CN108038161A - Information recommendation method, device and computing device based on photograph album - Google Patents
Information recommendation method, device and computing device based on photograph album Download PDFInfo
- Publication number
- CN108038161A CN108038161A CN201711275689.9A CN201711275689A CN108038161A CN 108038161 A CN108038161 A CN 108038161A CN 201711275689 A CN201711275689 A CN 201711275689A CN 108038161 A CN108038161 A CN 108038161A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- picture
- pictures
- recommended
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本发明公开了一种基于相册的信息推荐方法、装置、计算设备及计算机存储介质。其中，方法包括：获取用户相册中的图片和/或视频；对图片和/或从视频中抽取的帧图片进行图像特征分析，根据图像特征分析结果确定用户的用户标签；对用户标签进行语义分析，根据语义分析结果得出满足用户需求的至少一个信息类型；根据至少一个信息类型查询相应类型的信息库以获取与用户标签相匹配的待推荐信息；将待推荐信息推荐给用户，如此，可以查找到与该用户感兴趣的信息，避免了由于推荐信息与用户兴趣爱好相关度低而导致用户并不点击查看推荐信息的问题，提高了用户查看相应信息的概率。
The invention discloses an album-based information recommendation method, device, computing equipment and computer storage medium. Among them, the method includes: obtaining pictures and/or videos in the user's album; performing image feature analysis on the pictures and/or frame pictures extracted from the video, and determining the user's user label according to the image feature analysis result; performing semantic analysis on the user label , get at least one information type that meets the user's needs according to the semantic analysis results; query the corresponding type of information base according to at least one information type to obtain the recommended information that matches the user's label; recommend the recommended information to the user. In this way, you can Finding the information that the user is interested in avoids the problem that the user does not click to view the recommended information due to the low correlation between the recommended information and the user's hobbies, and improves the probability of the user viewing the corresponding information.
Description
Technical field
The present invention relates to technical field of information processing, and in particular to a kind of information recommendation method based on photograph album, device, meter
Calculate equipment and computer-readable storage medium.
Background technology
With the development of science and technology, the application program of terminal device is more and more, photograph album is one of terminal device important
It is that more and more users like oneself or to oneself important picture and/or video (example for the application program of storage
Such as, the picture and/or video shot in tourism way, picture and/or video for being shot in meeting etc.) it is stored in photograph album, this
A little pictures and/or video, which contain, reflects its preference or behavioural habits, can embody the hobby etc. of user, if however,
Only picture and/or video are stored in user's photograph album, the value of these pictures and/or video can not be fully demonstrated.
Existing information recommendation technology be typically according to the historical behavior of user, excavate user it is interested wait to push away
Information is recommended, not in view of the influence of the picture in user's photograph album and/or video to recommendation information.
The content of the invention
In view of the above problems, it is proposed that the present invention overcomes the above problem in order to provide one kind or solves at least in part
State the information recommendation method based on photograph album, device, computing device and the computer-readable storage medium of problem.
According to an aspect of the invention, there is provided a kind of information recommendation method based on photograph album, it includes：
Obtain the picture and/or video in user's photograph album；
The frame picture extracted to picture and/or from video carries out image characteristic analysis, according to image characteristic analysis result
Determine the user tag of user；
Semantic analysis is carried out to user tag, at least one information for meeting user demand is drawn according to semantic analysis result
Type；
The information bank that respective type is inquired about according at least one information type is waited to push away to obtain with what user tag matched
Recommend information；
By information recommendation to be recommended to user.
Alternatively, the frame picture extracted to picture and/or from video carries out image characteristic analysis and further comprises：
The frame picture extracted to picture and/or from video is classified；
Image characteristic analysis is carried out to picture and/or frame picture respectively according to classification.
Alternatively, the frame picture extracted to picture and/or from video carries out classification and further comprises：By picture and/or
Frame picture classification is to the one or more in following classification：Personage's classification, life classification, landscape classification, cuisines classification, household class
Not, culture and arts classification, scientific and technological classification.
Alternatively, the user tag for determining user according to image characteristic analysis result further comprises：
By carrying out image characteristic analysis to belonging to the other picture of figure kind and/or frame picture, the natural category of user is determined
Property；
And/or by carrying out image characteristic analysis to belonging to the other picture of non-figure kind and/or frame picture, determine user
Behavior property；
The user tag of user is determined according to natural quality and/or behavior property.
Alternatively, the information bank that respective type is inquired about according at least one information type is matched with obtaining with user tag
Information to be recommended further comprise：
The title or brief introduction or function of information in the information bank of respective type are inquired about according at least one information type
Introduce to obtain the information to be recommended that the keyword of information matches with user tag.
Alternatively, semantic analysis is carried out to user tag, is drawn according to semantic analysis result and meet user demand at least
One information type further comprises：
Segmenting word processing is carried out to user tag；
The result handled according to segmenting word carries out user view identification, draws at least one info class for meeting user demand
Type.
Alternatively, information to be recommended includes：News, shopping information, advertisement, article, exhibition activity, cuisines way, cuisines
Dining room, travelling route, public platform.
According to another aspect of the present invention, there is provided a kind of information recommending apparatus based on photograph album, it includes：
Acquisition module, suitable for obtaining picture and/or video in user's photograph album；
Characteristics analysis module, the frame picture suitable for being extracted to picture and/or from video carry out image characteristic analysis；
Determining module, suitable for determining the user tag of user according to image characteristic analysis result；
Semantic module, suitable for carrying out semantic analysis to user tag, draws according to semantic analysis result and meets user
At least one information type of demand；
Enquiry module, suitable for inquiring about the information bank of respective type according at least one information type to obtain and user tag
The information to be recommended to match；
Recommending module, suitable for by information recommendation to be recommended to user.
Alternatively, characteristics analysis module further comprises：
Taxon, the frame picture suitable for being extracted to picture and/or from video are classified；
Characteristic analysis unit, suitable for carrying out image characteristic analysis to picture and/or frame picture respectively according to classification.
Alternatively, taxon is further adapted for：By picture and/or frame picture classification to one kind in following classification or more
Kind：Personage's classification, life classification, landscape classification, cuisines classification, household classification, culture and arts classification, scientific and technological classification.
Optionally it is determined that module is further adapted for：
By carrying out image characteristic analysis to belonging to the other picture of figure kind and/or frame picture, the natural category of user is determined
Property；
And/or by carrying out image characteristic analysis to belonging to the other picture of non-figure kind and/or frame picture, determine user
Behavior property；
The user tag of user is determined according to natural quality and/or behavior property.
Alternatively, enquiry module is further adapted for：Inquired about according at least one information type in the information bank of respective type
The title of information or brief introduction or function introduction are to obtain the information to be recommended that the keyword of information and user tag match.
Alternatively, semantic module further comprises：
Segmenting word processing unit, suitable for carrying out segmenting word processing to user tag；
Intention assessment unit, the result suitable for being handled according to segmenting word carry out user view identification, draw and meet user's need
At least one information type asked.
Alternatively, information to be recommended includes：News, shopping information, advertisement, article, exhibition activity, cuisines way, cuisines
Dining room, travelling route, public platform.
According to another aspect of the invention, there is provided a kind of computing device, including：Processor, memory, communication interface and
Communication bus, processor, memory and communication interface complete mutual communication by communication bus；
Memory is used to store an at least executable instruction, and executable instruction makes processor perform the above-mentioned letter based on photograph album
Cease the corresponding operation of recommendation method.
In accordance with a further aspect of the present invention, there is provided a kind of computer-readable storage medium, is stored with least one in storage medium
Executable instruction, executable instruction make processor perform such as the corresponding operation of the above-mentioned information recommendation method based on photograph album.
The scheme provided according to the present invention, since the picture in user's photograph album and/or video embody the interest love of user
OK etc., therefore, by obtaining picture and/or video in user's photograph album, taken out to the picture in user's photograph album and/or from video
The frame picture taken carries out image characteristic analysis, and user tag is determined further according to image characteristic analysis result, and user tag is carried out
Semantic analysis, at least one information type for meeting user demand is drawn according to semantic analysis result, according at least one information
The information bank of type queries respective type to obtain the information to be recommended to match with user tag, in this way, can find with
The user's information interested, avoid causes user not click on since recommendation information is low with the user interest hobby degree of correlation
The problem of checking recommendation information, improves the probability that user checks corresponding information.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole attached drawing, identical component is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 shows the flow diagram of the information recommendation method according to an embodiment of the invention based on photograph album；
Fig. 2 shows the flow diagram of the information recommendation method in accordance with another embodiment of the present invention based on photograph album；
Fig. 3 shows the structure diagram of the information recommending apparatus according to an embodiment of the invention based on photograph album；
Fig. 4 shows the structure diagram of the information recommending apparatus according to an embodiment of the invention based on photograph album；
Fig. 5 shows a kind of structure diagram of computing device according to an embodiment of the invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Fig. 1 shows the flow diagram of the information recommendation method according to an embodiment of the invention based on photograph album.Such as
Shown in Fig. 1, this method comprises the following steps：
Step S100, obtains picture and/or video in user's photograph album.
Picture or video in user's photograph album mentioned here can be the picture or user that user voluntarily shoots
Using the picture and/or video obtained in application program process, user the picture browsed or video can be preserved to
In user's photograph album, such as from picture or the video download of wechat circle of friends or preserved from Taobao website, further, it is also possible to be
User utilizes the picture that screenshot capture function is intercepted.
Step S101, the frame picture extracted to picture and/or from video carries out image characteristic analysis, according to characteristics of image
Analysis result determines the user tag of user.
After the picture and/or video in getting user's photograph album, server-side is to accessed picture and/or from video
The frame picture of middle extraction carries out image characteristic analysis and obtains corresponding image characteristic analysis as a result, according to image characteristic analysis result
It can determine the user tag of user, in the present embodiment, user tag is the description to user, it is succinct, accurately general
Hobby of user etc. is included.
Step S102, carries out semantic analysis to user tag, is drawn according to semantic analysis result and meet user demand extremely
A few information type.
User tag is a keyword that is succinct, summarizing, and user may can not be immediately arrived at according to the user's label
Demand information, therefore, after the user tag of user is determined according to step S101, can carry out semantic analysis to user tag,
At least one information type for meeting user demand is drawn according to semantic analysis result, for example, determining user's mark in step S101
Sign as Sichuan cuisine intelligent, by carrying out semantic analysis to user tag, it is probably that Sichuan cuisine dining room, Sichuan cuisine are done to analyze user demand
Method, obtains the corresponding information type of user demand as store information, manufacture craft, is merely illustrative of here, without any
Restriction effect.
Step S103, the information bank of respective type is inquired about to obtain and user tag phase according at least one information type
The information to be recommended matched somebody with somebody.
Substantial amounts of information is stored with information bank, may information be much the information unrelated with the user, it is therefore desirable to
The information to match with user tag is filtered out from information bank, specifically, is being met at least one letter of user demand
After ceasing type, the information bank of respective type is inquired about, and then determines the information to be recommended to match with user tag, for example, user
Label is " Sichuan cuisine intelligent ", determines the corresponding information type of user demand as store information, manufacture craft, then from respective type
Sichuan cuisine shop, Sichuan cuisine way are searched in information bank, can get following Sichuan cuisine shop is：Eyebrow state Dong Po restaurants, Boiled Fish township, Lao Jie
Rabbit salt helps dish；And the way of following Sichuan cuisine：Stirfried bean curd in hot sauce, boiling sliced meat, hair and blood are prosperous.
Step S104, by information recommendation to be recommended to user.
After the information to be recommended to match with user tag is found, information to be recommended can be pushed to the user,
By the information to be recommended thus according to the picture in user's photograph album and/or video retrieval, therefore, avoid due to recommendation information with
The user interest hobby degree of correlation it is low and the problem of cause user not click on the information for checking recommendation, improve user and check accordingly
The probability of information.
The method that above-described embodiment provides according to the present invention, since the picture in user's photograph album and/or video embody use
The hobby at family etc., therefore, by obtaining picture and/or video in user's photograph album, to the picture in user's photograph album and/or
The frame picture that is extracted from video carries out image characteristic analysis, and user tag is determined further according to image characteristic analysis result, to
Family label carries out semantic analysis, at least one information type for meeting user demand is drawn according to semantic analysis result, according to extremely
The information bank of few information type inquiry respective type is to obtain the information to be recommended to match with user tag, in this way, can
To find the information interested with the user, avoid causes to use since recommendation information is low with the user interest hobby degree of correlation
The problem of checking recommendation information is not clicked at family, improves the probability that user checks corresponding information.
Fig. 2 shows the flow diagram of the information recommendation method in accordance with another embodiment of the present invention based on photograph album.
As shown in Fig. 2, this method comprises the following steps：
Step S200, obtains picture and/or video in user's photograph album.
User's photograph album in the embodiment of the present invention can be high in the clouds photograph album or the photograph album of client local, if
High in the clouds photograph album, then can obtain picture and/or video directly from the high in the clouds photograph album of cloud server；If client local
Photograph album, then can be uploaded to server-side, in this way, server-side can by client by the picture in user's photograph album and/or video
Get the picture and/or video in user's photograph album.
Picture or video in user's photograph album mentioned here can be the picture or user that user voluntarily shoots
In the picture and/or video obtained using application program process, user the picture browsed to or video can be preserved to
In user's photograph album, such as from picture or the video download of wechat circle of friends or preserved from Taobao website, further, it is also possible to be
User utilizes the picture that screenshot capture function is intercepted.
Step S201, the frame picture extracted to picture and/or from video are classified.
It is well known that video is made of frame picture one by one, image characteristic analysis is carried out for the ease of follow-up,
Need exist for carrying out decoding process to the video got, obtain the frame picture of composition video.
Accessed picture may be in terms of hundred or a thousand sheets in step S200, and the length of video determines decoding process again
The quantity of the frame picture obtained afterwards, that is to say, that obtain substantial amounts of picture and/or frame picture, and these pictures and/or frame figure
Piece may adhere to different classifications separately, if without any processing to these pictures and/or frame picture, directly carry out image characteristic analysis
It may result in that analytic process is complex, and reduce the accuracy of analysis, in order to accurately determine the user of user
Label, before the frame picture that is extracted to picture and/or from video carries out image characteristic analysis, it is also necessary to by picture and/or
The frame picture classification extracted from video, for example, can be by picture and/or frame picture classification to one kind in following classification or more
Kind：Personage's classification, life classification, landscape classification, cuisines classification, household classification, culture and arts classification, scientific and technological classification, specifically,
The different characteristic that can be reflected according to image information in picture and/or frame picture, picture and/or frame picture are divided into not
Same classification.
Step S202, image characteristic analysis is carried out according to classification to picture and/or frame picture respectively.
, can after picture and/or the frame picture extracted from video are divided into different classifications according to step S201
To carry out image characteristic analysis to picture and/or frame picture respectively according to classification, for example, according to image information in picture
And/or picture and/or frame picture are divided into following classification by the different characteristic reflected in frame picture：Personage's classification, landscape class
Not, after cuisines classification, household classification, characteristics of image can be carried out to picture and/or frame picture with one classification of a classification
Analysis, it is for instance possible to use neutral net first carries out image characteristic analysis to the picture in personage's classification and/or frame picture,
After to the picture in the category and/or frame picture analyzing, then image is carried out to the picture in landscape classification and/or frame picture
Signature analysis, followed by image characteristic analysis is carried out to the picture in cuisines classification and/or frame picture, finally in household classification
Picture and/or frame picture carry out image characteristic analysis, be merely illustrative of here, without any restriction effect, this area
Any classification order that can be set for image characteristic analysis according to being actually needed of technology.According to classification to picture and/or frame
Picture carries out image characteristic analysis, easy to determine all user tags of user, recommends different classes of information to user.
Step S203, by carrying out image characteristic analysis to belonging to the other picture of figure kind and/or frame picture, determines user
Natural quality.
If classify in step s 201 to picture and/or frame picture, obtained classification includes personage's classification, then leads to
Cross and carry out image characteristic analysis to belonging to the other picture of figure kind and/or frame picture, it may be determined that the natural quality of user, its
In, natural quality is that the essential description to nature things looks, rule, phenomenon and feature illustrates, is the think of from people
Think will domination, the explanation for the part for adjusting to change, the natural quality of user can include one kind or more in following information
Kind：Gender, age bracket, height, build, occupation, industry etc., are merely exemplary to illustrate here, without any restriction effect.
Step S204, by carrying out image characteristic analysis to belonging to the other picture of non-figure kind and/or frame picture, determines to use
The behavior property at family.
Life classification, landscape classification, cuisines classification, household classification, culture and arts classification, science and technology in the embodiment of the present invention
It is other that classification may be collectively referred to as non-figure kind, if classify in step s 201 to picture and/or frame picture, obtained classification
It is other for non-figure kind, then by carrying out image characteristic analysis to belonging to the other picture of non-figure kind and/or frame picture, it may be determined that
The behavior property of user, wherein, behavior property is definite according to user behavior, for characterizing user behavior feature, for
Behavior property determined by different user behaviors is different, for example, carrying out figure by the picture to landscape classification and/or frame picture
Picture signature analysis, determines the tourism favor of user, such as user preference natural land or humane landscape, the behavior property of user
It may relate to following aspect：Preference, tourism favor, shopping preferences, food and drink custom etc. are browsed, is merely illustrative of, does not have here
There is any restriction effect.
Step S205, the user tag of user is determined according to natural quality and behavior property.
, can be according to nature after the natural quality and behavior property of user is determined according to step S203 and step S204
Attribute and behavior property determine the user tag of user, for example, behavior property is related to mountain-climbing, then can determine user's mark of user
Sign for climb the mountain intelligent, be merely illustrative of here without any restriction effect.
In embodiments of the present invention, by carrying out image characteristic analysis to picture and/or frame picture, use may only be determined
The natural quality or behavior property at family, can so determine the user tag of user according only to natural quality or behavior property.
Step S206, segmenting word processing is carried out to user tag.
The user tag determined in step S205 is to judge the foundation of user's information needed type.User tag is a letter
Keyword that is clean, summarizing, may can not immediately arrive at user demand information, therefore, to user tag according to the user's label
It is necessary to carry out semantics recognition.Wherein, a kind of method of semantic analysis is first to carry out segmenting word processing to user tag, will
User tag is cut into significant word, then according to segmenting word processing as a result, carrying out user view identification.
There are a variety of segmenting word methods in the prior art, for example, the segmenting method based on string matching, point based on understanding
Word method and segmenting method based on statistics etc..Those skilled in the art can be chosen according to demand, or comprehensive use
A variety of methods.
Step S207, the result handled according to segmenting word carry out user view identification, draw and meet user demand at least
One information type.
Intention assessment based on the result that segmenting word is handled, however, same segmenting word result may include it is a variety of
It is intended to.For example, for user tag " Sichuan cuisine intelligent ", although segmenting word processing can recognize that user relatively has deep love for Sichuan cuisine,
But the intention that the search key represents is probably various, including dining room, Sichuan cuisine way etc..To ensure that user demand is expired
Sufficient, the intention assessment in step S207 should consider all possible intention.
Similar with segmenting word, there is also a variety of intension recognizing methods, such as vocabulary in the prior art to match, statistical model, rule
The methods of then parsing, those skilled in the art according to circumstances can flexibly select.
Step S208, the title of information or content letter in the information bank of respective type are inquired about according at least one information type
It is situated between or function introduction is to obtain the information to be recommended that the keyword of information and user tag match.
Substantial amounts of information is stored with information bank, may information be much the information unrelated with the user, it is therefore desirable to
The information to match with user tag is filtered out from information bank, specifically, is being met at least one letter of user demand
After ceasing type, the title of information or brief introduction or function introduction in the information bank of respective type are inquired about, and then determine keyword
The information to be recommended to match with user tag, for example, user tag is " Sichuan cuisine intelligent ", determines the corresponding information of user demand
Type is store information, manufacture craft, then the Sichuan cuisine for including " Sichuan cuisine " during shop is introduced is searched from the information bank of respective type
The Sichuan cuisine way that shop and vegetable include " Sichuan cuisine " in introducing, can get following Sichuan cuisine shop is：Eyebrow state Dong Po restaurants, boiling
Teng Yu townshiies, old street rabbit salt side dish；And the way of following Sichuan cuisine：Stirfried bean curd in hot sauce, boiling sliced meat, hair and blood are prosperous.
Wherein, information to be recommended includes：News, shopping information, advertisement, article, exhibition activity, cuisines way, cuisines meal
The Room, travelling route, public platform, are merely illustrative of here, without any restriction effect.
Step S209, by information recommendation to be recommended to user.
After the information to be recommended to match with user tag is found, information to be recommended can be pushed to the user,
For example, recommending gourmet restaurant to user, gourmet restaurant title, address, dining room specialty etc. can together be recommended use
Family, by the information to be recommended thus according to the picture in user's photograph album and/or video retrieval, therefore, avoids due to recommendation
Breath and user interest like the degree of correlation it is low and the problem of cause user not click on the information for checking recommendation, improve user and check
The probability of corresponding information.
The method that above-described embodiment provides according to the present invention, picture and/or video in user's photograph album embody user's
Hobby, different classes of picture and/or video can embody different hobbies, therefore, be carried out based on user's photograph album
Information recommendation, can not only find the information interested with the user, but also be to recommend different types of information to user, full
Foot demand of the user to Diversity of information, in addition, it is thus also avoided that due to recommendation information and user interest like the degree of correlation it is low and
Cause user not click on the problem of checking recommendation information, improve the probability that user checks corresponding information.
Fig. 3 shows the structure diagram of the information recommending apparatus according to an embodiment of the invention based on photograph album.Such as
Shown in Fig. 3, which includes：Acquisition module 300, characteristics analysis module 310, determining module 320, semantic module 330, look into
Ask module 340, recommending module 350.
Acquisition module 300, suitable for obtaining picture and/or video in user's photograph album.
Characteristics analysis module 310, the frame picture suitable for being extracted to picture and/or from video carry out image characteristic analysis.
Determining module 320, suitable for determining the user tag of user according to image characteristic analysis result.
Semantic module 330, suitable for carrying out semantic analysis to user tag, show that satisfaction is used according to semantic analysis result
At least one information type of family demand.
Enquiry module 340, suitable for inquiring about the information bank of respective type according at least one information type to obtain and user
The information to be recommended that label matches；
Recommending module 350, suitable for by information recommendation to be recommended to user.
The device that above-described embodiment provides according to the present invention, since the picture in user's photograph album and/or video embody use
The hobby at family etc., therefore, by obtaining picture and/or video in user's photograph album, to the picture in user's photograph album and/or
The frame picture that is extracted from video carries out image characteristic analysis, and user tag is determined further according to image characteristic analysis result, to
Family label carries out semantic analysis, at least one information type for meeting user demand is drawn according to semantic analysis result, according to extremely
The information bank of few information type inquiry respective type is to obtain the information to be recommended to match with user tag, in this way, can
To find the information interested with the user, avoid causes to use since recommendation information is low with the user interest hobby degree of correlation
The problem of checking recommendation information is not clicked at family, improves the probability that user checks corresponding information.
Fig. 4 shows the structure diagram of the information recommending apparatus according to an embodiment of the invention based on photograph album.Such as
Shown in Fig. 4, which includes：Acquisition module 400, characteristics analysis module 410, determining module 420, semantic module 430, look into
Ask module 440, recommending module 450.
Acquisition module 400, suitable for obtaining picture and/or video in user's photograph album.
Characteristics analysis module 410 further comprises：Taxon 411 and characteristic analysis unit 412.
Taxon 411, the frame picture suitable for being extracted to picture and/or from video are classified；
Wherein, taxon 411 is further adapted for：By picture and/or frame picture classification to one kind in following classification or
It is a variety of：Personage's classification, life classification, landscape classification, cuisines classification, household classification, culture and arts classification, scientific and technological classification.
Characteristic analysis unit 412, suitable for carrying out image characteristic analysis to picture and/or frame picture respectively according to classification.
Determining module 420 is further adapted for：By carrying out characteristics of image to belonging to the other picture of figure kind and/or frame picture
Analysis, determines the natural quality of user；And/or by carrying out image spy to belonging to the other picture of non-figure kind and/or frame picture
Sign analysis, determines the behavior property of user；The user tag of user is determined according to natural quality and/or behavior property.
Semantic module 430 further comprises：Segmenting word processing unit 431 and intention assessment unit 432.
Segmenting word processing unit 431, suitable for carrying out segmenting word processing to user tag；
Intention assessment unit 432, the result suitable for being handled according to segmenting word carry out user view identification, draw and meet user
At least one information type of demand.
Enquiry module 440 is further adapted for：Information in the information bank of respective type is inquired about according at least one information type
Title or brief introduction or function introduction to obtain the information to be recommended that the keyword of information and user tag match.
Wherein, information to be recommended includes：News, shopping information, advertisement, article, exhibition activity, cuisines way, cuisines meal
The Room, travelling route, public platform.
Recommending module 450, suitable for by information recommendation to be recommended to user.
The device that above-described embodiment provides according to the present invention, picture and/or video in user's photograph album embody user's
Hobby, different classes of picture and/or video can embody different hobbies, therefore, be carried out based on user's photograph album
Information recommendation, can not only find the information interested with the user, but also be to recommend different types of information to user, full
Foot demand of the user to Diversity of information, in addition, it is thus also avoided that due to recommendation information and user interest like the degree of correlation it is low and
Cause user not click on the problem of checking recommendation information, improve the probability that user checks corresponding information.
Present invention also provides a kind of nonvolatile computer storage media, the computer-readable storage medium is stored with least
One executable instruction, the computer executable instructions can perform the information recommendation based on photograph album in above-mentioned any means embodiment
Method.
Fig. 5 shows a kind of structure diagram of computing device according to an embodiment of the invention, and the present invention is specific real
Specific implementation of the example not to computing device is applied to limit.
As shown in figure 5, the computing device can include：Processor (processor) 502, communication interface
(Communications Interface) 504, memory (memory) 506 and communication bus 508.
Wherein：
Processor 502, communication interface 504 and memory 506 complete mutual communication by communication bus 508.
Communication interface 504, for communicating with the network element of miscellaneous equipment such as client or other servers etc..
Processor 502, for executive program 510, can specifically perform the above-mentioned information recommendation method based on photograph album and implement
Correlation step in example.
Specifically, program 510 can include program code, which includes computer-managed instruction.
Processor 502 is probably central processor CPU, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the embodiment of the present invention one or more integrate electricity
Road.The one or more processors that computing device includes, can be same type of processors, such as one or more CPU；Also may be used
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 506, for storing program 510.Memory 506 may include high-speed RAM memory, it is also possible to further include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 510 specifically can be used for so that processor 502 perform in above-mentioned any means embodiment based on photograph album
Information recommendation method.The specific implementation of each step may refer in the above-mentioned information recommendation embodiment based on photograph album in program 510
Corresponding steps and unit in corresponding description, this will not be repeated here.It is apparent to those skilled in the art that it is
What is described is convenienct and succinct, and the equipment of foregoing description and the specific work process of module, may be referred in preceding method embodiment
Corresponding process description, details are not described herein.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification that this place provides, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description to the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, summary and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) realize the information recommendation equipment according to embodiments of the present invention based on photograph album
In some or all components some or all functions.The present invention is also implemented as being used to perform as described herein
The some or all equipment or program of device (for example, computer program and computer program product) of method.So
Realization the present invention program can store on a computer-readable medium, or can have one or more signal shape
Formula.Such signal can be downloaded from internet website and obtained, and either be provided or with any other shape on carrier signal
Formula provides.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer real
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711275689.9A CN108038161A (en) | 2017-12-06 | 2017-12-06 | Information recommendation method, device and computing device based on photograph album |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711275689.9A CN108038161A (en) | 2017-12-06 | 2017-12-06 | Information recommendation method, device and computing device based on photograph album |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108038161A true CN108038161A (en) | 2018-05-15 |
Family
ID=62095415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711275689.9A Pending CN108038161A (en) | 2017-12-06 | 2017-12-06 | Information recommendation method, device and computing device based on photograph album |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108038161A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063001A (en) * | 2018-07-09 | 2018-12-21 | 北京小米移动软件有限公司 | page display method and device |
| CN109508321A (en) * | 2018-09-30 | 2019-03-22 | Oppo广东移动通信有限公司 | image display method and related product |
| CN109547814A (en) * | 2018-12-13 | 2019-03-29 | 北京达佳互联信息技术有限公司 | Video recommendation method, device, server and storage medium |
| CN109740010A (en) * | 2018-12-29 | 2019-05-10 | 上海诚数信息科技有限公司 | The analysis method and system of the photograph album of intelligent terminal |
| CN110032658A (en) * | 2019-03-19 | 2019-07-19 | 深圳壹账通智能科技有限公司 | Text matching technique, device, equipment and storage medium based on image analysis |
| CN110418191A (en) * | 2019-06-24 | 2019-11-05 | 华为技术有限公司 | A kind of generation method and device of short-sighted frequency |
| CN111209423A (en) * | 2020-01-07 | 2020-05-29 | 腾讯科技（深圳）有限公司 | Image management method and device based on electronic album and storage medium |
| CN111368209A (en) * | 2020-03-25 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111447260A (en) * | 2020-03-20 | 2020-07-24 | 北京字节跳动网络技术有限公司 | Information pushing and information publishing method and device |
| CN111695971A (en) * | 2020-06-12 | 2020-09-22 | 腾讯科技（深圳）有限公司 | Article recommendation method, device and equipment and computer storage medium |
| CN112115293A (en) * | 2020-09-27 | 2020-12-22 | 广州三星通信技术研究有限公司 | Content recommendation method and content recommendation device |
| CN112148959A (en) * | 2019-06-27 | 2020-12-29 | 百度在线网络技术（北京）有限公司 | Information recommendation method and device |
| CN112602080A (en) * | 2018-06-27 | 2021-04-02 | 尤尔实验室有限公司 | Connected evaporator device system |
| CN112699311A (en) * | 2020-12-31 | 2021-04-23 | 上海博泰悦臻网络技术服务有限公司 | Information pushing method, storage medium and electronic equipment |
| CN114003751A (en) * | 2021-11-11 | 2022-02-01 | 上海传英信息技术有限公司 | Information processing method, intelligent terminal and storage medium |
| CN114372164A (en) * | 2020-10-15 | 2022-04-19 | 上海倍增智能科技有限公司 | A personalized intelligent recommendation system and its recommendation method |
| CN114792260A (en) * | 2021-01-26 | 2022-07-26 | 上海博泰悦臻网络技术服务有限公司 | Image-based intelligent recommendation method, device, medium and electronic device |
| CN117251621A (en) * | 2023-07-26 | 2023-12-19 | 中国银行股份有限公司 | Service matching methods, devices, computer equipment, storage media and products |
| US12263299B2 (en) | 2018-06-26 | 2025-04-01 | Juul Labs, Inc. | Devices and methods for cessation of nicotine addiction |
| US12332618B2 (en) | 2017-12-21 | 2025-06-17 | Juul Labs, Inc. | Vaporizer controls |
| US12349738B2 (en) | 2017-11-22 | 2025-07-08 | Juul Labs, Inc. | User interface and user experience for a vaporizer device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8082511B2 (en) * | 2007-02-28 | 2011-12-20 | Aol Inc. | Active and passive personalization techniques |
| CN103268330A (en) * | 2013-05-07 | 2013-08-28 | 天津大学 | Method of Extracting User Interest Based on Image Content |
| CN103514299A (en) * | 2013-10-18 | 2014-01-15 | 北京奇虎科技有限公司 | Information searching method and device |
| CN104239457A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Search recommending method and device |
| CN104699770A (en) * | 2015-03-02 | 2015-06-10 | 惠州Tcl移动通信有限公司 | Method and system for analyzing and acquiring character features of user based on mobile terminal |
| CN105373596A (en) * | 2015-10-27 | 2016-03-02 | 努比亚技术有限公司 | Mobile terminal based on user interest mining and user interest mining method |
| US20160148515A1 (en) * | 2014-11-20 | 2016-05-26 | MyChild, Inc. | Web and mobile parent engagement and learning management system |
| CN105955994A (en) * | 2016-04-19 | 2016-09-21 | 乐视控股（北京）有限公司 | Information recommend method and information recommend device based on gallery |
| CN106372956A (en) * | 2015-07-23 | 2017-02-01 | 苏宁云商集团股份有限公司 | Method and system for intention entity recognition based on user query log |
| CN106951448A (en) * | 2017-02-20 | 2017-07-14 | 竹间智能科技（上海）有限公司 | A kind of personalization, which is worn, takes recommendation method and system |
| CN107122404A (en) * | 2017-03-22 | 2017-09-01 | 北京晓数聚传媒科技有限公司 | A kind of user view data extracting method and device |
-
2017
- 2017-12-06 CN CN201711275689.9A patent/CN108038161A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8082511B2 (en) * | 2007-02-28 | 2011-12-20 | Aol Inc. | Active and passive personalization techniques |
| CN103268330A (en) * | 2013-05-07 | 2013-08-28 | 天津大学 | Method of Extracting User Interest Based on Image Content |
| CN103514299A (en) * | 2013-10-18 | 2014-01-15 | 北京奇虎科技有限公司 | Information searching method and device |
| CN104239457A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Search recommending method and device |
| US20160148515A1 (en) * | 2014-11-20 | 2016-05-26 | MyChild, Inc. | Web and mobile parent engagement and learning management system |
| CN104699770A (en) * | 2015-03-02 | 2015-06-10 | 惠州Tcl移动通信有限公司 | Method and system for analyzing and acquiring character features of user based on mobile terminal |
| CN106372956A (en) * | 2015-07-23 | 2017-02-01 | 苏宁云商集团股份有限公司 | Method and system for intention entity recognition based on user query log |
| CN105373596A (en) * | 2015-10-27 | 2016-03-02 | 努比亚技术有限公司 | Mobile terminal based on user interest mining and user interest mining method |
| CN105955994A (en) * | 2016-04-19 | 2016-09-21 | 乐视控股（北京）有限公司 | Information recommend method and information recommend device based on gallery |
| CN106951448A (en) * | 2017-02-20 | 2017-07-14 | 竹间智能科技（上海）有限公司 | A kind of personalization, which is worn, takes recommendation method and system |
| CN107122404A (en) * | 2017-03-22 | 2017-09-01 | 北京晓数聚传媒科技有限公司 | A kind of user view data extracting method and device |
Non-Patent Citations (1)
| Title |
|---|
| 张仁宇: "基于用户相册的兴趣挖掘", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12349738B2 (en) | 2017-11-22 | 2025-07-08 | Juul Labs, Inc. | User interface and user experience for a vaporizer device |
| US12332618B2 (en) | 2017-12-21 | 2025-06-17 | Juul Labs, Inc. | Vaporizer controls |
| US12263299B2 (en) | 2018-06-26 | 2025-04-01 | Juul Labs, Inc. | Devices and methods for cessation of nicotine addiction |
| CN112602080A (en) * | 2018-06-27 | 2021-04-02 | 尤尔实验室有限公司 | Connected evaporator device system |
| CN109063001A (en) * | 2018-07-09 | 2018-12-21 | 北京小米移动软件有限公司 | page display method and device |
| WO2020063014A1 (en) * | 2018-09-30 | 2020-04-02 | Oppo广东移动通信有限公司 | Image display method and related product |
| CN109508321B (en) * | 2018-09-30 | 2022-01-28 | Oppo广东移动通信有限公司 | Image display method and related product |
| CN109508321A (en) * | 2018-09-30 | 2019-03-22 | Oppo广东移动通信有限公司 | image display method and related product |
| CN109547814A (en) * | 2018-12-13 | 2019-03-29 | 北京达佳互联信息技术有限公司 | Video recommendation method, device, server and storage medium |
| CN109547814B (en) * | 2018-12-13 | 2021-07-16 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
| CN109740010A (en) * | 2018-12-29 | 2019-05-10 | 上海诚数信息科技有限公司 | The analysis method and system of the photograph album of intelligent terminal |
| CN110032658A (en) * | 2019-03-19 | 2019-07-19 | 深圳壹账通智能科技有限公司 | Text matching technique, device, equipment and storage medium based on image analysis |
| CN110418191A (en) * | 2019-06-24 | 2019-11-05 | 华为技术有限公司 | A kind of generation method and device of short-sighted frequency |
| CN112148959A (en) * | 2019-06-27 | 2020-12-29 | 百度在线网络技术（北京）有限公司 | Information recommendation method and device |
| CN111209423A (en) * | 2020-01-07 | 2020-05-29 | 腾讯科技（深圳）有限公司 | Image management method and device based on electronic album and storage medium |
| CN111209423B (en) * | 2020-01-07 | 2023-04-07 | 腾讯科技（深圳）有限公司 | Image management method and device based on electronic album and storage medium |
| CN111447260A (en) * | 2020-03-20 | 2020-07-24 | 北京字节跳动网络技术有限公司 | Information pushing and information publishing method and device |
| CN111368209B (en) * | 2020-03-25 | 2022-04-12 | 北京字节跳动网络技术有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111368209A (en) * | 2020-03-25 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111695971A (en) * | 2020-06-12 | 2020-09-22 | 腾讯科技（深圳）有限公司 | Article recommendation method, device and equipment and computer storage medium |
| CN111695971B (en) * | 2020-06-12 | 2024-01-12 | 腾讯科技（深圳）有限公司 | Article recommendation method, apparatus and device, and computer storage medium |
| CN112115293A (en) * | 2020-09-27 | 2020-12-22 | 广州三星通信技术研究有限公司 | Content recommendation method and content recommendation device |
| CN114372164A (en) * | 2020-10-15 | 2022-04-19 | 上海倍增智能科技有限公司 | A personalized intelligent recommendation system and its recommendation method |
| CN112699311A (en) * | 2020-12-31 | 2021-04-23 | 上海博泰悦臻网络技术服务有限公司 | Information pushing method, storage medium and electronic equipment |
| CN114792260A (en) * | 2021-01-26 | 2022-07-26 | 上海博泰悦臻网络技术服务有限公司 | Image-based intelligent recommendation method, device, medium and electronic device |
| CN114003751A (en) * | 2021-11-11 | 2022-02-01 | 上海传英信息技术有限公司 | Information processing method, intelligent terminal and storage medium |
| CN117251621A (en) * | 2023-07-26 | 2023-12-19 | 中国银行股份有限公司 | Service matching methods, devices, computer equipment, storage media and products |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108038161A (en) | Information recommendation method, device and computing device based on photograph album | |
| CN108694223B (en) | User portrait database construction method and device | |
| US20240086472A1 (en) | Social network searching with breadcrumbs | |
| CN107424043B (en) | Product recommendation method and device and electronic equipment | |
| CN107735782B (en) | Image and Text Data Hierarchical Classifiers | |
| CN102279872B (en) | Inquiring intention identification drived by search results | |
| JP4637969B1 (en) | Properly understand the intent of web pages and user preferences, and recommend the best information in real time | |
| JP6343035B2 (en) | Generate ad campaign | |
| US10360623B2 (en) | Visually generated consumer product presentation | |
| CN105512180B (en) | A kind of search recommended method and device | |
| CN104636371B (en) | Information recommendation method and equipment | |
| US20140172821A1 (en) | Generating filters for refining search results | |
| US20230214895A1 (en) | Methods and systems for product discovery in user generated content | |
| CN104036038A (en) | News recommendation method and system | |
| CN107784059A (en) | For searching for and selecting the method and system and machine-readable medium of image | |
| CN107748754A (en) | A kind of knowledge mapping improving method and device | |
| CN102016845A (en) | Social network powered query refinement and recommendations | |
| CN109389442A (en) | Method of Commodity Recommendation and device, storage medium and electric terminal | |
| CN102999560A (en) | Improvement of relevance of search engine result page between name and other search queries by using social network features | |
| CN108021672A (en) | Social recommendation method, apparatus and computing device based on photograph album | |
| WO2016000555A1 (en) | Methods and systems for recommending social network-based content and news | |
| JP7387432B2 (en) | Systems and methods for collecting data related to unauthorized content in a networked environment | |
| WO2016065987A1 (en) | Multimedia content providing method and device | |
| CN103970850A (en) | Website information recommending method and system | |
| EP2884451A1 (en) | Product and content association |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180515 |