Voice command recognition device and voice command recognition method

Abstract

The present disclosure provides a voice command recognition device and a voice command recognition method. The voice command recognition device includes: a processor, registering one or more voice commands selected by analyzing one or more voice commands repeatedly used by a user or a voice command speaking pattern of the user to generate a package command; and a storage device, storing data or an algorithm for the processor to perform voice recognition.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of priority from Korean Patent Application No. 10-2019-0162818 filed on December 9, 2019, in the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to a voice command recognition device and a voice command recognition method, and more particularly, to a technology for registering and executing multiple voice commands as a package. Background Art

[0004] In recent years, the technology of operating electronic devices through voice recognition has been developed and applied to various fields. In order to ensure the safety of the vehicle, the technology of recognizing the driver's voice to operate the device in the vehicle has been developed.

[0005] According to the existing voice recognition technology, when a user outputs a voice command, the domain of the output voice command is analyzed, voice recognition may be performed based on a database for each domain, and a result of the voice recognition may be output.

[0006] Therefore, when the same device is operated every day, the same user should speak the voice command every day. Since the recognition rate is different each time the same command is spoken, the command needs to be reused. Summary of the invention

[0007] The present disclosure is made to solve the above-mentioned problems occurring in the prior art while keeping the advantages achieved by the prior art unchanged.

[0008] One aspect of the present disclosure provides a voice command recognition apparatus and a voice command recognition method, which analyze one or more voice commands repeatedly used by a user or a voice command speaking pattern of the user to generate the one or more voice commands into a package command.

[0009] Another aspect of the present disclosure provides a voice command recognition apparatus and a voice command recognition method, which determine whether to execute commands in a package command sequentially or simultaneously when a package command is spoken.

[0010] Another aspect of the present disclosure provides a voice command recognition apparatus and a voice command recognition method, which analyze a voice command additionally spoken when a pre-generated package command is spoken, and perform one of addition, correction and deletion on the package command.

[0011] Another aspect of the present disclosure provides a voice command recognition device and a voice command recognition method, which, when a pre-generated package command is spoken, determines the current surrounding situation and performs addition, correction or deletion on the package command.

[0012] The technical problems to be solved by the present invention are not limited to the above problems, and any other technical problems not mentioned herein will be clearly understood by those skilled in the art from the following description.

[0013] According to one aspect of the present disclosure, a voice command recognition device may include: a processor, registering one or more voice commands selected by analyzing one or more voice commands repeatedly used by a user or the user's voice command speaking pattern to generate a package command; and a storage device, storing data or algorithms used by the processor for voice recognition.

[0014] In an embodiment, when a package command is spoken, the processor may determine whether to execute one or more voice commands registered in the package command sequentially or simultaneously.

[0015] In an embodiment, when the domains of one or more voice commands registered in a package command are the same as each other, the processor may execute the one or more voice commands sequentially, and when the domains of one or more voice commands registered in a package command are different from each other, the processor may execute the one or more voice commands simultaneously.

[0016] In an embodiment, when one or more voice commands registered in a package command are sequentially executed when the package command is spoken, the processor may collect information about the next voice command to be executed in advance.

[0017] In an embodiment, the processor may analyze the voice command utterance pattern by identifying whether there are commands executed sequentially within a threshold time after a command is spoken, and when the commands executed sequentially within the threshold time are spoken more than a predetermined number of times, the processor may generate the command into a package command.

[0018] In an embodiment, even when one or more voice commands are changed in order and spoken, the processor may recognize that the same command is executed and may increase the number of times spoken.

[0019] In an embodiment, when there is an additional spoken voice command when one package command is spoken, the processor may additionally register the additional spoken voice command in the one package command.

[0020] In an embodiment, when one package command to which an additional spoken voice command is additionally registered is spoken, the processor may execute one or more voice commands pre-registered in one package command and the additional spoken voice command together.

[0021] In an embodiment, when a command requesting cancellation of one of one or more voice commands registered in the package command is additionally spoken when a package command is spoken, the processor may delete the voice command requested to be cancelled from among the one or more voice commands registered in the package command.

[0022] In an embodiment, when a package command is spoken in which the voice command requested to be canceled is deleted, the processor may execute other voice commands except the deleted command among one or more voice commands pre-registered in one package command.

[0023] In an embodiment, when a package command is spoken, the processor may suggest correcting a portion of one or more voice commands registered in the package command or adding a voice command based on the surrounding situation.

[0024] In an embodiment, the surrounding conditions may include at least one or more of temperature, humidity, weather, light intensity, season, date, day of the week, time, location, traffic conditions, and vehicle speed.

[0025] In an embodiment, the processor may analyze a voice command additionally spoken when a package command is spoken, and perform at least one or more of correction, deletion, and addition on the package command.

[0026] According to another aspect of the present disclosure, a voice command recognition method may include: analyzing one or more voice commands repeatedly used by a user or a voice command uttering pattern of the user; and registering one or more voice commands selected by analyzing the one or more voice commands repeatedly used by the user or the voice command uttering pattern of the user to generate a package command.

[0027] In an embodiment, the voice command recognition method may further include: when a package command is spoken, determining whether to execute one or more voice commands registered in the package command sequentially or simultaneously.

[0028] In an embodiment, the voice command recognition method may further include: when the domains of one or more voice commands registered in a package command are the same as each other, sequentially executing the one or more voice commands, and when the domains of one or more voice commands registered in a package command are different from each other, simultaneously executing the one or more voice commands; and when one or more voice commands registered in a package command are sequentially executed when a package command is spoken, collecting information about the next voice command to be executed in advance.

[0029] In an embodiment, generating a package command may include: analyzing a voice command utterance pattern by identifying whether there are commands executed sequentially within a threshold time after a command is spoken, and generating the command into a package command when the commands executed sequentially within the threshold time are spoken more than a predetermined number of times; and even when one or more voice commands are changed in order and spoken, recognizing that the same command is executed and increasing the number of times they are spoken.

[0030] In an embodiment, the voice command recognition method may further include: when an additionally spoken voice command exists when one package command is spoken, additionally registering the additionally spoken voice command in the one package command.

[0031] In an embodiment, the voice command recognition method may further include: when a command requesting to cancel one of one or more voice commands registered in a package command is additionally spoken when a package command is spoken, deleting the voice command requested to be canceled from the one or more voice commands registered in the package command.

[0032] In an embodiment, the voice command recognition method may further include: when a package command is spoken, based on the surrounding situation, suggesting correcting a part of the voice commands among one or more voice commands registered in a package command or adding a voice command; and analyzing the voice commands spoken in addition to a package command when a package command is spoken, and performing at least one of correction, deletion and addition on a package command. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description in conjunction with the accompanying drawings:

[0034] Figure 1 is a block diagram showing a configuration of a voice command recognition apparatus according to an embodiment of the present disclosure;

[0035] Figure 2 is an exemplary screen showing a speech recognition analysis process for each domain according to an embodiment of the present disclosure;

[0036] Figure 3 are exemplary screens illustrating a process of registering and processing a package command using one or more voice commands that are repeatedly used according to an embodiment of the present disclosure;

[0037] Figure 4 are exemplary screens illustrating a process of registering and processing a package command using a user's voice command speaking mode according to an embodiment of the present disclosure;

[0038] Figure 5are exemplary screens illustrating a process of correcting and registering the additionally spoken voice command in a pre-generated package command when another voice command is additionally spoken when a pre-generated package command is spoken according to an embodiment of the present disclosure;

[0039] Figure 6 are exemplary screens illustrating a process of correcting a pre-generated package command based on surrounding circumstances when the pre-generated package command is spoken according to an embodiment of the present disclosure;

[0040] Figure 7 is a diagram illustrating an exemplary screen when a command requesting deregistration of one of one or more commands in the pre-generated package command is additionally spoken when a pre-generated package command is spoken according to an embodiment of the present disclosure;

[0041] Figure 8 The embodiment of the present disclosure is implemented in a composite manner. Figures 3 to 7 Example screens of the process for the case of

[0042] Fig. 9 is a block diagram illustrating a computing system according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0043] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. When adding reference numerals to the components of each drawing, it should be noted that the same reference numerals represent the same or equivalent components even if they are shown in different drawings. In addition, when describing the embodiments of the present disclosure, detailed descriptions of well-known features or functions will be excluded to avoid unnecessarily obscuring the main points of the present disclosure.

[0044] When describing components according to embodiments of the present disclosure, terms such as "first", "second", "A", "B", "(a)", "(b)", etc. may be used. These terms are only used to distinguish one component from another, and the nature, order or sequence of the components are not limited by the terms. Unless otherwise defined, all terms used herein, including technical terms or scientific terms, have the same meanings as those generally understood by technicians in the field to which the present disclosure belongs. Terms such as those defined in commonly used dictionaries will be interpreted as having the same meanings as the contextual meanings in the relevant technical field, and will not be interpreted as having ideal or overly formal meanings unless expressly defined in this application as having ideal or overly formal meanings.

[0045] Embodiments of the present disclosure may disclose a configuration for identifying the presence of commands spoken sequentially within a threshold time after one command is spoken to generate a package command, and a configuration for determining whether to execute commands in the package command sequentially or simultaneously to execute the package command.

[0046] Next, we will refer to Figures 1 to 9 Embodiments of the present disclosure are described in detail.

[0047] Figure 1 is a block diagram illustrating a configuration of a voice command recognition apparatus according to an embodiment of the present disclosure.

[0048] The voice command recognition device 100 according to an embodiment of the present disclosure can be implemented in a vehicle. In this case, the voice command recognition device 100 can be integrated with a control unit in the vehicle, or can be implemented as a separate device and connected to the control unit of the vehicle through a separate connection device.

[0049] The voice command recognition apparatus 100 may register one or more voice commands selected by analyzing one or more voice commands repeatedly used by a user or a voice command utterance pattern of the user to generate the one or more voice commands into one package command.

[0050] In addition, the voice command recognition apparatus 100 may analyze a voice command additionally spoken when a pre-generated one-package command is spoken, and perform one of addition, correction, and deletion on the one-package command.

[0051] In addition, the voice command recognition apparatus 100 may judge the current surrounding situation when a pre-generated package command is spoken, and perform one of addition, correction, and deletion on the package command.

[0052] Reference Figure 1 , the voice command recognition device 100 may include a communication device 110 , a storage device 120 , a display 130 , and a processor 140 .

[0053] The communication device 110 may be a hardware device implemented using various electronic circuits for transmitting and receiving signals via wireless or wired connections. In an embodiment of the present disclosure, the communication device 110 may use an in-vehicle network communication technology, and may use wireless Internet technology or short-range communication technology to perform vehicle-to-infrastructure (V2I) communication with a server, infrastructure, or another vehicle outside the vehicle. Here, the in-vehicle network communication technology may be to perform inter-vehicle communication through controller area network (CAN) communication, local area Internet (LIN) communication, Flex-Ray communication, etc. In addition, wireless Internet technology may include wireless local area network (WLAN), wireless broadband (WiBro), wireless fidelity (Wi-Fi), global microwave access interoperability (Wimax), etc. In addition, short-range communication technology may include Bluetooth, ZigBee, ultra-wideband (UWB), radio frequency identification (RFID), infrared data communication (IrDA), etc.

[0054] As an example, the communication device 110 may receive data for voice recognition from an external server and may communicate with a device in the vehicle to execute a voice command.

[0055] The storage device 120 may store data and / or algorithms required for the operation of the processor 140 , particularly algorithms and data related to speech recognition.

[0056] As an example, the storage device 120 may store a database for each domain used for speech recognition.

[0057] The storage device 120 may include at least one type of storage medium such as: flash memory, hard disk memory, micro memory, card memory (for example, secure digital (SD) card or extreme digital (XD) card), random access memory (RAM), static RAM (SRAM), read-only memory (ROM), programmable ROM (PROM), electrically erasable PROM (EEPROM), magnetic RAM (MRAM), magnetic disk, and optical disk.

[0058] The display 130 may include: an input device for receiving a control command from a user; and an output device for outputting the result of voice recognition of the voice command recognition device 100. Here, the input device may include a microphone, etc. In this case, the microphone, etc. may be provided separately from the display 130. The output device may include a display, and may further include a voice output device such as a speaker. In this case, when a touch sensor such as a touch film, a touch sheet, or a touch pad is provided in the display, the display may be used as a touch screen, and may be implemented in the form that the input device and the output device are integrated with each other. In an embodiment of the present disclosure, the output device may output the result of voice recognition, including one or more results of generation, addition, correction, and deletion of a command.

[0059] In this case, the display may include at least one of a liquid crystal display (LCD), a thin film transistor-LCD (TFT-LCD), an organic light emitting diode (OLED) display, a flexible display, a field emission display (FED), and a three-dimensional (3D) display.

[0060] The processor 140 may be electrically connected to the communication device 110, the storage device 120, the display 130, etc., and may electrically control each component. The processor 140 may be a circuit that executes software instructions, and may perform various data processing and calculations described below.

[0061] The processor 140 may process signals transmitted between various components of the voice command recognition apparatus 100. The processor 140 may include, for example, a voice recognition engine.

[0062] The processor 140 may analyze one or more voice commands that are repeatedly used by the user, or may analyze the user's voice command speaking pattern. In this case, when the number of times the user uses the voice command is greater than or equal to a predetermined number of times (N times), the processor 140 may determine the voice command as a repeatedly used voice command. In addition, when one or more voice commands are spoken sequentially, the processor 140 may select the voice command as a repeatedly used voice command by increasing the number of times spoken, regardless of the speaking order of the one or more voice commands. In other words, even when one or more voice commands are spoken more than a predetermined number of times, or when one or more voice commands are changed in order and spoken, the processor 140 may recognize that the same command is executed and the number of times spoken may be increased.

[0063] The processor 140 may register one or more voice commands selected by analyzing one or more voice commands repeatedly used by a user or a voice command utterance pattern of the user to generate the one or more voice commands into one package command.

[0064] When one package command is spoken, the processor 140 may determine whether to execute one or more voice commands registered in one package command sequentially or simultaneously.

[0065] The domains of one or more voice commands registered in one package command may be different from each other. When the domains of one or more voice commands registered in one package command are the same as each other, the processor 140 may execute the one or more voice commands sequentially. When the domains of one or more voice commands registered in one package command are different from each other, the processor 140 may execute the one or more voice commands simultaneously. When one or more voice commands registered in one package command are sequentially executed when one package command is spoken, the processor 140 may collect information about the next voice command to be executed in advance, thereby increasing the speed of executing the voice commands.

[0066] The processor 140 can analyze the voice command utterance pattern by identifying whether there are sequentially spoken commands within a threshold time after a command is spoken. When the sequentially spoken commands are spoken more than a predetermined number of times within the threshold time, the processor 140 can generate the commands into a package command.

[0067] Even when one or more voice commands are changed in order and spoken, the processor 140 may recognize that the same command is executed and may increase the number of times spoken.

[0068] When a voice command is additionally spoken when one package command is spoken, the processor 140 may additionally register the additionally spoken voice command in the one package command.

[0069] When one package command to which the additional spoken voice command is additionally registered is spoken, the processor 140 may execute one or more voice commands pre-registered in one package command and the additional spoken voice command together.

[0070] When a command requesting cancellation of one of the one or more voice commands registered in the package command is additionally spoken when a package command is spoken, the processor 140 may delete the voice command requested to be cancelled from among the one or more voice commands registered in the package command.

[0071] When a package command in which the voice command requested to be canceled is deleted is spoken, the processor 140 may execute other voice commands except the deleted command among one or more voice commands pre-registered in one package command.

[0072] When a package command is spoken, the processor 140 may suggest correcting a portion of the one or more voice commands registered in the package command or adding a voice command based on the surrounding conditions. In this case, the surrounding conditions may include at least one or more of temperature, humidity, weather, light intensity, season, date, day of the week, time, location, traffic conditions, and vehicle speed.

[0073] The processor 140 may analyze a voice command additionally spoken when a package command is spoken, and perform one or more of correction, deletion, and addition on the package command.

[0074] As described above, the embodiments of the present disclosure can register and execute one or more repeatedly used voice commands in an integrated manner in a package command, so that the user speaks one package command instead of multiple voice commands, thereby improving the voice recognition rate and increasing the voice command processing speed.

[0075] In addition, the embodiments of the present disclosure may analyze a user's voice command utterance pattern, or may judge surrounding circumstances, and perform one of correction, deletion, and addition on a pre-generated package command.

[0076] Figure 2 2 is an exemplary screen illustrating a speech recognition analysis process for each domain according to an embodiment of the present disclosure.

[0077] Reference Figure 2 , when the user says "What's the weather like today?" Figure 1 The voice command recognition device 100 can analyze the domain and can collect and output information about "weather". In addition, when the user says "How is your luck today?", the voice command recognition device 100 can analyze the domain and can collect and output information about "luck".

[0078] Next, we will refer to Figures 3 to 8The process of registering, deleting or adding one or more voice commands in a package command is described in detail.

[0079] Next, assume Figure 1 The voice command recognition device 100 performs Figures 3 to 8 In addition, Figures 3 to 8 The operations described in the description may be understood to be controlled by the processor 140 of the voice command recognition apparatus 100 .

[0080] Figure 3 are exemplary screens illustrating a process of registering and processing a package command using one or more voice commands that are repeatedly used according to an embodiment of the present disclosure.

[0081] Reference Figure 3 , an embodiment is illustrated as the voice command recognition device 100 collects voice commands executed after the vehicle is started, registers one or more commands repeatedly used by the user in a package command, and executes the registered one or more voice commands when a package command is spoken.

[0082] When Figure 3 As shown in the reference numeral 301, when three voice commands "Tell me the weather", "Tell me the stock information" and "Tell me the traffic conditions" are repeatedly spoken, as shown in the reference numeral 302, the voice command recognition device 100 can suggest registering the three commands as a package command.

[0083] When a package command is registered, as shown in reference numeral 303, when "package 1" is spoken as a package command, the voice command recognition apparatus 100 may collect and output information on weather, stock, and traffic domains.

[0084] Figure 4 2 are exemplary screens illustrating a process of registering and processing a package command using a user's voice command speaking mode according to an embodiment of the present disclosure.

[0085] Reference Figure 4 , Figure 1 The voice command recognition device 100 may collect voice commands executed after the vehicle is started, and may analyze a user's voice command utterance pattern.

[0086] When the voice commands "tell me the weather", "tell me the stock information", and "tell me the traffic conditions" are changed in order and repeatedly spoken, the voice command recognition device 100 can analyze the speaking frequency and time difference of each voice command, so that even when the commands are changed in order and executed, it can be recognized that the same command is executed and the number of times spoken is increased. In other words, in reference numeral 401, even when the voice commands "tell me the weather", "tell me the stock information", and "tell me the traffic conditions" are changed in order, the voice command recognition device 100 can record that the three commands are spoken three times.

[0087] Therefore, when three commands are spoken as a group more than a predetermined number of times and when the final command is executed, as indicated by reference numeral 402 , the voice command recognition apparatus 100 may suggest to the user that the three commands be registered as one package command (Package 1 ).

[0088] When three commands are registered as a package command (package 1), as shown in reference numeral 403, when the user says "package 1", the voice command recognition apparatus 100 can sequentially execute the voice commands "tell me the weather", "tell me the stock information", and "tell me the traffic conditions". In this case, when the domains of the executed one or more commands are different from each other, the voice command recognition apparatus 100 can collect information about the next command to be executed in advance when executing the first executed command, so that the information can be quickly provided.

[0089] Figure 5 2 are exemplary screens illustrating a process of correcting and registering the additionally spoken voice command in a pre-generated package command when another voice command is additionally spoken when a pre-generated package command is spoken according to an embodiment of the present disclosure.

[0090] Reference Figure 5 501, when a voice command "turn on the air conditioner" is additionally spoken when a package 1 in which a group of voice commands "tell me the weather", "tell me the stock information" and "tell me the traffic conditions" are registered is spoken, as shown in the reference numeral 502, Figure 1 The voice command recognition device 100 may suggest adding a voice command “turn on the air conditioner” to package 1 to correct and register package 1.

[0091] Thereafter, as indicated by reference numeral 503, when package 1 is spoken, the voice command recognition apparatus 100 may execute four commands “tell me the weather”, “tell me stock information”, “tell me traffic conditions”, and “turn on the air conditioner”.

[0092] Figure 62 is an exemplary screen showing a process of correcting a pre-generated packet command based on surrounding conditions when the pre-generated packet command is spoken according to an embodiment of the present disclosure. In this case, the surrounding conditions may include outside temperature, weather, season, humidity, light intensity, vehicle speed, inside temperature, etc.

[0093] Reference Figure 6 601, when a package 1 pre-generated by a voice command having weather, stock and traffic as domains is spoken, Figure 1 The voice command recognition device 100 can inform the user of the fields that cannot provide real-time information in weather, stocks, and traffic. In reference numeral 601, regarding stocks, the voice command recognition device 100 can determine the day of the week, and when today is a holiday, it is difficult to provide real-time stock information, so the voice command recognition device 100 can display an exemplary screen for notifying the user of stock information based on the last closing price.

[0094] In the figure mark 602, an embodiment is illustrated as that when a package 1 pre-generated by a voice command having weather, stocks, and traffic as domains is spoken, the voice command recognition device 100 determines the temperature inside the vehicle, suggests the user to turn on the air conditioner when the temperature inside the vehicle is high, and notifies the user of the weather, stocks, and traffic with the air conditioner turned on when the user accepts the suggestion.

[0095] In reference numeral 603, an embodiment of the present disclosure is illustrated that when package 1 pre-generated by a voice command having weather, stock, and traffic as domains is spoken, the voice command recognition device 100 determines the current weather, season, temperature, humidity, etc., and suggests vehicle air conditioning control suitable therefor. In reference numeral 603, an embodiment of the present disclosure is illustrated that because the current season is winter, the voice command recognition device 100 suggests adding a heater and heated steering wheel operation in package 1.

[0096] Figure 7 is a diagram illustrating an exemplary screen when a command requesting deregistration of one of one or more commands in the pre-generated package command is additionally spoken when a pre-generated package command is spoken according to an embodiment of the present disclosure.

[0097] Reference Figure 7 701, when a command to cancel the command to turn on the air conditioner is additionally spoken when the package 1 in which the voice commands related to weather, stocks, traffic, and air conditioning are registered is spoken, as shown in the reference numeral 702, Figure 1 The voice command recognition device 100 can delete the command to turn on the air conditioner from the package 1.

[0098] Figure 8 The embodiment of the present disclosure is implemented in a composite manner. Figures 3 to 7 Example screens of the process of the case.

[0099] Reference Figure 8 Reference numeral 801, Figure 1 The voice command recognition device 100 can recommend registering the frequently used voice commands "Tell me the weather", "Tell me the stock information" and "Tell me the traffic conditions" as package 1 by analyzing one or more voice commands repeatedly used by the user or the user's voice command utterance pattern.

[0100] When package 1 is generated, when the voice command "turn on the air conditioner" is additionally spoken when package 1 is spoken as shown in reference numeral 802, the voice command recognition device 100 can output a screen for asking whether to add the voice command "turn on the air conditioner" in package 1 as shown in reference numeral 803.

[0101] When package 1 is spoken after adding the voice command "turn on the air conditioner" in package 1, as shown in reference numeral 804, the voice command recognition apparatus 100 may suggest adding the voice command "turn on the heater" to replace the voice command "turn on the air conditioner" included in package 1 in consideration of the surrounding situation. As shown in reference numeral 805, the voice command recognition apparatus 100 may delete the command related to the air conditioner from package 1, and may register commands related to weather, stocks, traffic, and heater in package 1.

[0102] Therefore, the embodiment of the present disclosure can register one or more commands that are repeatedly used as a package command ( Figure 3 ). The embodiment of the present disclosure can analyze the user's voice command speaking mode, and can register one or more voice commands as a package command ( Figure 4 ).

[0103] In addition, when one or more voice commands are spoken in addition to speaking a pre-generated package command, the embodiment of the present disclosure can add a voice command to the pre-generated package command to correct and register the package command ( Figure 5 ).

[0104] In addition, the embodiments of the present disclosure can judge the current surrounding situation and can change and execute the pre-generated package command ( Figure 6 ).

[0105] In addition, when a command to cancel one of the one or more voice commands registered in the package command is spoken when a pre-generated package command is spoken, an embodiment of the present disclosure may reflect a command to cancel one of the one or more voice commands to delete the voice command requested to be canceled from the pre-generated package command.

[0106] Fig. 9 is a block diagram illustrating a computing system according to an embodiment of the present disclosure.

[0107] Reference Fig. 9 , the computing system 1000 may include at least one processor 1100 , a memory 1300 , a user interface input device 1400 , a user interface output device 1500 , a storage device 1600 , and a network interface 1700 connected to each other via a bus 1200 .

[0108] The processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in the memory 1300 and / or the storage device 1600. The memory 1300 and the storage device 1600 may include various types of volatile storage media or non-volatile storage media. For example, the memory 1300 may include a ROM (Read Only Memory) 1310 and a RAM (Random Access Memory) 1320.

[0109] Therefore, the operations of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly in a hardware or software module executed by the processor 1100, or in a combination of hardware and software modules. The software module may reside in a storage medium (i.e., memory 1300 and / or storage device 1600) such as RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, and a CD-ROM.

[0110] An exemplary storage medium may be coupled to the processor 1100, and the processor 1100 may read information from the storage medium and may record information in the storage medium. Alternatively, the storage medium may be integrated with the processor 1100. The processor 1100 and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may reside in a user terminal. In another case, the processor 1100 and the storage medium may reside in a user terminal as separate components.

[0111] The present technology can analyze one or more voice commands repeatedly used by a user or the user's voice command speaking pattern to register one or more voice commands as a package command, and can determine whether to execute each command in the package command sequentially or simultaneously when speaking a package command, so as to execute the registered one or more voice commands sequentially or simultaneously, thereby increasing user convenience.

[0112] The present technology can analyze a voice command that is additionally spoken when a pre-generated package command is spoken, and perform one of addition, correction, and deletion on the package command, thereby increasing user convenience.

[0113] The present technology can judge the current surrounding situation when a pre-generated package command is spoken, and perform one of adding, correcting and deleting a package command, thereby increasing user convenience.

[0114] Furthermore, various effects directly or indirectly determined by the present disclosure can be provided.

[0115] Although the present disclosure has been described above with reference to exemplary embodiments and the accompanying drawings, the present disclosure is not limited thereto but may be variously modified and changed by those skilled in the art without departing from the idea and scope of the present disclosure as claimed in the appended claims.

[0116] Therefore, the exemplary embodiments of the present disclosure are provided to explain the idea and scope of the present disclosure, rather than to limit the idea and scope of the present disclosure, and the idea and scope of the present disclosure are not limited by these embodiments. The scope of the present disclosure should be interpreted based on the attached claims, and all technical ideas within the scope equivalent to the claims should be included in the scope of the present disclosure.

Claims

1. A voice command recognition device, comprising: a processor that registers one or more voice commands selected by analyzing one or more voice commands repeatedly used by a user or a voice command utterance pattern of the user to generate a package command; as well as a storage device storing data or algorithms used by the processor to perform speech recognition, wherein the processor analyzes the voice command speaking pattern by identifying whether there are commands that are sequentially executed within a threshold time after a command is spoken, and when the commands that are sequentially executed within the threshold time are spoken more than a predetermined number of times, the processor generates the command as the one package command, When the one package command is spoken, the processor determines whether to execute the one or more voice commands registered in the one package command sequentially or simultaneously, and When the domains of the one or more voice commands registered in the one package command are identical to each other, the processor executes the one or more voice commands sequentially, and when the domains of the one or more voice commands registered in the one package command are different from each other, the processor executes the one or more voice commands simultaneously.

2. The voice command recognition device according to claim 1, wherein: When the one or more voice commands registered in the one package command are sequentially executed when the one package command is spoken, the processor collects information about a voice command to be executed next in advance.

3. The voice command recognition device according to claim 1, wherein: Even when the one or more voice commands are changed in order and spoken, the processor recognizes that the same command is executed and increases the number of times spoken.

4. The voice command recognition device according to claim 1, wherein: When there is an additionally spoken voice command when the one package command is spoken, the processor additionally registers the additionally spoken voice command in the one package command.

5. The voice command recognition device according to claim 4, wherein: When the one package command to which the additional spoken voice command is additionally registered is spoken, the processor executes the one or more voice commands pre-registered in the one package command and the additional spoken voice command together.

6. The voice command recognition device according to claim 1, wherein: When a command requesting to cancel one of the one or more voice commands registered in the one package command is additionally spoken when the one package command is spoken, the processor deletes the voice command requested to be canceled from among the one or more voice commands registered in the one package command.

7. The voice command recognition device according to claim 6, wherein: When a package command is spoken in which the voice command requested to be canceled is deleted, the processor executes other voice commands except the deleted command among the one or more voice commands pre-registered in the one package command.

8. The voice command recognition device according to claim 1, wherein: When the one package command is spoken, the processor suggests correcting a portion of the one or more voice commands registered in the one package command or adding a voice command based on surrounding conditions.

9. The voice command recognition device according to claim 8, wherein: The surrounding conditions include at least one or more of temperature, humidity, weather, light intensity, season, date, day of the week, time, location, traffic conditions, and vehicle speed.

10. The voice command recognition device according to claim 1, wherein: The processor analyzes a voice command additionally spoken when the one package command is spoken, and performs at least one or more of correction, deletion, and addition on the one package command.

11. A voice command recognition method, comprising: analyzing one or more voice commands repeatedly used by a user or a pattern of utterance of voice commands by the user; as well as registering one or more voice commands selected by analyzing the one or more voice commands repeatedly used by the user or a voice command utterance pattern of the user to generate a package command, The commands for generating a package include: analyzing the voice command utterance pattern by identifying whether there are commands that are sequentially executed within a threshold time after one command is uttered, and generating the command as the one-pack command when the commands that are sequentially executed within the threshold time are uttered more than a predetermined number of times, and The voice command recognition method further comprises: determining whether to execute the one or more voice commands registered in the one package command sequentially or simultaneously when the one package command is spoken; and When the domains of the one or more voice commands registered in the one package command are identical to each other, the one or more voice commands are sequentially executed, and when the domains of the one or more voice commands registered in the one package command are different from each other, the one or more voice commands are simultaneously executed.

12. The voice command recognition method according to claim 11, further comprising: When the one or more voice commands registered in the one package command are sequentially executed when the one package command is spoken, information on a voice command to be executed next is collected in advance.

13. The voice command recognition method according to claim 11, wherein: Generating a package command further includes: Even when the one or more voice commands are changed in order and spoken, it is recognized that the same command is executed and the number of times spoken is increased.

14. The voice command recognition method according to claim 11, further comprising: When there is an additionally spoken voice command when the one package command is spoken, the additionally spoken voice command is additionally registered in the one package command.

15. The voice command recognition method according to claim 11, further comprising: When a command requesting cancellation of one of the one or more voice commands registered in the one package command is additionally spoken when the one package command is spoken, the voice command requested to be cancelled is deleted from the one or more voice commands registered in the one package command.

16. The voice command recognition method according to claim 11, further comprising: When the one package command is spoken, based on surrounding conditions, it is suggested to correct a part of the one or more voice commands registered in the one package command or to add a voice command; as well as The voice command additionally spoken when the one package command is spoken is analyzed, and at least one of correction, deletion, and addition is performed on the one package command.

Images