CN105204357A

CN105204357A - Contextual model regulating method and device for intelligent household equipment

Info

Publication number: CN105204357A
Application number: CN201510601126.9A
Authority: CN
Inventors: 傅强; 王阳; 侯恩星
Original assignee: Xiaomi Inc
Current assignee: Beijing Xiaomi Technology Co Ltd; Xiaomi Inc
Priority date: 2015-09-18
Filing date: 2015-09-18
Publication date: 2015-12-30
Anticipated expiration: 2035-09-18
Also published as: CN105204357B

Abstract

The invention discloses a contextual model regulating method and device for intelligent household equipment. The method comprises the steps that audio information is acquired; if the fact that the audio information is determined to meet a triggering condition for performing model regulation is responded, the contextual model of the intelligent household equipment is regulated to a target contextual model corresponding to the audio information. According to the contextual model regulating method and device for the intelligent household equipment, the contextual model of the intelligent household equipment can be automatically regulated according to the audio information, manual control of a user is not needed, the contextual model regulation efficiency is improved, and convenience is brought to the user.

Description

The contextual model method of adjustment of intelligent home device and device

Technical field

The disclosure relates to communication technical field, particularly relates to contextual model method of adjustment and the device of intelligent home device.

Background technology

Along with the development of science and technology and the universal of internet, there is the various intelligent home device being convenient to people's daily life, for intelligent electric lamp, electric light can be shown with different contextual models by regulating the parameter such as color, colour temperature, brightness of intelligent electric lamp.But in correlation technique, user need select the contextual model of intelligent electric lamp by telepilot, realize the adjustment to intelligent electric lamp contextual model, regulated efficiency is low, poor user experience.

Summary of the invention

Present disclose provides contextual model method of adjustment and the device of intelligent home device, lower with the contextual model regulated efficiency solved in correlation technique, the problem that Consumer's Experience is poor.

According to the first aspect of disclosure embodiment, provide a kind of contextual model method of adjustment of intelligent home device, described method comprises:

Obtain audio-frequency information;

In response to determining that described audio-frequency information meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device is adjusted to the target context pattern that described audio-frequency information is corresponding.

Optionally, described in response to determining that described audio-frequency information meets the trigger condition of carrying out mode adjustment, comprising:

In response to target audio feature and the predetermined audio characteristic matching of determining described audio-frequency information.

Optionally, described target audio feature and predetermined audio characteristic matching in response to determining described audio-frequency information, comprising:

Similarity value in response to the target voice content and predetermined voice content of determining described audio-frequency information is more than or equal to similarity threshold.

In response to determining that the target voice intensity of described audio-frequency information is in default voice strength range.

In response to determining that the type of described audio-frequency information is predetermined voice type, described predetermined voice type at least comprises: music type.

Optionally, described in response to determining that the target audio feature of described audio-frequency information conforms to predetermined audio feature, comprising:

In response to determining that the acquisition time of described audio-frequency information is within the schedule time.

Optionally, before the described contextual model by intelligent home device adjusts to target context pattern corresponding to described audio-frequency information, described method also comprises:

Voice intensity is extracted from described audio-frequency information;

In response to determining that described voice intensity is more than or equal to described voice intensity threshold, the target audio feature of described audio-frequency information is mated with predetermined audio feature.

Optionally, the described contextual model by intelligent home device adjusts to target context pattern corresponding to described audio-frequency information, comprising:

Obtain the mode adjustment instruction that described audio-frequency information is corresponding;

Described mode adjustment instruction is sent to described intelligent home device, according to described mode adjustment instruction, contextual model is adjusted to described target context pattern to make described intelligent home device.

Optionally, described intelligent home device comprises intelligent electric lamp, described contextual model comprise audio-visual pattern, reading model, pattern of receiving a visitor, party pattern, dining pattern, the late into the night pattern, sleep pattern, dazzle in color pattern, soft pattern one or more.

According to the second aspect of disclosure embodiment, provide a kind of contextual model adjusting gear of intelligent home device, described device comprises:

Audio-frequency information acquiring unit, is configured to obtain audio-frequency information;

Contextual model adjustment unit, is configured to, when the described audio-frequency information that described audio-frequency information acquiring unit obtains meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device be adjusted to the target context pattern that described audio-frequency information is corresponding.

Optionally, described contextual model adjustment unit comprises:

Determine subelement, be configured to, when the target audio feature of the described audio-frequency information that described audio-frequency information acquiring unit obtains and predetermined audio characteristic matching, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment.

Optionally, describedly determine that subelement comprises:

First determination module, be configured to the target voice content of described audio-frequency information when described audio-frequency information acquiring unit obtains and the Similarity value of predetermined voice content when being more than or equal to similarity threshold, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment.

Optionally, describedly determine that subelement comprises:

Second determination module, is configured to, when the target voice intensity of the described audio-frequency information that described audio-frequency information acquiring unit obtains is in default voice strength range, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment.

Optionally, describedly determine that subelement comprises:

3rd determination module, be configured to when the type of the described audio-frequency information that described audio-frequency information acquiring unit obtains is predetermined voice type, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment, described predetermined voice type at least comprises: music type.

Optionally, describedly determine that subelement comprises:

4th determination module, is configured to, when the acquisition time of the described audio-frequency information that described audio-frequency information acquiring unit obtains is within the schedule time, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment.

Optionally, described device also comprises:

Voice intensity extraction unit, is configured to extract voice intensity the described audio-frequency information obtained from described audio-frequency information acquiring unit;

Audio feature extraction unit, is configured to, when the described voice intensity that described voice intensity extraction unit extracts is more than or equal to described voice intensity threshold, the target audio feature of described audio-frequency information be mated with predetermined audio feature.

Optionally, described contextual model adjustment unit comprises:

Instruction obtains subelement, is configured to obtain the mode adjustment instruction that the described audio-frequency information of described audio-frequency information acquiring unit acquisition is corresponding;

Contextual model adjustment subelement, the described mode adjustment instruction being configured to described instruction to obtain subelement acquisition is sent to described intelligent home device, according to described mode adjustment instruction, contextual model is adjusted to described target context pattern to make described intelligent home device.

According to the third aspect of disclosure embodiment, a kind of contextual model adjusting gear of intelligent home device is provided, comprises:

Processor;

For the storer of storage of processor executable instruction;

Wherein, described processor is configured to:

Obtain audio-frequency information;

The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect:

The disclosure is by obtaining audio-frequency information, when determining that audio-frequency information meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device is adjusted to the target context pattern that audio-frequency information is corresponding, realize the contextual model automatically adjusting intelligent home device according to audio-frequency information, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

The mode that the disclosure utilizes the target audio feature of audio-frequency information and predetermined audio feature to carry out mating judges whether audio-frequency information meets the trigger condition of carrying out mode adjustment, thus can judge whether trigger condition meets accurately, and then the contextual model of intelligent home device is automatically adjusted according to audio-frequency information, improve contextual model regulated efficiency.

The disclosure is by mating the target voice content in audio-frequency information with predetermined voice content, when Similarity value is more than or equal to similarity threshold, determine that audio-frequency information meets the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to voice content, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

The disclosure is when determining that the target voice intensity of audio-frequency information is in default voice strength range, judge to meet the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to voice intensity, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

The disclosure is when the type determining audio-frequency information is predetermined voice type, judge to meet the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to audio types, improve contextual model regulated efficiency, particularly when audio types is music type, automatically the intelligent home device of association is adjusted to the contextual model of applicable music, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

When the disclosure is by determining that the acquisition time of audio-frequency information is within the schedule time, judge to meet the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to acquisition time, improve contextual model regulated efficiency, bring facility to user.

Before the disclosure extracts target audio feature from audio-frequency information, voice intensity in audio-frequency information can also be judged, when voice intensity reaches voice intensity threshold, just from audio-frequency information, extract target audio feature, to determine whether user wants to carry out contextual model adjustment by voice to intelligent home device, avoids the situation of erroneous judgement.

The disclosure may be used in terminal, audio-frequency information is obtained by terminal, when audio-frequency information meets the trigger condition of carrying out mode adjustment, obtain the mode adjustment instruction that audio-frequency information is corresponding, mode adjustment instruction is sent to the intelligent home device with terminal association, according to mode adjustment instruction, contextual model is adjusted to described target context pattern to make intelligent home device.The disclosure can gather audio-frequency information by sound collector intrinsic in terminal, avoid arranging at intelligent home device the wasting of resources that sound collector causes, and because the distance of terminal distance users is generally near than the distance of intelligent home device distance users, radio reception is effective, thus improves judgment accuracy.

Intelligent home device in the disclosure can be intelligent electric lamp, automatically can be adjusted, improve the regulated efficiency of intelligent electric lamp contextual model, bring facility to user by the contextual model of the disclosure to intelligent electric lamp.

Should be understood that, it is only exemplary and explanatory that above general description and details hereinafter describe, and can not limit the disclosure.

Accompanying drawing explanation

Accompanying drawing to be herein merged in instructions and to form the part of this instructions, shows and meets embodiment of the present disclosure, and is used from instructions one and explains principle of the present disclosure.

Figure 1A is the process flow diagram of the contextual model method of adjustment of a kind of intelligent home device of the disclosure according to an exemplary embodiment.

Figure 1B is the application scenarios schematic diagram of the contextual model method of adjustment of a kind of intelligent home device of the disclosure according to an exemplary embodiment.

Fig. 2 to 5 is process flow diagrams of the contextual model method of adjustment of the another kind of intelligent home device of the disclosure according to an exemplary embodiment.

Fig. 6 is the block diagram of the contextual model adjusting gear of a kind of intelligent home device of the disclosure according to an exemplary embodiment.

Fig. 7 to 13 is block diagrams of the contextual model adjusting gear of the another kind of intelligent home device of the disclosure according to an exemplary embodiment.

Figure 14 is a structural representation of the contextual model adjusting gear of a kind of intelligent home device of the disclosure according to an exemplary embodiment.

Embodiment

Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the disclosure.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present disclosure are consistent.

The term used in the disclosure is only for the object describing specific embodiment, and the not intended to be limiting disclosure." one ", " described " and " being somebody's turn to do " of the singulative used in disclosure and the accompanying claims book is also intended to comprise most form, unless context clearly represents other implications.It is also understood that term "and/or" used herein refer to and comprise one or more project of listing be associated any or all may combine.

Term first, second, third, etc. may be adopted although should be appreciated that to describe various information in the disclosure, these information should not be limited to these terms.These terms are only used for the information of same type to be distinguished from each other out.Such as, when not departing from disclosure scope, the first information also can be called as the second information, and similarly, the second information also can be called as the first information.Depend on linguistic context, word as used in this " if " can be construed as into " ... time " or " when ... time " or " in response to determining ".

Disclosure method may be used in intelligent home device, when determining that audio-frequency information meets the trigger condition of carrying out mode adjustment, triggering and carrying out contextual model adjustment.The method also may be used in terminal, when determining that audio-frequency information meets the trigger condition of carrying out mode adjustment, determine the mode adjustment instruction that audio-frequency information is corresponding, mode adjustment instruction is sent to and intelligent home device, according to mode adjustment instruction, contextual model is adjusted to target context pattern to make intelligent home device.Wherein, intelligent home device can be the home equipment associated with terminal (actuating station of this method).It is that example is described that the disclosure is mainly applied to terminal in method.

As shown in Figure 1A, Figure 1A is the process flow diagram of the contextual model method of adjustment of a kind of intelligent home device according to an exemplary embodiment, and the method may be used for, in terminal, comprising the following steps:

In a step 101, audio-frequency information is obtained.

The terminal related in disclosure embodiment is the smart machine with wireless network access function, such as, and the portable terminals such as smart mobile phone, panel computer, Intelligent bracelet, PDA (PersonalDigitalAssistant, personal digital assistant).

Terminal can have the function gathering audio-frequency information, directly gathers audio-frequency information; Terminal also can set up wireless connections with the audio collecting device associated in advance, from audio collecting device, obtain audio-frequency information.Wherein, audio collecting device can after setting up unlimited connection with terminal, and the audio information transmissions that will implement to gather is to terminal, or audio collecting device gathers current audio-frequency information after receiving terminal request, and by audio information transmissions to terminal.

In a step 102, in response to determining that audio-frequency information meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device is adjusted to the target context pattern that audio-frequency information is corresponding.

In disclosure embodiment, trigger condition triggers the condition of carrying out mode adjustment, the trigger condition of carrying out mode adjustment can preset according to the feature of audio-frequency information, such as, the trigger condition of carrying out mode adjustment can be the target audio feature and predetermined audio characteristic matching etc. of audio-frequency information, further, the trigger condition of carrying out mode adjustment comprises one or more conditions following: can be that in audio-frequency information, target voice content meets coupling requirement; Also can be that in audio-frequency information, voice intensity meets coupling requirement; Can also be that the acquisition time of audio-frequency information reaches coupling and requires etc., reach after coupling requires at audio-frequency information and judge that it meets the trigger condition of carrying out mode adjustment.

As wherein a kind of embodiment, can judge whether audio-frequency information meets the trigger condition of carrying out mode adjustment, when audio-frequency information meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device is adjusted to the target context pattern that audio-frequency information is corresponding.In this embodiment, terminal can set up wireless connections with the intelligent home device associated in advance, then when audio-frequency information meets the trigger condition of carrying out mode adjustment, determine the mode adjustment instruction that audio-frequency information is corresponding, mode adjustment instruction is sent to intelligent home device, according to mode adjustment instruction, contextual model is adjusted to target context pattern to make intelligent home device.

Wherein, audio-frequency information can be phonetic order, then directly carry out contextual model adjustment to intelligent home device according to the phonetic order identified.Audio-frequency information may not be phonetic order, but specific audio-frequency information, the corresponding relation of audio-frequency information and mode adjustment instruction (target context pattern) can be set up in advance, when audio-frequency information meets the trigger condition of carrying out mode adjustment, determine the mode adjustment instruction that audio-frequency information is corresponding, according to mode adjustment instruction, contextual model adjustment is carried out to intelligent home device.

Wherein, contextual model also can be called scene mode, and contextual model is a whole set of answer-mode selected according to different sight.Intelligent home device can be the home equipment with wireless network access function and contextual model regulatory function, and such as, intelligent home device can be intelligent electric lamp, intelligent television, intelligent air condition, intelligent refrigerator etc.The intelligent home device related in the disclosure can be a home equipment, also can be the multiple home equipments linked according to different sight.The disclosure is mainly described for intelligent electric lamp.Intelligent home device comprises multiple different contextual model, and in often kind of contextual model, the controling parameters of intelligent home device is different.

For intelligent electric lamp, intelligent electric lamp can comprise fluorescent light, shot-light, Down lamp, pendent lamp etc., electric light can be shown with different contextual models by regulating the controling parameters such as color, colour temperature, brightness of intelligent electric lamp., namely in different contextual model, the controling parameters such as color, colour temperature, brightness of intelligent electric lamp is different.

The contextual model of intelligent electric lamp can comprise audio-visual pattern, reading model, pattern of receiving a visitor, party pattern, dining pattern, the late into the night pattern, sleep pattern, dazzle color pattern, soft pattern etc.Each pattern predefines corresponding lamp light mode, and such as, audio-visual pattern is the audio-visual lamp light mode of predefined applicable broadcasting; Reading model is the lamp light mode of predefined applicable reading; Party pattern is the lamp light mode of predefined applicable party; The pattern of receiving a visitor is the predefined lamp light mode being applicable to receiving a visitor; Dining pattern is the lamp light mode of predefined applicable dining; The late into the night, pattern was the lamp light mode of getting up the predefined applicable late into the night; Sleep pattern is the lamp light mode of predefined applicable sleep; Dazzling color pattern and can be called KTV pattern again, is lamp light mode during predefined applicable singing; Soft pattern is the pattern that light is softer.

For pattern in the late into the night, when user gets up toilet from the state of sleeping soundly, the unlatching in order to avoid electric light makes user sober up, and affects follow-up sleep, needs, by disclosure method, sleep pattern current for intelligent electric lamp is adjusted to pattern in the late into the night.Sleep pattern can be that all electric lights are in closed condition, and the late into the night, pattern can be set as slowly lighting electric light, and electric light brightness is 50% of normal brightness, or less.

As seen from the above-described embodiment, when determining that audio-frequency information meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device is adjusted to the target context pattern that audio-frequency information is corresponding, realize the contextual model automatically adjusting intelligent home device according to audio-frequency information, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

Shown in Figure 1B, Figure 1B is the application scenarios schematic diagram of the contextual model method of adjustment of a kind of intelligent home device of the disclosure according to an exemplary embodiment.In this application scenarios, comprise smart mobile phone 110 and intelligent electric lamp 120, smart mobile phone and intelligent electric lamp can carry out radio communication by WiFi or bluetooth, the audio-frequency information around mobile phone is gathered by the sound transducer in mobile phone, and judge whether audio-frequency information meets the trigger condition of carrying out mode adjustment, when meeting trigger condition, mode adjustment instruction corresponding for audio-frequency information is sent to intelligent electric lamp, according to mode adjustment instruction, contextual model is adjusted to target context pattern to make intelligent electric lamp.

As shown in Figure 2, Fig. 2 is the process flow diagram of the contextual model method of adjustment of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, comprises the following steps:

In step 201, audio-frequency information is obtained.

In step 202., the Similarity value in response to the target voice content and predetermined voice content of determining audio-frequency information is more than or equal to similarity threshold, the contextual model of intelligent home device is adjusted to the target context pattern that target voice content is corresponding.

In disclosure embodiment, target audio feature can be target voice content.By identifying that the mode of concrete sound content judges whether audio-frequency information meets the trigger condition of mode adjustment, when target voice content and predetermined voice content similarity are higher, judge target voice content and predetermined voice content matching, namely meet trigger condition, can contextual model adjustment be carried out.

Voice content identification mentioned by the disclosure can adopt template matches strategy, primary voice data is trained, obtain sample voice eigenvector storehouse, target voice eigenvector is compared with the sample voice eigenvector in sample voice eigenvector storehouse respectively, realizes the identification to target voice eigenvector.Further, carrying out in voice content identifying, target voice eigenvector can extracted from audio-frequency information.Target voice eigenvector is compared with multiple sample voice eigenvector respectively, obtains multiple Similarity value.Wherein, the eigenvector in predetermined voice content is sample voice eigenvector.Judge in multiple Similarity value, whether highest similarity value is more than or equal to similarity threshold.When highest similarity is greater than similarity threshold, judge target voice content and predetermined voice content matching.

Wherein, the method for speech recognition can be based on the alone word voice identification of dynamic time warpping pattern, based on Hidden Markov Model (HMM) speech recognition etc.It should be noted that, by speech recognition algorithm, target voice eigenvector is carried out identifying and see the speech recognition process in correlation technique, no longer can be repeated this disclosure embodiment.

Further, can carry out pre-service to obtained audio-frequency information, pretreated object filters the information irrelevant with speech recognition, retains important information, thus be conducive to extracting target voice eigenvector.Pre-service can comprise the digitizing of voice messaging, anti aliasing distortion filtering, pre-emphasis, framing windowing and end-point detection etc.After audio-frequency information completes sub-frame processing and end-point detection, target voice eigenvector can be extracted, thus improve the accuracy of extracting target voice eigenvector.

Wherein in a kind of implementation, target voice content can be phonetic order, then trained by the speech characteristic vector of each raw tone instruction, obtains sample voice eigenvector storehouse.When highest similarity value is more than or equal to similarity threshold in Similarity value, obtains the phonetic order that highest similarity value is corresponding, and then according to phonetic order, contextual model adjustment is carried out to intelligent home device.For intelligent electric lamp, mode adjustment instruction can be audio-visual pattern, reading model, pattern of receiving a visitor, party pattern, dining pattern, the late into the night pattern, sleep pattern, dazzle color pattern, soft pattern etc.Such as, when user thinks viewing film, can control by the voice of " audio-visual pattern " switching that intelligent electric lamp carries out audio-visual pattern, realize intelligent electric lamp and enter audio-visual pattern.

In another kind of implementation, target voice content also can be the predetermined voice content of non-phonetic order, namely has the voice content of certain sense.In implementation procedure, can specified speech content in advance, and set up the corresponding relation of predetermined voice Pattern and content adjustment instruction.When in Similarity value, highest similarity value is more than or equal to similarity threshold, determine the predetermined voice content that highest similarity value is corresponding, and the corresponding relation of instruction is adjusted according to predetermined voice Pattern and content, determine the mode adjustment instruction that highest similarity value is corresponding.Such as, various original sob is trained, obtain sample voice eigenvector storehouse.In advance by the soft Model Establishment corresponding relation of sob and intelligent electric lamp, then, when sob being detected and sob meets the demands, be soft pattern by the mode adjustment of intelligent electric lamp.

In addition, because the sound of each user is different, can according to alternative sounds identification different user, then predetermined voice content can also be the voice that validated user is prerecorded, then can the speech parameter of pre-stored different user in sample voice eigenvector storehouse, and set up the speech parameter of each user and the corresponding relation of mode adjustment instruction.Each user at least can store a speech parameter, and different phonetic parameter corresponding model identical can adjust instruction, also can corresponding different mode adjustment instruction.After extracting target voice eigenvector, the speech parameter of multiple user in target voice eigenvector and sample voice eigenvector storehouse can be compared, obtain Similarity value, when in Similarity value, highest similarity value is more than or equal to similarity threshold, the speech parameter corresponding according to highest similarity value determines user, and the mode adjustment instruction that user is corresponding can be determined, according to mode adjustment instruction, contextual model adjustment is carried out to intelligent home device.Visible, this embodiment can identify the voice signal that specific user sends, thus distinguishes different user, and performs mode adjustment instruction corresponding to this user.

In addition, if when highest similarity value is less than similarity threshold in Similarity value, the voice message of phonetic entry mistake can be carried out, also target voice eigenvector can be labeled as stranger's voice, and these stranger's voice can be carried out record, so that other validated users are inquired about.

As seen from the above-described embodiment, terminal is by mating the target voice content in audio-frequency information with predetermined voice content, when Similarity value is greater than similarity threshold, determine that audio-frequency information meets the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to voice content, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

In an optional implementation, before the contextual model of intelligent home device being adjusted to target context pattern corresponding to audio-frequency information, described method also comprises: from audio-frequency information, extract voice intensity; In response to determining that voice intensity is more than or equal to voice intensity threshold, the target audio feature of audio-frequency information is mated with predetermined audio feature.

In the present embodiment, voice intensity in audio-frequency information can be judged, voice intensity reach the target audio feature of audio-frequency information is carried out the trigger condition of mating with predetermined audio feature time, just the target audio feature of audio-frequency information is mated with predetermined audio feature, to determine whether user wants to carry out contextual model adjustment by voice to intelligent home device, avoids the situation of erroneous judgement.Wherein, voice intensity can be voice decibel.

On the one hand, voice intensity can be extracted from audio-frequency information; Voice intensity and voice intensity threshold are compared; When voice intensity is more than or equal to voice intensity threshold, determine that voice intensity reaches the trigger condition of the target audio feature of audio-frequency information and predetermined audio feature being carried out mating.When voice intensity is less than the first decibel threshold, determines that voice intensity does not reach the trigger condition of the target audio feature of audio-frequency information and predetermined audio feature being carried out mating, namely no longer carry out coupling step, avoid the wasting of resources.

On the other hand, first can also determine the mean intensity of the sound be currently received, when voice intensity exceedes the setting multiple of mean intensity (such as, voice intensity exceedes 1.5 times of mean intensity) time, determine the trigger condition of the target audio feature of audio-frequency information and predetermined audio feature being carried out mating.When voice intensity does not exceed the setting multiple of mean intensity, determine that voice intensity does not reach the trigger condition of the target audio feature of audio-frequency information and predetermined audio feature being carried out mating.

As shown in Figure 3, Fig. 3 is the process flow diagram of the contextual model method of adjustment of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, comprises the following steps:

In step 301, audio-frequency information is obtained.

In step 302, in response to determining that the target voice intensity of audio-frequency information is in default voice strength range, adjusts to the target context pattern that audio-frequency information is corresponding by the contextual model of intelligent home device.

Disclosure embodiment can extract target voice intensity from audio-frequency information, and target voice intensity can be the voice decibel in audio-frequency information.Judge that the target voice intensity extracted is whether in default voice strength range, when target voice intensity is in default voice strength range, judge that audio-frequency information meets the trigger condition of carrying out mode adjustment, then the contextual model of intelligent home device can be adjusted to target context pattern corresponding to default voice strength range.

Wherein, presetting voice strength range can be a upper range, also can be a lower range, and such as, presetting voice strength range can be the strength range being greater than the first voice intensity threshold, also can be the strength range being less than the second voice intensity threshold.

Wherein, the incidence relation of default voice strength range and target context pattern or mode adjustment instruction can be set up in advance, when the target voice intensity of audio-frequency information is in default voice strength range, can determine according to incidence relation the target context pattern that default voice strength range is corresponding.

Illustrate, when child crys, voice intensity is general larger, therefore default voice strength range can be set to the strength range being greater than the first voice intensity threshold, wherein, first voice intensity threshold is the standard judging whether to exist sob, when target voice intensity is greater than the first voice intensity threshold (when target voice intensity is in default voice strength range), assert in current environment to there is sob, then intelligent electric lamp can be adjusted to soft pattern, in addition, all right coordinated signals curtain closedown etc.

In addition, when target voice intensity is not in default voice strength range, judge that audio-frequency information does not reach the trigger condition of mode adjustment, then can be set as that flow process terminates, also can be set as proceeding the judgement to audio-frequency information in other embodiments, such as, can judge whether the target voice content of audio-frequency information and the Similarity value of predetermined voice content are more than or equal to similarity threshold, thus determine whether the trigger condition reaching mode adjustment.

Known, in the present embodiment from the voice intensity in previous embodiment, the judgement of target voice intensity is judged that object is different.The object that voice intensity and voice intensity threshold compare is that the present embodiment object is to determine whether voice intensity reaches the trigger condition of mode adjustment in order to determine whether voice intensity reaches the trigger condition of the target audio feature of audio-frequency information and predetermined audio feature being carried out mating by previous embodiment.

As seen from the above-described embodiment, when determining that the target voice intensity of audio-frequency information is in default voice strength range, judge to meet the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to voice intensity, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

As shown in Figure 4, Fig. 4 is the process flow diagram of the contextual model method of adjustment of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, comprises the following steps:

In step 401, audio-frequency information is obtained.

In step 402, in response to determining that the type of audio-frequency information is predetermined voice type, the contextual model of intelligent home device is adjusted to the target context pattern that audio-frequency information is corresponding, predetermined voice type at least comprises: music type.

Disclosure embodiment can identify the type of audio-frequency information, and determines whether predetermined voice type according to recognition result.Predetermined voice type can be music type, audio-visual type etc.The disclosure is mainly described for music type.

Disclosure embodiment can set up the incidence relation of music type and target context pattern (being namely applicable to the contextual model of music) in advance.When getting audio-frequency information, audio-frequency information being identified, judging whether it is music.Such as can by judging whether that there is the music information such as song or accompaniment judges whether the type of audio-frequency information is music type, when being defined as music type, then can determine the target context pattern that music type is corresponding, thus the contextual model of intelligent home device is adjusted to target context pattern.

Illustrate, when detect in current environmental sound there is song or melody time, then the contextual model of intelligent electric lamp can be switched to and dazzle color pattern, linkage closes curtain, starts microphone etc.

Wherein in a kind of optional implementation, concrete musical features can also be identified, such as, identify the music style of audio-frequency information, then determine corresponding target context pattern according to different music styles.

Wherein, music recognition can use technical Analysis and the pre-service music signal such as pre-emphasis, framing, windowing of speech signal analysis, also needs for the several principal characters of music signal in musicology: pitch, value, volume, rhythm etc. carry out analyzing and extracting simultaneously.In music recognition, music partitioning algorithm, pitch extraction algorithm, mode extraction algorithm, musical sound recognizer etc. can be adopted.It should be noted that, by Music Recognition Algorithm, music is carried out identifying and see the music recognition process in correlation technique, no longer can be repeated this disclosure embodiment.

In addition, when the type of audio-frequency information is not predetermined voice type, judge that audio-frequency information does not reach the trigger condition of mode adjustment, then can be set as that flow process terminates, also can be set as proceeding the judgement to audio-frequency information in other embodiments, such as, can judge whether the target voice content of audio-frequency information and the Similarity value of predetermined voice content are more than or equal to similarity threshold, thus determine whether the trigger condition reaching mode adjustment.

As seen from the above-described embodiment, when the type determining audio-frequency information is predetermined voice type, judge to meet the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to audio types, improve contextual model regulated efficiency, particularly when audio types is music type, automatically the intelligent home device of association is adjusted to the contextual model of applicable music, without the need to user's Non-follow control, improve contextual model regulated efficiency, facility is brought to user.

As shown in Figure 5, Fig. 5 is the process flow diagram of the contextual model method of adjustment of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, comprises the following steps:

In step 501, audio-frequency information is obtained.

In step 502, in response to determining that the acquisition time of audio-frequency information is within the schedule time, the contextual model of intelligent home device is adjusted to the target context pattern that audio-frequency information is corresponding.

Disclosure embodiment, by judging the acquisition time of audio-frequency information, when acquisition time is in preset time range, is determined the mode adjustment instruction that this preset time range is corresponding, is carried out contextual model adjustment according to mode adjustment instruction to intelligent home device.Such as, preset time range is set to 00:00 to 6:00, when collecting audio-frequency information within this time period, then the contextual model of intelligent electric lamp is adjusted to pattern in the late into the night, intelligent electric lamp is slowly lighted, and electric light brightness is 50% of normal brightness, avoid thoroughly waking user up, improve Consumer's Experience.

Wherein in a kind of optional implementation, after judging that the acquisition time of audio-frequency information is in preset time range, can also judge whether audio-frequency information is the audio-frequency information gathered first in this preset time period, if, then determine the mode adjustment instruction that this preset time range is corresponding, and according to mode adjustment instruction, contextual model adjustment is carried out to intelligent home device.Such as, preset time range is set to 6:00 to 8:00, when collecting audio-frequency information first in this preset time range, then the contextual model of intelligent electric lamp is switched to Chaoyang pattern, and can open by coordinated signals curtain.And for example, preset time period is set to 23:00 to 24:00, when collecting audio-frequency information first in this preset time range, then the contextual model of intelligent electric lamp is switched to sunset pattern, and linkage controls curtain closedown.

In addition, when acquisition time is not in preset time range, judge that audio-frequency information does not reach the trigger condition of mode adjustment, then can be set as that flow process terminates, also can be set as proceeding the judgement to audio-frequency information in other embodiments, such as, can judge whether the target voice content of audio-frequency information and the Similarity value of predetermined voice content are more than or equal to similarity threshold, thus determine whether the trigger condition reaching mode adjustment; Or whether the type judging audio-frequency information is predetermined voice type, thus determine whether the trigger condition etc. reaching mode adjustment.

As seen from the above-described embodiment, by the judgement of the acquisition time to audio-frequency information, thus determine whether the trigger condition meeting mode adjustment, and adjust instruction according to the incidence relation deterministic model of preset time period and mode adjustment instruction, thus according to mode adjustment instruction, contextual model adjustment is carried out to intelligent home device, realize the contextual model of adjustment intelligent home device automatically, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

Corresponding with the embodiment of the contextual model method of adjustment of aforementioned intelligent home equipment, the contextual model adjusting gear that the disclosure additionally provides intelligent home device and the embodiment of terminal applied thereof.

As shown in Figure 6, Fig. 6 is the contextual model adjusting gear block diagram of a kind of intelligent home device of the disclosure according to an exemplary embodiment, and described device comprises: audio-frequency information acquiring unit 610 and contextual model adjustment unit 620.

Wherein, audio-frequency information acquiring unit 610, is configured to obtain audio-frequency information.

Contextual model adjustment unit 620, is configured to, when the described audio-frequency information that described audio-frequency information acquiring unit obtains meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device be adjusted to the target context pattern that described audio-frequency information is corresponding.

As seen from the above-described embodiment, by obtaining audio-frequency information, when determining that audio-frequency information meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device is adjusted to the target context pattern that audio-frequency information is corresponding, realize the contextual model automatically adjusting intelligent home device according to audio-frequency information, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

As shown in Figure 7, Fig. 7 is the contextual model adjusting gear block diagram of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, this embodiment is on aforementioned basis embodiment illustrated in fig. 6, and described contextual model adjustment unit 620 comprises: determine subelement 621.

Wherein, determine subelement 621, be configured to, when the target audio feature of the described audio-frequency information that described audio-frequency information acquiring unit obtains and predetermined audio characteristic matching, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment.

Should be understood that, determine that subelement 621 is one of them subelement in contextual model adjustment unit 620, contextual model adjustment unit 620 can also comprise other subelements, such as, adjustment subelement can also be comprised, be configured to, when determining that subelement determination audio-frequency information meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device be adjusted to the target context pattern that described audio-frequency information is corresponding.

As seen from the above-described embodiment, the mode utilizing the target audio feature of audio-frequency information and predetermined audio feature to carry out mating judges whether audio-frequency information meets the trigger condition of carrying out mode adjustment, thus can judge whether trigger condition meets accurately, and then the contextual model of intelligent home device is automatically adjusted according to audio-frequency information, improve contextual model regulated efficiency.

As shown in Figure 8, Fig. 8 is the contextual model adjusting gear block diagram of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, this embodiment, on aforementioned basis embodiment illustrated in fig. 7, describedly determines that subelement 621 comprises: the first determination module 6211.

Wherein, first determination module 6211, be configured to the target voice content of described audio-frequency information when described audio-frequency information acquiring unit obtains and the Similarity value of predetermined voice content when being more than or equal to similarity threshold, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment.

As seen from the above-described embodiment, by the target voice content in audio-frequency information is mated with predetermined voice content, when Similarity value is more than or equal to similarity threshold, determine that audio-frequency information meets the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to voice content, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

As shown in Figure 9, Fig. 9 is the contextual model adjusting gear block diagram of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, this embodiment, on aforementioned basis embodiment illustrated in fig. 7, describedly determines that subelement 621 comprises: the second determination module 6212.

Wherein, the second determination module 6212, is configured to, when the target voice intensity of the described audio-frequency information that described audio-frequency information acquiring unit obtains is in default voice strength range, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment.

When determining that the target voice intensity of audio-frequency information is in default voice strength range, judge to meet the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to voice intensity, without the need to user's Non-follow control, improve contextual model regulated efficiency, bring facility to user.

As shown in Figure 10, Figure 10 is the contextual model adjusting gear block diagram of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, this embodiment, on aforementioned basis embodiment illustrated in fig. 7, describedly determines that subelement 621 comprises: the 3rd determination module 6213.

Wherein, 3rd determination module 6213, be configured to when the type of the described audio-frequency information that described audio-frequency information acquiring unit obtains is predetermined voice type, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment, described predetermined voice type at least comprises: music type.

As shown in figure 11, Figure 11 is the contextual model adjusting gear block diagram of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, this embodiment, on aforementioned basis embodiment illustrated in fig. 7, describedly determines that subelement 621 comprises: the 4th determination module 6214.

Wherein, the 4th determination module 6214, is configured to, when the acquisition time of the described audio-frequency information that described audio-frequency information acquiring unit obtains is within the schedule time, determine that described audio-frequency information meets the trigger condition of carrying out mode adjustment.

As seen from the above-described embodiment, during by determining that the acquisition time of audio-frequency information is within the schedule time, judge to meet the trigger condition of carrying out mode adjustment, and the contextual model of intelligent home device is adjusted to target context pattern corresponding to audio-frequency information, realize the contextual model automatically adjusting intelligent home device according to acquisition time, improve contextual model regulated efficiency, bring facility to user.

As shown in figure 12, Figure 12 is the contextual model adjusting gear block diagram of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, this embodiment is on aforementioned basis embodiment illustrated in fig. 7, and described device also comprises: voice intensity extraction unit 630 and audio feature extraction unit 640.

Wherein, voice intensity extraction unit 630, is configured to extract voice intensity the described audio-frequency information obtained from described audio-frequency information acquiring unit.

Audio feature extraction unit 640, is configured to, when the described voice intensity that described voice intensity extraction unit extracts is more than or equal to described voice intensity threshold, the target audio feature of described audio-frequency information be mated with predetermined audio feature.

As seen from the above-described embodiment, extract target audio feature from audio-frequency information before, voice intensity in audio-frequency information can also be judged, when voice intensity reaches voice intensity threshold, just from audio-frequency information, extract target audio feature, to determine whether user wants to carry out contextual model adjustment by voice to intelligent home device, avoids the situation of erroneous judgement.

As shown in figure 13, Figure 13 is the contextual model adjusting gear block diagram of the another kind of intelligent home device of the disclosure according to an exemplary embodiment, this embodiment is on aforementioned basis embodiment illustrated in fig. 6, and described contextual model adjustment unit 620 comprises: instruction obtains subelement 622 and contextual model adjustment subelement 623.

Wherein, instruction obtains subelement 622, is configured to obtain the mode adjustment instruction that the described audio-frequency information of described audio-frequency information acquiring unit acquisition is corresponding.

Contextual model adjustment subelement 623, the described mode adjustment instruction being configured to described instruction to obtain subelement acquisition is sent to described intelligent home device, according to described mode adjustment instruction, contextual model is adjusted to described target context pattern to make described intelligent home device.

As seen from the above-described embodiment, audio-frequency information is obtained by terminal, when audio-frequency information meets the trigger condition of carrying out mode adjustment, obtain the mode adjustment instruction that audio-frequency information is corresponding, mode adjustment instruction is sent to the intelligent home device with terminal association, according to mode adjustment instruction, contextual model is adjusted to described target context pattern to make intelligent home device.The disclosure can gather audio-frequency information by sound collector intrinsic in terminal, avoid arranging at intelligent home device the wasting of resources that sound collector causes, and because the distance of terminal distance users is generally near than the distance of intelligent home device distance users, radio reception is effective, thus improves judgment accuracy.

In an optional implementation, described intelligent home device is intelligent electric lamp, described contextual model comprise audio-visual pattern, reading model, pattern of receiving a visitor, party pattern, dining pattern, the late into the night pattern, sleep pattern, dazzle in color pattern, soft pattern one or more.

As seen from the above-described embodiment, the intelligent home device in the disclosure can be intelligent electric lamp, automatically can be controlled, improve the regulated efficiency of intelligent electric lamp contextual model, bring facility to user by the contextual model of the disclosure to intelligent electric lamp.

Accordingly, the disclosure also provides the contextual model adjusting gear of another kind of intelligent home device, and described device comprises: processor; For the storer of storage of processor executable instruction; Wherein, described processor is configured to:

Obtain audio-frequency information;

In said apparatus, the implementation procedure of the function and efficacy of unit specifically refers to the implementation procedure of corresponding step in said method, does not repeat them here.

For device embodiment, because it corresponds essentially to embodiment of the method, so relevant part illustrates see the part of embodiment of the method.Device embodiment described above is only schematic, the wherein said unit illustrated as separating component or can may not be and physically separates, parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of module wherein can be selected according to the actual needs to realize the object of disclosure scheme.Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.

As shown in figure 14, Figure 14 is a structural representation of a kind of contextual model adjusting gear 1400 for intelligent home device of the disclosure according to an exemplary embodiment.Such as, device 1400 can be the mobile phone with routing function, computing machine, digital broadcast terminal, messaging devices, game console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc.

With reference to Figure 14, device 1400 can comprise following one or more assembly: processing components 1402, storer 1404, power supply module 1406, multimedia groupware 1408, audio-frequency assembly 1410, the interface 1412 of I/O (I/O), sensor module 1414, and communications component 1416.

The integrated operation of the usual control device 1400 of processing components 1402, such as with display, call, data communication, camera operation and record operate the operation be associated.Processing components 1402 can comprise one or more processor 1420 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 1402 can comprise one or more module, and what be convenient between processing components 1402 and other assemblies is mutual.Such as, processing components 1402 can comprise multi-media module, mutual with what facilitate between multimedia groupware 1408 and processing components 1402.

Storer 1404 is configured to store various types of data to be supported in the operation of device 1400.The example of these data comprises for any application program of operation on device 1400 or the instruction of method, contact data, telephone book data, message, picture, video etc.Storer 1404 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), ROM (read-only memory) (ROM), magnetic store, flash memory, disk or CD.

The various assemblies that power supply module 1406 is device 1400 provide electric power.Power supply module 1406 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for device 1400 and be associated.

Multimedia groupware 1408 is included in the screen providing an output interface between described device 1400 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 1408 comprises a front-facing camera and/or post-positioned pick-up head.When device 1400 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.

Audio-frequency assembly 1410 is configured to export and/or input audio signal.Such as, audio-frequency assembly 1410 comprises a microphone (MIC), and when device 1400 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal received can be stored in storer 1404 further or be sent via communications component 1416.In certain embodiments, audio-frequency assembly 1410 also comprises a loudspeaker, for output audio signal.

I/O interface 1412 is for providing interface between processing components 1402 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.

Sensor module 1414 comprises one or more sensor, for providing the state estimation of various aspects for device 1400.Such as, sensor module 1414 can detect the opening/closing state of device 1400, the relative positioning of assembly, such as described assembly is display and the keypad of device 1400, the position of all right pick-up unit 1400 of sensor module 1414 or device 1400 assemblies changes, the presence or absence that user contacts with device 1400, the temperature variation of device 1400 orientation or acceleration/deceleration and device 1400.Sensor module 1414 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 1414 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor module 1414 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer, microwave remote sensor or temperature sensor.

Communications component 1416 is configured to the communication being convenient to wired or wireless mode between device 1400 and other equipment.Device 1400 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communications component 1416 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communications component 1416 also comprises near-field communication (NFC) module, to promote junction service.Such as, can based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.

In the exemplary embodiment, device 1400 can be realized, for performing said method by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD) (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.

In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the storer 1404 of instruction, above-mentioned instruction can perform said method by the processor 1420 of device 1400.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.

A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is performed by the processor of terminal, make terminal can perform a kind of contextual model method of adjustment of intelligent home device, described method comprises: obtain audio-frequency information; In response to determining that described audio-frequency information meets the trigger condition of carrying out mode adjustment, the contextual model of intelligent home device is adjusted to the target context pattern that described audio-frequency information is corresponding.

Those skilled in the art, at consideration instructions and after putting into practice invention disclosed herein, will easily expect other embodiment of the present disclosure.The disclosure is intended to contain any modification of the present disclosure, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present disclosure and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present disclosure and spirit are pointed out by claim below.

Should be understood that, the disclosure is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.The scope of the present disclosure is only limited by appended claim.

Claims

1. a contextual model method of adjustment for intelligent home device, is characterized in that, described method comprises:

Obtain audio-frequency information;

2. method according to claim 1, is characterized in that, described in response to determining that described audio-frequency information meets the trigger condition of carrying out mode adjustment, comprising:

3. method according to claim 2, is characterized in that, described target audio feature and predetermined audio characteristic matching in response to determining described audio-frequency information, comprising:

4. method according to claim 2, is characterized in that, described target audio feature and predetermined audio characteristic matching in response to determining described audio-frequency information, comprising:

5. method according to claim 2, is characterized in that, described target audio feature and predetermined audio characteristic matching in response to determining described audio-frequency information, comprising:

6. method according to claim 2, is characterized in that, described in response to determining that the target audio feature of described audio-frequency information conforms to predetermined audio feature, comprising:

7. method according to claim 2, is characterized in that, before the described contextual model by intelligent home device adjusts to target context pattern corresponding to described audio-frequency information, described method also comprises:

Voice intensity is extracted from described audio-frequency information;

8. method according to claim 1, is characterized in that, the described contextual model by intelligent home device adjusts to target context pattern corresponding to described audio-frequency information, comprising:

9. according to described method arbitrary in claim 1 to 8, it is characterized in that, described intelligent home device comprises intelligent electric lamp, described contextual model comprise audio-visual pattern, reading model, pattern of receiving a visitor, party pattern, dining pattern, the late into the night pattern, sleep pattern, dazzle in color pattern, soft pattern one or more.

10. a contextual model adjusting gear for intelligent home device, is characterized in that, described device comprises:

11. devices according to claim 10, is characterized in that, described contextual model adjustment unit comprises:

12. devices according to claim 11, is characterized in that, describedly determine that subelement comprises:

13. devices according to claim 11, is characterized in that, describedly determine that subelement comprises:

14. devices according to claim 11, is characterized in that, describedly determine that subelement comprises:

15. devices according to claim 11, is characterized in that, describedly determine that subelement comprises:

16. devices according to claim 11, is characterized in that, described device also comprises:

17. devices according to claim 10, is characterized in that, described contextual model adjustment unit comprises:

18. according to claim 10 to described device arbitrary in 17, it is characterized in that, described intelligent home device comprises intelligent electric lamp, described contextual model comprise audio-visual pattern, reading model, pattern of receiving a visitor, party pattern, dining pattern, the late into the night pattern, sleep pattern, dazzle in color pattern, soft pattern one or more.

The contextual model adjusting gear of 19. 1 kinds of intelligent home devices, is characterized in that, comprising:

Processor;

For the storer of storage of processor executable instruction;

Wherein, described processor is configured to:

Obtain audio-frequency information;