CN110046305A - A kind of method of artificial intelligence deep learning - Google Patents
A kind of method of artificial intelligence deep learning Download PDFInfo
- Publication number
- CN110046305A CN110046305A CN201910330364.9A CN201910330364A CN110046305A CN 110046305 A CN110046305 A CN 110046305A CN 201910330364 A CN201910330364 A CN 201910330364A CN 110046305 A CN110046305 A CN 110046305A
- Authority
- CN
- China
- Prior art keywords
- user
- sound
- sample
- age
- webpage
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000013135 deep learning Methods 0.000 title claims abstract description 16
- 238000005070 sampling Methods 0.000 claims abstract description 8
- 238000001914 filtration Methods 0.000 claims description 9
- 238000007792 addition Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002939 deleterious effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention particularly discloses a kind of methods of artificial intelligence deep learning, including adding label to all webpages first, while starting voice input when scanning for；Secondly the sound of the samplers sample user of client, and the sound of user is sampled；The sample that tone color identifier identifies user's sampling sound respectively is reused, the frequency and amplitude for obtaining sample are averaged sound frequency and acoustic amplitudes as average sample；It is retrieved in audio database again, finds age of the age as user corresponding to voice data identical with the sound frequency of sample and acoustic amplitudes；It reuses the speech recognition device identification content to be searched for of user and scans for；The label for the webpage that last query search arrives, on the client by web displaying.In the present invention, the identification of depth is carried out by the sound characteristic to user, judges the age characteristics of user, thus the webpage that search is consistent with the age of user feature, and user is presented.
Description
Technical field
The present invention relates to artificial intelligence field, in particular to a kind of method of artificial intelligence deep learning.
Background technique
With information-based arrival, more and more information are presented on people at the moment, and people generally pass through in browser
Search engine carry out the browsing of webpage, but the feature that current browser is certain customers just shows relevant information, this
Sample just probably says that the information of some unsuitable users is presented to the user, to cause bad user experience to user, such as
Fruit be children using browser carry out using when, if what is showed is some webpages for not meeting children's browsing,
It is just very easy to cause deleterious effect to the body and mind of children.
Summary of the invention
The purpose of the present invention is overcoming above-mentioned problems of the prior art, a kind of artificial intelligence deep learning is provided
Method is carried out the identification of depth by the sound characteristic to user, judges the age characteristics of user, thus search and the user year
The webpage that age feature is consistent, and user is presented.
The technical scheme is that a kind of method of artificial intelligence deep learning, includes the following steps:
S1: it is applicable in the label at age to all webpage additions, while being scanned for using the search engine of client
When start voice input；
S2: the sound of the samplers sample user of client, and the sound of user is sampled；
S3: it identifies the sample of user's sampling sound respectively using the tone color identifier built in client, obtains each sample
This sound frequency and acoustic amplitudes, remove respectively the minimum sample of the highest sample of frequency, frequency, the maximum sample of amplitude with
And the smallest sample of amplitude, and respectively by the frequency of remaining sample and amplitude be averaged as average sample sound frequency and
Acoustic amplitudes；
S4: being retrieved in audio database, finds sound identical with the sound frequency of average sample and acoustic amplitudes
Age of the age corresponding to sound data as user；
S5: using built in client speech recognition device identify the content to be searched for of user, and open search engine into
Row search；
S6: the label for being applicable in the age for the webpage that query search arrives, filtering do not meet the webpage at the age of user, will filter
Web displaying afterwards is on the client.
Preferably, in step s 6, the client is shown the link of webpage by way of hyperlink.
Preferably, in step s 6, if the age of user is shown as the age of children, not meeting the age filtering out
Webpage after, by with picture web displaying only text webpage top.
Preferably, in step sl, being directly entered voice input when starting the search engine of client.
Preferably, in step s 2, including the following steps:
S2-1: sampler falls extra noise using filters filter to the sound of user；
S2-2: according to the length of time of the sound of user, according to the quantity of the sample to be taken of the ratio-dependent of setting；
S2-3: the sound of the user of random intercepted samples quantity is the sample of sampling, the sound of each user is one
Sample.
A kind of method of artificial intelligence deep learning is provided in the embodiment of the present invention, have it is following the utility model has the advantages that
1, the identification that depth is carried out by the sound characteristic to user, judges the age characteristics of user, to search for and be somebody's turn to do
The webpage that age of user feature is consistent, and user is presented；
2, when user is children, the web displaying with picture is before the webpage of only text, so that children
The content of webpage is easy to understand.
Detailed description of the invention
Fig. 1 is a kind of overall flow schematic block diagram of the method for artificial intelligence deep learning of the invention；
Fig. 2 is a kind of schematic process flow diagram of the method for artificial intelligence deep learning of the invention in step s 2.
Specific embodiment
With reference to the accompanying drawing, the specific embodiment of the present invention is described in detail, it is to be understood that of the invention
Protection scope be not limited by the specific implementation.
Referring to Fig. 1, the embodiment of the invention provides a kind of methods of artificial intelligence deep learning, include the following steps:
S1: it is applicable in the label at age to all webpage additions, while being scanned for using the search engine of client
When start voice input；
S2: the sound of the samplers sample user of client, and the sound of user is sampled；
S3: it identifies the sample of user's sampling sound respectively using the tone color identifier built in client, obtains each sample
This sound frequency and acoustic amplitudes, remove respectively the minimum sample of the highest sample of frequency, frequency, the maximum sample of amplitude with
And the smallest sample of amplitude, and respectively by the frequency of remaining sample and amplitude be averaged as average sample sound frequency and
Acoustic amplitudes；
S4: being retrieved in audio database, finds sound identical with the sound frequency of average sample and acoustic amplitudes
Age of the age corresponding to sound data as user；
S5: using built in client speech recognition device identify the content to be searched for of user, and open search engine into
Row search；
S6: the label for being applicable in the age for the webpage that query search arrives, filtering do not meet the webpage at the age of user, will filter
Web displaying afterwards is on the client.
When user prepares to open webpage using search engine, the function of starting voice input receives the voice of user
The information of sound, since the tone color of the sound of the mankind can be with the increase at age, sound is more and more hoarse, therefore first from user's sound
The tone color of sound judges the age of client, after the age of user has been determined, is just realised that group's type of user, according to
The content to be expressed of speech recognition user at family starts search engine, the content to be expressed of client is searched for, finally according to webpage
Webpage is presented to user in label.
Further, in step s 6, the client is shown the link of webpage by way of hyperlink.Make
The content of webpage can be substantially understood from the hyperlink of webpage so that user's online is more light with the mode of hyperlink,
It is further to realize Chinese online, while also interface can be made more good.
Further, in step s 6, if the age of user is shown as the age of children, year is not met filtering out
After the webpage in age, by the web displaying with picture in the top of the webpage of only text.This to function will be specifically for children
Customization, due to there is maturation in the intelligence of children, browsing in general can more lift the interest of children with the webpage of picture,
Children can be also made more to be apparent to having in webpage simultaneously, it is therefore, same when judging user for children
When the inside entered the Web page retrieved, by the web displaying with picture in the top of the webpage of only text, due to user
It is all to carry out clicking browsing from the webpage of interface the top when carrying out web page browsing.
Further, in step sl, voice input is directly entered when starting the search engine of client.In starting visitor
When the end of family, it is directly entered voice input, the above method thus can be used to protect the web page browsing of each user,
Due to entering search engine using words input, then cannot would not also be produced according to the age of the speech recognition user of user
Raw beneficial effect described in the invention, therefore design and be directly entered voice input when starting the search engine of client.
Further, referring to fig. 2, in step s 2, include the following steps:
S2-1: sampler falls extra noise using filters filter to the sound of user；
S2-2: according to the length of time of the sound of user, according to the quantity of the sample to be taken of the ratio-dependent of setting；
S2-3: the sound of the user of random intercepted samples quantity is the sample of sampling, the sound of each user is one
Sample.
In step s 2, the noise generated in nature is further filtered out, it not only can more good judgement
The tone color of user out, it is more accurate hence for the Age estimation of user, it can also be by filtering noise, so that identification is interior
Appearance is more accurate, so that the demand that the search content of search engine is more close to the users therefore, will be miscellaneous in S2 step
Beneficial effect caused by the filtering of sound is obvious.
In conclusion the invention particularly discloses a kind of method of artificial intelligence deep learning, including S1, to all nets
Page addition is applicable in the label at age, while starting voice input when scanning for using the search engine of client；S2,
The sound of the samplers sample user of client, and the sound of user is sampled；S3, known using the tone color built in client
Other device identifies the sample of user's sampling sound respectively, obtains the sound frequency and acoustic amplitudes of each sample, removes frequency elimination respectively
The minimum sample of the highest sample of rate, frequency, the maximum sample of amplitude and the smallest sample of amplitude, and respectively by remaining sample
Frequency and amplitude be averaged sound frequency and acoustic amplitudes as average sample；S4, it is examined in audio database
Rope finds year of the age as user corresponding to voice data identical with the sound frequency of average sample and acoustic amplitudes
Age；S5, the content to be searched for of user is identified using the speech recognition device built in client, and open search engine and searched
Rope；The label for being applicable in the age for the webpage that S6, query search arrive, filtering do not meet the webpage at the age of user, will be filtered
Web displaying is on the client.In the present invention, the identification of depth is carried out by the sound characteristic to user, judges the age of user
Feature, thus the webpage that search is consistent with the age of user feature, and user is presented.
Disclosed above is only several specific embodiments of the invention, and still, the embodiment of the present invention is not limited to this, is appointed
What what those skilled in the art can think variation should all fall into protection scope of the present invention.
Claims (5)
1. a kind of method of artificial intelligence deep learning, which comprises the steps of:
S1: being applicable in the label at age to all webpage additions, at the same using the search engine of client scan for when
Wait starting voice input；
S2: the sound of the samplers sample user of client, and the sound of user is sampled；
S3: it identifies the sample of user's sampling sound respectively using the tone color identifier built in client, obtains each sample
Sound frequency and acoustic amplitudes remove the highest sample of frequency, frequency minimum sample, the maximum sample of amplitude and vibration respectively
The smallest sample, and the frequency of remaining sample and amplitude are averaged to sound frequency and sound as average sample respectively
Amplitude；
S4: being retrieved in audio database, finds sound number identical with the sound frequency of average sample and acoustic amplitudes
Age according to the corresponding age as user；
S5: the content to be searched for of user is identified using the speech recognition device built in client, and opens search engine and is searched
Rope；
S6: the label for being applicable in the age for the webpage that query search arrives, filtering do not meet the webpage at the age of user, will be filtered
Web displaying is on the client.
2. a kind of method of artificial intelligence deep learning as described in claim 1, which is characterized in that in step s 6, described
Client is shown the link of webpage by way of hyperlink.
3. a kind of method of artificial intelligence deep learning as described in claim 1, which is characterized in that in step s 6, if
The age of user is shown as the age of children, then after filtering out and not meeting the webpage at age, will have the web displaying of picture
In the top of the webpage of only text.
4. a kind of method of artificial intelligence deep learning as described in claim 1, which is characterized in that in step sl, opening
Voice input is directly entered when the search engine of dynamic client.
5. a kind of method of artificial intelligence deep learning as described in claim 1, which is characterized in that in step s 2, including
Following steps:
S2-1: sampler falls extra noise using filters filter to the sound of user；
S2-2: according to the length of time of the sound of user, according to the quantity of the sample to be taken of the ratio-dependent of setting；
S2-3: the sound of the user of random intercepted samples quantity is the sample of sampling, the sound of each user is a sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910330364.9A CN110046305A (en) | 2019-04-23 | 2019-04-23 | A kind of method of artificial intelligence deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910330364.9A CN110046305A (en) | 2019-04-23 | 2019-04-23 | A kind of method of artificial intelligence deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110046305A true CN110046305A (en) | 2019-07-23 |
Family
ID=67278781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910330364.9A Pending CN110046305A (en) | 2019-04-23 | 2019-04-23 | A kind of method of artificial intelligence deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110046305A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516083A (en) * | 2019-08-30 | 2019-11-29 | 京东方科技集团股份有限公司 | Photograph album management method, storage medium and electronic equipment |
| CN110706814A (en) * | 2019-10-14 | 2020-01-17 | 郑州西亚斯学院 | Distributed intelligent economic management system |
| CN117690431A (en) * | 2023-12-25 | 2024-03-12 | 杭州恒芯微电子技术有限公司 | Microphone system based on voice recognition |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100100383A1 (en) * | 2008-10-17 | 2010-04-22 | Aibelive Co., Ltd. | System and method for searching webpage with voice control |
| CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术（北京）有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
| CN106096366A (en) * | 2016-06-08 | 2016-11-09 | 北京奇虎科技有限公司 | A kind of information processing method, device and equipment |
| CN106548773A (en) * | 2016-11-04 | 2017-03-29 | 百度在线网络技术（北京）有限公司 | Child user searching method and device based on artificial intelligence |
| CN106777089A (en) * | 2016-12-13 | 2017-05-31 | 北京奇虎科技有限公司 | Content screen method, device and mobile terminal |
| CN107548564A (en) * | 2016-04-29 | 2018-01-05 | 华为技术有限公司 | A kind of phonetic entry abnormal determination method, apparatus, terminal and storage medium |
| CN107610706A (en) * | 2017-09-13 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | The processing method and processing unit of phonetic search result |
| CN108920541A (en) * | 2018-06-12 | 2018-11-30 | 广东小天才科技有限公司 | Recognition method based on voice search and family education machine |
| CN108986796A (en) * | 2018-06-21 | 2018-12-11 | 广东小天才科技有限公司 | Voice search method and device |
| CN109255053A (en) * | 2018-09-14 | 2019-01-22 | 北京奇艺世纪科技有限公司 | Resource search method, device, terminal, server, computer readable storage medium |
-
2019
- 2019-04-23 CN CN201910330364.9A patent/CN110046305A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100100383A1 (en) * | 2008-10-17 | 2010-04-22 | Aibelive Co., Ltd. | System and method for searching webpage with voice control |
| CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术（北京）有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
| CN107548564A (en) * | 2016-04-29 | 2018-01-05 | 华为技术有限公司 | A kind of phonetic entry abnormal determination method, apparatus, terminal and storage medium |
| CN106096366A (en) * | 2016-06-08 | 2016-11-09 | 北京奇虎科技有限公司 | A kind of information processing method, device and equipment |
| CN106548773A (en) * | 2016-11-04 | 2017-03-29 | 百度在线网络技术（北京）有限公司 | Child user searching method and device based on artificial intelligence |
| CN106777089A (en) * | 2016-12-13 | 2017-05-31 | 北京奇虎科技有限公司 | Content screen method, device and mobile terminal |
| CN107610706A (en) * | 2017-09-13 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | The processing method and processing unit of phonetic search result |
| CN108920541A (en) * | 2018-06-12 | 2018-11-30 | 广东小天才科技有限公司 | Recognition method based on voice search and family education machine |
| CN108986796A (en) * | 2018-06-21 | 2018-12-11 | 广东小天才科技有限公司 | Voice search method and device |
| CN109255053A (en) * | 2018-09-14 | 2019-01-22 | 北京奇艺世纪科技有限公司 | Resource search method, device, terminal, server, computer readable storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516083A (en) * | 2019-08-30 | 2019-11-29 | 京东方科技集团股份有限公司 | Photograph album management method, storage medium and electronic equipment |
| CN110516083B (en) * | 2019-08-30 | 2022-07-12 | 京东方科技集团股份有限公司 | Album management method, storage medium and electronic device |
| US11580971B2 (en) | 2019-08-30 | 2023-02-14 | Boe Technology Group Co., Ltd. | Photo album management method, storage medium and electronic device |
| CN110706814A (en) * | 2019-10-14 | 2020-01-17 | 郑州西亚斯学院 | Distributed intelligent economic management system |
| CN117690431A (en) * | 2023-12-25 | 2024-03-12 | 杭州恒芯微电子技术有限公司 | Microphone system based on voice recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046305A (en) | A kind of method of artificial intelligence deep learning | |
| US7366668B1 (en) | Voice interface for a search engine | |
| US6665644B1 (en) | Conversational data mining | |
| US9653072B2 (en) | Apparatus and method for forming search engine queries based on spoken utterances | |
| CN110769111A (en) | Noise reduction method, system, storage medium and terminal | |
| CN106682090A (en) | Active interaction implementing device, active interaction implementing method and intelligent voice interaction equipment | |
| CN109256118B (en) | End-to-end Chinese dialect identification system and method based on generative auditory model | |
| CN111783534B (en) | Sleep stage method based on deep learning | |
| CN106250553A (en) | A kind of service recommendation method and terminal | |
| CN108491517A (en) | A kind of region agricultural information service speech polling terminal | |
| CN110136709A (en) | Audio recognition method and video conferencing system based on speech recognition | |
| CN107871499A (en) | Audio recognition method, system, computer equipment and computer-readable recording medium | |
| CN116665676B (en) | Semantic recognition method for intelligent voice outbound system | |
| CN110277087A (en) | A kind of broadcast singal anticipation preprocess method | |
| CN112927723A (en) | High-performance anti-noise speech emotion recognition method based on deep neural network | |
| CN111933113A (en) | Voice recognition method, device, equipment and medium | |
| CN113269305B (en) | Feedback voice strengthening method for strengthening memory | |
| CN117292688B (en) | Control method based on intelligent voice mouse and intelligent voice mouse | |
| CN117316165B (en) | Conference audio analysis processing method and system based on time sequence | |
| CN110933236B (en) | Machine learning-based null number identification method | |
| CN108650145A (en) | Phone number characteristic automatic extraction method under a kind of home broadband WiFi | |
| CN113194210A (en) | Voice call access method and device | |
| CN115273821A (en) | Speech recognition system based on semantic understanding of computer application scene | |
| CN110322894B (en) | Sound-based oscillogram generation and panda detection method | |
| CN113438368A (en) | Method, device and computer readable storage medium for realizing ring back tone detection |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190723 |
|
| RJ01 | Rejection of invention patent application after publication |