WO2016183961A1 - 智能设备的界面切换方法、***、设备及非易失性计算机存储介质 - Google Patents

智能设备的界面切换方法、***、设备及非易失性计算机存储介质 Download PDF

Info

Publication number
WO2016183961A1
WO2016183961A1 PCT/CN2015/088516 CN2015088516W WO2016183961A1 WO 2016183961 A1 WO2016183961 A1 WO 2016183961A1 CN 2015088516 W CN2015088516 W CN 2015088516W WO 2016183961 A1 WO2016183961 A1 WO 2016183961A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
emotion
interface
type
voice signal
Prior art date
Application number
PCT/CN2015/088516
Other languages
English (en)
French (fr)
Inventor
赵鹏飞
Original Assignee
百度在线网络技术(北京)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 百度在线网络技术(北京)有限公司 filed Critical 百度在线网络技术(北京)有限公司
Publication of WO2016183961A1 publication Critical patent/WO2016183961A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/63Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state

Definitions

  • the present invention relates to the field of mobile communications technologies, and in particular, to an interface switching method, system, device, and non-volatile computer storage medium for a smart device.
  • the smart device can provide various setting permissions to the user, and the user can set the smart device according to his or her preference or needs.
  • the user can select a candidate interface as the interface of the smart device in the setting menu of the smart device according to his or her preference.
  • the switching mode of this interface depends on the manual operation of the user. If the user does not perform manual switching, the interface update cannot be implemented. Therefore, the interface switching mode of the smart device in the prior art has a relatively high operation cost and a low switching efficiency.
  • the embodiments of the present invention provide an interface switching method, system, device, and non-volatile computer storage medium for an intelligent device, which can implement the boundary of automatically executing the smart device. Face switching to improve interface switching efficiency.
  • An aspect of the embodiments of the present invention provides a method for switching an interface of a smart device, including:
  • the acquiring the emotion type of the user according to the voice signal of the user includes:
  • the type of emotion of the user is determined according to the emotional value of the user.
  • the acquiring the emotion type of the user according to the voice signal of the user includes:
  • the emotion feature information is identified using a speech emotion recognition model to obtain the user's emotion type.
  • any possible implementation manner further provide an implementation manner, where the acquiring a target interface that matches the type of emotion of the user includes:
  • a lookup is made in the correspondence to obtain a target interface that matches the sentiment type.
  • the acquiring the voice signal of the user includes: collecting a voice signal of the user when the user performs voice interaction with the smart device.
  • Another aspect of the embodiments of the present invention provides an interface switching system for a smart device, including:
  • a voice collection unit configured to acquire a voice signal of the user
  • An emotion recognition unit configured to acquire an emotion type of the user according to the voice signal of the user
  • An interface obtaining unit configured to acquire a target interface that matches an emotion type of the user
  • An interface switching unit is configured to switch an interface of the smart device according to the target interface.
  • emotion recognition unit is specifically configured to:
  • the type of emotion of the user is determined according to the emotional value of the user.
  • emotion recognition unit is specifically configured to:
  • the emotion feature information is identified using a speech emotion recognition model to obtain the user's emotion type.
  • a lookup is made in the correspondence to obtain a target interface that matches the sentiment type.
  • the voice collection unit is specifically configured to: collect a voice signal of the user when the user performs voice interaction with the smart device.
  • an apparatus comprising:
  • One or more processors are One or more processors;
  • a memory that stores one or more programs
  • a nonvolatile computer storage medium storing one or more programs when the one or more programs are executed by a device causes The device:
  • the interface switching of the smart device can be automatically performed according to the voice signal of the user.
  • the technical solution provided by the embodiment of the present invention can avoid the reliance on the user to manually switch the interface, reduce the operation cost of the interface switching mode of the smart device, and improve the interface switching efficiency.
  • FIG. 1 is a schematic flowchart of a method for switching an interface of a smart device according to an embodiment of the present invention
  • FIG. 2 is a functional block diagram of an interface switching system of a smart device according to an embodiment of the present invention.
  • the word “if” as used herein may be interpreted as “when” or “when” or “in response to determining” or “in response to detecting.”
  • the phrase “if determined” or “if detected (conditions or events stated)” may be interpreted as “when determined” or “in response to determination” or “when detected (stated condition or event) “Time” or “in response to a test (condition or event stated)”.
  • FIG. 1 it is a schematic flowchart of a method for switching an interface of a smart device according to an embodiment of the present invention. As shown in the figure, the method includes the following steps:
  • S104 Switch an interface of the smart device according to the target interface.
  • the method for acquiring the voice signal of the user in S101 is specifically described in the embodiment of the present invention.
  • This step can be specifically To include:
  • the method for acquiring a voice signal of a user may include, but is not limited to, collecting a voice signal of the user when the user performs voice interaction with the smart device.
  • the smart device has a voice interaction function, and the voice signals input by the user are mostly characterized by short, targeted, and emotional. Therefore, in the embodiment of the present invention, the interface switching of the smart device is implemented according to the voice signal of the user. operating.
  • the smart device may include, but is not limited to, a smart terminal or a wearable smart device.
  • the smart terminal involved in the embodiments of the present invention may include, but is not limited to, a personal computer (PC), a personal digital assistant (PDA), a wireless handheld device, and a tablet computer. , mobile phone.
  • the wearable smart device may include, but is not limited to, a smart watch, a smart bracelet, or smart glasses.
  • the voice signal of the user may be collected by using a voice collection module in the smart device.
  • the voice collection module may include but is not limited to: a microphone.
  • the microphone may include, but is not limited to, a microphone in a smart device or a microphone in a headset connected to the smart device or the like.
  • the headset connected to the smart device may include, but is not limited to, a Bluetooth headset or a wired headset.
  • the method for acquiring the sentiment type of the user according to the voice signal of the user in S102 is specifically described in the embodiment of the present invention.
  • the step may specifically include:
  • the method for acquiring the sentiment type of the user according to the voice signal of the user may include, but is not limited to, the following two types:
  • emotional feature information is extracted from the user's voice signal. Then, the emotion feature information is identified by a classifier to obtain an emotional value of the user. Finally, the type of emotion of the user is determined according to the emotional value of the user.
  • the support vector machine can be used as a classifier to identify the extracted emotion feature information to calculate the emotion value of the user. Then, according to the emotion value of the user, in the correspondence relationship between the emotion value and the emotion type, the emotion type corresponding to the emotion value is acquired as the emotion type of the user.
  • the emotion types may correspond to a range of emotion values, and the emotion type corresponding to the range of emotion values to which the acquired emotion values belong is used as the emotion type of the user.
  • voice samples of several passes may be recorded for each sentence in advance according to each emotion type, and used as training samples to construct a classifier using these training samples.
  • the Markov model can be used as a speech emotion recognition model, and the extracted emotion feature information is used as an input of the speech emotion recognition model, and the speech emotion recognition model acquires the probability of each emotion type according to the sentiment feature information, and The emotion model with the highest probability is taken as the output as the emotion type of the user.
  • the user's emotion type may include, but is not limited to, happy, angry, angry, calm, happy, sad, and surprised.
  • the emotional feature information may include, but is not limited to, a prosodic feature parameter.
  • the prosodic feature parameters may include, but are not limited to, a pitch frequency, an amplitude, a pronunciation duration, a speech rate, and the like.
  • the autocorrelation algorithm may be used to extract the pitch frequency curve of the speech signal, and then the values of the maximum value, the minimum value, and the range of the pitch frequency curve may be extracted as the characterization parameters of the pitch frequency.
  • the amplitude curve can be extracted by an autocorrelation algorithm, and then the average value, standard deviation, maximum value, and minimum value of the amplitude curve are extracted as the characterization parameters of the amplitude.
  • the duration of the pronunciation, the length of the voiced pronunciation, the length of the silent pronunciation, the ratio of the length of the voiced pronunciation to the length of the silent pronunciation can be calculated as the characterization parameters of the duration of the pronunciation.
  • the ratio of the number of words included in the speech signal to the duration of the utterance may be used as the speech rate.
  • the executor of the step S102 may be the smart device, or may be another smart device, or may be a server, which is not specifically limited in this embodiment of the present invention.
  • the execution body of the step S102 is another smart device
  • the execution body of the step S101 ie, the smart device
  • the execution body of the step S101 needs to perform analog-to-digital conversion processing on the collected voice signal of the user to obtain binary waveform data
  • the binary waveform data is sent to other smart devices, and the other smart devices acquire the emotion type of the user according to the voice signal of the user.
  • the other smart device can be a smart phone that communicates with the smart device.
  • the communication manner between the other smart device and the smart device may include, but is not limited to, Bluetooth, infrared or near field communication.
  • the execution body of the step S102 is a server
  • the execution body of the step S101 ie, the smart device
  • the execution body of the step S101 needs to perform analog-to-digital conversion processing on the collected voice signal of the user to obtain binary waveform data.
  • the binary waveform data is sent to other smart devices, and then uploaded to the server by other smart devices through the network, and the server obtains the emotion type of the user according to the voice signal of the user.
  • the execution body of the step S102 is a server
  • the execution body of the step S101 ie, the smart device
  • the method for obtaining the target interface matching the user's sentiment type in S103 is specifically described in the embodiment of the present invention.
  • the step may specifically include:
  • a method for acquiring a target interface that matches an emotion type of the user may include, but is not limited to: first, obtaining a correspondence between an emotion type and an interface. Then, using the emotion type of the user, a lookup is made in the correspondence to obtain a target interface that matches the emotion type.
  • the correspondence between the emotion type and the interface may be configured in advance in the execution body of step S103.
  • Each type of emotion may correspond to at least one interface, and may be searched in the corresponding relationship by using a type of emotion of the user, at least one corresponding to the type of emotion.
  • One of the interfaces is randomly selected as the target interface.
  • the interface between each emotion type can be divided by the color type.
  • a negative emotion type may correspond to a warm tone interface
  • an excited emotion type may correspond to a cool tone interface.
  • step S103 and step S102 may be the same or different. If the execution body of step S102 is the smart device, the execution body of step S103 is the smart device. Alternatively, if the execution body of step S102 is the smart device, the execution body of step S103 is the smart device or the other smart device. Alternatively, if the execution body of step S102 is the other smart device, the execution body of step S103 is the other smart device or the smart device. Alternatively, if the execution subject of step S102 is the server, the execution subject of step S103 is the server or the other smart device or the smart device, which is not specifically limited in the embodiment of the present invention.
  • the method for switching the interface of the smart device according to the target interface in S104 is performed in the embodiment of the present invention, based on the interface switching method of the smart device, the second embodiment, the third embodiment, and the fourth embodiment. specific description.
  • the step may specifically include:
  • the method for switching the interface of the smart device according to the target interface may include, but is not limited to, the smart device calling the operating system provided by the smart device according to the target interface.
  • the interface sets an interface function, so that the interface setting interface function switches the current interface of the smart device to the target interface, so as to implement automatic interface switching of the smart device.
  • Embodiments of the present invention further provide for implementing the steps and methods in the foregoing method embodiments. Embodiments are set.
  • FIG. 2 is a functional block diagram of an interface switching system of a smart device according to an embodiment of the present invention. As shown, the system includes:
  • the voice collection unit 201 is configured to acquire a voice signal of the user.
  • the emotion recognition unit 202 is configured to acquire the emotion type of the user according to the voice signal of the user;
  • An interface obtaining unit 203 configured to acquire a target interface that matches an emotion type of the user
  • the interface switching unit 204 is configured to switch the interface of the smart device according to the target interface.
  • the emotion recognition unit 202 is specifically configured to:
  • the type of emotion of the user is determined according to the emotional value of the user.
  • the emotion recognition unit 202 is specifically configured to:
  • the emotion feature information is identified using a speech emotion recognition model to obtain the user's emotion type.
  • the interface obtaining unit 203 is specifically configured to:
  • a lookup is made in the correspondence to obtain a target interface that matches the sentiment type.
  • the voice collection unit 201 is specifically configured to: collect the voice signal of the user when the user performs voice interaction with the smart device.
  • the voice signal of the user is obtained by acquiring a voice signal of the user according to the voice signal of the user; and further, acquiring a target interface that matches the emotion type of the user, and The target interface switches the interface of the smart device.
  • the interface switching of the smart device can be automatically performed according to the voice signal of the user.
  • the technical solution provided by the embodiment of the present invention can avoid the reliance on the user to manually switch the interface, reduce the operation cost of the interface switching mode of the smart device, and improve the interface switching efficiency. Improve the intelligence of smart devices.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined. Or it can be integrated into another system, or some features can be ignored or not executed.
  • Another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some
  • An indirect coupling or communication connection of an interface, device or unit may be in electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present invention. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Multimedia (AREA)
  • Child & Adolescent Psychology (AREA)
  • General Health & Medical Sciences (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种智能设备的界面切换方法、***、设备及非易失性计算机存储介质。该方法包括获取用户的语音信号(S101);根据所述用户的语音信号,获取所述用户的情感类型(S102);获取与所述用户的情感类型相匹配的目标界面(S103);根据所述目标界面,对智能设备的界面进行切换(S104)。因此,本方法能够自动执行智能设备的界面切换,提高界面切换的效率。

Description

智能设备的界面切换方法、***、设备及非易失性计算机存储介质
相关申请的交叉引用
本申请要求了申请日为2015年05月18日,申请号为201510254489.X发明名称为“一种智能设备的界面切换方法及***”的中国专利申请的优先权。
技术领域
本发明涉及移动通信技术领域,特别涉及一种智能设备的界面切换方法、***、设备及非易失性计算机存储介质。
背景技术
随着科学技术的迅猛发展,出现了多种多样的智能设备,这些智能设备成为人们生活中必不可少电子设备之一。目前,智能设备能够向用户提供各种设置权限,用户可以根据自身喜好或者需求对智能设备进行设置。
例如,用户可以根据自身喜好,在智能设备的设置菜单中选择一个候选界面作为智能设备的界面。然而,这种界面的切换方式需要依赖用户手动操作,如果用户不进行手动切换将无法实现界面更新。因此,现有技术中智能设备的界面切换方式操作成本比较高,切换效率比较低。
发明内容
有鉴于此,本发明实施例提供了一种智能设备的界面切换方法、***、设备及非易失性计算机存储介质,可以实现自动执行智能设备的界 面切换,提高界面切换效率。
本发明实施例的一方面,提供一种智能设备的界面切换方法,包括:
获取用户的语音信号;
根据所述用户的语音信号,获取所述用户的情感类型;
获取与所述用户的情感类型相匹配的目标界面;
根据所述目标界面,对智能设备的界面进行切换。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述用户的语音信号,获取所述用户的情感类型,包括:
从所述用户的语音信号中提取情感特征信息;
利用分类器对所述情感特征信息进行识别,以获得所述用户的情感值;
根据所述用户的情感值,确定所述用户的情感类型。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述用户的语音信号,获取所述用户的情感类型,包括:
从所述用户的语音信号中提取情感特征信息;
利用语音情感识别模型对所述情感特征信息进行识别,以获得所述用户的情感类型。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述获取与所述用户的情感类型相匹配的目标界面,包括:
获得情感类型与界面的对应关系;
利用所述用户的情感类型,在所述对应关系中进行查找,以获得与所述情感类型相匹配的目标界面。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式, 所述获取用户的语音信号,包括:采集所述用户与所述智能设备进行语音交互时所述用户的语音信号。
本发明实施例的另一方面,提供一种智能设备的界面切换***,包括:
语音采集单元,用于获取用户的语音信号;
情感识别单元,用于根据所述用户的语音信号,获取所述用户的情感类型;
界面获取单元,用于获取与所述用户的情感类型相匹配的目标界面;
界面切换单元,用于根据所述目标界面,对智能设备的界面进行切换。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述情感识别单元,具体用于:
从所述用户的语音信号中提取情感特征信息;
利用分类器对所述情感特征信息进行识别,以获得所述用户的情感值;
根据所述用户的情感值,确定所述用户的情感类型。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述情感识别单元,具体用于:
从所述用户的语音信号中提取情感特征信息;
利用语音情感识别模型对所述情感特征信息进行识别,以获得所述用户的情感类型。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述界面获取单元,具体用于:
获得情感类型与界面的对应关系;
利用所述用户的情感类型,在所述对应关系中进行查找,以获得与所述情感类型相匹配的目标界面。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述语音采集单元,具体用于:采集所述用户与所述智能设备进行语音交互时所述用户的语音信号。
本发明的另一方面,提供一种设备,包括:
一个或者多个处理器;
存储器,存储有一个或多个程序;
当所述一个或多个程序被所述一个或者多个处理器执行时,使得所述一个或多个处理器:
获取用户的语音信号;
根据所述用户的语音信号,获取所述用户的情感类型;
获取与所述用户的情感类型相匹配的目标界面;
根据所述目标界面,对智能设备的界面进行切换。
本发明的另一方面,提供一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
获取用户的语音信号;
根据所述用户的语音信号,获取所述用户的情感类型;
获取与所述用户的情感类型相匹配的目标界面;
根据所述目标界面,对智能设备的界面进行切换。
由以上技术方案可以看出,本发明实施例具有以下有益效果:
本发明实施例提供的技术方案中,能够根据用户的语音信号,实现自动执行智能设备的界面切换。与现有技术中,需要用户手动切换界面的方式相比,本发明实施例提供的技术方案可以避免对用户手动切换界面的依赖,降低智能设备的界面切换方式的操作成本,提高界面切换效率。
附图说明
为了更清楚地说明本发明实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其它的附图。
图1是本发明实施例所提供的智能设备的界面切换方法的流程示意图;
图2是本发明实施例所提供的智能设备的界面切换***的功能方块图。
具体实施方式
为了更好的理解本发明的技术方案,下面结合附图对本发明实施例进行详细描述。
应当明确,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其它实施例,都属于本发明保护的范围。
在本发明实施例中使用的术语是仅仅出于描述特定实施例的目的, 而非旨在限制本发明。在本发明实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式,除非上下文清楚地表示其他含义。
应当理解,本文中使用的术语“和/或”仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
取决于语境,如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”或“响应于检测”。类似地,取决于语境,短语“如果确定”或“如果检测(陈述的条件或事件)”可以被解释成为“当确定时”或“响应于确定”或“当检测(陈述的条件或事件)时”或“响应于检测(陈述的条件或事件)”。
实施例一
本发明实施例给出一种智能设备的界面切换方法,请参考图1,其为本发明实施例所提供的智能设备的界面切换方法的流程示意图,如图所示,该方法包括以下步骤:
S101,获取用户的语音信号。
S102,根据所述用户的语音信号,获取所述用户的情感类型。
S103,获取与所述用户的情感类型相匹配的目标界面。
S104,根据所述目标界面,对智能设备的界面进行切换。
实施例二
基于上述实施例一所提供的智能设备的界面切换方法,本发明实施例对S101中获取用户的语音信号的方法进行具体描述。该步骤具体可 以包括:
举例说明,本发明实施例中,获取用户的语音信号的方法可以包括但不限于:采集所述用户与所述智能设备进行语音交互时所述用户的语音信号。
目前,智能设备都具有语音交互功能,而用户输入的语音信号大多具有精短的、目的性和情感性较强的特点,因此本发明实施例中,根据用户的语音信号实现智能设备的界面切换操作。
优选的,本发明实施例中,所述智能设备可以包括但不限于智能终端或者穿戴式智能设备。
需要说明的是,本发明实施例中所涉及的智能终端可以包括但不限于个人计算机(Personal Computer,PC)、个人数字助理(Personal Digital Assistant,PDA)、无线手持设备、平板电脑(Tablet Computer)、手机。
例如,所述穿戴式智能设备可以包括但不限于:智能手表、智能手环或者智能眼镜等。
优选的,当所述用户与所述智能设备进行语音交互时,可以但不限于利用所述智能设备中的语音采集模块采集用户的语音信号。
优选的,所述语音采集模块可以包括但不限于:麦克风。
例如,所述麦克风可以包括但不限于:智能设备中的麦克风或者与智能设备连接的耳机中的麦克风等。
例如,所述与智能设备连接的耳机可以包括但不限于:蓝牙耳机或者有线耳机。
实施例三
基于上述实施例一所提供的智能设备的界面切换方法和实施例一,本发明实施例对S102中根据所述用户的语音信号,获取所述用户的情感类型的方法进行具体描述。该步骤具体可以包括:
举例说明,本发明实施例中,根据所述用户的语音信号,获取所述用户的情感类型的方法可以包括但不限于以下两种:
第一种:首先,从所述用户的语音信号中提取情感特征信息。然后,利用分类器对所述情感特征信息进行识别,以获得所述用户的情感值。最后,根据所述用户的情感值,确定所述用户的情感类型。
优选的,可以利用支持向量机(Support Vector Machine,SVM)作为分类器,对提取出的情感特征信息进行识别,以计算出所述用户的情感值。然后,根据所述用户的情感值,在情感值与情感类型的对应关系中,获取所述情感值对应的情感类型,以作为所述用户的情感类型。其中,每种情感类型可以对应一个情感值范围,将获取的情感值所属的情感值范围对应的情感类型作为所述用户的情感类型。
例如,可以预先根据每种情感类型,对每个语句录制若干遍的语音样本,并作为训练样本,利用这些训练样本构建分类器。
第二种:从所述用户的语音信号中提取情感特征信息。然后,利用语音情感识别模型对所述情感特征信息进行识别,以获得所述用户的情感类型。
优选的,可以利用马尔可夫模型作为语音情感识别模型,将提取出的情感特征信息作为该语音情感识别模型的输入,语音情感识别模型根据该情感特征信息,获取每种情感类型的概率,并将其中概率最高的情感模型作为输出,作为所述用户的情感类型。
优选的,本发明实施例中,所述用户的情感类型可以包括但不限于:高兴、生气、愤怒、平静、高兴、悲伤和惊奇等。
优选的,所述情感特征信息可以包括但不限于韵律特征参数。
例如,所述韵律特征参数可以包括但不限于:基音频率、振幅、发音持续时间和语速等。
例如,可以采用自相关算法提取语音信号的基音频率曲线,然后提取基音频率曲线的最大值、最小值和极差等数值作为基音频率的表征参数。
再例如,可以采用自相关算法提取振幅曲线,然后提取振幅曲线的平均值、标准差、最大值和最小值等作为振幅的表征参数。
再例如,可以计算发音持续时长、有声发音时长、无声发音时长、有声发音时长与无声发音时长的比值等作为发音持续时间的表征参数。
再例如,可以利用语音信号中所含文字个数与发音持续时长的比值作为语速。
需要说明的,步骤S102的执行主体可以为所述智能设备,或者还可以为其他智能设备,或者,也可以为服务器,本发明实施例对此不进行特别限定。
例如,若所述步骤S102的执行主体为其他智能设备,则步骤S101的执行主体(即所述智能设备)需要将采集的用户的语音信号进行模数转换处理,以获得二进制的波形数据,并将该二进制的波形数据发送给其他智能设备,由其他智能设备根据所述用户的语音信号,获取所述用户的情感类型。
例如,所述其他智能设备可以为与所述智能设备通信的智能手机。
优选的,所述其他智能设备与所述智能设备之间的通信方式可以包括但不限于蓝牙、红外或者近场通讯等。
或者,再例如,若所述步骤S102的执行主体为服务器,则步骤S101的执行主体(即所述智能设备)需要将采集的用户的语音信号进行模数转换处理,以获得二进制的波形数据,并将该二进制的波形数据发送给其他智能设备,再由其他智能设备通过网络上传给服务器,由服务器根据所述用户的语音信号,获取所述用户的情感类型。
或者,再例如,若所述步骤S102的执行主体为服务器,则步骤S101的执行主体(即所述智能设备)需要将采集的用户的语音信号进行模数转换处理,以获得二进制的波形数据,并将该二进制的波形数据通过网络上传给服务器,由服务器根据所述用户的语音信号,获取所述用户的情感类型。
实施例四
基于上述实施例一所提供的智能设备的界面切换方法、实施例二和实施例三,本发明实施例对S103中获取与所述用户的情感类型相匹配的目标界面的方法进行具体描述。该步骤具体可以包括:
举例说明,本发明实施例中,获取与所述用户的情感类型相匹配的目标界面的方法可以包括但不限于:首先,获得情感类型与界面的对应关系。然后,利用所述用户的情感类型,在所述对应关系中进行查找,以获得与所述情感类型相匹配的目标界面。
优选的,可以预先在步骤S103的执行主体中配置情感类型与界面的对应关系。其中,每种情感类型可以对应至少一个界面,可以利用用户的情感类型在所述对应关系中进行查找,在该情感类型对应的至少一 个界面中随机选择一个作为所述目标界面。
优选的,每种情感类型之间的界面可以通过颜色类型进行划分。例如,消极的情感类型可以对应暖色调的界面,激动的情感类型可以对应冷色调的界面。
需要说明的是,步骤S103与步骤S102的执行主体可以相同,也可以不同。若步骤S102的执行主体为所述智能设备,步骤S103的执行主体为所述智能设备。或者,若步骤S102的执行主体为所述智能设备,步骤S103的执行主体为所述智能设备或者所述其他智能设备。或者,若步骤S102的执行主体为所述其他智能设备,步骤S103的执行主体为所述其他智能设备或者所述智能设备。或者,若步骤S102的执行主体为所述服务器,步骤S103的执行主体为所述服务器或者所述其他智能设备或者所述智能设备,本发明实施例对此不进行特别限定。
实施例五
基于上述实施例一所提供的智能设备的界面切换方法、实施例二、实施例三和实施例四,本发明实施例对S104中根据所述目标界面,对智能设备的界面进行切换的方法进行具体描述。该步骤具体可以包括:
举例说明,本发明实施例中,根据所述目标界面,对智能设备的界面进行切换的方法可以包括但不限于:所述智能设备根据所述目标界面,调用所述智能设备的操作***提供的界面设置接口函数,以使得所述界面设置接口函数将所述智能设备当前的界面切换为所述目标界面,以实现智能设备的界面自动切换。
实施例六
本发明实施例进一步给出实现上述方法实施例中各步骤及方法的装 置实施例。
请参考图2,其为本发明实施例所提供的智能设备的界面切换***的功能方块图。如图所示,该***包括:
语音采集单元201,用于获取用户的语音信号;
情感识别单元202,用于根据所述用户的语音信号,获取所述用户的情感类型;
界面获取单元203,用于获取与所述用户的情感类型相匹配的目标界面;
界面切换单元204,用于根据所述目标界面,对智能设备的界面进行切换。
优选的,所述情感识别单元202,具体用于:
从所述用户的语音信号中提取情感特征信息;
利用分类器对所述情感特征信息进行识别,以获得所述用户的情感值;
根据所述用户的情感值,确定所述用户的情感类型。
优选的,所述情感识别单元202,具体用于:
从所述用户的语音信号中提取情感特征信息;
利用语音情感识别模型对所述情感特征信息进行识别,以获得所述用户的情感类型。
优选的,所述界面获取单元203,具体用于:
获得情感类型与界面的对应关系;
利用所述用户的情感类型,在所述对应关系中进行查找,以获得与所述情感类型相匹配的目标界面。
优选的,所述语音采集单元201,具体用于:采集所述用户与所述智能设备进行语音交互时所述用户的语音信号。
由于本实施例中的各单元能够执行图1所示的方法,本实施例未详细描述的部分,可参考对图1的相关说明。
本发明实施例的技术方案具有以下有益效果:
本发明实施例中,通过获取用户的语音信号;从而,根据所述用户的语音信号,获取所述用户的情感类型;进而,获取与所述用户的情感类型相匹配的目标界面,以及根据所述目标界面,对智能设备的界面进行切换。
本发明实施例提供的技术方案中,能够根据用户的语音信号,实现自动执行智能设备的界面切换。与现有技术中,需要用户手动切换界面的方式相比,本发明实施例提供的技术方案可以避免对用户手动切换界面的依赖,降低智能设备的界面切换方式的操作成本,提高界面切换效率,提高智能设备的智能化程度。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的***,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本发明所提供的几个实施例中,应该理解到,所揭露的***,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如,多个单元或组件可以结合或者可以集成到另一个***,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些 接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元,可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中,包括若干指令用以使得一台计算机装置(可以是个人计算机,服务器,或者网络装置等)或处理器(Processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内,所做的任何修改、等同替换、改进等,均应包含在本发明保护的范围之内。

Claims (12)

  1. 一种智能设备的界面切换方法,其特征在于,所述方法包括:
    获取用户的语音信号;
    根据所述用户的语音信号,获取所述用户的情感类型;
    获取与所述用户的情感类型相匹配的目标界面;
    根据所述目标界面,对智能设备的界面进行切换。
  2. 根据权利要求1所述的方法,其特征在于,所述根据所述用户的语音信号,获取所述用户的情感类型,包括:
    从所述用户的语音信号中提取情感特征信息;
    利用分类器对所述情感特征信息进行识别,以获得所述用户的情感值;
    根据所述用户的情感值,确定所述用户的情感类型。
  3. 根据权利要求1所述的方法,其特征在于,所述根据所述用户的语音信号,获取所述用户的情感类型,包括:
    从所述用户的语音信号中提取情感特征信息;
    利用语音情感识别模型对所述情感特征信息进行识别,以获得所述用户的情感类型。
  4. 根据权利要求1至3中任一项所述的方法,其特征在于,所述获取与所述用户的情感类型相匹配的目标界面,包括:
    获得情感类型与界面的对应关系;
    利用所述用户的情感类型,在所述对应关系中进行查找,以获得与所述情感类型相匹配的目标界面。
  5. 根据权利要求1至3中任一项所述的方法,其特征在于,所述 获取用户的语音信号,包括:采集所述用户与所述智能设备进行语音交互时所述用户的语音信号。
  6. 一种智能设备的界面切换***,其特征在于,所述***包括:
    语音采集单元,用于获取用户的语音信号;
    情感识别单元,用于根据所述用户的语音信号,获取所述用户的情感类型;
    界面获取单元,用于获取与所述用户的情感类型相匹配的目标界面;
    界面切换单元,用于根据所述目标界面,对智能设备的界面进行切换。
  7. 根据权利要求6所述的***,其特征在于,所述情感识别单元,具体用于:
    从所述用户的语音信号中提取情感特征信息;
    利用分类器对所述情感特征信息进行识别,以获得所述用户的情感值;
    根据所述用户的情感值,确定所述用户的情感类型。
  8. 根据权利要求6所述的***,其特征在于,所述情感识别单元,具体用于:
    从所述用户的语音信号中提取情感特征信息;
    利用语音情感识别模型对所述情感特征信息进行识别,以获得所述用户的情感类型。
  9. 根据权利要求6至8中任一项所述的***,其特征在于,所述界面获取单元,具体用于:
    获得情感类型与界面的对应关系;
    利用所述用户的情感类型,在所述对应关系中进行查找,以获得与所述情感类型相匹配的目标界面。
  10. 根据权利要求6至8中任一项所述的***,其特征在于,所述语音采集单元,具体用于:采集所述用户与所述智能设备进行语音交互时所述用户的语音信号。
  11. 一种设备,包括:
    一个或者多个处理器;
    存储器,存储有一个或多个程序;
    当所述一个或多个程序被所述一个或者多个处理器执行时,使得所述一个或多个处理器:
    获取用户的语音信号;
    根据所述用户的语音信号,获取所述用户的情感类型;
    获取与所述用户的情感类型相匹配的目标界面;
    根据所述目标界面,对智能设备的界面进行切换。
  12. 一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
    获取用户的语音信号;
    根据所述用户的语音信号,获取所述用户的情感类型;
    获取与所述用户的情感类型相匹配的目标界面;
    根据所述目标界面,对智能设备的界面进行切换。
PCT/CN2015/088516 2015-05-18 2015-08-31 智能设备的界面切换方法、***、设备及非易失性计算机存储介质 WO2016183961A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510254489.XA CN104992715A (zh) 2015-05-18 2015-05-18 一种智能设备的界面切换方法及***
CN201510254489.X 2015-05-18

Publications (1)

Publication Number Publication Date
WO2016183961A1 true WO2016183961A1 (zh) 2016-11-24

Family

ID=54304518

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/088516 WO2016183961A1 (zh) 2015-05-18 2015-08-31 智能设备的界面切换方法、***、设备及非易失性计算机存储介质

Country Status (2)

Country Link
CN (1) CN104992715A (zh)
WO (1) WO2016183961A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105739688A (zh) * 2016-01-21 2016-07-06 北京光年无限科技有限公司 一种基于情感体系的人机交互方法、装置和交互***
WO2018023516A1 (zh) * 2016-08-04 2018-02-08 易晓阳 一种语音交互识别控制方法
CN108877794A (zh) * 2018-06-04 2018-11-23 百度在线网络技术(北京)有限公司 用于人机交互的方法、装置、电子设备和计算机可读存储介质
CN109215679A (zh) 2018-08-06 2019-01-15 百度在线网络技术(北京)有限公司 基于用户情绪的对话方法和装置
CN109587347A (zh) * 2019-01-28 2019-04-05 珠海格力电器股份有限公司 显示屏参数的调整方法、装置和***,移动终端
CN112435735B (zh) * 2020-12-01 2024-07-05 重庆金山医疗技术研究院有限公司 一种切换方法、装置、设备和介质及***
CN113593532B (zh) * 2021-08-31 2024-06-18 竹间智能科技(上海)有限公司 语音情绪识别模型训练方法及电子设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1581149A (zh) * 2004-03-25 2005-02-16 东南大学 运用人的情绪和情绪变化信息构建人机界面的方法
CN102479024A (zh) * 2010-11-24 2012-05-30 国基电子(上海)有限公司 手持装置及其用户界面构建方法
CN103126690A (zh) * 2013-01-28 2013-06-05 周万荣 一种基于应用的人体情绪识别及控制方法及设备和***
CN103634472A (zh) * 2013-12-06 2014-03-12 惠州Tcl移动通信有限公司 根据通话语音判断用户心情及性格的方法、***及手机
US20140114655A1 (en) * 2012-10-19 2014-04-24 Sony Computer Entertainment Inc. Emotion recognition using auditory attention cues extracted from users voice
US20140257820A1 (en) * 2013-03-10 2014-09-11 Nice-Systems Ltd Method and apparatus for real time emotion detection in audio interactions
CN104464756A (zh) * 2014-12-10 2015-03-25 黑龙江真美广播通讯器材有限公司 一种小型说话人情感识别***

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101201980B (zh) * 2007-12-19 2010-06-02 北京交通大学 一种基于语音情感识别的远程汉语教学***
US9196248B2 (en) * 2013-02-13 2015-11-24 Bayerische Motoren Werke Aktiengesellschaft Voice-interfaced in-vehicle assistance
CN103544963B (zh) * 2013-11-07 2016-09-07 东南大学 一种基于核半监督判别分析的语音情感识别方法
CN103905644A (zh) * 2014-03-27 2014-07-02 郑明� 移动终端通话界面的生成方法及设备
CN104091602A (zh) * 2014-07-11 2014-10-08 电子科技大学 一种基于模糊支持向量机的语音情感识别方法
CN104200814B (zh) * 2014-08-15 2017-07-21 浙江大学 基于语义细胞的语音情感识别方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1581149A (zh) * 2004-03-25 2005-02-16 东南大学 运用人的情绪和情绪变化信息构建人机界面的方法
CN102479024A (zh) * 2010-11-24 2012-05-30 国基电子(上海)有限公司 手持装置及其用户界面构建方法
US20140114655A1 (en) * 2012-10-19 2014-04-24 Sony Computer Entertainment Inc. Emotion recognition using auditory attention cues extracted from users voice
CN103126690A (zh) * 2013-01-28 2013-06-05 周万荣 一种基于应用的人体情绪识别及控制方法及设备和***
US20140257820A1 (en) * 2013-03-10 2014-09-11 Nice-Systems Ltd Method and apparatus for real time emotion detection in audio interactions
CN103634472A (zh) * 2013-12-06 2014-03-12 惠州Tcl移动通信有限公司 根据通话语音判断用户心情及性格的方法、***及手机
CN104464756A (zh) * 2014-12-10 2015-03-25 黑龙江真美广播通讯器材有限公司 一种小型说话人情感识别***

Also Published As

Publication number Publication date
CN104992715A (zh) 2015-10-21

Similar Documents

Publication Publication Date Title
WO2016183961A1 (zh) 智能设备的界面切换方法、***、设备及非易失性计算机存储介质
CN109447234B (zh) 一种模型训练方法、合成说话表情的方法和相关装置
CN112074900B (zh) 用于自然语言处理的音频分析
US10270736B2 (en) Account adding method, terminal, server, and computer storage medium
WO2018121275A1 (zh) 一种智能硬件设备中的语音识别纠错方法和装置
CN110634483A (zh) 人机交互方法、装置、电子设备及存储介质
KR102628211B1 (ko) 전자 장치 및 그 제어 방법
WO2019096056A1 (zh) 语音识别方法、装置及***
WO2021008538A1 (zh) 语音交互方法及相关装置
CN110097875B (zh) 基于麦克风信号的语音交互唤醒电子设备、方法和介质
CN110428806B (zh) 基于麦克风信号的语音交互唤醒电子设备、方法和介质
CN111583944A (zh) 变声方法及装置
CN110223711B (zh) 基于麦克风信号的语音交互唤醒电子设备、方法和介质
CN110570840B (zh) 一种基于人工智能的智能设备唤醒方法和装置
JP6585733B2 (ja) 情報処理装置
US11657800B2 (en) Electronic device with wakeup word determined multi-mode operation
US20150310878A1 (en) Method and apparatus for determining emotion information from user voice
CN111105796A (zh) 无线耳机控制装置及控制方法、语音控制设置方法和***
KR20160106075A (ko) 오디오 스트림에서 음악 작품을 식별하기 위한 방법 및 디바이스
WO2020244411A1 (zh) 基于麦克风信号的语音交互唤醒电子设备、方法和介质
WO2014180402A1 (zh) 通讯录的设置方法及装置
CN110910876A (zh) 物品声寻装置及控制方法、语音控制设置方法和***
CN111522592A (zh) 一种基于人工智能的智能终端唤醒方法和装置
CN115148185A (zh) 语音合成方法及装置、电子设备及存储介质
CN112262432A (zh) 语音处理装置、语音处理方法以及记录介质

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: 15892339

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: 15892339

Country of ref document: EP

Kind code of ref document: A1