CN107918614B - Recommendation method and server for singing accompaniment - Google Patents
Recommendation method and server for singing accompaniment Download PDFInfo
- Publication number
- CN107918614B CN107918614B CN201610879632.9A CN201610879632A CN107918614B CN 107918614 B CN107918614 B CN 107918614B CN 201610879632 A CN201610879632 A CN 201610879632A CN 107918614 B CN107918614 B CN 107918614B
- Authority
- CN
- China
- Prior art keywords
- singing
- user
- clustering
- filtering
- vector
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Reverberation, Karaoke And Other Acoustics (AREA)
Abstract
The invention provides a recommendation method and a server of singing accompaniment, wherein the method is applied to a network platform singing requesting system consisting of the server and a plurality of users, and comprises the following steps: the server acquires the singing behavior data of the user and the singed artist identification information; establishing a vector space corresponding to the artist identification according to the user singing data, and clustering the artist identification according to the vector space to obtain a clustering result; and filtering the clustering result to obtain a filtering result. And recommending singing accompaniment according to the filtering result. By the recommendation method of the singing accompaniment, the precision of song classification during song recommendation can be improved.
Description
Technical Field
The invention relates to the technical field of internet platform singing, in particular to a recommendation method and a server for singing accompaniment.
Background
The network platform singing application is a music service product which develops rapidly in recent years, the traditional singing function is transplanted to an internet platform, and a virtual singing platform is provided for vast singing enthusiasts through a network. At present, with the vigorous development of network music, people have higher and higher requirements on music services, and various large music service websites successively promote the personalized music recommendation function, namely, through the analysis of historical behaviors such as user access behaviors, collection records and the like, the interest and hobbies of users are mined, and music which meets the appreciation tastes of the users is recommended for the users.
Most users who request to sing on line lack professional music knowledge, the style, the mode and the rhythm of songs and the tone characteristics of singers are not well known, and the songs are suitable for the users and are not well known, so that great blindness exists in song selection. Therefore, it is very important to perform accurate personalized recommendation for network singing services. Meanwhile, because the singing song is different from the listening song in user behaviors, compared with the passive song listening behavior which does not need too much user participation and feedback, the singing is active, and the user needs to actively participate in the whole process, and once the song does not accord with the user interest, the user experience is reduced, so that the network singing recommendation is required to be more accurate and closer to the real interest of the user.
The existing recommendation methods mainly comprise the following two methods: the first method comprises the following steps: and performing collaborative filtering by using behaviors of users, wherein the second type is as follows: machine learning is carried out through the music labels, a classifier model is built, and singing recommendation is completed through the classifier model.
However, the two methods are not very suitable for song singing situations, and the existing first collaborative filtering recommendation method is large in calculation amount and low in recommendation speed; and often for some users with higher concentration on special artists, their special attributes often cannot be reflected. The recommendation effect using collaborative filtering is not ideal in user behavior; the existing second recommendation method using music labels is not ideal in accuracy in singing scenes, and the concentration of the labels (mostly popular and wounded) causes that song categories cannot be well distinguished. The artists serve as important attributes of music, can well give user classifications in a singing scene, and can serve as important methods for recommendation.
Therefore, the existing recommendation scheme of the singing accompaniment has the problems of fuzzy classification and low accuracy of recommendation results when songs are recommended.
Disclosure of Invention
The invention provides a recommendation method and a server for singing accompaniment, which aim to solve the problems of fuzzy classification and low accuracy of recommendation results when song recommendation is carried out in a collaborative filtering and label recommendation mode in the prior art.
In order to solve the above problems, the present invention discloses a recommendation method of singing accompaniment, which is applied to a network platform singing requesting system composed of a server and a plurality of users, and the method comprises the following steps:
the server acquires the singing behavior data of the user and the singed artist identification information;
establishing a vector space corresponding to the artist identification according to the user singing data, and clustering the artist identification according to the vector space to obtain a clustering result;
and filtering the clustering result to obtain a filtering result.
And recommending singing accompaniment according to the filtering result.
In order to solve the above problems, the present invention discloses a server, including:
the obtaining module is used for obtaining the singing behavior data of the user and the singed artist identification information;
the clustering module is used for establishing a vector space corresponding to the artist identification according to the user singing data, and clustering the artist identification to obtain a clustering result;
the filtering module is used for filtering the clustering result to obtain a filtering result;
and the recommending module is used for recommending the singing accompaniment according to the filtering result.
Compared with the prior art, the invention has the following advantages:
according to the recommendation method of singing accompaniment provided by the embodiment of the invention, the vector space corresponding to the artist can be established through the singing behavior of the user, the artist is clustered through the calculation of the vector space, and the clustering result is screened, so that the precision of song classification during song recommendation can be improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating steps of a method for recommending singing accompaniment according to a first embodiment of the present invention;
fig. 2 is a flowchart illustrating steps of a method for recommending singing accompaniment according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a server according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a server according to a fourth embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
Referring to fig. 1, a flowchart of a recommendation method of singing accompaniment according to a first embodiment of the present invention is shown, and the recommendation method of singing accompaniment according to the embodiment of the present invention includes the following steps:
step 101: the server obtains the singing behavior data of the user and the singed artist identification information.
The user singing behavior data includes artists that the user has sung, and the number of times the user has sung these artists' songs.
Step 102: and establishing a vector space corresponding to the artist identification according to the singing data of the user, and clustering the artist identification to obtain a clustering result.
For example, artist a is singed 0 times, 1 time, and 3 times by users a, b, and c, respectively. If the sample size is three, a, b and c, each value in the vector is 0, 3 and 4; 0 for not sung, 3 for sung, and 4 for multiple sung. The vector corresponding to artist a is (0, 3, 4); and by analogy, obtaining the vector of each artist and forming a vector space.
It should be noted that, in the specific implementation process, the values of singing, and multiple singing may be set by those skilled in the art according to actual needs, and this is not specifically limited in the embodiment of the present invention. And the numerical values of the three can be the same or different.
Step 103: and filtering the clustering result to obtain a filtering result.
The data obtained from step 102 may be relatively coarse, and may be distributed among a large group of unrelated artists, as well as those who fall on an order; for the artists who fall the order, the fact that the user may be more attentive indicates that songs singing these artists do not sing songs of other artists any more; and the screening is needed for large and medium populations.
Step 104: and recommending singing accompaniment according to the filtering result.
According to the recommendation method of singing accompaniment provided by the embodiment of the invention, the vector space corresponding to the artist can be established through the singing behavior of the user, the artist is clustered through the calculation of the vector space, and the clustering result is screened, so that the precision of song classification during song recommendation can be improved.
Example two
Referring to fig. 2, a flowchart of a recommendation method of singing accompaniment according to a second embodiment of the present invention is shown, and the recommendation method of singing accompaniment according to the second embodiment of the present invention includes the following steps:
step 201: the server obtains the singing behavior data of the user and the singed artist identification information.
Step 202: and establishing a vector space corresponding to the artist identification according to the singing data of the user, and clustering the artist identification to obtain a clustering result.
One preferred clustering approach is:
s1: extracting user singing behavior data meeting conditions from the obtained user singing behavior data;
the user singing behavior data meeting the conditions are historical data of songs sung by users who normally log in and use the mobile application in a certain period, and the data are data left by data generated by users who are not active for a long time or users who have single singing behavior and have short singing time and 'song swiping' for increasing the attention degree of artists or the singing times of accounts.
S2: determining the amount of the users contained in the extracted user singing behavior data;
the user singing behavior data comprises data such as singing times and singing time of each user for each artist. The user amount is the number of user accounts that generate the data.
S3: establishing a vector space with the dimensionality being the determined user quantity;
s4: determining a vector corresponding to each artist identification in a vector space; for example, artist a is singed 0 times, 1 time, and 3 times by users a, b, and c, respectively. If the sample size is three, a, b and c, each value in the vector is 0, 3 and 4; if 0 represents not sung, 3 represents sung, and 4 represents singing for a plurality of times, the vector corresponding to artist A is (0, 3, 4).
It should be noted that, in the specific implementation process, the values of singing, and multiple singing may be set by those skilled in the art according to actual needs, and this is not specifically limited in the embodiment of the present invention. And the numerical values of the three can be the same or different.
In the manner of step S1, and so on, the vectors for each artist are obtained and constitute a vector space.
S5: a set number of starting points is determined in vector space.
The number of starting points is generally 1/10 that is the number of sampling users, and in a specific implementation, the number of starting points can be set by a person skilled in the art according to actual needs.
S6: and calculating the distance from each vector to each starting point, and comparing the distances from each vector to each starting point to obtain the shortest distance.
S7: and dividing the vectors into groups established by the starting points corresponding to the shortest distances according to the shortest distances to obtain clustering results.
S8: and calculating the center point of each group according to the clustering result.
S9: and comparing the central point with the initial point, finishing clustering if the central point is consistent with the initial point, taking the central point as the initial point if the central point is inconsistent with the initial point, returning to the step of calculating the distance from each vector to each initial point, and comparing the distance from each vector to each initial point to obtain the shortest distance.
It should be noted that S5 to S9 are processes for performing clustering once, and in a specific implementation process, if the previous clustering does not meet the clustering standard, the process needs to return to perform S5 to perform the next clustering again, and the process repeats S5 to S9 until the clustering reaches the clustering standard and then stops.
Step 203: the server captures webpage information containing artist identification in the Internet.
Step 204: and filtering the artist identification irrelevant to the group in the clustering result according to the webpage information to obtain a filtering result.
The data obtained in step 202 will be relatively coarse, and there may be several artists without relationship distributed in a large group, and there will also be artists who fall on the list; for the artists who fall the order, the fact that the user may be more attentive indicates that songs singing these artists do not sing songs of other artists any more; and the screening is needed for large and medium populations. Step 203 may grab many web pages for all artists within a group. And if the situation that a certain artist and any other artist appear on the same page does not appear in all the captured webpages, filtering the artist from the group.
Step 205: the server obtains popular song information identified by the artist.
Step 206: and acquiring the artist identification corresponding to the current singing song of the user.
Step 207: and recommending popular song information according to the screening result and the artist identification corresponding to the current singing song of the user.
For example, the system detects that the song currently sung by the user is artist A's work. In the clustering result, the group of the artist A also has the artist B and the artist, so the server recommends popular songs of the artist A, the artist B and the artist C to the user.
The recommendation method of singing accompaniment provided by the embodiment of the invention has the beneficial effects of the recommendation method of singing accompaniment in the first embodiment, and can further improve the accuracy of artist song screening by capturing webpage information containing artist identification in the internet, and screening and filtering the clustering result again.
EXAMPLE III
Referring to fig. 3, a schematic diagram of a server according to the present invention is shown. The server shown in this embodiment includes.
The obtaining module 301 is configured to obtain singing behavior data of a user and artist identification information that is sung.
The clustering module 302 is configured to establish a vector space corresponding to the artist identifier according to the user singing data, and cluster the artist identifier to obtain a clustering result.
And the filtering module 303 is configured to filter the clustering result to obtain a filtering result.
And the recommending module 304 is configured to recommend the singing accompaniment according to the filtering result.
The server provided by the embodiment of the invention can establish the vector space corresponding to the artist through the singing behavior of the user, cluster the artist through the calculation of the vector space and screen the clustering result, thereby improving the classification accuracy when recommending songs.
Example four
Referring to fig. 4, a schematic diagram of a server according to the present invention is shown. The server shown in this embodiment includes:
the obtaining module 401 is configured to obtain singing behavior data of a user and singed artist identification information; the clustering module 402 is used for establishing a vector space corresponding to the artist identification according to the singing data of the user, and clustering the artist identification to obtain a clustering result; a filtering module 403, configured to filter the clustering result to obtain a filtering result; and a recommending module 404, configured to recommend singing accompaniment according to the filtering result.
Preferably, the clustering module 402 includes: the first clustering submodule 4021 extracts user singing behavior data meeting the conditions from the acquired user singing behavior data; the second clustering sub-module 4022 determines the amount of users contained in the extracted user singing behavior data; a starting point initialization submodule 4023, configured to determine starting points of a set number in a vector space; the distance calculation submodule 4024 is configured to calculate a distance from each vector to each starting point, and compare the distances from each vector to each starting point to obtain a shortest distance; the group division submodule 4025 is configured to divide the vectors into groups established at starting points corresponding to the shortest distances according to the shortest distances to obtain clustering results; the central point calculating submodule 4026 is configured to calculate a central point of each group according to the clustering result; the comparison execution sub-module 4027 is configured to compare the center point with the start point, complete clustering if the center point is consistent with the start point, and return to calculating the distance from each vector to each start point and compare the distances from each vector to each start point to obtain the shortest distance if the center point is not consistent with the start point.
Preferably, the filtering module 403 shown in this embodiment includes: the grabbing submodule 4031 is used for grabbing webpage information containing artist identification in the internet; and the filtering execution sub-module 4032 is used for filtering the artist identification irrelevant to the group in the clustering result according to the webpage information to obtain a filtering result.
Preferably, the recommending module 404 shown in the present embodiment includes: a song collection submodule 4041 for obtaining popular song information identified by the artist; the detection submodule 4042 is used for acquiring an artist identifier corresponding to the song currently sung by the user; and the recommending submodule 4043 is used for recommending popular song information according to the screening result and the artist identification corresponding to the song currently performed by the user.
The server of the embodiment of the present invention is used to implement a method for recommending a singing accompaniment corresponding to the first embodiment and the second embodiment, and has the beneficial effects of the corresponding method embodiments, which are not described herein again.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The recommendation method and the server for singing accompaniment provided by the invention are described in detail, specific examples are applied in the description to explain the implementation steps and the implementation device of the invention, and the description of the above embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention. It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (6)
1. A recommendation method of singing accompaniment is applied to a network platform singing system consisting of a server and a plurality of users, and is characterized by comprising the following steps:
the server acquires the singing behavior data of the user and the singed artist identification information;
according to the user singing behavior data, establishing a vector space corresponding to the artist identification, and clustering the artist identification according to the vector space to obtain a clustering result;
filtering the clustering result to obtain a filtering result;
according to the filtering result, recommending singing accompaniment;
wherein the user singing behavior data comprises the times of singing of artists' songs by the user;
the step of establishing a vector space corresponding to the artist identification according to the user singing behavior data, and clustering the artist identification according to the vector space comprises the following steps:
extracting user singing behavior data meeting conditions from the obtained user singing behavior data;
determining the amount of the users contained in the extracted user singing behavior data; establishing a vector space with the dimension of the user quantity; determining a vector corresponding to each artist identification in the vector space;
determining a set number of starting points in the vector space;
for each vector, calculating the distance from the vector to each starting point, and comparing the distances from the vector to each starting point to obtain the shortest distance; dividing the vectors into groups established by the starting points corresponding to the shortest distance to obtain clustering results;
calculating the central point of each group according to the clustering result;
comparing the central point with the starting point, finishing clustering if the central point is consistent with the starting point, taking the central point as the starting point if the central point is inconsistent with the starting point, returning to the step of calculating the distance from each vector to each starting point, and comparing the distance from each vector to each starting point to obtain the shortest distance.
2. The recommendation method of singing accompaniment according to claim 1, wherein said step of filtering said clustering result comprises:
the server captures webpage information containing the artist identification in the Internet;
and filtering the artist identification irrelevant to the group in the clustering result according to the webpage information to obtain a filtering result.
3. The method for recommending singing accompaniment according to claim 2, wherein the step of recommending the singing accompaniment according to the filtering result comprises:
the server acquires the popular song information of the artist identification;
detecting an artist identification corresponding to a song currently sung by a user;
and recommending the popular song information according to the filtering result and the artist identification corresponding to the current singing song of the user.
4. A server, characterized in that the server comprises:
the obtaining module is used for obtaining the singing behavior data of the user and the singed artist identification information;
the clustering module is used for establishing a vector space corresponding to the artist identification according to the user behavior singing data, and clustering the artist identification to obtain a clustering result;
the filtering module is used for filtering the clustering result to obtain a filtering result;
the recommendation module is used for recommending singing accompaniment according to the filtering result;
wherein the user singing behavior data comprises the times of singing of artists' songs by the user;
the clustering module comprises:
the first clustering submodule is used for extracting data meeting the singing behavior of the user from the acquired data of the singing behavior of the user;
the second clustering submodule is used for determining the user amount contained in the extracted user singing behavior data; establishing a vector space with the dimension of the user quantity; determining a vector corresponding to each artist identification in the vector space;
the starting point initialization submodule is used for determining the starting points of a set number in the vector space;
the distance calculation submodule is used for calculating the distance from each vector to each starting point and comparing the distance from each vector to each starting point to obtain the shortest distance;
the group division submodule is used for dividing each vector into a group established by a starting point corresponding to the shortest distance according to the shortest distance to obtain a clustering result;
the central point calculation submodule is used for calculating the central point of each group according to the clustering result;
and the comparison execution submodule is used for comparing the central point with the starting point, finishing clustering if the central point is consistent with the starting point, taking the central point as the starting point if the central point is inconsistent with the starting point, and returning to execute the distance calculation submodule.
5. The server according to claim 4, wherein the filtering module comprises:
the grabbing submodule is used for grabbing webpage information containing the artist identification in the Internet;
and the filtering execution sub-module is used for filtering the artist identification irrelevant to the group in the clustering result according to the webpage information to obtain a filtering result.
6. The server of claim 5, wherein the recommendation module comprises:
the song collecting submodule is used for acquiring popular song information of the artist identification;
the detection submodule is used for detecting the artist identification corresponding to the song currently sung by the user;
and the recommending submodule is used for recommending the popular song information according to the filtering result and the artist identification corresponding to the current singing song of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610879632.9A CN107918614B (en) | 2016-10-08 | 2016-10-08 | Recommendation method and server for singing accompaniment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610879632.9A CN107918614B (en) | 2016-10-08 | 2016-10-08 | Recommendation method and server for singing accompaniment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107918614A CN107918614A (en) | 2018-04-17 |
| CN107918614B true CN107918614B (en) | 2020-11-10 |
Family
ID=61891688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610879632.9A Active CN107918614B (en) | 2016-10-08 | 2016-10-08 | Recommendation method and server for singing accompaniment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107918614B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402534A (en) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术（上海）有限公司 | Background music recommending system for reading literature works and realizing method of background music recommending system |
| CN102654860A (en) * | 2011-03-01 | 2012-09-05 | 北京彩云在线技术开发有限公司 | Personalized music recommendation method and system |
| CN105575393A (en) * | 2015-12-02 | 2016-05-11 | 中国传媒大学 | Personalized song recommendation method based on voice timbre |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005071569A1 (en) * | 2004-01-20 | 2005-08-04 | Koninklijke Philips Electronics, N.V. | Playlist based on artist and song similarity |
| CN100555287C (en) * | 2007-09-06 | 2009-10-28 | 腾讯科技（深圳）有限公司 | internet music file sequencing method, system and searching method and search engine |
| CN102654859B (en) * | 2011-03-01 | 2014-04-23 | 北京彩云在线技术开发有限公司 | Method and system for recommending songs |
| CN102402625A (en) * | 2011-12-28 | 2012-04-04 | 深圳市五巨科技有限公司 | Method and system for recommending music |
| CN103927366B (en) * | 2014-04-21 | 2017-03-22 | 苏州大学 | Method and system for automatically playing songs according to pictures |
-
2016
- 2016-10-08 CN CN201610879632.9A patent/CN107918614B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402534A (en) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术（上海）有限公司 | Background music recommending system for reading literature works and realizing method of background music recommending system |
| CN102654860A (en) * | 2011-03-01 | 2012-09-05 | 北京彩云在线技术开发有限公司 | Personalized music recommendation method and system |
| CN105575393A (en) * | 2015-12-02 | 2016-05-11 | 中国传媒大学 | Personalized song recommendation method based on voice timbre |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107918614A (en) | 2018-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100359854C (en) | Information transmission system by collaborative filtering, information processing device and program | |
| CN107330750B (en) | A kind of recommended products figure method and device, electronic equipment | |
| CN109492180A (en) | Resource recommendation method, device, computer equipment and computer readable storage medium | |
| US20090259606A1 (en) | Diversified, self-organizing map system and method | |
| CN106982381B (en) | Home page recommendation processing method and device | |
| CN103927309B (en) | A kind of method and device to business object markup information label | |
| CN103426003A (en) | Implementation method and system for enhancing real interaction | |
| CN109903127A (en) | Group recommendation method and device, storage medium and server | |
| US20140074828A1 (en) | Systems and methods for cataloging consumer preferences in creative content | |
| KR101804967B1 (en) | Method and system to recommend music contents by database composed of user's context, recommended music and use pattern | |
| JP4893940B2 (en) | Information processing apparatus and method, and program | |
| CN116595398A (en) | Resource intelligent matching method and related device based on meta universe | |
| WO2007077991A1 (en) | Information processing device and method, and program | |
| KR20120101233A (en) | Method for providing sentiment information and method and system for providing contents recommendation using sentiment information | |
| JP2011165131A (en) | Information processor, method, and program | |
| CN102857471A (en) | Multimedia interacting method and system | |
| CN105426392B (en) | Collaborative filtering recommendation method and system | |
| CN105574480B (en) | A kind of information processing method, device and terminal | |
| CN112466334A (en) | Audio identification method, equipment and medium | |
| US20130108180A1 (en) | Information processing device, information processing method, and program | |
| CN115062013A (en) | Information recommendation method, device, equipment and storage medium | |
| CN106997340B (en) | Word stock generation method and device and document classification method and device using word stock | |
| US20220075804A1 (en) | Method and device for providing guide information for enhancement of artist's reputation | |
| CN108460131B (en) | Classification label processing method and device | |
| CN108932262B (en) | Song recommendation method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |