Voice control system and method for voice selection, and smart robot using the same

{
  "publication_number": "US10672395B2",
  "country": "US",
  "kind": "B2",
  "title": "Voice control system and method for voice selection, and smart robot using the same",
  "abstract": "Disclosed are a voice control system, a method for selecting options and a smart robot using the same. The method includes: detecting whether there is any first command sentence in a voice signal; determining a set of the voice options corresponding to the first command sentence; sequentially playing each voice option of the set of voice options, wherein there is a predetermined time interval between every two voice options; within the predetermined time interval, detecting whether there is a response sentence in the voice signal; determining whether the response sentence matches with one of the voice options when there is the response sentence in the voice signal; and if the response sentence matches with one of the voice options, outputting the task content corresponding to the voice option and then making the voice control system enter a sleep mode.",
  "claims": [
    "1. A voice control system, entering a sleep mode or a working mode, comprising: an audio detection device, in the sleep mode continuously detecting whether there is a wake-up sentence in a voice signal received by a receiver, and generating an indication signal when the wake-up sentence is detected; a memory, storing an interaction program and a database, wherein a plurality of first command sentences, sets of voice options and a plurality of task contents are stored in the database, each first command sentence corresponds to one set of the voice options, and each voice option corresponds to one of the task contents; and a processor, connected to the audio detection device and the memory, wherein the voice control system operates in the working mode after the processor is woken up by the indication signal, and in the working mode the processor executes the interaction program to: control the audio detection device to detect whether there is any first command sentence in the voice signal received by the receiver; determine the set of the voice options corresponding to the first command sentence; through a player, sequentially play each voice option of the set of the voice options, wherein there is a predetermined time interval between every two voice options played by the player; within the predetermined time interval, control the audio detection device to detect whether there is a response sentence in a voice signal received by the receiver; determine whether the response sentence matches with one of the voice options when there is the response sentence in the voice signal received by the receiver; and if the response sentence matches with one of the voice options, output the task content corresponding to the voice option and then make the voice control system enter the sleep mode.",
    "2. The voice control system according to claim 1, wherein when there is no response sentence detected in the voice signal received by the receiver, or when the response sentence does not match with any of the voice options, the processor further executes the interaction program to: determine whether the voice options have all been played; control the player to continue sequentially playing the remaining voice options when the voice options have not yet all been played; and control the audio detection device to detect whether there is any first command sentence in the voice signal received by the receiver when the voice options have all been played.",
    "3. The voice control system according to claim 1, wherein when the processor controls the player to sequentially play each voice option of the set of the voice options, the audio detection device stops detecting the voice signal received by the receiver, but within the predetermined time interval, the audio detection device again detects the voice signal received by the receiver.",
    "4. The voice control system according to claim 1, wherein within the predetermined time interval, the processor extends the predetermined time interval when the amplitude of the voice signal received by the receiver is larger than a threshold value.",
    "5. The voice control system according to claim 1, wherein when determining whether the response sentence matches with one of the voice options, the processor further executes the interaction program to: convert a response sentence to a text data; translate the text data to a machine language through a natural language processing logic; and determine whether the response sentence matches with one of the voice options according to the machine language.",
    "6. The voice control system according to claim 5, wherein when determining whether the response sentence matches with one of the voice options according to the machine language, the processor determines whether the response sentence is one of the voice options, a specific number corresponding to one of the voice options, a synonymy of one of the voice options, or a simplified term corresponding to one of the voice options.",
    "7. The voice control system according to claim 6, wherein when the response sentence does not match with any of the voice options, the specific number corresponding to any of the voice options, the synonymy of any of the voice options, or the simplified term corresponding to any of the voice options, the processor generates a spelling data of the response sentence and then determines whether the spelling data of the response sentence matches with a spelling data of one of the voice options.",
    "8. The voice control system according to claim 1, wherein a plurality of second command sentences are stored in the memory, each second command sentence corresponds to one of the task contents, and the processor further executes the interaction program further to: control the audio detection device to detect whether one of the second command sentences is in the voice signal received by the receiver; and output the task content corresponding to the second command sentence, and then make the voice control system enter the sleep mode.",
    "9. A method for selecting options, adapted to a voice control system, wherein the voice control system enters a sleep mode or a working mode, the voice control system includes an audio detection device, a memory and a processor, a plurality of first command sentences, sets of voice options and a plurality of task contents are stored in the database, each first command sentence corresponds to one set of the voice options, each voice option corresponds to one of the task contents, the processor is connected to the audio detection device and the memory, the processor is configured to execute an interaction program to implement the method, and the method comprises: detecting whether there is any first command sentence in the voice signal received by a receiver; determining the set of the voice options corresponding to the first command sentence; through a player, sequentially playing each voice option of the set of the voice options, wherein there is a predetermined time interval between every two voice options played by the player; within the predetermined time interval, detecting whether there is a response sentence in a voice signal received by the receiver; determining whether the response sentence matches with one of the voice options when there is the response sentence in the voice signal received by the receiver; and if the response sentence matches with one of the voice options, outputting the task content corresponding to the voice option, and then making the voice control system enter the sleep mode.",
    "10. The method according to claim 9, further comprising: determining whether the voice options have all been played; controlling the player to continue sequentially playing the remaining voice options when the voice options have not yet all been played; and controlling the audio detection device to detect whether there is any first command sentence in the voice signal received by the receiver when the voice options have all been played.",
    "11. The method according to claim 9, further comprising: when the player sequentially plays each voice option of the set of the voice options, stopping detection of the voice signal received by the receiver, but within the predetermined time interval, restarting detection of the voice signal received by the receiver.",
    "12. The method according to claim 9, further comprising: within the predetermined time interval, extending the predetermined time interval when the amplitude of the voice signal received by the receiver is larger than a threshold value.",
    "13. The method according to claim 9, wherein the step of determining whether the response sentence matches with one of the voice options includes: converting a response sentence to a text data; translating the text data to a machine language through a natural language processing logic; and determining whether the response sentence matches with one of the voice options according to the machine language.",
    "14. The method according to claim 13, wherein the step of determining whether the response sentence matches with one of the voice options according to the machine language includes: determining whether the response sentence is one of the voice options, a specific number corresponding to one of the voice options, a synonymy of one of the voice options, or a simplified term corresponding to one of the voice options.",
    "15. The method according to claim 14, wherein the step of determining whether the response sentence does not match with one of the voice options according to the machine language further includes: generating a spelling data of the response sentence and then determining whether the spelling data of the response sentence matches with a spelling data of one of the voice options when the response sentence does not match with any of the voice options, the specific number corresponding to any of the voice options, the synonymy of any of the voice options, or the simplified term corresponding to any of the voice options.",
    "16. The method according to claim 9, wherein a plurality of second command sentences are stored in the memory, each second command sentence corresponds to one of the task contents, and the method further comprises: controlling the audio detection device to detect whether one of the second command sentences is in the voice signal received by the receiver; and outputting the task content corresponding to the second command sentence, and then making the voice control system enter the sleep mode.",
    "17. A smart robot, comprising: a CPU; and a voice control system according to claim 1, configured to provide a plurality of voice options according to a command sentence in a voice signal received by a receiver, recognize a response sentence and accordingly output a task content; wherein the CPU generates a control signal according to the task content such that the smart robot executes an action according to the control signal.",
    "18. The smart robot according to claim 17, wherein in the voice control system, the processor is a built-in processing unit or a cloud server."
  ],
  "description_excerpt": "1. Field of the Invention The present disclosure relates to a voice control system, a method for voice selection and a smart robot using the same; in particular, to a voice control system, a method for voice selection and a smart robot that can clearly provide a user with options to select from and then correctly recognize the option chosen by the user. 2. Description of Related Art Generally, a robot refers to a machine device that can automatically execute assigned tasks. A robot can be controlled based on some simple logic circuits or advanced computer programs. Thus, a robot is usually a high-end mechatronic device. In recent years, many new technologies in robotics have been developed, giving birth to different types of robots such as the industrial robot, the service robot and the like. For convenience considerations, service robots with various applications have become much more accepted by people, such as a personal companion robot, a domestic-use robot or a professional service robot. These robots are capable of recognizing the meaning of what a user says and accordingly interacts with the user or provides relevant services to the user.\n\nWhen a user issues a command, the robot may provide the user with several options based on its built-in program. However, misjudgments may often occur due to interferences resulting from background noises. Also, the user can often only issue a command after the robot has specified all available options. In addition, the robot can accurately recognize the command delivered by the user only when the command completely matches with one of the options provided by the robot.",
  "cpc": [
    "G10L 15/22",
    "B25J 13/003",
    "G06F 3/167",
    "G10L 15/18",
    "G10L 15/26",
    "G10L 2015/088",
    "G10L 2015/223",
    "G10L 25/51",
    "G10L 25/78"
  ],
  "ipc": [
    "G06F 3/16",
    "G10L 15/08",
    "G10L 15/18",
    "G10L 15/22",
    "G10L 25/78"
  ],
  "assignees": [
    "AROBOT INNOVATION CO LTD",
    "ADATA TECH CO LTD"
  ],
  "inventors": [
    "WANG ROU-WEN",
    "KUO HUNG-PIN",
    "HSU YIN CHUAN",
    "LIU HSIANG HAN"
  ],
  "filing_date": "2018-04-10",
  "publication_date": "2020-06-02",
  "grant_date": "2020-06-02",
  "priority_date": "2017-12-22",
  "application_number": "US-201815949105-A",
  "family_id": "66213756",
  "citations": [
    "US10430156B2",
    "US10504509B2",
    "US2011210849A1",
    "US2013218574A1",
    "US2013275875A1",
    "US2014108017A1",
    "US2016098992A1",
    "US2016133255A1",
    "US2016210965A1",
    "US2016358603A1",
    "US2017011745A1",
    "US2017018276A1",
    "US2017344195A1",
    "US2017352350A1",
    "US2018158460A1",
    "US2018174581A1",
    "US2018260680A1",
    "US2018308490A1",
    "US2018322872A1",
    "US2019027152A1",
    "US2019043488A1",
    "US2019115025A1",
    "US2019187787A1",
    "US2019198020A1",
    "US2019206399A1",
    "US2019207777A1",
    "US2019214010A1",
    "US2019237089A1",
    "US2019275680A1",
    "US9495959B2"
  ]
}