WO2018006374A1 - 一种基于主动唤醒的功能推荐方法、系统及机器人 - Google Patents

一种基于主动唤醒的功能推荐方法、系统及机器人 Download PDF

Info

Publication number
WO2018006374A1
WO2018006374A1 PCT/CN2016/089218 CN2016089218W WO2018006374A1 WO 2018006374 A1 WO2018006374 A1 WO 2018006374A1 CN 2016089218 W CN2016089218 W CN 2016089218W WO 2018006374 A1 WO2018006374 A1 WO 2018006374A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
function
preset
robot
wake
Prior art date
Application number
PCT/CN2016/089218
Other languages
English (en)
French (fr)
Inventor
杨新宇
王昊奋
邱楠
Original Assignee
深圳狗尾草智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳狗尾草智能科技有限公司 filed Critical 深圳狗尾草智能科技有限公司
Priority to PCT/CN2016/089218 priority Critical patent/WO2018006374A1/zh
Priority to CN201680001756.5A priority patent/CN106462256A/zh
Publication of WO2018006374A1 publication Critical patent/WO2018006374A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/34Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3438Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment monitoring of user actions
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/017Gesture based interaction, e.g. based on a set of recognized hand gestures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Definitions

  • the present invention relates to the field of robot interaction technologies, and in particular, to a function recommendation method, system and robot based on active wakeup.
  • robots are used more and more. For example, some elderly people and children can interact with robots, including dialogue and entertainment. When interacting with the robot, the user often causes the robot to run a function, such as playing a song, reading a novel, etc., to increase the user's sense of communication and let the user feel companionship.
  • a function such as playing a song, reading a novel, etc.
  • the object of the present invention is to provide a function recommendation method, system and robot based on active wake-up, which enables the robot to actively communicate with the user and set the content of the communication, thereby improving the user experience.
  • a functional recommendation method based on active wakeup including:
  • the robot is actively woken up;
  • the function recommended to the user is determined according to the user's usage parameters for each function.
  • the method further comprises: recommending the function to the user by means of multi-modal feedback.
  • the manner of the multi-modal feedback includes but is not limited to voice feedback, and is determined to be used
  • the step of the function recommended by the user further includes: recommending the function to the user at least by means of voice feedback.
  • the usage parameter includes, but is not limited to, a frequency of use or/and a duration of use of the function in a preset time period, and the step of determining a function recommended to the user according to the usage parameter of each function by the user specifically includes: :
  • At least the function of reaching the preset frequency of use or/and the duration of use within a preset time period is selected, and the function is recommended to the user.
  • the recommendation is performed according to the frequency of use or/and the duration of use.
  • the invention discloses a function recommendation system based on active wakeup, comprising:
  • the obtaining module is configured to obtain multi-modal information of the user
  • a matching module configured to match the multimodal information of the user according to a preset wakeup parameter
  • the wake-up module is configured to actively wake up the robot if the multi-modal information of the user matches the preset wake-up parameter;
  • the processing module is configured to determine a function recommended to the user according to the usage parameter of the user for each function.
  • the system further comprises a recommendation module for recommending the function to the user by means of multi-modal feedback.
  • the manner of the multi-modal feedback includes, but is not limited to, voice feedback, and the recommendation module is specifically configured to: recommend the function to the user at least by means of voice feedback.
  • the usage parameter includes, but is not limited to, a frequency of use or/and a duration of use of the function in a preset time period
  • the processing module is specifically configured to: at least select a preset usage frequency within a preset time period Or / and the function of the duration, recommend this function to the user.
  • the recommendation is performed according to the frequency of use or/and the duration of use.
  • a robot comprising a function recommendation system based on active wakeup as described in any of the above.
  • the active wake-based function recommendation method of the present invention includes: acquiring user multi-modal information; and matching with the user multi-modal information according to a preset wake-up parameter; When the user multi-modal information matches the preset wake-up parameters, the robot is actively woken up; according to the user's usage parameters for each function, the function recommended to the user is determined. This allows you to get the user's multimodal information such as the user's specific distance from the robot. When the action or expression is set, the robot matches the multi-modal information with the wake-up parameters. If the match is consistent, the robot will wake up actively. After that, the robot will recommend the corresponding function to the user's usage parameters, such as the user's usage behavior. In this way, the robot can be more anthropomorphic when interacting with humans. This method can enhance the anthropomorphicity of robot interactive content generation, enhance the human-computer interaction experience, and improve intelligence.
  • FIG. 1 is a flowchart of a function recommendation method based on active wakeup according to Embodiment 1 of the present invention
  • FIG. 2 is a schematic diagram of a function recommendation system based on active wakeup according to Embodiment 2 of the present invention.
  • Computer devices include user devices and network devices.
  • the user equipment or the client includes but is not limited to a computer, a smart phone, a PDA, etc.;
  • the network device includes but is not limited to a single network server, a server group composed of multiple network servers, or a cloud computing-based computer or network server. cloud.
  • the computer device can operate alone to carry out the invention, and can also access the network and implement the invention through interoperation with other computer devices in the network.
  • the network in which the computer device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.
  • first means “first,” “second,” and the like may be used herein to describe the various elements, but the elements should not be limited by these terms, and the terms are used only to distinguish one element from another.
  • the term “and/or” used herein includes any and all combinations of one or more of the associated listed items. When a unit is referred to as being “connected” or “coupled” to another unit, it can be directly connected or coupled to the other unit, or an intermediate unit can be present.
  • a function recommendation method based on active wakeup including:
  • the function recommendation method based on the active wake-up in this embodiment includes: acquiring multi-modal information of the user; matching the multi-modal information according to the preset wake-up parameter; and if the user multi-modal information and the preset wake-up parameter If they match, the robot will be actively woken up; according to the user's usage parameters for each function, the function recommended to the user is determined.
  • the robot matches the multi-modal information with the wake-up parameter, and if the matching is consistent, the robot will wake up actively, after which the robot will
  • the use parameters of the function such as the user's usage behavior, recommend the corresponding function to the user, so that the robot can be more anthropomorphized when interacting with the human, so that the robot has a human lifestyle in the life time axis, and the method can enhance the robot interaction.
  • the anthropomorphic nature of content generation enhances the human-computer interaction experience and enhances intelligence.
  • the inventor has developed a virtual robot display device and an imaging system capable of forming a 3D animated image, and the virtual robot's host accepts human instructions such as voice to interact with humans, and then a virtual 3D animated image. According to the instructions of the host, the sound and action are replied, so that the robot can be more anthropomorphic, not only can interact with humans in sounds and expressions, but also interact with humans in actions, etc., greatly improving the experience of interaction.
  • the multimodal information in this embodiment may be one of user expression, voice information, gesture information, scene information, image information, video information, face information, pupil iris information, light sense information, and fingerprint information.
  • voice information voice information
  • gesture information scene information
  • image information video information
  • face information face information
  • pupil iris information light sense information
  • fingerprint information fingerprint information.
  • the user's expression is preferred, so that the recognition is accurate and the recognition efficiency is high.
  • the active wake-up method can give the user multi-modal information, for example, the user's actions, the user's After the expression is collected, it is compared with the preset wake-up parameters. If the preset wake-up parameter is reached, the robot will wake up actively and will not wake up if it is not reached. For example, after a human close to a robot, the detection module of the robot detects the proximity of the human, and actively wakes up itself to interact with humans. Wake-up robots can also perform expressions, actions, or other dynamic behaviors made by humans. If humans are standing still, do not make expressions and movements, or are in a static state such as lying still, then they may not reach the preset. The wake-up parameters are thus not considered to wake the robot, and the robot does not actively wake itself up when it detects these behaviors.
  • the usage parameter includes, but is not limited to, including a frequency of use or/and a duration of use of the function within a preset time period, and determining, according to a usage parameter of each function by the user, determining a function recommended to the user.
  • the steps specifically include:
  • At least the function of reaching the preset frequency of use or/and the duration of use within a preset time period is selected, and the function is recommended to the user.
  • the preset use frequency is 5 times. If the user uses the function of playing music for 6 times in this time period according to the previous statistics, then the robot actively takes the initiative. After waking up, the robot will recommend the function of playing music to the user for the user to use the function more quickly.
  • the preset usage frequency is 5 times
  • the usage time is 1 hour
  • only the preset usage time is 1 hour.
  • Usage parameters can also include, for example, playing habits, such as playing music every morning.
  • the recommendation is performed according to the frequency of use or/and the duration of use is from high to low.
  • the method further includes recommending the function to the user by means of multi-modal feedback.
  • the function can be recommended to the user through multi-modal feedback, such as voice feedback, video feedback, voice and motion feedback, etc., so that the user can quickly and accurately understand the recommended function.
  • multi-modal feedback such as voice feedback, video feedback, voice and motion feedback, etc.
  • the manner of the multi-modal feedback includes, but is not limited to, including voice feedback, and after the step of determining a function recommended to the user, the method further includes: at least a party through voice feedback.
  • the function is recommended to the user.
  • this embodiment discloses a function recommendation system based on active wakeup, including:
  • the obtaining module 201 is configured to acquire user multi-modal information.
  • the matching module 202 is configured to match the multi-modality information of the user according to the preset wake-up parameter;
  • the wake-up module 203 is configured to actively wake up the robot if the multi-modality information of the user matches the preset wake-up parameter;
  • the processing module 204 is configured to determine a function recommended to the user according to the usage parameter of the user for each function.
  • the robot matches the multi-modal information with the wake-up parameter, and if the matching is consistent, the robot will wake up actively, after which the robot will
  • the use parameters of the function such as the user's usage behavior, recommend the corresponding function to the user, so that the robot can be more anthropomorphized when interacting with the human, so that the robot has a human lifestyle in the life time axis, and the method can enhance the robot interaction.
  • the anthropomorphic nature of content generation enhances the human-computer interaction experience and enhances intelligence.
  • the inventor has developed a virtual robot display device and an imaging system capable of forming a 3D animated image, and the virtual robot's host accepts human instructions such as voice to interact with humans, and then a virtual 3D animated image. According to the instructions of the host, the sound and action are replied, so that the robot can be more anthropomorphic, not only can interact with humans in sounds and expressions, but also interact with humans in actions, etc., greatly improving the experience of interaction.
  • the multimodal information in this embodiment may be one of user expression, voice information, gesture information, scene information, image information, video information, face information, pupil iris information, light sense information, and fingerprint information.
  • voice information voice information
  • gesture information scene information
  • image information video information
  • face information face information
  • pupil iris information light sense information
  • fingerprint information fingerprint information.
  • the user's expression is preferred, so that the recognition is accurate and the recognition efficiency is high.
  • the active wake-up method can compare the user multi-modal information, for example, the user's motion, the user's expression, etc., with the preset wake-up parameters, and if the preset wake-up parameter is reached, the robot will actively wake up if If it is not reached, it will not wake up. For example, when humans are near the machine After the human, the detection module of the robot detects the proximity of the human being, and then actively wakes up itself to interact with humans. Wake-up robots can also perform expressions, actions, or other dynamic behaviors made by humans. If humans are standing still, do not make expressions and movements, or are in a static state such as lying still, then they may not reach the preset. The wake-up parameters are thus not considered to wake the robot, and the robot does not actively wake itself up when it detects these behaviors.
  • the usage parameter includes, but is not limited to, including a frequency of use or/and a usage duration of the function in a preset time period, and the processing module is specifically configured to: at least select to reach a preset within a preset time period. This function is recommended to the user by the frequency of use or/and the duration of use.
  • the preset use frequency is 5 times. If the user uses the function of playing music for 6 times in this time period according to the previous statistics, then the robot actively takes the initiative. After waking up, the robot will recommend the function of playing music to the user for the user to use the function more quickly.
  • the preset usage frequency is 5 times
  • the usage time is 1 hour
  • only the preset usage time is 1 hour.
  • Usage parameters can also include, for example, playing habits, such as playing music every morning.
  • the recommendation is performed according to the frequency of use or/and the duration of use is from high to low.
  • the system further includes a recommendation module 205 for recommending the function to the user by means of multimodal feedback.
  • the function can be recommended to the user through multi-modal feedback, such as voice feedback, video feedback, voice and motion feedback, etc., so that the user can quickly and accurately understand the recommended function.
  • multi-modal feedback such as voice feedback, video feedback, voice and motion feedback, etc.
  • the manner of the multi-modal feedback includes, but is not limited to, voice feedback, and the recommendation module is specifically configured to: recommend the function to the user at least by means of voice feedback.
  • This embodiment discloses a robot comprising a function recommendation system based on active wakeup as described in any of the above.

Abstract

一种基于主动唤醒的功能推荐方法,包括:获取用户多模态信息(S101);根据预设的唤醒参数与所述用户多模态信息进行匹配(S102);若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒(S103);根据用户对每一功能的使用参数,确定向用户推荐的功能(S104)。在获取到用户的多模态信息时,机器人将多模态信息与唤醒参数进行匹配,若匹配一致则会主动唤醒,之后,机器人就会根据功能的使用参数,向用户推荐相应的功能,使机器人与人交互更加拟人化,该方法能够提升人机交互体验,提高智能性。

Description

一种基于主动唤醒的功能推荐方法、系统及机器人 技术领域
本发明涉及机器人交互技术领域,尤其涉及一种基于主动唤醒的功能推荐方法、系统及机器人。
背景技术
机器人作为与人类的交互工具,使用的场合越来越多,例如一些老人、小孩较孤独时,就可以与机器人交互,包括对话、娱乐等。用户在与机器人交互时,往往会让机器人运行一项功能,例如播放歌曲,读一段小说等等,以增加用户的沟通感,让用户感觉到陪伴。
为了让机器人与人类交互时更加拟人化,以及让用户使用机器人的体验感更好,就需要将机器人设计的更加智能,让机器人在用户没有进行交互时,就与用户打招呼、沟通,从而主动与用户交互,增加好感,提升用户体验。
因此,如何使机器人主动的与用户沟通,以及沟通的内容的设定,提升用户的使用体验,是本技术领域亟需解决的技术问题。
发明内容
本发明的目的是提供一种基于主动唤醒的功能推荐方法、系统及机器人,使机器人主动的与用户沟通,以及沟通的内容的设定,提升用户的使用体验。
本发明的目的是通过以下技术方案来实现的:
一种基于主动唤醒的功能推荐方法,包括:
获取用户多模态信息;
根据预设的唤醒参数与所述用户多模态信息进行匹配;
若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒;
根据用户对每一功能的使用参数,确定向用户推荐的功能。
优选的,在确定向用户推荐的功能的步骤之后还包括:通过多模态反馈的方式向用户推荐所述功能。
优选的,所述多模态反馈的方式包括但不限于语音反馈,在确定向用 户推荐的功能的步骤之后还包括:至少通过语音反馈的方式向用户推荐所述功能。
优选的,所述使用参数包括但不限于该功能在预设时间段内的使用频次或/和使用时长,所述根据用户对每一功能的使用参数,确定向用户推荐的功能的步骤具体包括:
至少选取在预设时间段内达到预设的使用频次或/和使用时长的功能,将该功能向用户进行推荐。
优选的,当在预设时间段内达到预设的使用频次或/和使用时长的功能大于一个时,按照使用频次或/和使用时长由高到低进行推荐。
本发明公开一种基于主动唤醒的功能推荐系统,包括:
获取模块,用于获取用户多模态信息;
匹配模块,用于根据预设的唤醒参数与所述用户多模态信息进行匹配;
唤醒模块,用于若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒;
处理模块,用于根据用户对每一功能的使用参数,确定向用户推荐的功能。
优选的,所述系统还包括推荐模块,用于通过多模态反馈的方式向用户推荐所述功能。
优选的,所述多模态反馈的方式包括但不限于语音反馈,所述推荐模块具体用于:至少通过语音反馈的方式向用户推荐所述功能。
优选的,所述使用参数包括但不限于该功能在预设时间段内的使用频次或/和使用时长,所述处理模块具体用于:至少选取在预设时间段内达到预设的使用频次或/和使用时长的功能,将该功能向用户进行推荐。
优选的,当在预设时间段内达到预设的使用频次或/和使用时长的功能大于一个时,按照使用频次或/和使用时长由高到低进行推荐。
一种机器人,包括如上述任一所述的一种基于主动唤醒的功能推荐系统。
相比现有技术,本发明具有以下优点:本发明的基于主动唤醒的功能推荐方法,包括:获取用户多模态信息;根据预设的唤醒参数与所述用户多模态信息进行匹配;若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒;根据用户对每一功能的使用参数,确定向用户推荐的功能。这样就可以在获取到用户的多模态信息例如用户距离机器人的特定位 置或动作表情时,机器人将多模态信息与唤醒参数进行匹配,若匹配一致则会主动唤醒,之后,机器人就会对功能的使用参数,如用户的使用行为,向用户推荐相应的功能,这样就可以使机器人与人交互时更加拟人化,该方法能够提升机器人交互内容生成的拟人性,提升人机交互体验,提高智能性。
附图说明
图1是本发明实施例一的一种基于主动唤醒的功能推荐方法的流程图;
图2是本发明实施例二的一种基于主动唤醒的功能推荐系统的示意图。
具体实施方式
虽然流程图将各项操作描述成顺序的处理,但是其中的许多操作可以被并行地、并发地或者同时实施。各项操作的顺序可以被重新安排。当其操作完成时处理可以被终止,但是还可以具有未包括在附图中的附加步骤。处理可以对应于方法、函数、规程、子例程、子程序等等。
计算机设备包括用户设备与网络设备。其中,用户设备或客户端包括但不限于电脑、智能手机、PDA等;网络设备包括但不限于单个网络服务器、多个网络服务器组成的服务器组或基于云计算的由大量计算机或网络服务器构成的云。计算机设备可单独运行来实现本发明,也可接入网络并通过与网络中的其他计算机设备的交互操作来实现本发明。计算机设备所处的网络包括但不限于互联网、广域网、城域网、局域网、VPN网络等。
在这里可能使用了术语“第一”、“第二”等等来描述各个单元,但是这些单元不应当受这些术语限制,使用这些术语仅仅是为了将一个单元与另一个单元进行区分。这里所使用的术语“和/或”包括其中一个或更多所列出的相关联项目的任意和所有组合。当一个单元被称为“连接”或“耦合”到另一单元时,其可以直接连接或耦合到所述另一单元,或者可以存在中间单元。
这里所使用的术语仅仅是为了描述具体实施例而不意图限制示例性实施例。除非上下文明确地另有所指,否则这里所使用的单数形式“一个”、“一项”还意图包括复数。还应当理解的是,这里所使用的术语“包括” 和/或“包含”规定所陈述的特征、整数、步骤、操作、单元和/或组件的存在,而不排除存在或添加一个或更多其他特征、整数、步骤、操作、单元、组件和/或其组合。
下面结合附图和较佳的实施例对本发明作进一步说明。
实施例一
如图1所示,本实施例中公开一种基于主动唤醒的功能推荐方法,包括:
S101、获取用户多模态信息;
S102、根据预设的唤醒参数与所述用户多模态信息进行匹配;
S103、若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒;
S104、根据用户对每一功能的使用参数,确定向用户推荐的功能。
本实施例的基于主动唤醒的功能推荐方法,包括:获取用户多模态信息;根据预设的唤醒参数与所述用户多模态信息进行匹配;若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒;根据用户对每一功能的使用参数,确定向用户推荐的功能。这样就可以在获取到用户的多模态信息例如用户距离机器人的特定位置或动作表情时,机器人将多模态信息与唤醒参数进行匹配,若匹配一致则会主动唤醒,之后,机器人就会对功能的使用参数,如用户的使用行为,向用户推荐相应的功能,这样就可以使机器人与人交互时更加拟人化,使得机器人在生活时间轴内具有人类的生活方式,该方法能够提升机器人交互内容生成的拟人性,提升人机交互体验,提高智能性。
本实施例中,发明人研究出一种虚拟机器人的显示设备和成像系统,能够形成3D的动画形象,虚拟机器人的主机接受人类的指令例如语音等与人类进行交互,然后虚拟的3D动画形象会根据主机的指令进行声音和动作的回复,这样就可以让机器人更加拟人化,不仅在声音、表情上能够与人类交互,而且还可以在动作等上与人类交互,大大提高了交互的体验感。
本实施例中的多模态信息可以是用户表情、语音信息、手势信息、场景信息、图像信息、视频信息、人脸信息、瞳孔虹膜信息、光感信息和指纹信息等其中的其中一种或几种。本实施例中优选为用户表情,这样识别的准确并且识别的效率高。
主动唤醒的方式可以将用户多模态信息,例如,用户的动作,用户的 表情等采集后与预设的唤醒参数进行比较,如果达到了预设的唤醒参数,那就将机器人主动唤醒,如果没有达到就不会唤醒。例如在人类靠近机器人之后,机器人的检测模块检测到人类的靠近,就会主动的唤醒自己,从而与人类进行交互。唤醒机器人还可以通过人类作出的表情,动作,或其他具有动态的行为,而如果人类是站立不动、不作出表情和动作,或者躺着不动等静态状态,那么就可以是没有达到预设的唤醒参数,从而不被视为唤醒机器人,机器人检测到这些行为时不会主动唤醒自己。
本实施例中,所述使用参数包括但不限于包括该功能在预设时间段内的使用频次或/和使用时长,所述根据用户对每一功能的使用参数,确定向用户推荐的功能的步骤具体包括:
至少选取在预设时间段内达到预设的使用频次或/和使用时长的功能,将该功能向用户进行推荐。
这样就可以通过筛选出用户常使用的一些功能,并且将这些功能主动推荐给用户。例如,在早上6点到12点的时间段内,预设的使用频次为5次,如果根据之前的统计,用户在这个时间段内使用播放音乐的功能的次数为6次,那么在机器人主动唤醒之后,机器人就会向用户推荐播放音乐的功能,以供用户更快捷的使用该功能。当然也可以预设的使用频次为5次,使用时长为1小时,或只设置预设的使用时长为1小时。当然达到预设条件的功能可能只有一个,也有可能大于一个,那么就可以将所有达到预设条件的功能都推荐。使用参数还可以包括,比如播放习惯,如每天早晨播放音乐等。
本实施例中,当在预设时间段内达到预设的使用频次或/和使用时长的功能大于一个时,按照使用频次或/和使用时长由高到低进行推荐。
这样就可以让达到预设条件的功能进行排序推荐,由高低到底进行排序,方便用户的选择和使用。
根据其中一个示例,在确定向用户推荐的功能的步骤之后还包括:通过多模态反馈的方式向用户推荐所述功能。
这样在确定了需要推荐的功能之后,可以通过多模态反馈,例如语音反馈,视频反馈,语音加动作的反馈等等多种方式向用户推荐功能,方便用户更快更准确的了解到推荐的功能。
根据其中一个示例,所述多模态反馈的方式包括但不限于包括语音反馈,在确定向用户推荐的功能的步骤之后还包括:至少通过语音反馈的方 式向用户推荐所述功能。
这样可以让机器人通过语音的方式向用户推荐功能,让用户更快更准确的了解到该功能。而且在反馈时,可以不仅使用语音反馈,还可以使用其他的如视频反馈,动作反馈等一种或多种方式进行反馈。
实施例二
如图2所示,本实施例公开一种基于主动唤醒的功能推荐系统,包括:
获取模块201,用于获取用户多模态信息;
匹配模块202,用于根据预设的唤醒参数与所述用户多模态信息进行匹配;
唤醒模块203,用于若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒;
处理模块204,用于根据用户对每一功能的使用参数,确定向用户推荐的功能。
这样就可以在获取到用户的多模态信息例如用户距离机器人的特定位置或动作表情时,机器人将多模态信息与唤醒参数进行匹配,若匹配一致则会主动唤醒,之后,机器人就会对功能的使用参数,如用户的使用行为,向用户推荐相应的功能,这样就可以使机器人与人交互时更加拟人化,使得机器人在生活时间轴内具有人类的生活方式,该方法能够提升机器人交互内容生成的拟人性,提升人机交互体验,提高智能性。
本实施例中,发明人研究出一种虚拟机器人的显示设备和成像系统,能够形成3D的动画形象,虚拟机器人的主机接受人类的指令例如语音等与人类进行交互,然后虚拟的3D动画形象会根据主机的指令进行声音和动作的回复,这样就可以让机器人更加拟人化,不仅在声音、表情上能够与人类交互,而且还可以在动作等上与人类交互,大大提高了交互的体验感。
本实施例中的多模态信息可以是用户表情、语音信息、手势信息、场景信息、图像信息、视频信息、人脸信息、瞳孔虹膜信息、光感信息和指纹信息等其中的其中一种或几种。本实施例中优选为用户表情,这样识别的准确并且识别的效率高。
主动唤醒的方式可以将用户多模态信息,例如,用户的动作,用户的表情等采集后与预设的唤醒参数进行比较,如果达到了预设的唤醒参数,那就将机器人主动唤醒,如果没有达到就不会唤醒。例如在人类靠近机器 人之后,机器人的检测模块检测到人类的靠近,就会主动的唤醒自己,从而与人类进行交互。唤醒机器人还可以通过人类作出的表情,动作,或其他具有动态的行为,而如果人类是站立不动、不作出表情和动作,或者躺着不动等静态状态,那么就可以是没有达到预设的唤醒参数,从而不被视为唤醒机器人,机器人检测到这些行为时不会主动唤醒自己。
本实施例中,所述使用参数包括但不限于包括该功能在预设时间段内的使用频次或/和使用时长,所述处理模块具体用于:至少选取在预设时间段内达到预设的使用频次或/和使用时长的功能,将该功能向用户进行推荐。
这样就可以通过筛选出用户常使用的一些功能,并且将这些功能主动推荐给用户。例如,在早上6点到12点的时间段内,预设的使用频次为5次,如果根据之前的统计,用户在这个时间段内使用播放音乐的功能的次数为6次,那么在机器人主动唤醒之后,机器人就会向用户推荐播放音乐的功能,以供用户更快捷的使用该功能。当然也可以预设的使用频次为5次,使用时长为1小时,或只设置预设的使用时长为1小时。当然达到预设条件的功能可能只有一个,也有可能大于一个,那么就可以将所有达到预设条件的功能都推荐。使用参数还可以包括,比如播放习惯,如每天早晨播放音乐等。
本实施例中,当在预设时间段内达到预设的使用频次或/和使用时长的功能大于一个时,按照使用频次或/和使用时长由高到低进行推荐。
这样就可以让达到预设条件的功能进行排序推荐,由高低到底进行排序,方便用户的选择和使用。
根据其中一个示例,所述系统还包括推荐模块205,用于通过多模态反馈的方式向用户推荐所述功能。
这样在确定了需要推荐的功能之后,可以通过多模态反馈,例如语音反馈,视频反馈,语音加动作的反馈等等多种方式向用户推荐功能,方便用户更快更准确的了解到推荐的功能。
根据其中一个示例,所述多模态反馈的方式包括但不限于语音反馈,所述推荐模块具体用于:至少通过语音反馈的方式向用户推荐所述功能。
这样可以让机器人通过语音的方式向用户推荐功能,让用户更快更准确的了解到该功能。而且在反馈时,可以不仅使用语音反馈,还可以使用其他的如视频反馈,动作反馈等一种或多种方式进行反馈。
本实施例公开一种机器人,包括如上述任一所述的一种基于主动唤醒的功能推荐系统。
以上内容是结合具体的优选实施方式对本发明所作的进一步详细说明,不能认定本发明的具体实施只局限于这些说明。对于本发明所属技术领域的普通技术人员来说,在不脱离本发明构思的前提下,还可以做出若干简单推演或替换,都应当视为属于本发明的保护范围。

Claims (11)

  1. 一种基于主动唤醒的功能推荐方法,其特征在于,包括:
    获取用户多模态信息;
    根据预设的唤醒参数与所述用户多模态信息进行匹配;
    若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒;
    根据用户对每一功能的使用参数,确定向用户推荐的功能。
  2. 根据权利要求1所述的推荐方法,其特征在于,在确定向用户推荐的功能的步骤之后还包括:通过多模态反馈的方式向用户推荐所述功能。
  3. 根据权利要求2所述的推荐方法,其特征在于,所述多模态反馈的方式包括但不限于语音反馈,在确定向用户推荐的功能的步骤之后还包括:至少通过语音反馈的方式向用户推荐所述功能。
  4. 根据权利要求1所述的推荐方法,其特征在于,所述使用参数包括但不限于该功能在预设时间段内的使用频次或/和使用时长,所述根据用户对每一功能的使用参数,确定向用户推荐的功能的步骤具体包括:
    至少选取在预设时间段内达到预设的使用频次或/和使用时长的功能,将该功能向用户进行推荐。
  5. 根据权利要求4所述的推荐方法,其特征在于,当在预设时间段内达到预设的使用频次或/和使用时长的功能大于一个时,按照使用频次或/和使用时长由高到低进行推荐。
  6. 一种基于主动唤醒的功能推荐系统,其特征在于,包括:
    获取模块,用于获取用户多模态信息;
    匹配模块,用于根据预设的唤醒参数与所述用户多模态信息进行匹配;
    唤醒模块,用于若用户多模态信息与预设的唤醒参数相匹配,则将机器人主动唤醒;
    处理模块,用于根据用户对每一功能的使用参数,确定向用户推荐的功能。
  7. 根据权利要求6所述的推荐系统,其特征在于,所述系统还包括推荐模块,用于通过多模态反馈的方式向用户推荐所述功能。
  8. 根据权利要求7所述的推荐系统,其特征在于,所述多模态反馈的方式包括但不限于包括语音反馈,所述推荐模块具体用于:至少通过语音反馈的方式向用户推荐所述功能。
  9. 根据权利要求7所述的推荐系统,其特征在于,所述使用参数包括 但不限于该功能在预设时间段内的使用频次或/和使用时长,所述处理模块具体用于:至少选取在预设时间段内达到预设的使用频次或/和使用时长的功能,将该功能向用户进行推荐。
  10. 根据权利要求7所述的推荐系统,其特征在于,当在预设时间段内达到预设的使用频次或/和使用时长的功能大于一个时,按照使用频次或/和使用时长由高到低进行推荐。
  11. 一种机器人,其特征在于,包括如权利要求6至10任一所述的一种基于主动唤醒的功能推荐系统。
PCT/CN2016/089218 2016-07-07 2016-07-07 一种基于主动唤醒的功能推荐方法、系统及机器人 WO2018006374A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2016/089218 WO2018006374A1 (zh) 2016-07-07 2016-07-07 一种基于主动唤醒的功能推荐方法、系统及机器人
CN201680001756.5A CN106462256A (zh) 2016-07-07 2016-07-07 一种基于主动唤醒的功能推荐方法、系统及机器人

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/089218 WO2018006374A1 (zh) 2016-07-07 2016-07-07 一种基于主动唤醒的功能推荐方法、系统及机器人

Publications (1)

Publication Number Publication Date
WO2018006374A1 true WO2018006374A1 (zh) 2018-01-11

Family

ID=58215730

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/089218 WO2018006374A1 (zh) 2016-07-07 2016-07-07 一种基于主动唤醒的功能推荐方法、系统及机器人

Country Status (2)

Country Link
CN (1) CN106462256A (zh)
WO (1) WO2018006374A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018006374A1 (zh) * 2016-07-07 2018-01-11 深圳狗尾草智能科技有限公司 一种基于主动唤醒的功能推荐方法、系统及机器人
CN107340865B (zh) * 2017-06-29 2020-12-11 北京光年无限科技有限公司 多模态虚拟机器人交互方法和系统
CN107977072B (zh) * 2017-07-28 2021-06-08 北京物灵智能科技有限公司 一种机器人使用的养成方法、养成专家系统及电子设备
CN107632706B (zh) * 2017-09-08 2021-01-22 北京光年无限科技有限公司 多模态虚拟人的应用数据处理方法和系统
CN109093631A (zh) * 2018-09-10 2018-12-28 中国科学技术大学 一种服务机器人唤醒方法及装置
CN110502112B (zh) * 2019-08-14 2023-11-14 北京金山安全软件有限公司 智能推荐方法、装置、电子设备和存储介质
CN110647652B (zh) * 2019-09-29 2022-10-28 百度在线网络技术(北京)有限公司 兴趣资源的处理方法、装置、设备和介质
CN110941774A (zh) * 2019-12-05 2020-03-31 深圳前海达闼云端智能科技有限公司 一种服务推荐方法
CN114488879A (zh) * 2021-12-30 2022-05-13 深圳鹏行智能研究有限公司 一种机器人控制方法以及机器人

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101264049B1 (ko) * 2012-03-30 2013-05-21 이성종 이동통신단말장치의 가상 로봇과 동기화되는 애완 로봇
CN103229521A (zh) * 2012-12-26 2013-07-31 华为技术有限公司 远程唤醒方法、装置及系统
CN104795068A (zh) * 2015-04-28 2015-07-22 深圳市锐曼智能装备有限公司 机器人的唤醒控制方法及其控制系统
CN204819530U (zh) * 2015-05-22 2015-12-02 欧阳锡伟 仿生家政服务机器人
CN106462256A (zh) * 2016-07-07 2017-02-22 深圳狗尾草智能科技有限公司 一种基于主动唤醒的功能推荐方法、系统及机器人

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140047273A (ko) * 2012-10-12 2014-04-22 피프가부시끼가이샤 로봇
CN104934033A (zh) * 2015-04-21 2015-09-23 深圳市锐曼智能装备有限公司 机器人的声源定位、唤醒识别的控制方法及其控制系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101264049B1 (ko) * 2012-03-30 2013-05-21 이성종 이동통신단말장치의 가상 로봇과 동기화되는 애완 로봇
CN103229521A (zh) * 2012-12-26 2013-07-31 华为技术有限公司 远程唤醒方法、装置及系统
CN104795068A (zh) * 2015-04-28 2015-07-22 深圳市锐曼智能装备有限公司 机器人的唤醒控制方法及其控制系统
CN204819530U (zh) * 2015-05-22 2015-12-02 欧阳锡伟 仿生家政服务机器人
CN106462256A (zh) * 2016-07-07 2017-02-22 深圳狗尾草智能科技有限公司 一种基于主动唤醒的功能推荐方法、系统及机器人

Also Published As

Publication number Publication date
CN106462256A (zh) 2017-02-22

Similar Documents

Publication Publication Date Title
WO2018006374A1 (zh) 一种基于主动唤醒的功能推荐方法、系统及机器人
US20230386462A1 (en) Reducing the need for manual start/end-pointing and trigger phrases
CN109427333B (zh) 激活语音识别服务的方法和用于实现所述方法的电子装置
US11221669B2 (en) Non-verbal engagement of a virtual assistant
CN107894833B (zh) 基于虚拟人的多模态交互处理方法及系统
CN107632706B (zh) 多模态虚拟人的应用数据处理方法和系统
US8321221B2 (en) Speech communication system and method, and robot apparatus
US11126140B2 (en) Electronic device, external device capable of being combined with the electronic device, and a display method thereof
CN112051743A (zh) 设备控制方法、冲突处理方法、相应的装置及电子设备
US11721333B2 (en) Electronic apparatus and control method thereof
WO2018000268A1 (zh) 一种机器人交互内容的生成方法、系统及机器人
WO2018006370A1 (zh) 一种虚拟3d机器人的交互方法、系统及机器人
WO2018000259A1 (zh) 一种机器人交互内容的生成方法、系统及机器人
CN112292724A (zh) 用于调用自动助理的动态和/或场境特定热词
CN106575504A (zh) 在机器人上执行软件应用
WO2018000267A1 (zh) 一种机器人交互内容的生成方法、系统及机器人
CN109955257A (zh) 一种机器人的唤醒方法、装置、终端设备和存储介质
US20210349433A1 (en) System and method for modifying an initial policy of an input/output device
KR20190105182A (ko) 전자 장치 및 그 제어 방법
WO2018000207A1 (zh) 基于单意图的技能包并行执行管理方法、系统及机器人
WO2018000261A1 (zh) 一种机器人交互内容的生成方法、系统及机器人
WO2018000266A1 (zh) 一种机器人交互内容的生成方法、系统及机器人
WO2018000258A1 (zh) 一种机器人交互内容的生成方法、系统及机器人
WO2018000260A1 (zh) 一种机器人交互内容的生成方法、系统及机器人
CN108388399A (zh) 虚拟偶像的状态管理方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16907879

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16907879

Country of ref document: EP

Kind code of ref document: A1