CN108460162A - Recommendation information processing method, device, equipment and medium - Google Patents
Recommendation information processing method, device, equipment and medium Download PDFInfo
- Publication number
- CN108460162A CN108460162A CN201810278994.1A CN201810278994A CN108460162A CN 108460162 A CN108460162 A CN 108460162A CN 201810278994 A CN201810278994 A CN 201810278994A CN 108460162 A CN108460162 A CN 108460162A
- Authority
- CN
- China
- Prior art keywords
- recommendation information
- map
- classification
- stratification
- similar
- 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of recommendation information processing method, device, equipment and media.Wherein, this method includes:Feature vector is extracted from recommendation information, and hierarchical clustering is carried out to recommendation information according to feature vector, obtains the hierarchical clustering result of recommendation information;The stratification map of recommendation information is generated according to the classification quantity of hierarchical clustering result, and using the number of recommendation information in each classification as weight using weighting dimension promise nomography;Receive the operation that user searches similar recommendation information similar to the specific recommendations information in stratification map;The prominent mode for showing similar recommendation information in stratification map.Through the invention, music exploring mode in the related technology is solved when guiding user to find new music/music artist, it can not provide intuitive reference information problem for reference, the technique effect that music/music artist provides intuitive reference information is explored for user to play.
Description
Technical field
The present invention relates to data processing field, in particular to a kind of recommendation information processing method, device, equipment and
Medium.
Background technology
Internet era is listened to using music Streaming Media as mainstream, and user is on Streaming Media mainly by each platform
Hold recommendation service, categorizing songs catalogue, radio station and function of search and finds music.Wherein content recommendation service is generated by user
It is a large amount of listen to data, analyze which content is similar, the function of checking, listen to " similar " be provided;It is listened also based on the history of user
An old song form is that prediction user likes degree to each content, is that user carries out personalized commending contents with the form of list.
The angle that music is explored from music artist, with the closest implementation of the present invention be discovr with
And music-map, the two applications can generate an interactive map, shown in map searched by searching for artist
Artist and artist similar with its.Map is supported to pull, and can show that two level is similar by clicking similar artist
Relationship, to guide user to find new music.
Inventor has found the relevant technologies in the course of the research, and there are following defects:
The recommendation service of mainstream music platform belongs to passive finding, depends critically upon user's history behavior, is easy more pushing away
It is similar, as being enclosed in an inner circle of people, it is difficult to jump out, it is unfavorable for finding new content.
Artist's map that Discovr and music-map are presented to the user can change and dynamic as center is artistical
It generates, does not include center artist and the artist except its similar artist, as shown in Figure 1;And do not support to scale, it can not
User is allowed to have global consciousness to map;Therefore, user explores new according to artist's map that Discovr and music-map is presented
Artist when, it is difficult to the characteristics of intuitively understanding between the artistical multiple similar artists in the center and difference increase use
Family selects the randomness and blindness of similar artist, is equally unfavorable for user and finds new content.
In conclusion guiding user to find new music/act of music for music exploring mode in the related technology
When family, it can not provide intuitive reference information problem for reference, currently no effective solution has been proposed.
Invention content
The present invention provides a kind of recommendation information processing method, device, equipment and media, at least to solve in the related technology
Music exploring mode guide user find new music/music artist when, can not provide intuitive reference information for
The problem of family refers to.
In a first aspect, an embodiment of the present invention provides a kind of recommendation information processing methods, including:
Feature vector is extracted from recommendation information, and level is carried out to the recommendation information according to described eigenvector and is gathered
Class obtains the hierarchical clustering result of the recommendation information;
Promise nomography is tieed up using weighting, according to the classification quantity of the hierarchical clustering result, and with described in each classification
The number of recommendation information generates the stratification map of the recommendation information as weight;
Receive the operation that user searches similar recommendation information similar to the specific recommendations information in the stratification map;
It is prominent in the stratification map to show the similar recommendation information.
Second aspect, an embodiment of the present invention provides a kind of recommendation information processing unit, described device includes:
Cluster module, for extracting feature vector from recommendation information, and according to described eigenvector to the recommendation
Breath carries out hierarchical clustering, obtains the hierarchical clustering result of the recommendation information;
Generation module, for tieing up promise nomography using weighting, according to the classification quantity of the hierarchical clustering result, and with every
The number of recommendation information described in a classification generates the stratification map of the recommendation information as weight;
Receiving module, for receiving, user searches and the specific recommendations information in the stratification map is similar similar pushes away
Recommend the operation of information;
Display module shows the similar recommendation information for prominent in the stratification map.
The third aspect, an embodiment of the present invention provides a kind of recommendation information processing equipments, including:At least one processor,
At least one processor and the computer program instructions being stored in the memory, when the computer program instructions are by institute
State the method realized when processor executes described in first aspect.
Fourth aspect, an embodiment of the present invention provides a kind of computer readable storage mediums, are stored thereon with computer journey
Sequence instructs, and the method described in first aspect is realized when the computer program instructions are executed by processor.
Recommendation information processing method, device, equipment and the medium provided through the embodiment of the present invention, using from recommendation information
Middle extraction feature vector, and hierarchical clustering is carried out to recommendation information according to feature vector, obtain the hierarchical clustering knot of recommendation information
Fruit;Promise nomography is tieed up using weighting, according to the classification quantity of hierarchical clustering result, and with the number of recommendation information in each classification
As weight, the stratification map of recommendation information is generated;User is received to search and the specific recommendations information phase in stratification map
As similar recommendation information operation;The prominent mode for showing similar recommendation information, recommendation information is gathered in stratification map
Class is illustrated in stratification map, and is protruded in stratification map and shown similar recommendation information so that in stratification map
Other recommendation informations be capable of providing reference of the user in relation to similar recommendation information.Said program is applied to music/music skill
In astrologist's information recommendation, the music exploring mode solved in the related technology is guiding user to find new music/act of music
It when family, can not provide intuitive reference information problem for reference, music/act of music is explored for user to play
Family provides the technique effect of intuitive reference information.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and is constituted part of this application, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings:
Fig. 1 is the schematic diagram according to artist's map of the relevant technologies;
Fig. 2 is the flow chart of recommendation information processing method according to the ... of the embodiment of the present invention;
Fig. 3 is the flow chart of stratification map generating process according to the preferred embodiment of the invention;
Fig. 4 is the structural schematic diagram of recommendation information processing unit according to the ... of the embodiment of the present invention;
Fig. 5 is the hardware architecture diagram of recommendation information processing equipment according to the ... of the embodiment of the present invention;
Fig. 6 is the schematic diagram of stratification map according to the preferred embodiment of the invention;
Fig. 7 is the schematic diagram according to the preferred embodiment of the invention that similar recommendation information is shown on stratification map.
Specific implementation mode
The feature and exemplary embodiment of various aspects of the invention is described more fully below, in order to make the mesh of the present invention
, technical solution and advantage be more clearly understood, with reference to the accompanying drawings and embodiments, the present invention is further retouched in detail
It states.It should be understood that specific embodiment described herein is only used for explaining the present invention, it is not intended to limit the present invention.For ability
For field technique personnel, the present invention can be implemented in the case of some details in not needing these details.It is right below
The description of embodiment is just for the sake of by showing that the example of the present invention is better understood from the present invention to provide.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or equipment including a series of elements includes not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that wanted including described
There is also other identical elements in the process, method, article or equipment of element.
A kind of recommendation information processing method is provided in the present embodiment, and Fig. 2 is recommendation according to the ... of the embodiment of the present invention
The flow chart for ceasing processing method, as shown in Fig. 2, the flow includes the following steps:
Step S201 extracts feature vector from recommendation information, and carries out level to recommendation information according to feature vector and gather
Class obtains the hierarchical clustering result of recommendation information;
Step S202 ties up promise nomography, according to the classification quantity of hierarchical clustering result, and in each classification using weighting
The number of recommendation information generates the stratification map of recommendation information as weight;
Step S203 receives user and searches similar recommendation information similar to the specific recommendations information in stratification map
Operation;
Step S204, it is prominent in stratification map to show similar recommendation information.
It through the above steps, can will all known certain class recommendation informations (such as singer, performer, author;Or sound
One kind in pleasure, film, TV play, books) it hierarchical cluster and is illustrated in stratification map, search stratification map in user
In a certain specific recommendations information similar recommendation information when (such as select specific recommendations information in stratification map, and click
It is supplied to the button of " searching similar recommendation information " function of the specific recommendations information), it is prominent in stratification map to show this
A little similar recommendation informations.
Since whole recommendation informations has been added to stratification map according to hierarchical cluster result in stratification map
In, therefore in the similar recommendation information of prominent displaying, will also be shown to the neighbouring recommendation information of similar recommendation information, this
A little neighbouring recommendation informations then can provide reference for similar recommendation information.For example, similar multiple phases with specific recommendations information
It is illustrated in stratification map like the similar recommendation information in recommendation information, with 1 and the similar recommendation information with 2
Different location be also all other recommendations with 1 also, in the similar recommendation information adjacent domain with 1
Information;Have the characteristics that 2 similar recommendation information adjacent domain, is all being other recommendation informations with 2.User is selecting
When selecting similar recommendation information, other recommendation informations of adjacent domain have provided reference to the user, and user pushes away according to adjacent domain
The substantially feature in this region can be understood by recommending information, to guide user to select interested recommendation information.
As it can be seen that through the above steps, being applied in music/music artist information recommendation, solving in the related technology
Music exploring mode can not provide intuitive reference information for user when guiding user to find new music/music artist
With reference to the problem of, explore music/music artist to play for user and provide the technique effect of intuitive reference information.
Optionally, after recommendation information is shown in stratification map, since stratification map probably exceeds
The indication range of equipment.Therefore, after similar recommendation information protrusion is illustrated in stratification map, exceed the display of equipment
The similar recommendation information of range will be not easy to be found by user.To solve the above-mentioned problems, the prominent displaying in stratification map
When similar recommendation information, the highlighted company between specific recommendations information and similar recommendation information can also be drawn in stratification map
Line.Highlighted line can guide user to look for all similar recommendation informations, and similar recommendation information is avoided to be unnoticed by the user.
In addition, while protruding displaying similar recommendation information using stratification map, list can also be extraly used
Form all similar recommendation informations are shown;When user selects some similar recommendation information in lists, this is similar
Position of the recommendation information in stratification map will automatic jump within the indication range of equipment, so as to understand this similar by user
Position of the recommendation information in stratification map, and understand the distribution situation of the neighbouring recommendation information of the similar recommendation information.
Arbitrary known stratification map generating mode in the prior art may be used in the mode for generating stratification map.
Optionally, in the present embodiment, promise nomography is tieed up using weighting, according to the classification quantity of hierarchical clustering result, and with each point
As weight, the stratification map for generating recommendation information includes the number of recommendation information in class:
Step S202-1 selectes origin coordinates, and using weighting dimension promise nomography, according to the upper layer point of hierarchical clustering result
Class quantity, the number of recommendation information calculates coordinate and the boundary of upper layer classification as weight in being classified using each upper layer;
Coordinate centered on the coordinate of upper layer classification is tieed up promise nomography by step S202-2 using weighting, poly- according to level
The quantity of next layer of classification in the upper layer classification of class result, recommendation information described in each next layer of classification in being classified with upper layer
Number calculates the coordinate of each next layer of classification and boundary in the classification of upper layer as weight;
Step S202-3 then repeats above-mentioned calculating process in the case where the number of plies of layering is more than two layers, until calculating
The coordinate of bottom classification and boundary;It should be noted that if being layered as two layers, next layer of classification of upper layer classification is bottom
Layer classification.
Step S202-4 generates the coordinate of whole recommendation informations in bottom classification at random in the boundary of bottom classification, and
Dimension promise nomography is executed, so that the coordinate of whole recommendation informations in bottom classification is evenly distributed in the boundary of bottom classification.
Optionally, above-mentioned stratification map is the map of scalable vector graphics format;Using scalable vector graphics
Format can depending on the user's operation zoom in and out map.When showing recommendation information in stratification map, preferential displaying is popular
Recommendation information (including icon and text information), and the recommendation information of opposite unexpected winner is hidden, to avoid in the display area of equipment
The recommendation information of display excessively influences user's identification.Hot recommendation information therein refers to attention rate/program request number/like number be more than
The recommendation information of a certain predetermined threshold.The degree that above-mentioned predetermined threshold is scaled according to stratification map is different and changes, to protect
Recommendation information quantity in the display area of holding equipment is suitable horizontal.
Optionally, above-mentioned recommendation information includes but not limited to following one:Singer, performer, author, music, film, electricity
Depending on acute, books.
Below by taking artist (such as singer, performer etc.) as an example, to the stratification map generating process of the present embodiment use
It is described and illustrates.
With reference to figure 3, stratification map generating process includes:
Data preparation
The record of listening to of user is handled, artistical vector characteristics in Qu Ku are obtained by way of collaborative filtering
Expression, and artist is divided into popular artist and non-popular artist's two major classes according to number is listened to.
Hierarchical clustering is carried out to popular artist, the clustering method used per strata class is spectral clustering, and spectral clustering is used
Similarity matrix be popular artist's feature vector cosine similarity matrix.Class number is set by iteration in spectral clustering,
To ensure the infima species number of similarity inside cluster result.It is all cluster can not separate again after, by cluster result according to
Artist's number in class is divided into two groups of major class and group, and when the similarity of group and major class is more than certain threshold value, it is small to merge this
In class to major class, to improve the accuracy of cluster.
The vector characteristics of each class are obtained according to popular artistical cluster result and vector characteristics, to unexpected winner artist
Classify, obtains all artistical cluster results and different classes of hierarchical relationship.
Map generates
The mutual cosine similarity matrix of top layer major class is calculated first, and then obtains Laplacian Matrix, to Laplce's square
Battle array carries out multi-dimentional scale scaling and realizes dimensionality reduction, obtains the two-dimentional origin coordinates of top layer major class.Included in each major class
Artist's number is different, so the ratio that artist's number in each major class is accounted for sum is set as weight, promise is tieed up by weighting
Nomography is adjusted coordinate, to ensure the uniformity of artist distribution.By coordinate centered on top layer coordinate, this is repeated
Process obtains the centre coordinate of each classification to bottom.The zone boundary of each classification is obtained based on improvement version dimension promise nomography,
Random Generative Art person's coordinate in boundary.After carrying out overlapping duplicate removal to all artist's coordinates, improvement version dimension promise is re-executed
Nomography obtains final artist's coordinate and class boundary coordinate, stores to database, and is rendered simultaneously according to coordinate, boundary
Show stratification map.Stratification map is as shown in Figure 6.
Optionally, when showing artist in stratification map, the page of stratification map is used interchangeably D3.js (one
The libraries kind JavaScript, full name are:Data-Driven Documents, data-driven document) to realize the dragging of map, contracting
It puts.When screen position changes, the artist that screen position planted agent shows is calculated according to current screen position and data coordinates
Coordinate, zone boundary, and compared with current DOM Document Object Model.Ignore if the two is identical, otherwise clears screen
External data, and new data is added in DOM Document Object Model, dynamic generation scalable vector graphics (Scalable
Vector Graphics, referred to as SVG) file display map datum.The real-time repetition removal calculation of practicality in the process has been shown in artist
Method, in display space deficiency, the artist that preferential display is popular, the artist of unexpected winner needs just show by scaling map
Show.
Optionally, with reference to figure 7, when clicking similar artist, first read similar artist list and its corresponding to
Coordinate, then can according to its coordinate be distributed calculate auto zoom ratio so that at least show three it is artistical on the basis of
It is as far as possible to show artist more, and generate parabola between the artistical coordinate position in source and similar artist coordinate position
Connection is explored to complete similar artist.
User is using a usage scenario of the stratification map of music artist:Which artist user can see
It is one group, the distant relationships between artist and artist.An artist name is clicked, it is artistical to pop up this on map
Details page, above it can be seen that artistical information, works and Similar content, user can complete to listen to, also may be used above
From the artist, the works of more similar artists are explored.
Additionally provide a kind of recommendation information processing unit in the present embodiment, the device is for realizing above-described embodiment and excellent
Embodiment is selected, repeating no more for explanation had been carried out.As used below, term " module ", " unit " or " son list
The combination of the software and/or hardware of predetermined function may be implemented in member " etc..Although device described in following embodiment preferably with
Software is realized, but the realization of the combination of hardware or software and hardware is also that may and be contemplated.
Fig. 4 is the structure diagram of recommendation information processing unit according to the ... of the embodiment of the present invention, as shown in figure 4, the device packet
It includes:
Cluster module 41, for extracting feature vector from recommendation information, and according to described eigenvector to the recommendation
Information carries out hierarchical clustering, obtains the hierarchical clustering result of the recommendation information;
Generation module 42, for tieing up promise nomography using weighting, according to the classification quantity of the hierarchical clustering result, and with
The number of recommendation information described in each classification generates the stratification map of the recommendation information as weight;
Receiving module 43, it is similar similar to the specific recommendations information in the stratification map for receiving user's lookup
The operation of recommendation information;
Display module 44 shows the similar recommendation information for prominent in the stratification map.
Optionally, display module 44 is additionally operable to:Drawn in the stratification map specific recommendations information with it is described
Highlighted line between similar recommendation information.
Optionally, generation module 42 is using weighting dimension promise nomography, according to the classification quantity of the hierarchical clustering result, and
Using the number of recommendation information described in each classification as weight, the stratification map for generating the recommendation information includes:
Selected origin coordinates, and using weighting dimension promise nomography is classified quantity according to the upper layer of the hierarchical clustering result,
Using the number of recommendation information described in the classification of each upper layer as weight, coordinate and the boundary of the upper layer classification are calculated;
Coordinate centered on the coordinate that the upper layer is classified ties up promise nomography, according to the hierarchical clustering using weighting
As a result the quantity of next layer of classification in upper layer classification, in being classified using the upper layer number of each next layer of classification as
Weight calculates the coordinate of each next layer of classification and boundary in the upper layer classification;Above-mentioned calculating process is repeated, until calculating
The coordinate of bottom classification and boundary;
It generates the coordinate of whole recommendation informations in the bottom classification at random in the boundary of bottom classification, and executes
Promise nomography is tieed up, so that the coordinate of whole recommendation informations in bottom classification is evenly distributed on the boundary of the bottom classification
It is interior.
Optionally, the stratification map is the map of scalable vector graphics format.
Optionally, the recommendation information includes but not limited to following one:Singer, performer, author, music, film, TV
Acute, books.
It should be noted that above-mentioned modules can be realized by software or hardware, for the latter, Ke Yitong
Following manner realization is crossed, but not limited to this:Above-mentioned module is respectively positioned in same processor;Alternatively, above-mentioned module be located at it is more
In a processor.
In addition, the recommendation information processing method in conjunction with Fig. 2 embodiment of the present invention described can be set by recommendation information processing
It is standby to realize.Fig. 5 shows the hardware architecture diagram of recommendation information processing equipment provided in an embodiment of the present invention.
Recommendation information processing equipment may include processor 51 and be stored with the memory 52 of computer program instructions.
Specifically, above-mentioned processor 51 may include central processing unit (CPU) or specific integrated circuit
(Application Specific Integrated Circuit, ASIC), or may be configured to implement implementation of the present invention
One or more integrated circuits of example.
Memory 52 may include the mass storage for data or instruction.For example unrestricted, memory
52 may include hard disk drive (Hard Disk Drive, HDD), floppy disk, flash memory, CD, magneto-optic disk, tape or logical
With the combination of universal serial bus (Universal Serial Bus, USB) driver or two or more the above.It is closing
In the case of suitable, memory 52 may include the medium of removable or non-removable (or fixed).In a suitable case, memory
52 can be inside or outside data processing equipment.In a particular embodiment, memory 52 is non-volatile solid state memory.
In specific embodiment, memory 52 includes read-only memory (ROM).In a suitable case, which can be masked edit program
ROM, programming ROM (PROM), erasable PROM (EPROM), electric erasable PROM (EEPROM), electrically-alterable ROM (EAROM)
Or the combination of flash memory or two or more the above.
Processor 51 is by reading and executing the computer program instructions stored in memory 52, to realize above-described embodiment
In any one recommendation information processing method.
In one example, recommendation information processing equipment may also include communication interface 53 and bus 50.Wherein, such as Fig. 5 institutes
Show, processor 51, memory 52, communication interface 53 are connected by bus 50 and complete mutual communication.
Communication interface 53 is mainly used for realizing in the embodiment of the present invention between each module, device, unit and/or equipment
Communication.
Bus 50 includes hardware, software or both, and the component of recommendation information processing equipment is coupled to each other together.Citing
For and it is unrestricted, bus may include accelerated graphics port (AGP) or other graphics bus, enhancing Industry Standard Architecture (EISA)
Bus, front side bus (FSB), super transmission (HT) interconnection, the interconnection of Industry Standard Architecture (ISA) bus, infinite bandwidth, low pin count
(LPC) bus, memory bus, micro- channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express
(PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association part (VLB) bus or other conjunctions
The combination of suitable bus or two or more the above.In a suitable case, bus 50 may include one or more
Bus.Although specific bus has been described and illustrated in the embodiment of the present invention, the present invention considers any suitable bus or interconnection.
The recommendation information processing equipment can be executed based on the data got at the recommendation information in the embodiment of the present invention
Reason method, to realize the recommendation information processing method described in conjunction with Fig. 2.
In addition, in conjunction with the recommendation information processing method in above-described embodiment, the embodiment of the present invention can provide a kind of computer
Readable storage medium storing program for executing is realized.It is stored with computer program instructions on the computer readable storage medium;The computer program refers to
The when of being executed by processor is enabled to realize any one recommendation information processing method in above-described embodiment.
In conclusion through the embodiment of the present invention, artistical similarity relation data are presented in a manner of map, support
Scaling browses on map, selection checks artist information on map, checks similar artist, listens to artist's musical works etc.
Operation.On artist's map, user can be assorted with direct feel to the whole world how many artist, artistical grouping relationship
, the artist that artistical distant relationships are, I likes where and artist similar with this artist again
Where.Map not only intuitively presents the overall picture in the music world, is also convenient for user and understands the music oneself dabbled in whole sounds
The location of in the happy world, the degree of freedom that user explores map is promoted, operating space is increased, further goes to visit conducive to user
The more unknown artistical music of Suo Faxian.
In addition, stratification map shows the tree-shaped relationship of artist genre by way of the hierarchical relationship of similar territory, allow
User can go to find artist or artistical music from more macroscopical angle.
It should be clear that the invention is not limited in specific configuration described above and shown in figure and processing.
For brevity, it is omitted here the detailed description to known method.In the above-described embodiments, several tools have been described and illustrated
The step of body, is as example.But procedure of the invention is not limited to described and illustrated specific steps, this field
Technical staff can be variously modified, modification and addition after the spirit for understanding the present invention, or suitable between changing the step
Sequence.
Functional block shown in structures described above block diagram can be implemented as hardware, software, firmware or their group
It closes.When realizing in hardware, it may, for example, be electronic circuit, application-specific integrated circuit (ASIC), firmware appropriate, insert
Part, function card etc..When being realized with software mode, element of the invention is used to execute program or the generation of required task
Code section.Either code segment can be stored in machine readable media program or the data-signal by being carried in carrier wave is passing
Defeated medium or communication links are sent." machine readable media " may include any medium for capableing of storage or transmission information.
The example of machine readable media includes electronic circuit, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), soft
Disk, CD-ROM, CD, hard disk, fiber medium, radio frequency (RF) link, etc..Code segment can be via such as internet, inline
The computer network of net etc. is downloaded.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, any made by repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of recommendation information processing method, which is characterized in that including:
Feature vector is extracted from recommendation information, and hierarchical clustering is carried out to the recommendation information according to described eigenvector, is obtained
To the hierarchical clustering result of the recommendation information;
Promise nomography is tieed up using weighting, according to the classification quantity of the hierarchical clustering result, and to recommend described in each classification
The number of information generates the stratification map of the recommendation information as weight;
Receive the operation that user searches similar recommendation information similar to the specific recommendations information in the stratification map;
It is prominent in the stratification map to show the similar recommendation information.
2. according to the method described in claim 1, it is characterized in that, prominent displaying is described in the stratification map similar pushes away
Recommending information further includes:
The highlighted line between the specific recommendations information and the similar recommendation information is drawn in the stratification map.
3. according to the method described in claim 1, it is characterized in that, using weighting dimension promise nomography, according to the hierarchical clustering
As a result classification quantity, and using the number of recommendation information described in each classification as weight, generate the layer of the recommendation information
Secondaryization map includes:
Selected origin coordinates, and using weighting dimension promise nomography, according to the upper layer classification quantity of the hierarchical clustering result, with every
The number of recommendation information described in a upper layer classification calculates coordinate and the boundary of the upper layer classification as weight;
Coordinate centered on the coordinate that the upper layer is classified ties up promise nomography, according to the hierarchical clustering result using weighting
Upper layer classification in next layer of classification quantity, recommendation information described in each next layer of classification in being classified with the upper layer
Number as weight, calculate the coordinate of each next layer of classification and boundary in the upper layer classification;Above-mentioned calculating process is repeated,
Until calculating coordinate and the boundary of bottom classification;
It generates the coordinate of whole recommendation informations in the bottom classification at random in the boundary of bottom classification, and executes dimension promise
Nomography, so that the coordinate of whole recommendation informations in bottom classification is evenly distributed in the boundary of the bottom classification.
4. according to the method described in claim 1, it is characterized in that, the stratification map is scalable vector graphics format
Map.
5. method according to claim 1 to 4, which is characterized in that the recommendation information includes following one:
Singer, performer, author, music, film, TV play, books.
6. a kind of recommendation information processing unit, which is characterized in that described device includes:
Cluster module, for extracting feature vector from recommendation information, and according to described eigenvector to the recommendation information into
Row hierarchical clustering obtains the hierarchical clustering result of the recommendation information;
Generation module, for tieing up promise nomography using weighting, according to the classification quantity of the hierarchical clustering result, and with each point
The number of recommendation information described in class generates the stratification map of the recommendation information as weight;
Receiving module searches similar recommendation similar to the specific recommendations information in the stratification map for receiving user
The operation of breath;
Display module shows the similar recommendation information for prominent in the stratification map.
7. a kind of recommendation information processing equipment, which is characterized in that including:At least one processor, at least one processor and
The computer program instructions being stored in the memory are realized when the computer program instructions are executed by the processor
Method as described in any one of claim 1-5.
8. a kind of computer readable storage medium, is stored thereon with computer program instructions, which is characterized in that when the computer
The method as described in any one of claim 1-5 is realized when program instruction is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810278994.1A CN108460162A (en) | 2018-03-31 | 2018-03-31 | Recommendation information processing method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810278994.1A CN108460162A (en) | 2018-03-31 | 2018-03-31 | Recommendation information processing method, device, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108460162A true CN108460162A (en) | 2018-08-28 |
Family
ID=63237958
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810278994.1A Pending CN108460162A (en) | 2018-03-31 | 2018-03-31 | Recommendation information processing method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108460162A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109388732A (en) * | 2018-10-16 | 2019-02-26 | 腾讯音乐娱乐科技(深圳)有限公司 | Music ground map generalization and display methods, device and storage medium |
CN110213633A (en) * | 2019-06-03 | 2019-09-06 | 重庆蓝岸通讯技术有限公司 | A kind of display processing method of streaming media broadcast station list |
CN112667906A (en) * | 2020-12-31 | 2021-04-16 | 上海众源网络有限公司 | Recommendation method and device for up master and electronic equipment |
CN112749296A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
CN113486237A (en) * | 2021-06-07 | 2021-10-08 | 海南太美航空股份有限公司 | Flight information recommendation method and system, storage medium and electronic equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105718528A (en) * | 2016-01-15 | 2016-06-29 | 上海交通大学 | Academic map display method based on reference relationship among thesises |
CN106919577A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | Based on method, device and search engine that search word scans for recommending |
-
2018
- 2018-03-31 CN CN201810278994.1A patent/CN108460162A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106919577A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | Based on method, device and search engine that search word scans for recommending |
CN105718528A (en) * | 2016-01-15 | 2016-06-29 | 上海交通大学 | Academic map display method based on reference relationship among thesises |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109388732A (en) * | 2018-10-16 | 2019-02-26 | 腾讯音乐娱乐科技(深圳)有限公司 | Music ground map generalization and display methods, device and storage medium |
CN109388732B (en) * | 2018-10-16 | 2022-02-25 | 腾讯音乐娱乐科技(深圳)有限公司 | Music map generating and displaying method, device and storage medium |
CN110213633A (en) * | 2019-06-03 | 2019-09-06 | 重庆蓝岸通讯技术有限公司 | A kind of display processing method of streaming media broadcast station list |
CN112749296A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
CN112749296B (en) * | 2019-10-31 | 2024-01-26 | 北京达佳互联信息技术有限公司 | Video recommendation method, device, server and storage medium |
CN112667906A (en) * | 2020-12-31 | 2021-04-16 | 上海众源网络有限公司 | Recommendation method and device for up master and electronic equipment |
CN113486237A (en) * | 2021-06-07 | 2021-10-08 | 海南太美航空股份有限公司 | Flight information recommendation method and system, storage medium and electronic equipment |
CN113486237B (en) * | 2021-06-07 | 2023-06-27 | 海南太美航空股份有限公司 | Flight information recommendation method and system, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108460162A (en) | Recommendation information processing method, device, equipment and medium | |
Federico et al. | A survey on visual approaches for analyzing scientific literature and patents | |
US8321456B2 (en) | Generating metadata for association with a collection of content items | |
Bonnin et al. | Automated generation of music playlists: Survey and experiments | |
US8356038B2 (en) | User to user recommender | |
CN111046221B (en) | Song recommendation method, device, terminal equipment and storage medium | |
US20160004738A1 (en) | Systems and methods of generating a navigable, editable media map | |
US9727906B1 (en) | Generating item clusters based on aggregated search history data | |
CN111680254B (en) | Content recommendation method and device | |
US20130110838A1 (en) | Method and system to organize and visualize media | |
CN108304493B (en) | Hypernym mining method and device based on knowledge graph | |
Nocaj et al. | Organizing search results with a reference map | |
CN105488068B (en) | It searches for music and establishes the method and device of index, search result judgment method | |
CN104102733B (en) | Search for content providing and search engine | |
Knees et al. | Intelligent User Interfaces for Music Discovery. | |
US11803588B2 (en) | Audiovisual content curation system | |
US20130346385A1 (en) | System and method for a purposeful sharing environment | |
CN111723289B (en) | Information recommendation method and device | |
Gu et al. | Csbr: A compositional semantics-based service bundle recommendation approach for mashup development | |
CN106776910A (en) | The display methods and device of a kind of Search Results | |
US20150268932A1 (en) | Systems and methods to generate a playlist from a media map | |
Hong et al. | Semantic tag recommendation based on associated words exploiting the interwiki links of Wikipedia | |
Jain et al. | Organizing query completions for web search | |
US20060282464A1 (en) | Multi-dial system for inter-channel surfing of digital media files | |
CN108460131A (en) | A kind of tag along sort processing method and processing device |
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: 20180828 |
|
RJ01 | Rejection of invention patent application after publication |