map image may include compressing the map image and clustering the compressed map image by color using a K-means algorithm. Selecting a first sound source from a plurality of sound sources classified as a first terrain based on the first color ratio, and selecting a second sound source from a plurality of sound sources classified as a second terrain based on the second color ratio may include matching the first color with the first terrain and matching the second color with the second terrain. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The objects, features and advantages of the present invention will be more clearly understood through the following detailed description presented in conjunction with the accompanying drawings, in which:

[0021] Figure 1 is a schematic diagram illustrating the interior of a vehicle according to an exemplary embodiment.

[0022] Figure 2 is a control block diagram of a vehicle according to an exemplary embodiment.

[0023] Figure 3 is a flowchart illustrating vehicle control according to an exemplary embodiment.

[0024] Figure 4 is a schematic diagram illustrating a state in which a landmark name included in a route guidance text is output using natural language processing according to an exemplary embodiment.

[0025] Figure 5 is a schematic diagram illustrating a process of outputting a sentiment ratio corresponding to a landmark name using an artificial neural network model according to an exemplary embodiment.

[0026] Figure 6 is a schematic diagram illustrating a process of synthesizing a driving sound based on an emotion ratio according to an exemplary embodiment.

[0027] Figure 7 is a flowchart of vehicle control according to another exemplary embodiment.

[0028] Figure 8 is a schematic diagram illustrating a state of determining a terrain included in a map image using a specific algorithm according to an exemplary embodiment.

[0029] Figure 9 is a schematic diagram illustrating a process of synthesizing a driving sound based on a terrain ratio according to an exemplary embodiment. DETAILED DESCRIPTION

[0030] It should be understood that the term "vehicle" or "vehicular" or other similar terms used herein generally include motor vehicles, such as passenger cars including sport utility vehicles (SUVs), buses, trucks, various commercial vehicles, watercraft including various boats, ships, aircraft, etc., and include hybrid vehicles, electric vehicles, plug-in hybrid electric vehicles, hydrogen-powered vehicles, and other alternative fuel vehicles (e.g., fuels derived from non-petroleum energy sources). As referred to herein, a hybrid vehicle is a vehicle that has two or more power sources, such as both gasoline-powered and electric-powered vehicles.

[0031] Although the exemplary embodiments are described as using multiple units to perform the exemplary processes, it should be understood that the exemplary processes can also be performed by one or more modules. Furthermore, it should be understood that the term controller / control unit refers to a hardware device that includes a memory and a processor and is specifically programmed to perform the processes described herein. The memory is configured to store the modules, and the processor is specifically configured to execute the modules to perform one or more processes described further below.

[0032] Furthermore, the control logic of the present invention can be implemented as a non-transitory computer-readable medium on a computer-readable medium containing executable program instructions executed by a processor, a controller / controller unit, etc. Examples of computer-readable media include, but are not limited to, ROM, RAM, compact disc (CD)-ROMs, magnetic tapes, floppy disks, flash drives, smart cards, and optical data storage devices. The computer-readable recording medium can also be distributed over a network of connected computer systems so that the computer-readable media is stored and executed in a distributed manner, for example, via a telematics server or a controller area network (CAN).

[0033] Unless otherwise stated or apparent from the context, the term "about" as used herein is understood to mean within the normal tolerance range in the art, such as within 2 standard deviations of the mean. "About" can be understood to mean within 10%, 9%, 8%, 7%, 6%, 5%, 4%, 3%, 2%, 1%, 0.5%, 0.1%, 0.05%, or 0.01% of the specified value. Unless the context clearly indicates otherwise, all numerical values ​​provided herein are modified by the term "about."

[0034] Like reference numerals denote like elements. This disclosure does not describe all elements of the exemplary embodiments, and there is overlap between general contents or embodiments in the technical field to which the present invention pertains. This specification does not describe all elements of the exemplary embodiments of the present invention, and detailed descriptions of contents well known in the art may be omitted, or redundant descriptions of substantially the same configurations may be omitted.

[0035] Throughout the specification, when an element is referred to as being “connected to” another element, it may be directly or indirectly connected to the other element, and “indirectly connected to” includes being connected to the other element via a wireless communication network. The terms “component, module, member, block” used in the specification may be implemented in software or hardware, and multiple “components, modules, members, blocks” may be implemented as one component, and one “component, module, member, block” may also include multiple components. Throughout the specification, when an element is referred to as being “connected to” another element, it may be directly or indirectly connected to the other element, and “indirectly connected to” includes being connected to the other element via a wireless communication network.

[0036] In addition, when a part is referred to as "comprising" a certain component, this means that it may further include other components, without excluding other components, unless otherwise specified. Unless the context clearly indicates an exception, a singular expression includes a plural expression. In addition, terms such as "~ unit", "~ group", "~ block", "~ component" and "~ module" may represent a unit that processes at least one function or operation. For example, these terms may refer to at least one hardware (such as a field programmable gate array (FPGA) / application specific integrated circuit (ASIC)), at least one software stored in a memory, or at least one process processed by a processor.

[0037] The symbols attached to each step are used to identify each step, and these symbols do not indicate the order of each step, and unless a specific order is clearly indicated in the context, the execution of each step is different from the specified order. Hereinafter, the working principle and exemplary embodiments of the present invention will be described with reference to the accompanying drawings.

[0038] Figure 1 : is a schematic diagram showing the interior of a vehicle according to an exemplary embodiment. Figure 1 , the vehicle according to the exemplary embodiment may include the AVN device 110 and the speaker 140, and the driver of the vehicle according to the exemplary embodiment may possess the navigation terminal 200. The controller may operate various components of the vehicle.

[0039] The audio video navigation (AVN) device 110 may refer to a multimedia device that integrates audio, video, navigation, and telematics. The AVN device 110 may be configured to provide driving route guidance to the user by receiving a destination set by the user, calculating driving route information based on the destination and the current location of the vehicle, and displaying the calculated driving route information.

[0040] Specifically, the AVN device 110 may be configured to request the user to select a destination by inputting a destination name received from the user via touch input or voice input and displaying a list of locations matching the input destination name. Furthermore, the AVN device 110 may be configured to provide guidance regarding the vehicle's driving direction by generating driving route information based on a driving route set according to the user's selected destination and displaying the generated driving route information.

[0041] The driving route information may include: TBT information indicating direction information (e.g., 11 o'clock, 1 o'clock, right turn, 5 o'clock, U-turn, 8 o'clock, left turn), route guidance text for guiding the driving direction, and a map image based on the current position of the driving vehicle. The TBT information and route guidance text may be output as voice through the audio system of the AVN device 110, and the TBT information, route guidance text, and map image may be output visually through the screen of the AVN device 110.

[0042] The AVN device 110 may be installed in the center console of the vehicle, but is not limited thereto. The navigation terminal 200 owned by the driver may also provide the same functions as the AVN device 110. The navigation terminal 200 may refer to a user terminal such as a driver's smartphone, tablet personal computer (PC), or notebook computer, and may refer to any terminal device capable of executing a navigation application that guides a route to a destination.

[0043] The screen displayed on the navigation terminal 200 may be displayed on the AVN device 110 of the vehicle based on short-range communication and / or long-range communication with the vehicle. Hereinafter, the AVN device 110 provided in the vehicle and / or the navigation terminal 200 owned by the driver will be collectively referred to as a navigation system.

[0044] Speaker 140 can be configured to output various sounds within the vehicle. To this end, speakers 140 can be located on both vehicle doors, but any other location is acceptable, as long as the driver inside the vehicle can hear the output sound. Speaker 140 can refer to any device capable of converting electrical signals into sound and outputting the sound. To this end, speaker 140 can include a voice coil and an amplifier configured to adjust the volume of the output sound by adjusting the amount of current supplied to the voice coil.

[0045] Figure 2 is a control block diagram of a vehicle according to an exemplary embodiment. Figure 2 According to an exemplary embodiment, a vehicle may include: a navigation system, a database 120, a controller 130, and a speaker 140. The navigation system is configured to calculate driving route information and transmit the information to the vehicle; the database 120 is configured to store a plurality of sound sources; the controller 130 is configured to operate the speaker 140 to select a sound source from the database 120 based on the driving route information received from the navigation system, and output a driving sound generated based on the selected sound source; the speaker 140 is configured to output the driving sound based on a control signal from the controller 130.

[0046] As described above, the navigation system may include the AVN device 110 installed in the vehicle and the navigation terminal 200 owned by the driver. The navigation system may be configured to transmit various information via in-vehicle communication, short-range communication, and / or long-range communication with the controller 130. For example, driving route information calculated by the navigation system may be transmitted to the controller 130.

[0047] The database 120 according to the exemplary embodiment may be configured to store a plurality of sound sources classified into a plurality of emotions and / or a plurality of sound sources classified into a plurality of terrains. In this case, the plurality of emotions may include emotions such as happiness, joy, sadness, excitement, fear, anger, and calmness, and the plurality of terrains may include terrains such as cities, mountains, rivers, roads, beaches, and tunnels.

[0048] For example, database 120 may be configured to store multiple sound sources categorized as a "happy" state, and the multiple sound sources categorized as "happy" may be further distinguished within the "happy" category based on the ratio of the "happy" state. Furthermore, database 120 may be configured to store multiple sound sources categorized as "urban" terrain, and the multiple sound sources may be further distinguished within the "urban" terrain category based on the "urban" terrain ratio. Specifically, database 120 may be configured to store sound sources corresponding to a driver's emotional state in which the ratio of a "happy" state is approximately 75% and the ratio of a "sad" state is approximately 25%. Furthermore, database 120 may be configured to store sound sources corresponding to a terrain ratio of a map image in which the ratio of a city is approximately 75% and the ratio of a mountainous area is approximately 25%.

[0049] Database 120 may be implemented as at least one of a non-volatile storage device (e.g., cache, read-only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), and flash memory), a volatile storage device (e.g., random access memory (RAM)), or a storage medium (e.g., a hard disk drive (HDD) or a compact disc read-only memory (CD-ROM)) to store various information, but is not limited thereto. Database 120 may be a memory implemented as a separate chip, or may be processor 131 corresponding to controller 130 and a single chip.

[0050] The controller 130 according to the exemplary embodiment may select at least one sound source from a plurality of sound sources stored in the database 120 based on data received from the navigation system. In addition, the controller 130 may be configured to synthesize a driving sound based on each selected sound source and determine a playback period for outputting the synthesized driving sound.

[0051] For example, the controller 130 can be configured to: output a landmark name based on the route guidance text included in the driving route information calculated by the navigation system; output a first emotion ratio and a second emotion ratio corresponding to the landmark name based on the landmark name; select a first sound source from multiple sound sources classified as the first emotion based on the first emotion ratio; select a second sound source from multiple sound sources classified as the second emotion based on the second emotion ratio; determine a first playback period and a second playback period based on the first emotion ratio and the second emotion ratio; and output, by the speaker 140, a first sound generated based on the first sound source during the first playback period and a second sound generated based on the second sound source during the second playback period.

[0052] In another example, the controller 130 can be configured to: receive a map image output from a navigation system; output a first color ratio and a second color ratio that form the map image; select a first sound source from a plurality of sound sources classified as a first terrain based on the first color ratio; select a second sound source from a plurality of sound sources classified as a second terrain based on the second color ratio; determine a first playback period and a second playback period based on the first color ratio and the second color ratio; and output, by the speaker 140, a first sound generated based on the first sound source during the first playback period and a second sound generated based on the second sound source during the second playback period.

[0053] The controller 130 may include at least one memory 132 and at least one processor 131, wherein the at least one memory 132 is configured to store a program for outputting a landmark name based on a route guidance text, a program for outputting an emotion ratio corresponding to a landmark name, a program for selecting at least one sound source based on the emotion ratio, a program for processing a map image and outputting a color ratio forming a map image, a program for outputting a terrain ratio corresponding to the color ratio, a program for selecting at least one sound source based on the terrain ratio, and a program for generating driving sounds; the at least one processor 131 is capable of executing the programs stored in the at least one memory 132.

[0054] The programs stored in the memory 132 include a natural language processing (NLP) algorithm, a K-means algorithm, a convolutional neural network (CNN) algorithm, a generative adversarial network (GAN) algorithm, a recurrent neural network (RNN) algorithm, a long short-term memory network (LSTM) algorithm (a type of RNN algorithm), and an artificial intelligence algorithm (artificial neural network model) such as a region-based convolutional neural network (R-CNN) algorithm. The speaker 140 according to the exemplary embodiment can output a driving sound based on a control signal (e.g., an electrical signal) received from the controller 130.

[0055] The various components of the vehicle according to the exemplary embodiment have been described in detail above. It goes without saying that the various components of the above-mentioned vehicle can be freely changed at the level of general technical scope. Hereinafter, a method for controlling a vehicle using the various components of the above-mentioned vehicle will be described in detail.

[0056] Figure 3 is a flowchart illustrating vehicle control according to an exemplary embodiment. Figure 4 is a schematic diagram illustrating a state in which landmark names included in a route guidance text are output by using natural language processing. Figure 5 is a schematic diagram illustrating a process of outputting sentiment ratios corresponding to landmark names using an artificial neural network model. Figure 6 is a schematic diagram illustrating a process of synthesizing a driving sound based on an emotion ratio.

[0057] refer to Figure 3 According to an exemplary embodiment, the controller 130 may receive driving route information from the internal navigation system (AVN device) 110 and / or the external navigation system (navigation terminal) 200 (step 1000). The controller 130 may be configured to output a landmark name based on a route guidance text included in the driving route information (step 1100). Specifically, the route guidance text may include a plurality of landmark names.

[0058] refer to Figure 4, the route guidance text included in the driving route information may include the text "turn left at Yeonsinnei Station", the text "turn right at Sungnyemun intersection" and the text "to Namsan Park". The controller 130 may be configured to use natural language processing (NLP) to output the landmark names included in the route guidance text. For example, the controller 130 may be configured to extract only the landmark name "Yeonsinnei Station" from the text "turn left at Yeonsinnei Station". Only the landmark name "Sungnyemun" may be extracted from the text "turn right at Sungnyemun intersection". In addition, only the landmark name "Namsan Park" may be extracted from the phrase "to Namsan Park".

[0059] Specifically, the controller 130 may be configured to separate the main landmark names by applying a separation rule to the surveys that mention the destination and direction. Thereafter, the controller 130 may be configured to output the sentiment ratio corresponding to the landmark name (step 1200). Specifically, referring to Figure 5 , the controller 130 may be configured to use the landmark name as input data of the LSTM to output a sentiment ratio corresponding to the landmark name.

[0060] For example, when the landmark name "Yeonsinnae Station" is input, the LSTM can be configured to output an emotion ratio of approximately 75% joy and approximately 20% sadness. When the landmark name "Sungnyemun Gate" is input, it can output an emotion ratio of approximately 55% calm and approximately 18% sadness. When the landmark name "Namsan Park" is input, it can output an emotion ratio of approximately 52% joy and approximately 4% calm. Accordingly, the LSTM can use multiple landmark names as training data for pre-learning.

[0061] The controller 130 may be configured to determine a comprehensive emotion ratio corresponding to a landmark name based on the emotion ratio corresponding to each landmark name. For example, for a route leading to "Yeonsinnae Station - Sungnyemun - Namsan Park," the controller 130 may be configured to calculate an emotion ratio of approximately 60% for happiness (hereinafter referred to as "first emotion"), approximately 30% for calmness (hereinafter referred to as "second emotion"), and approximately 10% for sadness (hereinafter referred to as "third emotion").

[0062] The controller 130 may be configured to select a first sound source based on a first emotion ratio, a second sound source based on a second emotion ratio, and a third sound source based on a third emotion ratio (step 1300). Specifically, the first sound source may refer to any sound source classified as the first emotion and stored in the database 120, the second sound source may refer to any sound source classified as the second emotion and stored in the database 120, and the third sound source may refer to any sound source classified as the third emotion and stored in the database 120.

[0063] Specifically, the controller 130 can be configured to determine the first playback period, the second playback period, and the third playback period based on the first emotion ratio, the second emotion ratio, and the third emotion ratio. For example, when it is assumed that the estimated driving time of the route to "Yeonsinnei Station-Sunggnyemun-Namsan Park" is 20 minutes, the controller 130 can be configured to determine that the first playback period of the driving sound generated based on the first sound source (hereinafter referred to as "the first sound") is 12 minutes, the second playback period of the driving sound generated based on the second sound source (hereinafter referred to as "the second sound") is 6 minutes, and the third playback period of the driving sound generated based on the third sound source (hereinafter referred to as "the third sound") can be determined to be 2 minutes. The controller 130 can be configured to generate the first sound, the second sound, and the third sound based on the first sound source, the second sound source, and the third sound source (step 1400).

[0064] refer to Figure 5 , the controller 130 may be configured to select a sound source 121a corresponding to the first emotion ratio from the plurality of sound sources 121a, 121b, 121c, and 121d classified as the first emotion in the database 120. In addition, the controller 130 may be configured to select a sound source 125c corresponding to the second emotion ratio from the plurality of sound sources 125a, 125b, 125c, and 125d classified as the second emotion in the database 120.

[0065] In addition, the controller 130 may be configured to select a sound source 124b corresponding to the third emotion ratio from the plurality of sound sources 124a, 124b, 124c, and 124d classified as the third emotion in the database 120. The controller 130 may be configured to: during the first playback period, determine a plurality of first target engine sound levels based on at least one of the output torque, speed, and accelerator pedal force of the vehicle, and synthesize the first sound based on the selected first sound source 121a and the plurality of first target engine sound levels.

[0066] Similarly, the controller 130 can be configured to: during a second playback cycle, determine a plurality of second target engine sound levels based on at least one of the vehicle's output torque, speed, and accelerator pedal force, and synthesize a second sound based on the selected second sound source 125c and the plurality of second target engine sound levels; during a third playback cycle, determine a plurality of third target engine sound levels based on at least one of the vehicle's output torque, speed, and accelerator pedal force, and synthesize a third sound based on the selected third sound source 124b and the plurality of third target engine sound levels.

[0067] In the case of an electric vehicle, since it lacks an engine, a target engine sound level cannot be selected based on the engine RPM. Accordingly, the controller 130 can be configured to estimate the RPM of a vehicle assuming it is equipped with an engine based on at least one of the vehicle's output torque, speed, and accelerator pedal force, and determine multiple target engine sound levels based on the engine RPM. In other words, the database 120 or the memory 132 can be configured to store a lookup table indicating the relationship between a specific output torque, a specific speed, and a specific accelerator pedal force of the vehicle and the target engine sound level, and the controller 130 can be configured to determine multiple target engine sound levels based on the lookup table stored in the database 120 or the memory 132.

[0068] The controller 130 may be configured to select some first target engine sound levels from the first target engine sound levels determined according to the lookup table based on the first emotion ratio, the second emotion ratio, and the third emotion ratio. For example, even when the target engine sound levels determined based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure are 1st, 2nd, 6th, and 7th, only 1st and 2nd may be selected as the first target engine sound levels based on the first emotion ratio, the second emotion ratio, and the third emotion ratio.

[0069] For example, when the second emotion ratio corresponding to a calm state is high, only a few levels may be selected as the target engine sound levels to produce a calmer driving sound. The controller 130 may be configured to determine a plurality of second target engine sound levels and a plurality of third target engine sound levels in the same manner as described above, and may be configured to select the second target engine sound levels and the third target engine sound levels based on the first emotion ratio, the second emotion ratio, and the third emotion ratio.

[0070] The controller 130 can be configured to: generate a first sound by synthesizing a first sound source 121a selected from the database 120 with a signal having a selected first target engine sound level; generate a second sound by synthesizing a second sound source 125c selected from the database 120 with a signal having a selected second target engine sound level; and generate a third sound by synthesizing a third sound source 124b selected from the database 120 with a signal having a selected third target engine sound level.

[0071] The signal having the target engine sound level for synthesis may be stored in the memory 132 or the database 120. Thereafter, the controller 130 may be configured to operate the speaker 140 to output the resulting first sound during the first playback period, the second sound during the second playback period, and the third sound during the third playback period (step 1500).

[0072] Specifically, the controller 130 may be configured to determine the volume of the first sound, the second sound, and the third sound based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure. For example, the controller 130 may be configured to determine the volume of the first sound, the second sound, and the third sound to be higher as the vehicle's output torque, speed, and accelerator pedal pressure increase.

[0073] According to the vehicle and vehicle control method according to the exemplary embodiment described above, the vehicle can provide various driving sounds that automatically reflect the names of landmarks included in the driving route, rather than always the same driving sound. Accordingly, the marketability of the vehicle can be improved by giving the driver driving pleasure.

[0074] In the following, reference will be made to Figures 7 to 9 A method of controlling a vehicle according to another exemplary embodiment is described in detail. Figure 7 is a flowchart of vehicle control according to another exemplary embodiment. Figure 8 is a schematic diagram illustrating a state in which a terrain included in a map image is determined using a specific algorithm. Figure 9 is a schematic diagram illustrating a process of synthesizing driving sounds based on a terrain ratio.

[0075] refer to Figure 7 , the controller 130 according to the exemplary embodiment may be configured to receive a map image from the internal navigation system (AVN device) 110 and / or the external navigation system (navigation terminal) 200 (step 2000). Specifically, the controller 130 may be configured to receive the map image at a preset interval. The controller 130 may be configured to compress / change the map image output from the navigation system and output the ratio of the colors included in the map image based on the RGB data of the map image (step 2100).

[0076] Specifically, refer to Figure 8 , the controller 130 can be configured to convert the color information of the map image into RGB format, convert the image size to a preset training data size, extract the RGB information of each pixel, convert the RGB 3D data into 2D data, and then apply the K-means algorithm to output the first color ratio, the second color ratio, and the third color ratio that form the map image. In other words, the controller 130 can be configured to compress the map image using the K-means algorithm and cluster the compressed map image by color.

[0077] Assuming that the map image is classified into a first color, a second color, and a third color, the controller 130 may be configured to associate each color with each terrain. For example, the controller 130 may be configured to match gray (hereinafter referred to as the "first color") with a city (hereinafter referred to as the "first terrain"), green (hereinafter referred to as the "second color") with a mountain (hereinafter referred to as the "second terrain"), and black (hereinafter referred to as the "third color") with a tunnel (hereinafter referred to as the "third terrain").

[0078] Information on the terrain corresponding to each color may be stored in the database 120 and / or the memory 132. Thereafter, the controller 130 may be configured to determine a first terrain ratio, a second terrain ratio, and a third terrain ratio based on a ratio of the number of pixels clustered in the first color, a ratio of the number of pixels clustered in the second color, and a ratio of the number of pixels clustered in the third color.

[0079] For example, controller 130 may be configured to determine that the first terrain ratio is approximately 60%, the second terrain ratio is approximately 30%, and the third terrain ratio is approximately 10%. Specifically, the color and terrain type may not be matched 1:1. For example, a terrain-mapped city may correspond to gray, while a terrain-mapped city may also correspond to beige. In other words, each of the first color, the second color, and the third color may include multiple colors.

[0080] refer to Figure 9 , the controller 130 can be configured to: select a first sound source 126a from a plurality of sound sources 126a, 126b, 126c, and 126d classified as a first landform based on a first color ratio; select a second sound source 127c from a plurality of sound sources 127a, 127b, 127c, and 127d classified as a second landform based on a second color ratio; and select a third sound source 128d from a plurality of sound sources 128a, 128b, 128c, and 128d classified as a third landform based on a third color ratio (step 2200).

[0081] Specifically, the controller 130 may be configured to determine a first play period, a second play period, and a third play period based on the first color ratio, the second color ratio, and the third color ratio. In other words, the controller 130 may be configured to determine the first play period, the second play period, and the third play period based on the first terrain ratio, the second terrain ratio, and the third terrain ratio, respectively.

[0082] For example, assuming that the reception period of the map image from the navigation system is 20 minutes, the controller 130 can be configured to: set the first playback period of the driving sound generated based on the first sound source 126a (hereinafter referred to as "first sound") to 12 minutes; set the second playback period of the driving sound generated based on the second sound source 127c (hereinafter referred to as "second sound") to 6 minutes; and the third playback period of the driving sound generated based on the third sound source 128d (hereinafter referred to as "third sound") can be determined to be 2 minutes.

[0083] As described above, the controller 130 can be configured to: during the first playback period, determine a plurality of first target engine sound levels based on at least one of the output torque, speed, and accelerator pedal pressure of the vehicle, and synthesize the first sound based on the selected first sound source 126a and the plurality of first target engine sound levels.

[0084] Similarly, the controller 130 can be configured to: during a second playback period, determine a plurality of second target engine sound levels based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure, and synthesize a second sound based on the selected second sound source 127c and the plurality of second target engine sound levels; during a third playback period, determine a plurality of third target engine sound levels based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure, and synthesize a third sound based on the selected third sound source 128d and the plurality of third target engine sound levels.

[0085] Specifically, the controller 130 can be configured to select some first target engine sound levels from the first target engine sound levels determined according to the lookup table based on the first color ratio (first terrain ratio), the second color ratio (second terrain ratio) and the third color ratio (third terrain ratio).

[0086] For example, even when the first target engine sound level determined based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure is 1st, 2nd, 6th, and 7th, only 1st and 2nd may be selected as the first target engine sound level based on the first color ratio, the second color ratio, and the third color ratio.

[0087] For example, when the second terrain ratio corresponding to a mountain range is high, only a few levels may be selected as the target engine sound level to produce a calmer driving sound. The controller 130 may be configured to determine a plurality of second target engine sound levels and a plurality of third target engine sound levels in the same manner as described above, and may be configured to select some of the second target engine sound levels and the third target engine sound levels based on the first color ratio, the second color ratio, and the third color ratio.

[0088] In addition, the controller 130 can be configured to: generate a first sound by synthesizing a first sound source 126a selected from the database 120 with a signal having a selected first target engine sound level; generate a second sound by synthesizing a second sound source 127c selected from the database 120 with a signal having a selected second target engine sound level; and generate a third sound by synthesizing a third sound source 128d selected from the database 120 with a signal having a selected third target engine sound level (step 2300).

[0089] Afterwards, the controller 130 may be configured to operate the speaker 140 to output the resulting first sound during the first playback period, the second sound during the second playback period, and the third sound during the third playback period (step 2400). Specifically, the controller 130 may be configured to determine the volume of the first sound, the second sound, and the third sound based on at least one of the vehicle's output torque, speed, and accelerator pedal pressure. For example, the controller 130 may be configured to determine the volume of the first sound, the second sound, and the third sound to be higher as the vehicle's output torque, speed, and accelerator pedal pressure increase.

[0090] According to the vehicle and vehicle control method according to the exemplary embodiment described above, the vehicle can provide various driving sounds that automatically reflect the map image based on the current vehicle position, rather than always the same driving sound. Accordingly, the marketability of the vehicle can be improved by giving the driver driving pleasure.

[0091] On the other hand, the disclosed exemplary embodiments can be implemented in the form of a recording medium for storing computer-executable instructions. The instructions can be stored in the form of program code, and when executed by a processor, a program module can be generated to perform the operations of the disclosed exemplary embodiments. The recording medium can be implemented as a non-transitory computer-readable recording medium.

[0092] Non-transitory computer-readable recording media include all types of recording media (having instructions that can be decoded by a computer), such as read-only memory (ROM), random access memory (RAM), magnetic tapes, magnetic disks, flash memories, optical data storage devices, and the like.

[0093] As described above, the disclosed exemplary embodiments have been described with reference to the accompanying drawings. Although exemplary embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes may be made to these exemplary embodiments without departing from the principles and spirit of the invention, the scope of the invention being defined by the claims and their equivalents.

[0094] According to the present invention, it is possible to meet the user's request by outputting a driving sound generated based on information received from a navigation system instead of outputting a unified driving sound.

Claims

1. A vehicle comprising: a database configured to store a plurality of different sound sources classified as a first emotion and a plurality of different sound sources classified as a second emotion; speaker; as well as The controller is configured as follows: outputting a landmark name based on route guidance text included in driving route information calculated by a navigation system; outputting a first emotion ratio and a second emotion ratio corresponding to the landmark name based on the landmark name; wherein the plurality of different sound sources classified as the first emotion each correspond to a different intensity of the first emotion, and the controller is configured to select the first sound source corresponding to the intensity of the first emotion ratio; wherein the plurality of different sound sources classified as the second emotion each correspond to a different intensity of the second emotion, and the controller is configured to select the second sound source corresponding to the intensity of the second emotion ratio; determining a first play period and a second play period based on the first emotion ratio and the second emotion ratio; outputting a first sound generated based on a first sound source during a first play period; A second sound generated based on a second sound source is output during a second play period.

2. The vehicle according to claim 1, wherein The controller is configured to output landmark names included in the route guidance text using natural language processing.

3. The vehicle according to claim 1, wherein: The controller is configured to use the landmark name as input data of the long short-term memory network to output a first emotion ratio and a second emotion ratio corresponding to the landmark name.

4. The vehicle according to claim 1, wherein The controller is configured as follows: During a first playback period in which the first sound is output, determining a plurality of first target engine sound levels based on at least one of an output torque, a speed, and an accelerator pedal pressure of the vehicle, and synthesizing the first sound based on the first sound source and the plurality of first target engine sound levels; During a second playback period in which the second sound is output, a plurality of second target engine sound levels are determined based on at least one of an output torque, a speed, and an accelerator pedal pressure of the vehicle, and the second sound is synthesized based on the second sound source and the plurality of second target engine sound levels.

5. The vehicle according to claim 4, wherein The controller is configured as follows: selecting some first target engine sound levels from a plurality of first target engine sound levels based on the first emotion ratio and the second emotion ratio, and synthesizing a first sound based on the first sound source and the selected some of the first target engine sound levels; Some second target engine sound levels among a plurality of second target engine sound levels are selected based on the first emotion ratio and the second emotion ratio, and a second sound is synthesized based on the second sound source and the selected portion of the second target engine sound commands.

6. The vehicle according to claim 1, wherein The controller is configured to determine volumes of the first sound and the second sound based on at least one of an output torque, a speed, and an accelerator pedal pressure of the vehicle.

7. The vehicle according to claim 1, wherein: The first emotion and the second emotion are one of happiness, joy, sadness, excitement, fear, anger or calmness.

8. A vehicle comprising: a database configured to store a plurality of different sound sources classified as a first terrain and a plurality of different sound sources classified as a second terrain; speaker; as well as The controller is configured as follows: receiving a map image output from a navigation system; outputting a first color ratio and a second color ratio forming a map image by processing the map image; wherein the plurality of different sound sources classified as the first terrain each correspond to a different type of the first terrain, and the controller is configured to select a first sound source corresponding to an intensity of the first color ratio; wherein the plurality of different sound sources classified as the second terrain each correspond to a different type of the second terrain, and the controller is configured to select the second sound source corresponding to the intensity of the second color ratio; determining a first play period and a second play period based on the first color ratio and the second color ratio; outputting, by the speaker, a first sound generated based on a first sound source during a first playback period; A second sound generated based on a second sound source is output during a second play period.

9. The vehicle according to claim 8, wherein: The controller is configured to compress the map image and cluster the compressed map image by color using a K-means algorithm.

10. The vehicle according to claim 8, wherein The controller is configured to match a first color to a first topography and a second color to a second topography.

11. The vehicle according to claim 8, wherein The controller is configured as follows: During a first playback period in which the first sound is output, determining a plurality of first target engine sound levels based on at least one of an output torque, a speed, and an accelerator pedal pressure of the vehicle, and synthesizing the first sound based on the first sound source and the plurality of first target engine sound levels; During a second playback period in which the second sound is output, a plurality of second target engine sound levels are determined based on at least one of an output torque, a speed, and an accelerator pedal pressure of the vehicle, and the second sound is synthesized based on the second sound source and the plurality of second target engine sound levels.

12. The vehicle according to claim 11, wherein The controller is configured as follows: selecting some first target engine sound levels from a plurality of first target engine sound levels based on the first color ratio and the second color ratio, and synthesizing a first sound based on the first sound source and the selected some of the first target engine sound levels; Some second target engine sound levels among a plurality of second target engine sound levels are selected based on the first color ratio and the second color ratio, and a second sound is synthesized based on the second sound source and the selected some second target engine sound levels.

13. The vehicle according to claim 8, wherein The controller is configured to determine volumes of the first sound and the second sound based on at least one of an output torque, a speed, and an accelerator pedal pressure of the vehicle.

14. The vehicle according to claim 8, wherein The first terrain and the second terrain are one of a city, a mountain, a river, a road, a beach or a tunnel.

15. A method for controlling a vehicle, the vehicle comprising a database storing a plurality of different sound sources classified as a first emotion and a plurality of different sound sources classified as a second emotion, the method comprising: outputting, by a controller, a landmark name based on route guidance text included in driving route information calculated by a navigation system; outputting, by the controller, a first emotion ratio and a second emotion ratio corresponding to the landmark name based on the landmark name; A controller selects a first sound source and a second sound source, wherein the plurality of different sound sources classified as the first emotion each correspond to a different intensity of the first emotion, and the first sound source corresponding to the intensity ratio of the first emotion is selected; wherein the plurality of different sound sources classified as the second emotion each correspond to a different intensity of the second emotion, and the second sound source corresponding to the intensity ratio of the second emotion is selected; determining, by the controller, a first play period and a second play period based on the first emotion ratio and the second emotion ratio; During a first play period, the controller outputs a first sound generated based on a first sound source; During the second play period, the controller outputs a second sound generated based on the second sound source.

16. The method according to claim 15, wherein Outputting the landmark name based on the route guidance text included in the driving route information calculated by the navigation system includes outputting the landmark name included in the route guidance text using natural language processing.

17. The method according to claim 15, wherein: Outputting the first emotion ratio and the second emotion ratio corresponding to the landmark name based on the landmark name includes: using the landmark name as input data of a long short-term memory network to output the first emotion ratio and the second emotion ratio corresponding to the landmark name.

18. A method for controlling a vehicle, the vehicle comprising a database storing a plurality of different sound sources classified as a first terrain and a plurality of different sound sources classified as a second terrain, the method comprising: receiving, by the controller, a map image output from the navigation system; The controller processes the map image to output a first color ratio and a second color ratio forming the map image; A controller selects a first sound source and a second sound source, wherein the plurality of different sound sources classified as the first landform each correspond to a different type of the first landform, and the first sound source corresponding to the intensity of the first color ratio is selected; wherein the plurality of different sound sources classified as the second landform each correspond to a different type of the second landform, and the second sound source corresponding to the intensity of the second color ratio is selected; determining, by the controller, a first play period and a second play period based on the first color ratio and the second color ratio; The controller outputs a first sound generated based on a first sound source through a speaker during a first play period, and outputs a second sound generated based on a second sound source during a second play period.

19. The method according to claim 18, wherein Outputting the first color ratio and the second color ratio of the map image by processing the map image includes compressing the map image and clustering the compressed map image by color using a K-means algorithm.

20. The method according to claim 18, wherein Selecting a first sound source from a plurality of sound sources classified as a first terrain based on a first color ratio and selecting a second sound source from a plurality of sound sources classified as a second terrain based on a second color ratio includes matching the first color with the first terrain and matching the second color with the second terrain.

Images