CN103021404A - Advertisement identification method based on audio - Google Patents
Advertisement identification method based on audio Download PDFInfo
- Publication number
- CN103021404A CN103021404A CN201210480848XA CN201210480848A CN103021404A CN 103021404 A CN103021404 A CN 103021404A CN 201210480848X A CN201210480848X A CN 201210480848XA CN 201210480848 A CN201210480848 A CN 201210480848A CN 103021404 A CN103021404 A CN 103021404A
- Authority
- CN
- China
- Prior art keywords
- audio frequency
- advertisement
- note
- melody characteristics
- melody
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an advertisement identification method based on audio, which comprises the following steps: a) acquiring audio of audio video advertisement and collecting the detailed information of the commodity corresponding to the advertisement; b) extracting melody characteristic of the advertisement audio and storing the melody characteristic of the advertisement audio together with the commodity information in a database; c) obtaining a humming audio recorded by a user and extracting the melody characteristic of the humming audio; and d) searching the melody characteristic of the advertisement audio similar to that of the humming audio from the database, and if finding out, returning the community information corresponding to the melody characteristic of the advertisement audio to the user. By adoption of the advertisement identification method disclosed by the invention based on audio, the search comparison can be performed fast and exactly and the community information corresponding to the advertisement audio is returned to the user in time.
Description
Technical field
The present invention relates to a kind of advertisement recognition method, relate in particular to a kind of advertisement recognition method based on audio frequency.
Background technology
Nowadays, the propagation of advertisement has been not limited to traditional media such as televisor, newspaper, and more and more audio frequency and video advertisements appear in the public transport, on the subway, in the radio, in the dining room, in the elevator.People's shopping way is also more diversified, selects the consumer go solid shop/brick and mortar store to buy product to reduce gradually, and increasing people selects shopping online, and along with the raising of mobile technology, also becomes many people's selection by the mobile platform shopping.But usually, the consumer need to seek the shopping approach voluntarily after hearing out or finishing watching advertisement, such as the online search, not only Search Results is inaccurate, but also can cause the user to produce desire to purchase and the actual time interval that occurs to exist between the buying behavior in various degree.Show according to investigations, consumer's desire to purchase is As time goes on constantly to descend, if can in the shortest time after the user produces desire to purchase to the commodity in the audio frequency and video advertisement, for it provides merchandise news and purchase approach, will greatly promote consumption.Therefore, be necessary to provide a kind of advertisement recognition method based on audio frequency, can be quickly and accurately that the advertisement audio frequency is corresponding merchandise news returns to the user.
Summary of the invention
Technical matters to be solved by this invention provides a kind of advertisement recognition method based on audio frequency, can search for contrast to audio-frequency information fast and accurately, and the merchandise news that the advertisement audio frequency is corresponding in time returns to the user.
The present invention solves the problems of the technologies described above the technical scheme that adopts to provide a kind of advertisement recognition method based on audio frequency, comprises the steps: a) to gather the audio frequency of audio frequency and video advertisement, and collects the details with the corresponding commodity of this advertisement; B) extract the melody characteristics of this advertisement audio frequency, and be saved in together melody characteristics and the merchandise news of this advertisement audio frequency in the database; C) obtain the humming audio frequency that the user records, and extract the melody characteristics of this humming audio frequency; D) in database, search the melody characteristics of the advertisement audio frequency similar with the melody characteristics of described humming audio frequency, as find, then the corresponding merchandise news of the melody characteristics of this advertisement audio frequency is returned to the user.
The above-mentioned advertisement recognition method based on audio frequency, wherein, described melody characteristics is the note fragment sequence:
, wherein,
Represent note pitch,
For note continues duration, m is the note segments, and i is natural number,
The above-mentioned advertisement recognition method based on audio frequency, wherein, it is 5～15 seconds that described note fragment sequence continues duration.
The above-mentioned advertisement recognition method based on audio frequency, wherein, described steps d) search similar melody characteristics in and comprise following process:
Calculate two melody characteristics similarities:
Wherein, A=
, B=
Be the melody characteristics of two similarities to be compared, m is the note segments of melody characteristics A, and W is the length of the note fragment of melody characteristics A, and n is the note segments of melody characteristics B, and U is the length of the note fragment of melody characteristics B,
Be note
Arrive
Distance,
The length of note is moved in expression;
When reaching predetermined threshold value, the similarity of two melody characteristicses judges that then two melody characteristicses conform to.
The above-mentioned advertisement recognition method based on audio frequency, wherein, the predetermined threshold value scope of described similarity is [0.86,1].
The above-mentioned advertisement recognition method based on audio frequency, wherein, described merchandise news returns to the user by the commodity purchasing link.
The present invention contrasts prior art following beneficial effect: the advertisement recognition method based on audio frequency provided by the invention, first the melody characteristics in the advertisement audio frequency is extracted, and collect its corresponding merchandise news and store in the database of server, then to user's humming audio extraction melody characteristics, thereby realize fast and accurately search contrast, and the corresponding merchandise news of the advertisement audio frequency of coupling is in time returned to the user.
Description of drawings
Fig. 1 is the advertisement identification process synoptic diagram that the present invention is based on audio frequency.
Embodiment
The invention will be further described below in conjunction with drawings and Examples.
Fig. 1 is the advertisement identification process synoptic diagram that the present invention is based on audio frequency.
See also Fig. 1, the advertisement recognition method based on audio frequency provided by the invention comprises the steps:
S101: server end gathers the audio frequency of audio frequency and video advertisement, and collects the details with the corresponding commodity of this advertisement;
S102: extract the melody characteristics of this advertisement audio frequency, and melody characteristics and the merchandise news of this advertisement audio frequency is saved in the database together.Melody characteristics can adopt following note fragment sequence:
, wherein,
Represent note pitch,
For note continues duration, m is the note segments, and i is natural number,
Consider recognition speed and accuracy rate, it is 5～15 seconds that described note fragment sequence continues duration.
S103: obtain the humming audio frequency that the user records, and extract the melody characteristics of this humming audio frequency; Directly hum 10 seconds audio frequency and upload to the webserver by mobile phone terminal such as the user.
S104: server is searched the melody characteristics of the advertisement audio frequency similar with the melody characteristics of described humming audio frequency in database, as finds, and then the corresponding merchandise news of the melody characteristics of this advertisement audio frequency is returned to the user.
Searching similar melody characteristics can be by calculating two melody characteristics similarities, judges then that when the similarity of two melody characteristicses reaches predetermined threshold value two melody characteristicses conform to, and similarity is one [0,1] floating number between, if similarity reaches between [0.86,1], can think to reach threshold value.Similarity is calculated as follows:
Wherein, A=
, B=
Be the melody characteristics of two similarities to be compared, m is the note segments of melody characteristics A, and W is the length of the note fragment of melody characteristics A, and n is the note segments of melody characteristics B, and U is the length of the note fragment of melody characteristics B,
Be note
Arrive
Distance,
The length of note is moved in expression.
Consider the advertisement audio frequency that has magnanimity on the network, in order to solve the storage efficiency problem of magnanimity advertisement audio frequency, and improve retrieval efficient.The invention allows for a kind of compacter melody characteristics of describing based on global information and extract recognition methods, comprise following process:
D1) extract power spectrum after each note fragment sequence is added Hamming window, then with power spectrum according to Mel (Mel) logarithm frequency scale, be divided into several subbands;
D2) calculate each sub belt energy, obtain the distribution of each sub belt energy, each sub belt energy is carried out normalization, obtain the energy vector;
D3) the energy vector quantity is changed into code word in the Codebook of Vector Quantization;
D4) judge that then two melody characteristicses are similar if two note fragment sequence code words are identical.
After adopting said method, melody characteristics large young pathbreaker reduce greatly, thereby further saved the server stores computational resource, and the complexity of server disposition.
In sum, advertisement recognition method based on audio frequency provided by the invention, first the melody characteristics in the advertisement audio frequency is extracted, and collect its corresponding merchandise news and store in the database of server, then to user's humming audio extraction melody characteristics, thereby realize fast and accurately search contrast, and the corresponding merchandise news of the advertisement audio frequency of coupling is in time returned to the user.
Although the present invention discloses as above with preferred embodiment; so it is not to limit the present invention, any those skilled in the art, without departing from the spirit and scope of the present invention; when can doing a little modification and perfect, so protection scope of the present invention is when with being as the criterion that claims were defined.
Claims (6)
1. the advertisement recognition method based on audio frequency is characterized in that, comprises the steps:
A) gather the audio frequency of audio frequency and video advertisement, and collect the details with the corresponding commodity of this advertisement;
B) extract the melody characteristics of this advertisement audio frequency, and be saved in together melody characteristics and the merchandise news of this advertisement audio frequency in the database;
C) obtain the humming audio frequency that the user records, and extract the melody characteristics of this humming audio frequency;
D) in database, search the melody characteristics of the advertisement audio frequency similar with the melody characteristics of described humming audio frequency, as find, then the corresponding merchandise news of the melody characteristics of this advertisement audio frequency is returned to the user.
2. the advertisement recognition method based on audio frequency as claimed in claim 1 is characterized in that, described melody characteristics is the note fragment sequence:
, wherein,
Represent note pitch,
For note continues duration, m is the note segments, and i is natural number,
3. the advertisement recognition method based on audio frequency as claimed in claim 2 is characterized in that, it is 5～15 seconds that described note fragment sequence continues duration.
4. the advertisement recognition method based on audio frequency as claimed in claim 2 is characterized in that, described steps d) in search similar melody characteristics and comprise following process:
Calculate two melody characteristics similarities:
Wherein, A=
, B=
Be the melody characteristics of two similarities to be compared, m is the note segments of melody characteristics A, and W is the length of the note fragment of melody characteristics A, and n is the note segments of melody characteristics B, and U is the length of the note fragment of melody characteristics B,
Be note
Arrive
Distance,
The length of note is moved in expression;
When reaching predetermined threshold value, the similarity of two melody characteristicses judges that then two melody characteristicses conform to.
5. the advertisement recognition method based on audio frequency as claimed in claim 4 is characterized in that, the predetermined threshold value scope of described similarity is [0.86,1].
6. such as each described advertisement recognition method based on audio frequency of claim 1～5, it is characterized in that described merchandise news returns to the user by the commodity purchasing link.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210480848XA CN103021404A (en) | 2012-11-23 | 2012-11-23 | Advertisement identification method based on audio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210480848XA CN103021404A (en) | 2012-11-23 | 2012-11-23 | Advertisement identification method based on audio |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103021404A true CN103021404A (en) | 2013-04-03 |
Family
ID=47969936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210480848XA Pending CN103021404A (en) | 2012-11-23 | 2012-11-23 | Advertisement identification method based on audio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103021404A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103200429A (en) * | 2013-04-09 | 2013-07-10 | 上海合合信息科技发展有限公司 | Method and system for carrying out interaction with advertisements in televisions and radio stations |
| CN103237260A (en) * | 2013-04-09 | 2013-08-07 | 上海合合信息科技发展有限公司 | System and method for acquiring advertisements from television and radio channels in real time |
| CN104317967A (en) * | 2014-11-17 | 2015-01-28 | 北京航空航天大学 | Two-layer advertisement audio retrieval method based on audio fingerprints |
| CN104376477A (en) * | 2013-08-16 | 2015-02-25 | 鸿富锦精密工业（深圳）有限公司 | Electronic device and advertisement push system and method |
| CN104835049A (en) * | 2015-05-21 | 2015-08-12 | 唐洛鹏 | Purchase link pushing method and system |
| CN104899318A (en) * | 2015-06-18 | 2015-09-09 | 上海融视广告传媒有限公司 | Media interaction method based on audio |
| CN105321101A (en) * | 2015-11-10 | 2016-02-10 | 张家港智帆技术咨询有限公司 | Audio based information acquisition method |
| CN107124648A (en) * | 2017-04-17 | 2017-09-01 | 浙江德塔森特数据技术有限公司 | The method that advertisement video is originated is recognized by intelligent terminal |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101158967A (en) * | 2007-11-16 | 2008-04-09 | 北京交通大学 | Quick-speed audio advertisement recognition method based on layered matching |
| CN101471068A (en) * | 2007-12-26 | 2009-07-01 | 三星电子株式会社 | Method and system for searching music files based on wave shape through humming music rhythm |
| US20090271395A1 (en) * | 2008-04-24 | 2009-10-29 | Chi Mei Communication Systems, Inc. | Media file searching system and method for a mobile phone |
| CN102053998A (en) * | 2009-11-04 | 2011-05-11 | 周明全 | Method and system device for retrieving songs based on voice modes |
| CN102521281A (en) * | 2011-11-25 | 2012-06-27 | 北京师范大学 | Humming computer music searching method based on longest matching subsequence algorithm |
-
2012
- 2012-11-23 CN CN201210480848XA patent/CN103021404A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101158967A (en) * | 2007-11-16 | 2008-04-09 | 北京交通大学 | Quick-speed audio advertisement recognition method based on layered matching |
| CN101471068A (en) * | 2007-12-26 | 2009-07-01 | 三星电子株式会社 | Method and system for searching music files based on wave shape through humming music rhythm |
| US20090271395A1 (en) * | 2008-04-24 | 2009-10-29 | Chi Mei Communication Systems, Inc. | Media file searching system and method for a mobile phone |
| CN102053998A (en) * | 2009-11-04 | 2011-05-11 | 周明全 | Method and system device for retrieving songs based on voice modes |
| CN102521281A (en) * | 2011-11-25 | 2012-06-27 | 北京师范大学 | Humming computer music searching method based on longest matching subsequence algorithm |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103200429A (en) * | 2013-04-09 | 2013-07-10 | 上海合合信息科技发展有限公司 | Method and system for carrying out interaction with advertisements in televisions and radio stations |
| CN103237260A (en) * | 2013-04-09 | 2013-08-07 | 上海合合信息科技发展有限公司 | System and method for acquiring advertisements from television and radio channels in real time |
| CN103200429B (en) * | 2013-04-09 | 2016-12-28 | 上海合合信息科技发展有限公司 | The method and system interacted with the advertisement in TV, radio station |
| CN103237260B (en) * | 2013-04-09 | 2016-12-28 | 上海合合信息科技发展有限公司 | The system and method for advertisement is obtained in real time from TV, station channel |
| CN104376477A (en) * | 2013-08-16 | 2015-02-25 | 鸿富锦精密工业（深圳）有限公司 | Electronic device and advertisement push system and method |
| CN104317967A (en) * | 2014-11-17 | 2015-01-28 | 北京航空航天大学 | Two-layer advertisement audio retrieval method based on audio fingerprints |
| CN104835049A (en) * | 2015-05-21 | 2015-08-12 | 唐洛鹏 | Purchase link pushing method and system |
| CN104899318A (en) * | 2015-06-18 | 2015-09-09 | 上海融视广告传媒有限公司 | Media interaction method based on audio |
| CN105321101A (en) * | 2015-11-10 | 2016-02-10 | 张家港智帆技术咨询有限公司 | Audio based information acquisition method |
| CN107124648A (en) * | 2017-04-17 | 2017-09-01 | 浙江德塔森特数据技术有限公司 | The method that advertisement video is originated is recognized by intelligent terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103021404A (en) | Advertisement identification method based on audio | |
| CN108241667A (en) | For the method and apparatus of pushed information | |
| CN107071578A (en) | IPTV program commending methods | |
| CN105095211B (en) | The acquisition methods and device of multi-medium data | |
| CN102542489B (en) | One kind is based on the associated recommendation method of user interest | |
| CN103593371B (en) | Recommend the method and apparatus of search keyword | |
| CN101271559A (en) | Cooperation recommending system based on user partial interest digging | |
| CN102592116A (en) | Cloud computing application method, system and terminal equipment, and cloud computing platform | |
| CN105023178B (en) | A kind of electronic commerce recommending method based on ontology | |
| CN111400507B (en) | Entity matching method and device | |
| CN104462336A (en) | Information pushing method and device | |
| CN105320706A (en) | Processing method and device of search result | |
| CN102063433A (en) | Method and device for recommending related items | |
| CN102760169A (en) | Method for detecting advertising slots in television direct transmission streams | |
| CN102982153A (en) | Information retrieval method and device | |
| CN103237136B (en) | The search method of mobile terminal and descriptor thereof | |
| CN103970802A (en) | Song recommending method and device | |
| CN104751354A (en) | Advertisement cluster screening method | |
| CN103853749A (en) | Mode-based audio retrieval method and system | |
| CN103389975A (en) | News recommending method and system | |
| CN103309869A (en) | Method and system for recommending display keyword of data object | |
| CN106776859A (en) | Mobile solution App commending systems based on user preference | |
| CN105608105B (en) | It is a kind of that method is recommended based on the music for listening to context | |
| CN103577472A (en) | Method and system for obtaining and presuming personal information as well as method and system for classifying and retrieving commodities | |
| CN103020153A (en) | Advertisement identification method based on videos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130403 |
|
| RJ01 | Rejection of invention patent application after publication |