CN108491537B - User preference information processing method, device, equipment and medium - Google Patents
User preference information processing method, device, equipment and medium Download PDFInfo
- Publication number
- CN108491537B CN108491537B CN201810279000.8A CN201810279000A CN108491537B CN 108491537 B CN108491537 B CN 108491537B CN 201810279000 A CN201810279000 A CN 201810279000A CN 108491537 B CN108491537 B CN 108491537B
- Authority
- CN
- China
- Prior art keywords
- artist
- preference information
- value
- user
- taking
- 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.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a user preference information processing method, a device, equipment and a medium. Wherein, the method comprises the following steps: extracting preference information of a user for music from a music listening record of the user; quantizing the preference information to obtain a preference information quantized value; adding the preference information quantization value of the same artist, and taking the value obtained by the addition as the weight value of the artist; and drawing a contour map on the artist hierarchical map according to the weight value. The invention solves the problem that the music preference information of the user is difficult to be displayed by adopting the artist as the granularity in the related technology, and realizes the technical effect of displaying the music preference information of the user by adopting the artist as the granularity and adopting an intuitive graphical form.
Description
Technical Field
The present invention relates to the field of data processing, and in particular, to a method, an apparatus, a device, and a medium for processing user preference information.
Background
The stream media in the internet age becomes the main form of listening to music, and users do not need to be limited to entity music, so that the taste is more diversified. In recent years, there has been an increasing number of listening records and visual presentations of music tastes for users, and typical cases such as expir. This is most similar to the present solution from the point of view of rendering as a map. In addition, there are QQ music (refer to FIG. 1), which are presented in the form of a pie chart or the like by analyzing the preference of the user for singers, genres, languages and years, respectively.
The inventor finds out in the research process that:
1. fm's solution has the disadvantage that the genre of the artist itself has no obvious relation to the geographical location, so that the method does not reflect the music taste distribution of the user. And the map is equivalent to a real map, so that the freshness of the user is lost, and the map has no positive significance for the user to find new music.
2. The QQ music scheme is essentially a ranking list for listening to data in different dimensions of a user, only the historical data is stated, no novelty exists in the display mode, and no positive significance is brought to the fact that the user finds new music. In addition, the classification of music/artists is very abstract according to genre classification of artists or language classification of music, etc.; for example, when a QQ music scheme is used to present a user's music preferences, it is difficult to reflect the user's preferences for particular artists in a particular genre or language.
In summary, no effective solution has been proposed at present for the problem in the related art that the preference information of the music of the user is difficult to be displayed by adopting the artist as the granularity.
Disclosure of Invention
The invention provides a user preference information processing method, a device, equipment and a medium, which at least solve the problem that the preference information of music of a user is difficult to be displayed by adopting artist as granularity in the related technology.
In a first aspect, an embodiment of the present invention provides a method for processing user preference information, including:
extracting preference information of a user for music from a music listening record of the user;
quantizing the preference information to obtain a preference information quantization value;
adding the preference information quantization values of the same artist, and taking the value obtained by the addition as a weight value of the artist;
and drawing a contour map on the artist hierarchical map according to the weight value.
In a second aspect, an embodiment of the present invention provides a user preference information processing apparatus, including:
the extraction module is used for extracting preference information of a user on music from a music listening record of the user;
the quantization module is used for quantizing the preference information to obtain a preference information quantization value;
the adding module is used for adding the preference information quantized values of the same artist and taking the value obtained by adding as the weight value of the artist;
and the drawing module is used for drawing a contour map on the artist hierarchical map according to the weight value.
In a third aspect, an embodiment of the present invention provides a user preference information processing apparatus, including: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which computer program instructions are stored, which, when executed by a processor, implement the method of the first aspect.
By the method, the device, the equipment and the medium for processing the user preference information, the preference information of the user on the music is extracted from the music listening record of the user; quantizing the preference information to obtain a preference information quantized value; adding the preference information quantization value of the same artist, and taking the value obtained by the addition as the weight value of the artist; according to the weight value, the contour map is drawn on the artist hierarchical map, so that the problem that the music preference information of the user is difficult to display by taking the artist as the granularity in the related technology is solved, and the technical effect of displaying the music preference information of the user by taking the artist as the granularity and adopting an intuitive graphical form is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a schematic diagram of presentation of QQ music user preference data according to the related art;
fig. 2 is a flowchart of a user preference information processing method according to an embodiment of the present invention;
fig. 3 is a flowchart of a user preference information processing method according to a preferred embodiment of the present invention;
fig. 4 is a block diagram of a configuration of a user preference information processing apparatus according to an embodiment of the present invention;
fig. 5 is a hardware configuration diagram of a user preference information processing apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a contour map drawn in an artist hierarchical map in accordance with a preferred embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the present embodiment, a user preference information processing method is provided, and fig. 2 is a flowchart of the user preference information processing method according to the embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S301, extracting preference information of a user to music from the music listening record of the user;
step S302, quantifying preference information to obtain a preference information quantification value;
step S303, adding the preference information quantization value of the same artist, and taking the value obtained by the addition as the weight value of the artist;
and step S304, drawing a contour map on the artist hierarchical map according to the weight value.
Through the steps, the quantitative value of the preference information of the same artist is used as the weight value of the artist, a contour map is drawn on the artist hierarchical map, and each vertex in the contour map is the coordinate of the artist in the artist hierarchical map. Since the artists are distributed among the hierarchical map of artists according to their characteristics, wherein more similar artists are closer together and less similar artists are farther apart. Therefore, on the one hand, the contour map which is obtained according to the weighted value of the artist on the artist hierarchical map can represent the preference information of the user for the artist/music with the artist as the granularity, and on the other hand, the position of the contour map in the artist hierarchical map can also intuitively represent the style characteristics of the artist. Therefore, through the steps, the problem that the music preference information of the user is difficult to display by taking the artist as the granularity in the related technology is solved, and the technical effect of displaying the music preference information of the user by taking the artist as the granularity and adopting an intuitive graphical form is achieved.
In addition, the artist-hierarchical map depicts an entire artist/music world, depicting a range of music preferences that are personally unique to the user throughout the entire artist/music world, also increasing the user's understanding of the location of the artist/music world, as well as his own preferences, within the artist/music world, and increasing enjoyment.
The manner of generating the artist hierarchical map may be any known manner of generating artist hierarchical maps in the art. Optionally, in this embodiment, generating the artist hierarchical map includes: extracting a feature vector from artist information, and performing hierarchical clustering on the artist according to the feature vector to obtain a hierarchical clustering result of the artist; and generating the artist hierarchical map by adopting a weighted Voronoi diagram algorithm according to the classification quantity of the hierarchical clustering results and taking the number of the artists in each classification as a weight.
Optionally, the artist hierarchical map may be generated in the following manner:
step 2, taking the coordinates of the upper-layer classification as central coordinates, adopting a weighted Voronoi diagram algorithm, and calculating the coordinates and boundaries of each lower-layer classification in the upper-layer classification according to the number of the lower-layer classifications in the upper-layer classification of the hierarchical clustering result and the number of the artists in each lower-layer classification in the upper-layer classification as weights;
And 4, randomly generating coordinates of all artists in the bottom classification in the boundary of the bottom classification, and executing a Voronoi diagram algorithm to uniformly distribute the coordinates of all artists in the bottom classification in the boundary of the bottom classification.
Optionally, the artist hierarchical map is a map in a scalable vector graphics format; with the scalable vector graphics format, the map can be scaled according to the user's operation. When the artists are shown in the artist hierarchical map, hot artists (including icons and text information) are preferentially shown, while relatively cold artists are hidden, so that the artists displayed in the display area of the device are prevented from affecting the user identification too much. Wherein popular artists refer to artists whose attention/number of on-demand/number of likes is greater than a certain predetermined threshold. The predetermined threshold described above varies depending on the degree to which the artist hierarchical map is zoomed to keep the number of artists within the display area of the device at a suitable level.
Optionally, in order to avoid the influence of a single extreme operation performed by the user on the music/artist on the contour map generation result, before adding the preference information quantized values of the same artist and using the added values as the weight values of the corresponding artists, the preference information quantized values of the same artist are also filtered.
When a user listens to a piece of music, possible actions include at least one of: play completely, skip, mark hearts (meaning "i like"), drop into trash (meaning "i dislike"); these operations are referred to as preference information in the present embodiment.
In some examples, the user's preference information is quantified in the following manner: when the user marks a piece of music with the red heart, quantizing this preference information to 5 (a preferred value, in other embodiments other values may be selected, and are not limited herein); when the user plays a piece of music completely, quantizing the preference information into 1 (the preference value, other values can be selected in other embodiments, and are not limited herein); when the user skips playing a piece of music, quantizes the preference information to-1 (the preference value, other values can be selected in other embodiments, and is not limited herein); when the user drops a piece of music into the trash can, this preference information is quantized to-5 (a preferred value, other values may be selected in other embodiments, and are not limited herein).
Considering that there may be accidental factors in some operations of the user on music of the same artist, for example, when the user first listens to a piece of music, the user marks a red heart for the music, but the user does not know the artist, and the user has not made any other contact with other music of the artist, it cannot be determined that the user likes the artist according to the operation of marking the red heart. Therefore, in order to exclude the distortion of the user's preference information determination caused by too little sampling, the preference quantization value of the artist is also filtered in the present embodiment.
Optionally, the filtering the preference information quantization value of the same artist comprises: filtering the preference information quantized values of the same artist if the number of the preference information quantized values of the same artist is less than 2; or to filter out the quantized value of the preference information having the largest absolute value among the quantized values of the preference information of the same artist.
Optionally, the drawing of the contour map on the artist hierarchical map according to the weight value includes the steps of:
step S304-1, drawing an influence range of the artist by taking an artist coordinate of the artist corresponding to the weight value as a center and taking an absolute value of the weight value as a radius, wherein the absolute value of the influence of the artist in the influence range attenuates along with the increase of the distance from the artist coordinate, and the influence of the artist on the artist coordinate is the weight value;
step S304-2, under the condition that the influence ranges of the plurality of artists are mutually overlapped, the influence of a certain point in the overlapping area of the influence ranges is the sum of the influences of the plurality of artists on the certain point;
and step S304-3, drawing a contour map according to the influence of the artist on the artist hierarchical map.
A schematic diagram of a contour map drawn on an artist hierarchical map is shown in figure 6.
When a computer is used to implement the contour map drawing process described above, the artist coordinates and weight values for pairs of artists are stored in the user's private map matrix. The flow of drawing the contour map by using a computer is shown in fig. 3, referring to fig. 3, in order to realize the irregularity of the boundary, a little noise is added to the calculation result, and the normalization is realized on the numerical value by hyperbolic tangent, so that the normalized private map matrix of the user is obtained. In order to reduce the load on the display end, the matrix is subjected to Gaussian blur to smooth the image boundary. And (3) solving contour lines of the private map data matrix to obtain a plurality of contour lines representing 'like' and contour lines representing 'dislike' which respectively correspond to positive values and negative values of the data. When a user requests the My map, contour lines to be displayed at the moment are dynamically generated according to the zoom level of the current user map, and different colors are drawn among polygonal areas formed by different contour lines. When the user's map zoom level changes, the contours are redrawn.
Optionally, when the artist hierarchical map generated in the above manner is used, the user can see which artists are a group and the distance relationship between artists. Clicking on an artist's name pops up a detail page for that artist on which the artist's information, composition and similar content can be viewed, on which the user can listen, or from which the user can explore more similar artist's works.
Alternatively, in the present embodiment, a darker color of the private map (i.e., the contour map superimposed on the artist-level map) indicates a more liked (disliked) and a larger area indicates a more heard. On the complete music map, the user can visually see the position and the range of the personal map, and macroscopically knows the preference or the difference of the user. When the private map is used, the closer an artist is to a favorite part of the private map, the higher the possibility that the user likes it; clicking on an artist in a private map looks at his similar artists, facilitating the exploitation of the user's knowledge of the new music field when similar artists appear in an infrequent grouping.
Compared with classification and visualization of user listening records on a real map such as an expl.fm, the embodiment of the invention generates a virtual map according to the listening data of artists, on the map, the artists do not cluster according to geographical positions any more, but cluster according to own styles and listener tastes, and the user can more intuitively see the music styles involved in the user and the music styles unfamiliar with the user through the visualization of the data on the map, so that the user can conveniently find new music.
In this embodiment, a user preference information processing apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description already made is omitted for brevity. As used hereinafter, the terms "module," "unit" or "sub-unit" and the like may implement a combination of software and/or hardware of predetermined functions. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 4 is a block diagram of a configuration of a user preference information processing apparatus according to an embodiment of the present invention, as shown in fig. 4, the apparatus including:
an extracting module 51, configured to extract preference information of a user for music from a music listening record of the user;
a quantization module 52, configured to quantize the preference information to obtain a quantized value of the preference information;
a summing module 53, configured to sum the preference information quantization values of the same artist, and use the summed value as a weight value of the artist;
and a drawing module 54, configured to draw a contour map on the artist hierarchical map according to the weight value.
Optionally, the apparatus further comprises: the clustering module is used for extracting a feature vector from artist information and performing hierarchical clustering on the artist according to the feature vector to obtain a hierarchical clustering result of the artist; and the generating module is used for generating the artist hierarchical map by adopting a weighted Voronoi diagram algorithm according to the classification quantity of the hierarchical clustering results and taking the number of the artists in each classification as a weight.
Optionally, the generating module generates the artist hierarchical map by using a weighted voronoi diagram algorithm according to the classification number of the hierarchical clustering results and using the number of the artists in each classification as a weight, including: selecting an initial coordinate, adopting a weighted Voronoi diagram algorithm, calculating the coordinate and the boundary of the upper-layer classification according to the upper-layer classification quantity of the hierarchical clustering result and taking the number of the artists in each upper-layer classification as the weight of the weighted Voronoi diagram algorithm; taking the coordinate of the upper-layer classification as a central coordinate, adopting a weighted Voronoi diagram algorithm, according to the number of the next-layer classification in the upper-layer classification of the hierarchical clustering result, and taking the number of the artists in each next-layer classification in the upper-layer classification as a weight, and calculating the coordinate and the boundary of each next-layer classification in the upper-layer classification; repeating the calculation process until the coordinates and the boundaries of the bottom layer classification are calculated; and randomly generating coordinates of all artists in the bottom layer classification in the boundary of the bottom layer classification, and executing a Voronoi diagram algorithm to enable the coordinates of all artists in the bottom layer classification to be uniformly distributed in the boundary of the bottom layer classification.
Optionally, the apparatus further comprises a filtering module, configured to filter the quantized value of the preference information of the same artist before adding the quantized value of the preference information of the same artist and taking the added value as a weight value of a corresponding artist.
Optionally, the filtering module filtering the preference information quantization value of the same artist comprises: filtering out the preference information quantized values of the same artist, in a case where the number of the preference information quantized values of the same artist is less than 2; or filtering out a preference information quantized value having the largest absolute value among the preference information quantized values of the same artist.
Optionally, the drawing module 54 draws a contour map on the artist hierarchical map according to the weight value includes: drawing an influence range of the artist by taking an artist coordinate of the artist corresponding to the weight value as a center and taking an absolute value of the weight value as a radius, wherein the absolute value of the influence of the artist in the influence range is attenuated along with the distance from the artist coordinate, the influence of the artist on the artist coordinate is the weight value, and the influence of the artist on the boundary of the influence range is zero; in the case where the influence ranges of a plurality of artists overlap with each other, the influence at a certain point in the overlapping area of the influence ranges is the sum of the influences of the plurality of artists at the certain point; and drawing the contour map according to the influence of the artist on the artist hierarchical map.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in a plurality of processors.
In addition, the user preference information processing method of the embodiment of the present invention described in conjunction with fig. 2 may be implemented by a user preference information processing apparatus. Fig. 5 is a diagram illustrating a hardware configuration of a user preference information processing apparatus according to an embodiment of the present invention.
The user preference information processing device may comprise a processor 61 and a memory 62 storing computer program instructions.
Specifically, the processor 61 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits implementing the embodiments of the present invention.
Memory 62 may include mass storage for data or instructions. By way of example, and not limitation, memory 62 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 62 may include removable or non-removable (or fixed) media, where appropriate. The memory 62 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 62 is a non-volatile solid-state memory. In a particular embodiment, the memory 62 includes Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.
The processor 61 implements any one of the user preference information processing methods in the above-described embodiments by reading and executing computer program instructions stored in the memory 62.
In one example, the user preference information processing apparatus may further include a communication interface 63 and a bus 60. As shown in fig. 5, the processor 61, the memory 62, and the communication interface 63 are connected via a bus 60 to complete communication therebetween.
The communication interface 63 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiment of the present invention.
The bus 60 includes hardware, software, or both to couple the components of the user preference information processing apparatus to each other. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 60 may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.
The user preference information processing apparatus may execute the user preference information processing method in the embodiment of the present invention based on the acquired data, thereby implementing the user preference information processing method described in conjunction with fig. 2.
In addition, in combination with the user preference information processing method in the above embodiments, the embodiments of the present invention may be implemented by providing a computer-readable storage medium. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the user preference information processing methods in the above embodiments.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A user preference information processing method, comprising:
extracting preference information of a user for music from a music listening record of the user;
quantizing the preference information to obtain a preference information quantization value;
adding the preference information quantization values of the same artist, and taking the value obtained by the addition as a weight value of the artist;
drawing a contour map on the artist hierarchical map according to the weight value; the drawing a contour map on an artist hierarchical map according to the weight values includes: drawing an influence range of the artist by taking an artist coordinate of the artist corresponding to the weight value as a center and taking an absolute value of the weight value as a radius, wherein the absolute value of the influence of the artist in the influence range is attenuated as the distance from the artist coordinate increases, and the influence of the artist on the artist coordinate is the weight value; in the case where the influence ranges of a plurality of artists overlap with each other, the influence at a certain point in the overlapping area of the influence ranges is the sum of the influences of the plurality of artists at the certain point; drawing the contour map according to the influence of the artist on the artist hierarchical map;
wherein the method further comprises:
extracting a feature vector from artist information, and performing hierarchical clustering on the artist according to the feature vector to obtain a hierarchical clustering result of the artist;
generating an artist hierarchical map by adopting a weighted Voronoi diagram algorithm according to the classification quantity of the hierarchical clustering results and taking the number of the artists in each classification as a weight;
the generating the artist hierarchical map by adopting a weighted voronoi diagram algorithm according to the classification quantity of the hierarchical clustering results and taking the number of the artists in each classification as a weight comprises the following steps:
selecting an initial coordinate, adopting a weighted Voronoi diagram algorithm, calculating the coordinate and the boundary of the upper-layer classification according to the upper-layer classification quantity of the hierarchical clustering result and taking the number of the artists in each upper-layer classification as the weight of the weighted Voronoi diagram algorithm;
taking the coordinate of the upper-layer classification as a central coordinate, adopting a weighted Voronoi diagram algorithm, according to the number of the next-layer classification in the upper-layer classification of the hierarchical clustering result, and taking the number of the artists in each next-layer classification in the upper-layer classification as a weight, and calculating the coordinate and the boundary of each next-layer classification in the upper-layer classification; repeating the calculation process until the coordinates and the boundaries of the bottom layer classification are calculated;
and randomly generating coordinates of all artists in the bottom layer classification in the boundary of the bottom layer classification, and executing a Voronoi diagram algorithm to enable the coordinates of all artists in the bottom layer classification to be uniformly distributed in the boundary of the bottom layer classification.
2. The method according to claim 1, wherein before adding the preference information quantization value of the same artist and taking the added value as a weight value of the corresponding artist, the method further comprises:
filtering the preference information quantization value of the same artist.
3. The method of claim 2, wherein filtering the preference information quantization value of the same artist comprises:
filtering out the preference information quantized values of the same artist, in a case where the number of the preference information quantized values of the same artist is less than 2; or
Filtering out a preference information quantized value having the largest absolute value among the preference information quantized values of the same artist.
4. A user preference information processing apparatus for implementing the method according to any one of claims 1 to 3, the apparatus comprising:
the extraction module is used for extracting preference information of a user on music from a music listening record of the user;
the quantization module is used for quantizing the preference information to obtain a preference information quantization value;
the adding module is used for adding the preference information quantized values of the same artist and taking the value obtained by adding as the weight value of the artist;
a drawing module, configured to draw a contour map on an artist hierarchical map according to the weight value, wherein the apparatus further includes:
the clustering module is used for extracting a feature vector from artist information and performing hierarchical clustering on the artist according to the feature vector to obtain a hierarchical clustering result of the artist; and
the generating module is used for generating the artist hierarchical map by adopting a weighted Voronoi diagram algorithm according to the classification quantity of the hierarchical clustering results and taking the number of the artists in each classification as a weight;
and the filtering module is used for filtering the preference information quantized value of the same artist before adding the preference information quantized value of the same artist and taking the value obtained by adding as a weighted value of the corresponding artist.
5. A user preference information processing apparatus characterized by comprising: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of any of claims 1-3.
6. A computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810279000.8A CN108491537B (en) | 2018-03-31 | 2018-03-31 | User preference information processing method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810279000.8A CN108491537B (en) | 2018-03-31 | 2018-03-31 | User preference information processing method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108491537A CN108491537A (en) | 2018-09-04 |
| CN108491537B true CN108491537B (en) | 2022-01-28 |
Family
ID=63317397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810279000.8A Active CN108491537B (en) | 2018-03-31 | 2018-03-31 | User preference information processing method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108491537B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104054104A (en) * | 2011-11-16 | 2014-09-17 | 谷歌股份有限公司 | Displaying auto-generated facts about a music library |
| CN104077339A (en) * | 2013-07-09 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Multimedia data user preference degree acquiring method, device and system |
| CN105608105A (en) * | 2015-10-30 | 2016-05-25 | 浙江大学 | Context listening based music recommendation method |
| EP3040909A1 (en) * | 2015-01-05 | 2016-07-06 | Delphi Technologies, Inc. | Method of providing an envelope with respect to a cluster |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102053988A (en) * | 2009-10-30 | 2011-05-11 | 国际商业机器公司 | Method and system for visualization of data set |
| CN106021228B (en) * | 2016-05-18 | 2019-08-20 | 德稻全球创新网络（北京）有限公司 | A kind of method and system carrying out text analyzing using knowledge topographic map |
-
2018
- 2018-03-31 CN CN201810279000.8A patent/CN108491537B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104054104A (en) * | 2011-11-16 | 2014-09-17 | 谷歌股份有限公司 | Displaying auto-generated facts about a music library |
| CN104077339A (en) * | 2013-07-09 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Multimedia data user preference degree acquiring method, device and system |
| EP3040909A1 (en) * | 2015-01-05 | 2016-07-06 | Delphi Technologies, Inc. | Method of providing an envelope with respect to a cluster |
| CN105608105A (en) * | 2015-10-30 | 2016-05-25 | 浙江大学 | Context listening based music recommendation method |
Non-Patent Citations (2)
| Title |
|---|
| 一个基于聚类算法的推荐系统的设计与实现;刘赫;《CNKI硕士学位论文》;20061231;第二、三章 * |
| 音乐推荐系统的设计和实现;李世旭;《CNKI硕士学位论文》;20160331;第三、四章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108491537A (en) | 2018-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108520076B (en) | Electronic book recommendation method, electronic device and computer storage medium | |
| US10460247B2 (en) | Attribute weighting for media content-based recommendation | |
| US8484224B1 (en) | System and method for ranking geofeeds and content within geofeeds | |
| JP5524219B2 (en) | Interactive image selection method | |
| CN110457577B (en) | Data processing method, device, equipment and computer storage medium | |
| WO2010021625A1 (en) | Automatic creation of a scalable relevance ordered representation of an image collection | |
| CN109409949A (en) | Determination method, apparatus, electronic equipment and the storage medium of user group's classification | |
| CN106599047B (en) | Information pushing method and device | |
| CN106504104A (en) | A kind of method of social activity of being made friends based on face recognition | |
| CN107590420A (en) | Scene extraction method of key frame and device in video analysis | |
| US9325754B2 (en) | Information processing device and information processing method | |
| US10990807B2 (en) | Selecting representative recent digital portraits as cover images | |
| CN106897398B (en) | Video display method and device | |
| US9886504B2 (en) | Audio file management method, device and storage medium | |
| CN109241437A (en) | A kind of generation method, advertisement recognition method and the system of advertisement identification model | |
| CN108460162A (en) | Recommendation information processing method, device, equipment and medium | |
| CN110297942B (en) | Video exploration method, device, equipment and storage medium | |
| CN109785336B (en) | Image segmentation method and device based on multipath convolutional neural network model | |
| CN108491537B (en) | User preference information processing method, device, equipment and medium | |
| CN108804676A (en) | A kind of model sort method, device, equipment and computer readable storage medium | |
| CN106599114A (en) | Music recommendation method and system | |
| JP6623597B2 (en) | Information processing device and program | |
| JP5670732B2 (en) | How to select at least one of a collection of content items | |
| LeBlanc et al. | Adaptive risk group refinement | |
| CN114418624A (en) | Item recommendation method and device, electronic equipment and readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |