CN108989551A - Position indicating method, device, storage medium and electronic equipment - Google Patents
Position indicating method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN108989551A CN108989551A CN201810682024.8A CN201810682024A CN108989551A CN 108989551 A CN108989551 A CN 108989551A CN 201810682024 A CN201810682024 A CN 201810682024A CN 108989551 A CN108989551 A CN 108989551A
- Authority
- CN
- China
- Prior art keywords
- electronic equipment
- realtime graphic
- position indicating
- voice signal
- signal
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 230000001755 vocal effect Effects 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 description 55
- 238000004422 calculation algorithm Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 15
- 230000005611 electricity Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000004040 coloring Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72457—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to geographic location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/74—Details of telephonic subscriber devices with voice recognition means
Landscapes
- Engineering & Computer Science (AREA)
- Environmental & Geological Engineering (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
- Telephone Function (AREA)
Abstract
The embodiment of the present application discloses a kind of position indicating method, device, storage medium and electronic equipment, wherein can detect and currently whether change in location occur, if then obtaining the realtime graphic of current location.Object identification is carried out to the realtime graphic got, obtains object information.Acquire the voice signal in external environment, and obtain that voice signal includes it is instructions to be performed.It is instructions to be performed for prompt for trigger position instruction when, according to object information generation position indicating information, and the output position prompt information in a manner of voice.The application can be when user can not find electronic equipment, according to the object information of object at present position, position indicating is carried out to user, user can be helped to recall the last position for using electronic equipment out, to which preferably guidance user finds electronic equipment, the probability that electronic equipment is found is improved.
Description
Technical field
This application involves technical field of electronic equipment, and in particular to a kind of position indicating method, device, storage medium and electricity
Sub- equipment.
Background technique
Currently, with the development of technology, it is man-machine between interactive mode become more and more abundant.In the related technology, user
The electronic equipments such as mobile phone, tablet computer can be controlled by voice, i.e., electronic equipment is in the language for receiving user's sending
After sound signal, corresponding operation can be executed according to the voice signal.For example, electronics is set when user can not find electronic equipment
Standby to carry out position indicating in a manner of jingle bell according to the voice signal of user, guidance user finds electronic equipment, still, and
It is not all with can accomplish that sound is listened to distinguish position per family.
Summary of the invention
The embodiment of the present application provides a kind of position indicating method, device, storage medium and electronic equipment, can be improved electricity
The probability that sub- equipment is found.
In a first aspect, the embodiment of the present application provides a kind of position indicating method, which includes:
Whether detecting currently occurs change in location, if then obtaining the realtime graphic of current location;
Object identification is carried out to the realtime graphic, obtains object information;
Acquire the voice signal in external environment, and obtain that the voice signal includes it is instructions to be performed;
If the instruction instructions to be performed to be prompted for trigger position, position is generated according to the object information and is mentioned
Show information, and exports the position indicating information in a manner of voice.
Second aspect, the embodiment of the present application provide a kind of position prompt device, which includes:
Whether image collection module currently occurs change in location for detecting, if then obtaining the real-time figure of current location
Picture;
Object identification module obtains object information for carrying out object identification to the realtime graphic;
Instruction acquisition module, for acquiring the voice signal in external environment, and obtain that the voice signal includes to
It executes instruction;
Position indicating module, for it is described it is instructions to be performed for prompt for trigger position instruction when, according to described
Object information generates position indicating information, and the position indicating information is exported in a manner of voice.
The third aspect, the embodiment of the present application provide a kind of storage medium, are stored thereon with computer program, when the meter
When calculation machine program is run on computers, so that the computer is executed as in position indicating method provided by the embodiments of the present application
The step of.
Fourth aspect, the embodiment of the present application provide a kind of electronic equipment, including processor and memory, the memory
There is computer program, the processor is by calling the computer program, for executing such as position provided by the embodiments of the present application
Set the step in reminding method.
Electronic equipment in the embodiment of the present application can be detected and currently whether change in location occur, if then obtaining current
The realtime graphic of position.Object identification is carried out to the realtime graphic got, obtains object information.Acquire the language in external environment
Sound signal, and obtain that voice signal includes it is instructions to be performed.It is instructions to be performed for prompt for trigger position instruction when,
Position indicating information, and the output position prompt information in a manner of voice are generated according to object information.The application can be in user
When can not find electronic equipment, according to the object information of object at present position, position indicating, Neng Goubang are carried out to user
It helps user to recall the last position for using electronic equipment out and so that preferably guidance user finds electronic equipment improves electricity
The probability that sub- equipment is found.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a flow diagram of position indicating method provided by the embodiments of the present application.
Fig. 2 is a schematic diagram of electronic equipment position in the embodiment of the present application.
Fig. 3 is the schematic diagram of electronic equipment output position prompt information in the embodiment of the present application.
Fig. 4 is another flow diagram of position indicating method provided by the embodiments of the present application.
Fig. 5 is another schematic diagram of electronic equipment position in the embodiment of the present application.
Fig. 6 is a structural schematic diagram of position prompt device provided by the embodiments of the present application.
Fig. 7 is a structural schematic diagram of electronic equipment provided by the embodiments of the present application.
Fig. 8 is another structural schematic diagram of electronic equipment provided by the embodiments of the present application.
Specific embodiment
Schema is please referred to, wherein identical component symbol represents identical component, the principle of the application is to implement one
It is illustrated in computing environment appropriate.The following description be based on illustrated by the application specific embodiment, should not be by
It is considered as limitation the application other specific embodiments not detailed herein.
In the following description, the specific embodiment of the application will refer to the step as performed by one or multi-section computer
And symbol illustrates, unless otherwise stating clearly.Therefore, these steps and operation will have to mention for several times is executed by computer, this paper institute
The computer execution of finger includes by representing with the computer processing unit of the electronic signal of the data in a structuring pattern
Operation.This operation is converted at the data or the position being maintained in the memory system of the computer, reconfigurable
Or in addition change the running of the computer in mode known to the tester of this field.The maintained data structure of the data
For the provider location of the memory, there is the specific feature as defined in the data format.But the application principle is with above-mentioned text
Word illustrates that be not represented as a kind of limitation, this field tester will appreciate that plurality of step and behaviour as described below
Also it may be implemented in hardware.
Term as used herein " module " can regard the software object to execute in the arithmetic system as.It is as described herein
Different components, module, engine and service can be regarded as the objective for implementation in the arithmetic system.And device as described herein and side
Method can be implemented in the form of software, can also be implemented on hardware certainly, within the application protection scope.
Term " first ", " second " and " third " in the application etc. are for distinguishing different objects, rather than for retouching
State particular order.In addition, term " includes " and " having " and their any deformations, it is intended that cover and non-exclusive include.
Such as contain series of steps or module process, method, system, product or equipment be not limited to listed step or
Module, but some embodiments further include the steps that not listing or module or some embodiments further include for these processes,
Method, product or equipment intrinsic other steps or module.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
The embodiment of the present application provides a kind of position indicating method, and the executing subject of the position indicating method can be the application
The position prompt device that embodiment provides, or it is integrated with the electronic equipment of the position prompt device, wherein the position indicating fills
Setting can be realized by the way of hardware or software.Wherein, electronic equipment can be smart phone, tablet computer, palm electricity
The equipment such as brain, laptop or desktop computer.
Fig. 1 is please referred to, Fig. 1 is the flow diagram of position indicating method provided by the embodiments of the present application.As shown in Figure 1,
The process of position indicating method provided by the embodiments of the present application can be such that
101, whether detecting currently occurs change in location, if then obtaining the realtime graphic of current location.
In the embodiment of the present application, electronic equipment can obtain location information in real time, and according to the location information got come
Identification currently whether change in location occurs, for example, electronic equipment can by the location information currently got with get before
Location information be compared, if two location information differences, determine currently to have occurred change in location;For another example, electronics is set
It is standby to calculate the distance between the location information currently got and the location information got before value, and judge the distance
Whether value is greater than pre-determined distance value, and (the pre-determined distance value can take according to actual needs desired value by those skilled in the art, this Shen
Please embodiment this is not particularly limited, for example, can be set to 1 meter, that is to say that the moving distance of electronic equipment is more than one meter
When, just determine that change in location occurs), if then determining that change in location currently has occurred.Detecting current generation change in location
When, electronic equipment is shot by camera, to shoot the realtime graphic of obtained current location.
Wherein, when obtaining location information, electronic equipment determines to be presently at outdoor environment first, is in interior
Environment, for example, electronic equipment can be currently at outdoor environment according to the intensity size for receiving satellite positioning signal to identify,
It is in indoor environment, if the satellite positioning signal intensity received is lower than preset threshold, determines to be in indoor environment,
If the satellite positioning signal intensity received is greater than or equal to preset threshold, determine to be in outdoor environment.Correspondingly, sentencing
When being in outdoor environment surely, electronic equipment can obtain location information using satellite positioning tech, determine in indoor ring
When border, electronic equipment can obtain location information using indoor positioning technologies.
102, object identification is carried out to the realtime graphic got, obtains object information.
After getting the realtime graphic of current location, electronic equipment can be using default object recognition technique to acquisition
The realtime graphic arrived carries out object identification, obtains object information, it should be noted which kind of object is the embodiment of the present application for using
Body identification technology is used as the default object recognition technique that object identification is carried out to aforementioned realtime graphic, is not particularly limited, can be by
Those skilled in the art select according to actual needs.For example, electronic equipment can be divided by the image, semantic of pre-training
Model identifies aforementioned realtime graphic, obtains the object information of object present in aforementioned realtime graphic.
Wherein, object information may include the type, color or other information that can describe object features of object.
For example, referring to figure 2., user's hand-hold electronic equipments are moved to the current location of diagram by somewhere, and are sat on chair shown in Fig. 4
The real-time figure of current location is got at this time at this point, change in location currently is had occurred in judgement by electronic equipment using electronic equipment
Picture takes the image of diagram desktop, which includes the telephone set of a black, carries out object to the realtime graphic
Identification, the object information obtained are as follows: type " telephone set ", color " black ".
103, acquire the voice signal in external environment, and obtain that voice signal includes it is instructions to be performed.
It should be noted that electronic equipment can acquire the voice signal in external environment in a number of different ways,
For example, electronic equipment can be by built-in microphone to the voice in external environment in electronic equipment non-External microphone
It is acquired, obtains voice signal;For another example, when electronic equipment is circumscribed with microphone, electronic equipment can be by external
Microphone is acquired the voice in external environment, obtains voice signal.
Wherein, electronic equipment is by microphone, (microphone herein can be built-in microphone, be also possible to external wheat
Gram wind) voice signal in acquisition external environment when, if microphone is simulation microphone, the voice signal of simulation will be collected,
Electronic equipment needs sample the voice signal of simulation at this time, and the voice signal of simulation is converted to digitized voice
Signal, for example, can be sampled with the sample frequency of 16KHz;In addition, electronic equipment will if microphone is digital microphone
Digitized voice signal is directly collected by digital microphone, without being converted.
When obtaining instructions to be performed included by aforementioned voice signal, electronic equipment first determines whether local with the presence or absence of language
Sound analytics engine, and if it exists, then aforementioned voice signal is input to local speech analysis engine and carries out voice solution by electronic equipment
Analysis, obtains speech analysis text.Wherein, to voice signal carry out speech analysis, that is to say by voice signal from " audio " to " text
The conversion process of word ".
In addition, electronic equipment can be in the following way from multiple voices local there are when multiple speech analysis engines
A speech analysis engine is chosen in analytics engine, and speech analysis is carried out to voice signal:
First, electronic equipment can randomly select a speech analysis engine from local multiple speech analysis engines,
Speech analysis is carried out to aforementioned voice signal.
Second, electronic equipment can be chosen from multiple speech analysis engines and be parsed into the highest speech analysis of power and draw
It holds up, speech analysis is carried out to aforementioned voice signal.
Third, electronic equipment can choose the parsing shortest speech analysis engine of duration from multiple speech analysis engines,
Speech analysis is carried out to aforementioned voice signal.
Fourth, electronic equipment can also from multiple speech analysis engines, choose be parsed into power reach default success rate,
And the parsing shortest speech analysis engine of duration carries out speech analysis to aforementioned voice signal.
It should be noted that those skilled in the art can also carry out speech analysis engine according to mode not listed above
Selection, or can in conjunction with multiple speech analysis engines to aforementioned voice signal carry out speech analysis, for example, electronic equipment can
To carry out speech analysis to aforementioned voice signal by two speech analysis engines simultaneously, and obtained in two speech analysis engines
Speech analysis text it is identical when, using the identical speech analysis text as the speech analysis text of aforementioned voice signal;Again
For example, electronic equipment can carry out speech analysis to aforementioned voice signal by least three speech analysis engines, and wherein
When the speech analysis text that at least two speech analysis engines obtain is identical, using the identical speech analysis text as preceding predicate
The speech analysis text of sound signal.
After parsing obtains the speech analysis text of aforementioned voice signal, electronic equipment is further from speech analysis text
What acquisition aforementioned voice signal included in this is instructions to be performed.
Wherein, electronic equipment is previously stored with multiple instruction keyword, and single instruction keyword or multiple instruction are crucial
The corresponding instruction of word combination.The speech analysis text that analytically obtains obtain that aforementioned voice signal includes it is instructions to be performed
When, electronic equipment carries out participle operation to aforementioned voice parsing text first, obtains the word sequence of corresponding speech analysis text, should
It include multiple words in word sequence.
After the word sequence for obtaining corresponding speech analysis text, electronic equipment carries out of instruction keyword to word sequence
Match, that is to say the instruction keyword found out in word sequence, so that matching obtains corresponding instruction, the instruction that matching is obtained is made
For the instructions to be performed of voice signal.Wherein, the matched and searched for instructing keyword includes exact matching and/or fuzzy matching.
In addition, after electronic equipment whether there is speech analysis engine in judgement local, if it does not exist, then by aforementioned voice
Signal is sent to server (server is to provide the server of speech analysis service), indicates that the server believes aforementioned voice
It number is parsed, and returns to the parsing obtained speech analysis text of aforementioned voice signal.In the language for receiving server return
After sound parses text, electronic equipment can obtain pending finger included by aforementioned voice signal from the speech analysis text
It enables.
104, it is instructions to be performed for prompt for trigger position instruction when, position indicating is generated according to object information and is believed
Breath, and the output position prompt information in a manner of voice.
In the embodiment of the present application, electronic equipment is identified after obtaining aforementioned voice signal and including instructions to be performed wait hold
Whether row instruction is the instruction prompted for trigger position, wherein the instruction for trigger position prompt can be according to the defeated of owner
Enter data to be configured, if recognizing the instruction instructions to be performed to prompt for trigger position, determines aforementioned voice signal
Enunciator be owner.For example, owner's setting instruction keyword combination " little Ou "+" you "+" where " it is for trigger position
The instruction of prompt, in this way, when owner can not find electronic equipment, it can be said that go out " little Ou you where ", correspondingly, when electricity
When sub- equipment receives voice signal " little Ou you where ", electronic equipment will determine voice signal " little Ou you where " hair
Sound person is owner, and the instruction instructions to be performed to prompt for trigger position that voice signal " little Ou you where " includes.
Based on above description, those skilled in the art arbitrarily understand, since electronic equipment is when position changes,
The realtime graphic of position is just obtained, and object identification is carried out to realtime graphic, object information is obtained, if in upper primary generation
After change in location, receive in the voice signal for carrying out position indicating, then illustrating that owner can not find electronic equipment, and it is electric
Sub- equipment position is the last position that change in location occurs, and be that is to say " current location " above-mentioned, and " aforesaid object letter
Breath " can reflect aforementioned " current location ".Therefore, electronic equipment instructions to be performed is recognize that aforementioned voice signal includes
When instruction for trigger position prompt, position indicating information is further generated according to aforesaid object information, in place to its institute
Carry out position indicating is set, in this way, owner can recall last " current location " for using electronic equipment out, to find electricity
Sub- equipment.
Wherein, electronic equipment is when generating position indicating information, the object information and presupposed information that identification can be obtained
(can be configured according to actual needs by those skilled in the art, the embodiment of the present application is not particularly limited this) is spelled
It connects, using obtained concatenation information as position indicating information.
Such as, it is assumed that presupposed information is " owner owner, I nearby has ", it is assumed that the object information got are as follows: type " electricity
Phone ", color " black ", electronic equipment carry out position indicating information according to presupposed information+colouring information+information form
Splicing, obtaining position indicating information is " owner owner, I nearby has the telephone set of black ", as shown in Figure 3.
From the foregoing, it will be observed that the electronic equipment in the embodiment of the present application, can detect and currently whether change in location occur, if then
Obtain the realtime graphic of current location.Object identification is carried out to the realtime graphic got, obtains object information.Acquire external rings
Voice signal in border, and obtain that voice signal includes it is instructions to be performed.Instructions to be performed for for trigger position prompt
Instruction when, position indicating information, and the output position prompt information in a manner of voice are generated according to object information.The application energy
Enough when user can not find electronic equipment, according to the object information of object at present position, position is carried out to user and is mentioned
Show, user can be helped to recall the last position for using electronic equipment out, so that preferably guidance user finds electronic equipment,
Improve the probability that electronic equipment is found.
Referring to figure 4., Fig. 4 is another flow diagram of position indicating method provided by the embodiments of the present application, such as Fig. 4 institute
Show, which may include:
201, whether detecting currently occurs change in location, if then obtaining the realtime graphic of current location.
In the embodiment of the present application, electronic equipment can obtain location information in real time, and according to the location information got come
Identification currently whether change in location occurs, for example, electronic equipment can by the location information currently got with get before
Location information be compared, if two location information differences, determine currently to have occurred change in location;For another example, electronics is set
It is standby to calculate the distance between the location information currently got and the location information got before value, and judge the distance
Whether value is greater than pre-determined distance value, and (the pre-determined distance value can take according to actual needs desired value by those skilled in the art, this Shen
Please embodiment this is not particularly limited, for example, can be set to 1 meter, that is to say that the moving distance of electronic equipment is more than one meter
When, just determine that change in location occurs), if then determining that change in location currently has occurred.Detecting current generation change in location
When, electronic equipment is shot by camera, to shoot the realtime graphic of obtained current location.
Wherein, when obtaining location information, electronic equipment determines to be presently at outdoor environment first, is in interior
Environment, for example, electronic equipment can be currently at outdoor environment according to the intensity size for receiving satellite positioning signal to identify,
It is in indoor environment, if the satellite positioning signal intensity received is lower than preset threshold, determines to be in indoor environment,
If the satellite positioning signal intensity received is greater than or equal to preset threshold, determine to be in outdoor environment.Correspondingly, sentencing
When being in outdoor environment surely, electronic equipment can obtain location information using satellite positioning tech, determine in indoor ring
When border, electronic equipment can obtain location information using indoor positioning technologies.
202, the salient region in the realtime graphic got is determined.
It is easily understood that there are the possibility of multiple objects in aforementioned realtime graphic, and the identification to whole objects is completed,
It needs to expend the not short time, moreover, nor each object can be this process effectively goes unnoticed by the user.For example, referring to figure 5., user
Hand-hold electronic equipments are moved to the current location of diagram by somewhere, and are sat using electronic equipment on chair shown in Fig. 4, at this point,
Change in location currently is had occurred in judgement by electronic equipment, is got the realtime graphic of current location at this time, that is, is taken diagram table
The image in face, the realtime graphic include the telephone set and object 1 and object 2 of a black.
It therefore, is the efficiency of lifting object identification, electronic equipment is after getting aforementioned realtime graphic, first to aforementioned
Realtime graphic carries out salient region (popular point is said, it is possible to the region being noted) and is identified, determines aforementioned real-time figure
Salient region as in, to carry out object identification to salient region.
Wherein, electronic equipment can identify the conspicuousness area in aforementioned realtime graphic by the identification model of pre-training
Domain.Wherein, identification model is machine learning algorithm, and machine learning algorithm can be learnt by continuous feature learning into picture
Which object conspicuousness it is higher, that is to say how study identifies salient region in image, for example, generally believe personage,
Animal is higher than the conspicuousness of sky, meadow and building.
In addition, electronic equipment can also identify the conspicuousness area in aforementioned realtime graphic by key area focusing etc.
Domain, the embodiment of the present application are not particularly limited this.
203, object identification is carried out to the salient region in aforementioned realtime graphic.
In the embodiment of the present application, electronic equipment is determining the salient region progress object identification in aforementioned realtime graphic,
It identifies that obtained object information will reflect in realtime graphic and is easy the object being this process effectively goes unnoticed by the user, in other words, that is to say easy side
User is helped to recall the last object for using position (i.e. " current location " of electronic equipment).
Wherein, electronic equipment can carry out the salient region in aforementioned realtime graphic using default object recognition technique
Object identification obtains object information.It should be noted that the embodiment of the present application for using which kind of object recognition technique be used as pair
Aforementioned realtime graphic carries out the default object recognition technique of object identification, is not particularly limited, can be by those skilled in the art's root
It is selected according to actual needs.For example, electronic equipment can be by the image, semantic parted pattern of pre-training to aforementioned real-time figure
As being identified, the object information of object present in the salient region of aforementioned realtime graphic is obtained.
In addition, object information may include the type, color or other information that can describe object features of object.
For example, being moved to current location (assuming that there are the telephone sets of a black for current location) by somewhere in user's hand-hold electronic equipments
When, correspondingly, change in location currently is had occurred in judgement by electronic equipment, the realtime graphic of current location is got at this time, and right
The realtime graphic carries out object identification, the object information obtained are as follows: type " telephone set ", color " black ".
204, the Noisy Speech Signal in external environment is acquired, and obtains the history noise letter of corresponding Noisy Speech Signal
Number.
It is easily understood that there are various noises in environment, for example, generated in office there are computer operation
Noise taps the noise etc. that keyboard generates.So, electronic equipment is when carrying out the acquisition of voice signal, it is clear that is difficult to collect
Pure voice signal.
Correspondingly, if user issues voice signal, electronic equipment will acquire when electronic equipment is in noisy environment
Noisy Speech Signal into external environment, making an uproar in the voice signal and external environment which is issued by user
Acoustical signal combines to be formed, if user does not issue voice signal, the noise signal that electronic equipment will only collect in external environment.Its
In, electronic equipment will cache collected Noisy Speech Signal and noise signal.
In the embodiment of the present application, electronic equipment is when collecting the Noisy Speech Signal in external environment, with noisy speech
The initial time of signal is finish time, obtains acquire before receiving Noisy Speech Signal, preset duration (preset duration
Desired value can be taken according to actual needs by those skilled in the art, the embodiment of the present application is not particularly limited this, for example, can be with
Be set as 500ms) history noise signal, using the noise signal as the history noise signal of corresponding Noisy Speech Signal.
For example, preset duration is configured as 500 milliseconds, the initial time of Noisy Speech Signal is on 06 20th, 2,018 18
When 24 divide 56 seconds 500 milliseconds again, then 24 divide 56 seconds on 06 20th, 2018 when electronic equipment obtains 2018 06 month 20 days 18
When 18 24 divide 56 seconds it is caching during 500 milliseconds again, when a length of 500 milliseconds of noise signal, using the noise signal as correspondence
The history noise signal of Noisy Speech Signal.
205, according to history noise signal, the noise signal during Noisy Speech Signal acquisition is obtained.
Electronic equipment is made an uproar after getting the history noise signal of corresponding Noisy Speech Signal according to the history got
Acoustical signal further gets the noise signal during Noisy Speech Signal acquisition.
For example, electronic equipment can be according to the history noise signal got, come during predicting Noisy Speech Signal acquisition
Noise profile, thus obtain Noisy Speech Signal acquisition during noise signal.
For another example, it is contemplated that the stability of noise, the noise variation in continuous time is usually smaller, and electronic equipment can incite somebody to action
Get history noise signal as Noisy Speech Signal acquisition during noise signal, wherein if history noise signal when
The long duration for being greater than Noisy Speech Signal, then can intercept making an uproar for duration identical as Noisy Speech Signal from history noise signal
Acoustical signal, as the noise signal during Noisy Speech Signal acquisition;If the duration of history noise signal is believed less than noisy speech
Number duration, then history noise signal can be replicated, splice multiple history noise signals with obtain and noisy speech believe
The noise signal of number identical duration, as the noise signal during Noisy Speech Signal acquisition.
206, noise signal is subjected to the noise-reduced speech signal that antiphase is superimposed, and superposition is obtained with Noisy Speech Signal
As voice signal to be processed.
After noise signal during getting Noisy Speech Signal acquisition, electronic equipment is first to the noise got
Signal carries out reverse phase processing, then reverse phase treated noise signal is overlapped with Noisy Speech Signal, is made an uproar language with cancellation band
Noise section in sound signal obtains noise-reduced speech signal, and using the obtained noise-reduced speech signal as voice to be processed
Signal is used as subsequent processing.
207, what acquisition aforementioned voice signal included is instructions to be performed.
When obtaining instructions to be performed included by aforementioned voice signal, electronic equipment first determines whether local with the presence or absence of language
Sound analytics engine, and if it exists, then aforementioned voice signal is input to local speech analysis engine and carries out voice solution by electronic equipment
Analysis, obtains speech analysis text.Wherein, to voice signal carry out speech analysis, that is to say by voice signal from " audio " to " text
The conversion process of word ".After parsing obtains the speech analysis text of aforementioned voice signal, electronic equipment is further from the voice
What acquisition aforementioned voice signal included in parsing text is instructions to be performed.
Wherein, electronic equipment is previously stored with multiple instruction keyword, and single instruction keyword or multiple instruction are crucial
The corresponding instruction of word combination.The speech analysis text that analytically obtains obtain that aforementioned voice signal includes it is instructions to be performed
When, electronic equipment carries out participle operation to aforementioned voice parsing text first, obtains the word sequence of corresponding speech analysis text, should
It include multiple words in word sequence.
After the word sequence for obtaining corresponding speech analysis text, electronic equipment carries out of instruction keyword to word sequence
Match, that is to say the instruction keyword found out in word sequence, so that matching obtains corresponding instruction, the instruction that matching is obtained is made
For the instructions to be performed of voice signal.Wherein, the matched and searched for instructing keyword includes exact matching and/or fuzzy matching.
In addition, after electronic equipment whether there is speech analysis engine in judgement local, if it does not exist, then by aforementioned voice
Signal is sent to server (server is to provide the server of speech analysis service), indicates that the server believes aforementioned voice
It number is parsed, and returns to the parsing obtained speech analysis text of aforementioned voice signal.In the language for receiving server return
After sound parses text, electronic equipment can obtain pending finger included by aforementioned voice signal from the speech analysis text
It enables.
208, get it is instructions to be performed for prompt for trigger position instruction when, given birth to according to aforesaid object information
At position indicating information, and export in a manner of voice the position indicating information of generation.
In the embodiment of the present application, electronic equipment is identified after obtaining aforementioned voice signal and including instructions to be performed wait hold
Whether row instruction is the instruction prompted for trigger position, wherein the instruction for trigger position prompt can be according to the defeated of owner
Enter data to be configured, if recognizing the instruction instructions to be performed to prompt for trigger position, determines aforementioned voice signal
Enunciator be owner.For example, owner's setting instruction keyword combination " little Ou "+" you "+" where " it is for trigger position
The instruction of prompt, in this way, when owner can not find electronic equipment, it can be said that go out " little Ou you where ", correspondingly, when electricity
When sub- equipment receives voice signal " little Ou you where ", electronic equipment will determine voice signal " little Ou you where " hair
Sound person is owner, and the instruction instructions to be performed to prompt for trigger position that voice signal " little Ou you where " includes.
Based on above description, those skilled in the art arbitrarily understand, since electronic equipment is when position changes,
The realtime graphic of position is just obtained, and object identification is carried out to realtime graphic, object information is obtained, if in upper primary generation
After change in location, receive in the voice signal for carrying out position indicating, then illustrating that owner can not find electronic equipment, and it is electric
Sub- equipment position is the last position that change in location occurs, and be that is to say " current location " above-mentioned, and " aforesaid object letter
Breath " can reflect aforementioned " current location ".Therefore, electronic equipment instructions to be performed is recognize that aforementioned voice signal includes
When instruction for trigger position prompt, position indicating information is further generated according to aforesaid object information, in place to its institute
Carry out position indicating is set, in this way, owner can recall last " current location " for using electronic equipment out, to find electricity
Sub- equipment.
Wherein, electronic equipment is when generating position indicating information, the object information and presupposed information that identification can be obtained
(can be configured according to actual needs by those skilled in the art, the embodiment of the present application is not particularly limited this) is spelled
It connects, using obtained concatenation information as position indicating information.
Such as, it is assumed that presupposed information is " owner owner, I nearby has ", it is assumed that the object information got are as follows: type " electricity
Phone ", color " black ", electronic equipment carry out position indicating information according to presupposed information+colouring information+information form
Splicing, obtaining position indicating information is " owner owner, I nearby has the telephone set of black ", as shown in Figure 3.
In one embodiment, " determining the salient region in the realtime graphic got " includes:
(1) neural network of pre-training is called, and obtains the image gradient of aforementioned realtime graphic by the neural network;
(2) image to be processed of corresponding aforementioned realtime graphic is generated according to the image gradient got;
(3) binary conversion treatment is carried out to aforementioned image to be processed, obtains binaryzation image to be processed;
(4) according to the connected region in binaryzation image to be processed, the salient region of aforementioned realtime graphic is obtained.
Wherein, electronic equipment first pre-processes aforementioned realtime graphic, for example, by aforementioned realtime graphic according to
256x256 pixel carries out size normalization processing, then pretreated realtime graphic is input to the neural network of pre-training,
The image gradient of pretreated realtime graphic is obtained by the neural computing.
After the image gradient for obtaining aforementioned realtime graphic, further according to the image gradient in different color channels
Maximum value on (for example, the channel R, channel B and the channel G) generates the image to be processed of corresponding aforementioned realtime graphic, should
Image to be processed can reflect the salient region of aforementioned realtime graphic to a certain extent.
After obtaining corresponding to the image to be processed of aforementioned realtime graphic, electronic equipment carries out binaryzation to image to be processed
Processing, obtains binaryzation image to be processed.Wherein, binary conversion treatment is carried out to image to be processed herein for using which kind of mode
It is not particularly limited, for example, maximum variance between clusters can be used.
After obtaining binaryzation image to be processed, electronic equipment further determines that out the company in binaryzation image to be processed
Logical region obtains the salient region of aforementioned realtime graphic then according to the connected region determined.For example, electronic equipment from
A connected region is determined in image to be processed, then it can be directly using the connected region as the conspicuousness of aforementioned realtime graphic
Region.For another example, electronic equipment determines multiple connected regions from image to be processed, then can be directly multiple by what is determined
Connected region is as multiple salient regions in aforementioned realtime graphic.
In one embodiment, " according to the connected region in aforementioned binaryzation image to be processed, aforementioned realtime graphic is obtained
Salient region " include:
There are when multiple connected regions in aforementioned binaryzation image to be processed, from multiple connected regions, one is chosen
Salient region of the connected region as aforementioned realtime graphic.
Wherein, electronic equipment is after determining the connected region in binaryzation image to be processed, if binaryzation is to be processed
There are multiple connected regions in image, then from multiple connected regions, choose a connected region as aforementioned realtime graphic
Salient region.Wherein, for which kind of mode to choose the connected region as salient region according to, the embodiment of the present application is not done
Concrete restriction, for example, electronic equipment in multiple connected regions for determining, can randomly select in the way of randomly selecting
Salient region of one connected region as aforementioned realtime graphic.
In one embodiment, " from multiple connected regions, a connected region is chosen as the aobvious of aforementioned realtime graphic
Work property region " includes:
From aforesaid plurality of connected region, conspicuousness area of the maximum connected region of area as aforementioned realtime graphic is chosen
Domain.
Wherein, the size of connected region i.e. its size for corresponding to object, area is bigger, and corresponding object is easier
It is noted.Therefore, electronic equipment can choose the maximum connected region of area as aforementioned from aforesaid plurality of connected region
The salient region of realtime graphic, in this way, the object information identified will when carrying out object identification to the salient region
It is easiest to the object being this process effectively goes unnoticed by the user in reflection realtime graphic, it is possible thereby to preferably user be helped to recall last use
The position (i.e. " current location " of electronic equipment) of electronic equipment.
In one embodiment, before " acquisition aforementioned voice signal includes instructions to be performed ", further includes:
(1) vocal print feature of aforementioned voice signal is obtained, and the vocal print feature got is verified;
(2) when aforementioned vocal print feature is verified, acquisition aforementioned voice signal includes instructions to be performed.
Although also cannot exclude the instruction it is easily understood that the instruction for trigger position prompt is arranged by owner
The possibility known by other people.Therefore, electronic equipment is recognized also according to enunciator's progress identity of the vocal print feature to aforementioned voice signal
Card.
Wherein, after obtaining voice signal to be processed, further obtain aforementioned voice signal includes electronic equipment
Vocal print feature.Wherein, vocal print feature include but is not limited to spectrum signature component, cepstrum characteristic component, formant characteristic component,
Fundamental tone characteristic component, reflection coefficient characteristic component, tone feature component, word speed characteristic component, emotional characteristics component, prosodic features
At least one of component and rhythm characteristic component characteristic component.
Later, electronic equipment obtains aforementioned vocal print feature and (presets vocal print feature with default vocal print feature and record in advance for owner
The vocal print feature entered) similarity, and judging whether the similarity that gets is greater than or equal to default similarity (can be by this field
Technical staff is configured according to actual needs).Wherein, when the similarity got is greater than or equal to default similarity, really
Fixed aforementioned vocal print feature is verified, and determines that the enunciator of aforementioned voice signal is owner.
Wherein, the available aforementioned vocal print feature of electronic equipment is at a distance from default vocal print feature, and will acquire away from
From the similarity as aforementioned vocal print feature and default vocal print feature.It should be noted that can by those skilled in the art according to
Actual needs chooses any one characteristic distance (such as Euclidean distance, manhatton distance, Chebyshev's distance etc.) to measure
The distance between aforementioned vocal print feature and default vocal print feature.
For example, the COS distance of available aforementioned vocal print feature and default vocal print feature, referring in particular to following formula:
Wherein, e indicates that the COS distance of aforementioned vocal print feature and default vocal print feature, f indicate aforementioned vocal print feature, N table
Show dimension (aforementioned vocal print feature with the dimension of default vocal print feature identical) of the aforementioned vocal print feature with default vocal print feature, fiTable
Show the feature vector of i-th dimension degree in aforementioned vocal print feature, giIndicate the feature vector of i-th dimension degree in default vocal print feature.
In one embodiment, " according to history noise signal, the noise signal during Noisy Speech Signal acquisition is obtained "
Include:
(1) model training is carried out using history noise signal as sample data, obtains noise prediction model;
(2) noise signal during Noisy Speech Signal acquisition is predicted according to noise prediction model.
Wherein, electronic equipment is after getting history noise signal, using the history noise signal as sample data, and
Model training is carried out according to default training algorithm, obtains noise prediction model.
It should be noted that training algorithm is machine learning algorithm, machine learning algorithm can be by constantly carrying out spy
Sign study is to predict data, for example, electronic equipment can predict current noise point according to the noise profile of history
Cloth.Wherein, machine learning algorithm may include: that decision Tree algorithms, regression algorithm, bayesian algorithm, neural network algorithm (can be with
Including deep neural network algorithm, convolutional neural networks algorithm and recurrent neural network algorithm etc.), clustering algorithm etc., it is right
It, can be by those skilled in the art according to actual needs in choosing which kind of training algorithm is used as default training algorithm progress model training
It is chosen.
For example, the default training algorithm of electronic equipment configuration is gauss hybrid models algorithm (for a kind of regression algorithm),
After getting history noise signal, using the history noise signal as sample data, and according to gauss hybrid models algorithm into
Row model training, training obtains a gauss hybrid models, and (noise prediction model includes multiple Gauss units, for describing noise
Distribution), using the gauss hybrid models as noise prediction model.Later, during electronic equipment acquires Noisy Speech Signal
The input of start time and finish time as noise prediction model, is input to noise prediction model and is handled, pre- by noise
It surveys model and exports the noise signal between aforementioned Noisy Speech Signal Harvest time.
In one embodiment, a kind of position prompt device is additionally provided.Fig. 6 is please referred to, Fig. 6 provides for the embodiment of the present application
Position prompt device 400 structural schematic diagram.Wherein the position prompt device is applied to electronic equipment, the position prompt device
It is as follows including image collection module 401, object identification module 402, instruction acquisition module 403 and position indicating module 404:
Whether image collection module 401 currently occurs change in location for detecting, if then obtaining the real-time of current location
Image.
Object identification module 402 obtains object information for carrying out object identification to the realtime graphic got.
Instruction acquisition module 403, for acquiring the voice signal in external environment, and obtain that voice signal includes wait hold
Row instruction.
Position indicating module 404, for it is instructions to be performed for prompt for trigger position instruction when, believed according to object
Breath generates position indicating information, and the output position prompt information in a manner of voice.
In one embodiment, object identification module 402 can be used for:
Determine the salient region in the realtime graphic got;
Object identification is carried out to the salient region in aforementioned realtime graphic.
In one embodiment, object identification module 402 can be used for:
The neural network of pre-training is called, and obtains the image gradient of aforementioned realtime graphic by the neural network;
The image to be processed of corresponding aforementioned realtime graphic is generated according to the image gradient got;
Binary conversion treatment is carried out to aforementioned image to be processed, obtains binaryzation image to be processed;
According to the connected region in binaryzation image to be processed, the salient region of aforementioned realtime graphic is obtained.
In one embodiment, object identification module 402 can be used for:
There are when multiple connected regions in aforementioned binaryzation image to be processed, from multiple connected regions, one is chosen
Salient region of the connected region as aforementioned realtime graphic.
In one embodiment, object identification module 402 can be used for:
From aforesaid plurality of connected region, conspicuousness area of the maximum connected region of area as aforementioned realtime graphic is chosen
Domain.
In one embodiment, instruction acquisition module 403 can be used for:
When collecting the Noisy Speech Signal in external environment, the history noise letter of corresponding Noisy Speech Signal is obtained
Number;
According to history noise signal, the noise signal during Noisy Speech Signal acquisition is obtained;
By noise signal and Noisy Speech Signal carry out noise-reduced speech signal that antiphase is superimposed, and superposition is obtained as
Aforementioned voice signal.
In one embodiment, instruction acquisition module 403 can be used for:
Model training is carried out using history noise signal as sample data, obtains noise prediction model;
The noise signal during Noisy Speech Signal acquisition is predicted according to noise prediction model.
In one embodiment, instruction acquisition module 403 can be used for:
The vocal print feature of aforementioned voice signal is obtained, and the vocal print feature got is verified;
When aforementioned vocal print feature is verified, acquisition aforementioned voice signal includes instructions to be performed.
Wherein, the step of each module executes in position prompt device 400 side that reference can be made to the above method embodiment describes
Method step.The position prompt device 400 can integrate in the electronic device, such as mobile phone, tablet computer.
It is realized when it is implemented, the above modules can be used as independent entity, any combination can also be carried out, as
Same or several entities realize that the specific implementation of above each unit can be found in the embodiment of front, and details are not described herein.
Currently whether occur from the foregoing, it will be observed that the position prompt device of the present embodiment can be detected by image collection module 401
Change in location, if then obtaining the realtime graphic of current location.The realtime graphic got is carried out by object identification module 402
Object identification obtains object information.Voice signal in external environment is acquired by instruction acquisition module 403, and obtains voice letter
Number include is instructions to be performed.By position indicating module 404 it is instructions to be performed for prompt for trigger position instruction when, root
Position indicating information, and the output position prompt information in a manner of voice are generated according to object information.The application can user without
When method finds electronic equipment, according to the object information of object at present position, position indicating is carried out to user, can be helped
User recalls the last position for using electronic equipment out and so that preferably guidance user finds electronic equipment improves electronics
The probability that equipment is found.
In one embodiment, a kind of electronic equipment is also provided.Please refer to Fig. 7, electronic equipment 500 include processor 501 with
And memory 502.Wherein, processor 501 and memory 502 are electrically connected.
Processor 500 is the control centre of electronic equipment 500, utilizes various interfaces and the entire electronic equipment of connection
Various pieces by the computer program of operation or load store in memory 502, and are called and are stored in memory 502
Interior data execute the various functions of electronic equipment 500 and handle data.
Memory 502 can be used for storing software program and module, and processor 501 is stored in memory 502 by operation
Computer program and module, thereby executing various function application and data processing.Memory 502 can mainly include storage
Program area and storage data area, wherein storing program area can computer program needed for storage program area, at least one function
(such as sound-playing function, image player function etc.) etc.;Storage data area can be stored to be created according to using for electronic equipment
Data etc..In addition, memory 502 may include high-speed random access memory, it can also include nonvolatile memory, example
Such as at least one disk memory, flush memory device or other volatile solid-state parts.Correspondingly, memory 502 may be used also
To include Memory Controller, to provide access of the processor 501 to memory 502.
In the embodiment of the present application, the processor 501 in electronic equipment 500 can be according to following step, by one or one
The corresponding instruction of the process of a above computer program is loaded into memory 502, and is stored in by the operation of processor 501
Computer program in reservoir 502, thus realize various functions, it is as follows:
Whether detecting currently occurs change in location, if then obtaining the realtime graphic of current location;
Object identification is carried out to the realtime graphic got, obtains object information;
Acquire the voice signal in external environment, and obtain that voice signal includes it is instructions to be performed;
It is instructions to be performed for prompt for trigger position instruction when, according to object information generation position indicating information,
And the output position prompt information in a manner of voice.
Also referring to Fig. 8, in some embodiments, electronic equipment 500 can also include: display 503, radio frequency electrical
Road 504, voicefrequency circuit 505 and power supply 506.Wherein, wherein display 503, radio circuit 504, voicefrequency circuit 505 and
Power supply 506 is electrically connected with processor 501 respectively.
Display 503 is displayed for information input by user or is supplied to the information and various figures use of user
Family interface, these graphical user interface can be made of figure, text, icon, video and any combination thereof.Display 503
May include display panel, in some embodiments, can using liquid crystal display (Liquid Crystal Display,
LCD) or the forms such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) configure display surface
Plate.
Radio circuit 504 can be used for transceiving radio frequency signal, to set by wireless communication with the network equipment or other electronics
It is standby to establish wireless telecommunications, the receiving and transmitting signal between the network equipment or other electronic equipments.
Voicefrequency circuit 505 can be used for providing the audio interface between user and electronic equipment by loudspeaker, microphone.
Power supply 506 is used to all parts power supply of electronic equipment 500.In some embodiments, power supply 506 can be with
It is logically contiguous by power-supply management system and processor 501, thus by power-supply management system realize management charging, electric discharge, with
And the functions such as power managed.
Although being not shown in Fig. 8, electronic equipment 500 can also include camera, bluetooth module etc., and details are not described herein.
In some embodiments, when carrying out object identification to the realtime graphic got, processor 501 can be executed
Following steps:
Determine the salient region in the realtime graphic got;
Object identification is carried out to the salient region in aforementioned realtime graphic.
In some embodiments, when determining the salient region in the realtime graphic that gets, processor 501 can be with
Execute following steps:
The neural network of pre-training is called, and obtains the image gradient of aforementioned realtime graphic by the neural network;
The image to be processed of corresponding aforementioned realtime graphic is generated according to the image gradient got;
Binary conversion treatment is carried out to aforementioned image to be processed, obtains binaryzation image to be processed;
According to the connected region in binaryzation image to be processed, the salient region of aforementioned realtime graphic is obtained.
In some embodiments, according to the connected region in binaryzation image to be processed, aforementioned realtime graphic is obtained
Salient region when, processor 501 can execute following steps:
There are when multiple connected regions in aforementioned binaryzation image to be processed, from multiple connected regions, one is chosen
Salient region of the connected region as aforementioned realtime graphic.
In some embodiments, a connected region from multiple connected regions, is being chosen as aforementioned realtime graphic
Salient region when, processor 501 can execute following steps:
From aforesaid plurality of connected region, conspicuousness area of the maximum connected region of area as aforementioned realtime graphic is chosen
Domain.
In some embodiments, when acquiring the voice signal in external environment, processor 501 can also be performed following
Step:
When collecting the Noisy Speech Signal in external environment, the history noise letter of corresponding Noisy Speech Signal is obtained
Number;
According to history noise signal, the noise signal during Noisy Speech Signal acquisition is obtained;
By noise signal and Noisy Speech Signal carry out noise-reduced speech signal that antiphase is superimposed, and superposition is obtained as
Aforementioned voice signal.
In some embodiments, according to history noise signal, the noise letter during Noisy Speech Signal acquisition is obtained
Number when, following steps can also be performed in processor 501:
Model training is carried out using history noise signal as sample data, obtains noise prediction model;
The noise signal during Noisy Speech Signal acquisition is predicted according to noise prediction model.
The embodiment of the present application also provides a kind of storage medium, and the storage medium is stored with computer program, when the meter
When calculation machine program is run on computers, so that the computer executes the position indicating method in any of the above-described embodiment, than
Such as: whether detecting currently occurs change in location, if then obtaining the realtime graphic of current location;To the realtime graphic got into
Row object identification, obtains object information;The voice signal in external environment is acquired, and obtains the pending finger that voice signal includes
It enables;It is instructions to be performed for prompt for trigger position instruction when, according to object information generation position indicating information, and with language
The mode output position prompt information of sound.
In the embodiment of the present application, storage medium can be magnetic disk, CD, read-only memory (Read Only Memory,
ROM) or random access device (Random Access Memory, RAM) etc..
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
It should be noted that for the position indicating method of the embodiment of the present application, this field common test personnel can be with
Understand all or part of the process for realizing the position indicating method of the embodiment of the present application, is that can be controlled by computer program
Relevant hardware is completed, and the computer program can be stored in a computer-readable storage medium, be such as stored in electronics
It in the memory of equipment, and is executed by least one processor in the electronic equipment, in the process of implementation may include such as position
The process of the embodiment of reminding method.Wherein, the storage medium can be magnetic disk, CD, read-only memory, arbitrary access note
Recall body etc..
For the position prompt device of the embodiment of the present application, each functional module be can integrate in a processing chip
In, it is also possible to modules and physically exists alone, can also be integrated in two or more modules in a module.It is above-mentioned
Integrated module both can take the form of hardware realization, can also be realized in the form of software function module.It is described integrated
If module realized in the form of software function module and when sold or used as an independent product, also can store one
In a computer-readable storage medium, the storage medium is for example read-only memory, disk or CD etc..
Above to a kind of position indicating method, device, storage medium and electronic equipment provided by the embodiment of the present application into
It has gone and has been discussed in detail, specific examples are used herein to illustrate the principle and implementation manner of the present application, the above implementation
The explanation of example is merely used to help understand the present processes and its core concept;Meanwhile for those skilled in the art, according to
According to the thought of the application, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification
It should not be construed as the limitation to the application.
Claims (10)
1. a kind of position indicating method, which is characterized in that the position indicating method includes:
Whether detecting currently occurs change in location, if then obtaining the realtime graphic of current location;
Object identification is carried out to the realtime graphic, obtains object information;
Acquire the voice signal in external environment, and obtain that the voice signal includes it is instructions to be performed;
It is described it is instructions to be performed for prompt for trigger position instruction when, position indicating is generated according to the object information and is believed
Breath, and the position indicating information is exported in a manner of voice.
2. position indicating method as described in claim 1, which is characterized in that carry out the step of object identification to the realtime graphic
Suddenly, comprising:
Determine the salient region in the realtime graphic;
Object identification is carried out to the salient region in the realtime graphic.
3. position indicating method as claimed in claim 2, is characterized in that, the salient region in the realtime graphic is determined
Step, comprising:
The neural network of pre-training is called, and obtains the image gradient of the realtime graphic by the neural network;
The image to be processed of the corresponding realtime graphic is generated according to described image gradient;
Binary conversion treatment is carried out to the image to be processed, obtains binaryzation image to be processed;
According to the connected region in binaryzation image to be processed, the salient region of the realtime graphic is obtained.
4. position indicating method as claimed in claim 3, which is characterized in that according to the company in binaryzation image to be processed
The step of leading to region, obtaining the salient region of the realtime graphic, comprising:
There are when multiple connected regions in binaryzation image to be processed, from the multiple connected region, one is chosen
Connected region is as the salient region.
5. position indicating mode as claimed in claim 4, which is characterized in that from the multiple connected region, choose one
The step of connected region is as the salient region, comprising:
From the multiple connected region, the maximum connected region of area is chosen as the salient region.
6. position indicating method as described in any one in claim 1-5, which is characterized in that obtaining the voice signal includes
Before step instructions to be performed, further includes:
The vocal print feature of the voice signal is obtained, and the vocal print feature is verified;
When the vocal print feature is verified, obtain that the voice signal includes is instructions to be performed.
7. position indicating method as described in any one in claim 1-5, which is characterized in that the voice letter in acquisition external environment
Number the step of, further includes:
The Noisy Speech Signal in external environment is acquired, and obtains the history noise signal of the corresponding Noisy Speech Signal;
According to the history noise signal, the noise signal during the Noisy Speech Signal acquisition is obtained;
The noise signal is subjected to the noise-reduced speech signal that antiphase is superimposed, and superposition is obtained with the Noisy Speech Signal
As the voice signal.
8. a kind of position prompt device, which is characterized in that the position prompt device includes:
Whether image collection module currently occurs change in location for detecting, if then obtaining the realtime graphic of current location;
Object identification module obtains object information for carrying out object identification to the realtime graphic;
Instruction acquisition module, for acquiring the voice signal in external environment, and obtain that the voice signal includes it is pending
Instruction;
Position indicating module, for it is described it is instructions to be performed for prompt for trigger position instruction when, according to the object
Information generates position indicating information, and the position indicating information is exported in a manner of voice.
9. a kind of storage medium, is stored thereon with computer program, which is characterized in that when the computer program on computers
When operation, so that the computer executes position indicating method as described in any one of claim 1 to 7.
10. a kind of electronic equipment, including processor and memory, which is characterized in that the processor is by calling the calculating
Machine program, for executing position indicating method as described in any one of claim 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810682024.8A CN108989551B (en) | 2018-06-27 | 2018-06-27 | Position prompting method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810682024.8A CN108989551B (en) | 2018-06-27 | 2018-06-27 | Position prompting method and device, storage medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108989551A true CN108989551A (en) | 2018-12-11 |
CN108989551B CN108989551B (en) | 2020-12-01 |
Family
ID=64538627
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810682024.8A Expired - Fee Related CN108989551B (en) | 2018-06-27 | 2018-06-27 | Position prompting method and device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108989551B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109961045A (en) * | 2019-03-25 | 2019-07-02 | 联想(北京)有限公司 | A kind of location information prompt method, device and electronic equipment |
CN111142095A (en) * | 2020-01-16 | 2020-05-12 | 三星电子(中国)研发中心 | Indoor positioning system, method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101334896A (en) * | 2008-07-25 | 2008-12-31 | 西安交通大学 | Processing method for measuring sub-pixel rim of digital picture |
CN105809695A (en) * | 2016-03-11 | 2016-07-27 | 深圳还是威健康科技有限公司 | Terminal searching method and device based on wearable device |
CN106529375A (en) * | 2015-09-11 | 2017-03-22 | 上海乐今通信技术有限公司 | Mobile terminal and object feature identification method for image of mobile terminal |
WO2017096761A1 (en) * | 2015-12-10 | 2017-06-15 | 杭州海康威视数字技术股份有限公司 | Method, device and system for looking for target object on basis of surveillance cameras |
CN106878535A (en) * | 2015-12-14 | 2017-06-20 | 北京奇虎科技有限公司 | The based reminding method and device of mobile terminal locations |
-
2018
- 2018-06-27 CN CN201810682024.8A patent/CN108989551B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101334896A (en) * | 2008-07-25 | 2008-12-31 | 西安交通大学 | Processing method for measuring sub-pixel rim of digital picture |
CN106529375A (en) * | 2015-09-11 | 2017-03-22 | 上海乐今通信技术有限公司 | Mobile terminal and object feature identification method for image of mobile terminal |
WO2017096761A1 (en) * | 2015-12-10 | 2017-06-15 | 杭州海康威视数字技术股份有限公司 | Method, device and system for looking for target object on basis of surveillance cameras |
CN106878535A (en) * | 2015-12-14 | 2017-06-20 | 北京奇虎科技有限公司 | The based reminding method and device of mobile terminal locations |
CN105809695A (en) * | 2016-03-11 | 2016-07-27 | 深圳还是威健康科技有限公司 | Terminal searching method and device based on wearable device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109961045A (en) * | 2019-03-25 | 2019-07-02 | 联想(北京)有限公司 | A kind of location information prompt method, device and electronic equipment |
CN109961045B (en) * | 2019-03-25 | 2021-10-22 | 联想(北京)有限公司 | Position information prompting method and device and electronic equipment |
CN111142095A (en) * | 2020-01-16 | 2020-05-12 | 三星电子(中国)研发中心 | Indoor positioning system, method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108989551B (en) | 2020-12-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110853618B (en) | Language identification method, model training method, device and equipment | |
CN112259106B (en) | Voiceprint recognition method and device, storage medium and computer equipment | |
CN108009521A (en) | Humanface image matching method, device, terminal and storage medium | |
DE112014000709B4 (en) | METHOD AND DEVICE FOR OPERATING A VOICE TRIGGER FOR A DIGITAL ASSISTANT | |
CN108962241A (en) | Position indicating method, device, storage medium and electronic equipment | |
CN108922525A (en) | Method of speech processing, device, storage medium and electronic equipment | |
CN108806684A (en) | Position indicating method, device, storage medium and electronic equipment | |
CN108305626A (en) | The sound control method and device of application program | |
CN110853617B (en) | Model training method, language identification method, device and equipment | |
CN108900965A (en) | Position indicating method, device, storage medium and electronic equipment | |
CN108463849A (en) | Determine the dialogue state of language model | |
CN108538311A (en) | Audio frequency classification method, device and computer readable storage medium | |
JP2016502140A (en) | Combination of auditory attention cue and phoneme posterior probability score for sound / vowel / syllable boundary detection | |
CN109903773A (en) | Audio-frequency processing method, device and storage medium | |
CN108711429A (en) | Electronic equipment and apparatus control method | |
CN112949708A (en) | Emotion recognition method and device, computer equipment and storage medium | |
CN110085217A (en) | Phonetic navigation method, device and terminal device | |
CN113129867A (en) | Training method of voice recognition model, voice recognition method, device and equipment | |
CN111462755A (en) | Information prompting method and device, electronic equipment and medium | |
CN108989551A (en) | Position indicating method, device, storage medium and electronic equipment | |
CN114333774B (en) | Speech recognition method, device, computer equipment and storage medium | |
CN110246494A (en) | Service request method, device and computer equipment based on speech recognition | |
CN109064720A (en) | Position indicating method, device, storage medium and electronic equipment | |
CN109427332A (en) | The electronic equipment and its operating method of operation are executed using voice command | |
CN113076397A (en) | Intention recognition method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201201 |