CN107239545A - Realize the system and method for text message real-time recommendation - Google Patents
Realize the system and method for text message real-time recommendation Download PDFInfo
- Publication number
- CN107239545A CN107239545A CN201710413824.5A CN201710413824A CN107239545A CN 107239545 A CN107239545 A CN 107239545A CN 201710413824 A CN201710413824 A CN 201710413824A CN 107239545 A CN107239545 A CN 107239545A
- Authority
- CN
- China
- Prior art keywords
- text message
- live view
- user
- displaying live
- text
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The disclosure discloses a kind of system and method for realizing text message real-time recommendation.The system includes:Online data services module, according to displaying live view information of the user to text message, the text message similar to displaying live view information is returned to user;User's displaying live view behavior collection module, according to user behavior of the user to text message, displaying live view information of the storage user to text message;Off-line data computing module, prestores the text message similar to popular text message, and in popular text message and displaying live view information match, text message is uploaded into online data services module;Online computing module in real time, when the popular text message stored in off-line data computing module fails with displaying live view information match, calculates the popular text message most like with displaying live view information, uploads to online data services module.By said system, the recommendation that the text message currently browsed according to user carries out text message is realized.
Description
Technical field
This disclosure relates to technical field of internet application, more particularly to a kind of system for realizing text message real-time recommendation and
Method.
Background technology
Current text message commending system is recorded by collecting the historical viewings of user, and is remembered according to the historical viewings of user
Record and calculated on backstage, and the historical viewings in result of calculation to user are recorded into similar text message and recommend user,
So as to realize the recommendation function of text message.
But in above-mentioned text message commending system, it may appear that due to needing to be recorded according to the historical viewings of user on backstage
Similar text message is calculated, therefore when user browses text message, it is impossible to the text message currently browsed according to user
The recommendation of text message is carried out in real time.
The content of the invention
Text message is carried out in real time in order to solve to exist in correlation technique the text message that can not be currently browsed according to user
Recommendation the problem of, present disclose provides a kind of system and method for realizing text message real-time recommendation.
A kind of system for realizing text message real-time recommendation, the system includes:
Online data services module, for according to displaying live view information of the user to text message, being returned and the reality to user
When browse the similar text message of information;
User's displaying live view behavior collection module, it is connected with the online data services module, user's displaying live view
Behavior collection module is used for according to user behavior of the user to text message, and storage user is believed the displaying live view of text message
Breath;
Off-line data computing module, it is connected with the online data services module, and the off-line data computing module is used for
The text message similar to popular text message is prestored, and in the popular text message and the displaying live view information phase
During matching, the text message is uploaded to the online data services module as the text similar to the displaying live view information
This information;
Online computing module in real time, it is connected with the online data services module, and the online computing module in real time is used for
When the popular text message stored in the off-line data computing module fails with the displaying live view information match, meter
Calculate the popular text message most like with the displaying live view information, and the popular text message uploaded to described
Online data services module is used as the text message similar to the displaying live view information.
A kind of method for realizing text message real-time recommendation, methods described includes:
According to user behavior of the user to text message, displaying live view information of the storage user to text message;
The text message similar to popular text message is prestored, and is believed in the popular text message and the displaying live view
When manner of breathing is matched, the text message is regard as the text message similar to the displaying live view information;
When the popular text message prestored fails with the displaying live view information match, calculate and the reality
When browse the most like text message of information, using the popular text message as similar to the displaying live view information
Text message;
The text message similar to the displaying live view information is returned to user.
The technical scheme provided by this disclosed embodiment can include the following benefits:
Online data services module, for according to displaying live view information of the user to text message, to user return with it is real-time clear
The similar text message of information of looking at;User's displaying live view behavior collection module, for according to user row of the user to text message
For displaying live view information of the storage user to text message;Off-line data computing module, for prestoring and popular text envelope
Text message as manner of breathing, and in popular text message and displaying live view information match, text message is uploaded to online
Data service module is used as the text message similar to displaying live view information;Online computing module in real time, in off-line data
When the popular text message of computing module storage is failed with displaying live view information match, calculate and displaying live view information most phase
As popular text message, and popular text message is uploaded to online data services module as similar to displaying live view information
Text message.By the above-mentioned system for realizing text message real-time recommendation, the text envelope currently browsed according to user is realized
Breath carries out the recommendation of text message in real time.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary, this can not be limited
It is open.
Brief description of the drawings
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows the implementation for meeting the present invention
Example, and in specification together for explaining principle of the invention.
Fig. 1 is a kind of system and device block diagram for realizing text message real-time recommendation according to an exemplary embodiment;
Fig. 2 is block diagram of user's displaying live view behavior collection module in one embodiment of Fig. 1 correspondence embodiments;
Fig. 3 is block diagram of the off-line data computing module in one embodiment of Fig. 1 correspondence embodiments;
Fig. 4 is block diagram of the online real-time computing module in one embodiment of Fig. 1 correspondence embodiments;
Fig. 5 is a kind of method flow diagram for realizing text message real-time recommendation according to an exemplary embodiment.
Embodiment
Here explanation will be performed to exemplary embodiment in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects be described in detail in claims, the present invention.
Fig. 1 is a kind of system and device block diagram for realizing text message real-time recommendation according to an exemplary embodiment.
As shown in figure 1, this realizes that the system of text message real-time recommendation includes but is not limited to:Online data services module 110, Yong Hushi
When navigation patterns collection module 130, off-line data computing module 150 and online computing module 170 in real time.
Online data services module 110, for according to displaying live view information of the user to text message, to user return with
The similar text message of displaying live view information.
Wherein, text message is the text information that browses of supply user in the device.User is to the real-time clear of text message
Information of looking at is obtained according to user to the user behavior of text message, and the text envelope that user browses is included in displaying live view information
Breath, so that online data services module 110 learns the hobby text message of user according to displaying live view information, realizes and is pushed away to user
Recommend text message.
The text message similar to displaying live view information is the content of text messages text envelope similar to displaying live view information
Breath.Text information is consistent with user to the user behavior of text message, so that online data services module 110 is returned to user
The text message similar to displaying live view information, making the text message of recommendation has ageing and accuracy.
User's displaying live view behavior collection module 130 is connected with online data services module 110.User's displaying live view
Behavior collection module 130 is used for according to user behavior of the user to text message, displaying live view of the storage user to text message
Information.
Wherein, user's displaying live view behavior collection module 130 is connected with online data services module 110.User behavior
It is click of the user to text message, the operation such as browses.When user carries out the user behavior to text message, user is clear in real time
Behavior collection module 130 of looking at obtains the information of user behavior, and user behavior storage is collected to the behavior of user's displaying live view
In module 130, displaying live view information of the user to text message is used as.Online data services module 110 can call user real
When navigation patterns collection module 130 in the displaying live view information that stores as the reference for recommending text message.
Off-line data computing module 150 is connected with online data services module 110, and off-line data computing module 150 is used
In prestoring the text message similar to popular text message, and in popular text message and displaying live view information match
When, text message is uploaded to online data services module 110 as the text message similar to displaying live view information.
Wherein, off-line data computing module 150 is connected with online data services module 110.Popular text message is to go through
History click volume is high or ageing strong text message.Off-line data computing module 150 is pre-stored within popular text envelope manner of breathing
As text message, called according to online data services module 110 real-time clear in user's displaying live view behavior collection module 130
Look at information, compare the displaying live view information text message similar to popular text message, when popular text message and displaying live view
Information is identical, i.e., when popular text message and displaying live view information match, by the similar text message of popular text message
Online data services module 110 is passed to, so as to return to user as the similar text message of displaying live view information.
Online computing module 170 in real time is connected with online data services module 110, and online computing module 170 in real time is used
When the popular text message stored in off-line data computing module 150 fails with displaying live view information match, calculate with
The most like popular text message of displaying live view information, and popular text message is uploaded into online data services module 110 made
For the text message similar to displaying live view information.
Wherein, online computing module 170 in real time is connected with online data services module 110.When off-line data calculates mould
When the text message that block 150 is stored does not upload to online data services module 110, that is, judge that off-line data computing module 150 is deposited
The popular text message of storage fails and displaying live view information match.Now calculate the hot topic most like with displaying live view information
Text message, and the popular text message is uploaded to online data services module 110 as similar to displaying live view information
Text message.
This realizes that the system of text message real-time recommendation first passes through user's displaying live view behavior collection module 130, according to
Family obtains displaying live view information of the user to text message to the user behavior of text message.After obtaining displaying live view information,
Displaying live view information is compared with the popular text message stored in off-line data computing module 150, when popular text message
During with displaying live view information match, then using the popular text message being previously obtained as online data services module 110 to
The text message similar to displaying live view information that family is returned, when popular text message and displaying live view information mismatch, then
Online computing module 170 in real time calculates the popular text message most like with displaying live view information, and by most like hot topic
The text message similar to displaying live view information that text message is returned as online data services module 110 to user.So as to
The system that text message real-time recommendation is realized according to this, realizes the text message currently browsed according to user and carries out text in real time
The recommendation of information.
Carry out the recommendation of text message in real time this embodiment achieves the text message currently browsed according to user.
Fig. 2 is block diagram of user's displaying live view behavior collection module in one embodiment of Fig. 1 correspondence embodiments.Such as Fig. 2
Shown, user's displaying live view behavior collection module 130 includes but is not limited to:User behavior clears up unit 131 and user browses
Data cell 133.
User behavior cleaning unit 131 is used for according to user behavior of the user to text message, obtains user to text envelope
The displaying live view information of breath.
Wherein, user behavior is operation of the user to text message, for example, click on, and the behavior such as browses.User behavior is cleared up
Unit 131 finds User action log of the user to text message, and user is entered from the User action log of all users
The text message of row user behavior, is used as displaying live view information of the user to text message.
User browse data unit 133 is connected with user behavior cleaning unit 131, and user browse data unit 133 is used
In displaying live view information of the storage user to text message.
Wherein, user browse data unit 133 is connected with user behavior cleaning unit 131.User browse data unit
133 get displaying live view information of the user behavior obtained user of cleaning unit 131 to text message.And by the displaying live view
Information is stored into user browse data unit 133, consequently facilitating online data services module 110 obtains user to text message
Displaying live view information.
This embodiment achieves function of the storage user to the displaying live view information of text message.
Fig. 3 is block diagram of the off-line data computing module in one embodiment of Fig. 1 correspondence embodiments.As shown in figure 3, should be from
Line data computation module 150 includes but is not limited to:Corpus of text training unit 151, natural language processing unit 153, similar text
This computing unit 155 and judge uploading unit 157.
Corpus of text training unit 151 is used to choose popular text message in advance.
Wherein, corpus of text training unit 151 is used to popular text message is pre-selected.Popular text message can include
History click volume is high or ageing strong text message.The popular text message of acquisition is via natural language processing unit 153
It is further processed.
Natural language processing unit 153 is connected with corpus of text training unit 151, and natural language processing unit 153 is used
According to the corresponding text mathematic vector of the popular text message of popular text message generation.
Wherein, natural language processing unit 153 is connected with corpus of text training unit 151.Natural language processing unit
153 read the popular text message that corpus of text training unit 151 is obtained, in one embodiment in the specific implementation, utilizing text
Present treatment Open-Source Tools, such as word2vec calculate the term vector of popular text message, while handling the idf values of each word.
Text message paragraph properties such as title, content, comment etc. are marked first during processing hot topic text message, and each paragraph is entered respectively
Row participle obtains the word in text message paragraph, in the word for each word that text message is obtained from the data anticipated
The idf values that vectorial progress processing is multiplied by each word obtain the new vector of single word multiplied by default paragraph weight, by text
The new addition of vectors of each word of information obtains the text mathematic vector of article.
The formula for obtaining text mathematic vector is described as:
Text vector mathematics=word term vector 1+ word term vector 2+ words term vector 3 ... .+ word term vector n, wherein word
Term vector=word2vec term vector * word idf value * paragraph weights.
Similar Text computing unit 155 is connected with natural language processing unit 153, and Similar Text computing unit 155 is used
According to text mathematic vector, find the text message similar to popular text message and stored.
Wherein, Similar Text computing unit 155 is connected with natural language processing unit 153.Similar Text computing unit
The text mathematic vector that the processing of 155 reception nature language processing unit 153 is obtained.In implementing for exemplary embodiment
In, Similar Text computing unit 155 utilizes big data technology, such as map/reduce, using between PC cluster text mathematic vector
Angle.When angle is smaller between text mathematic vector, that is, represent that two text mathematic vectors are more similar.Between calculating text mathematic vector
The cosine value of angle, takes cosine value maximum, the i.e. minimum several text messages of angle and stores.The text message of storage is available in
Line data service module 110 is called.
The data storage of the text message of storage is the id and corresponding Similar Text information id of popular text message, is compared
Textual form storage takes that memory space is smaller economizes on resources.
Judge that uploading unit 157 is connected with Similar Text computing unit 155, judge that uploading unit 157 is used to judge heat
Whether door text message and displaying live view information match, if it has, then the text message similar to popular text message is uploaded
The text message similar to displaying live view information is used as to online data services module 110.
Wherein, judge that uploading unit 157 is connected with Similar Text computing unit 155, judge that uploading unit 157 obtains phase
Like the text message id stored in text computing unit 155.Judge hot topic text message id and displaying live view information id whether phase
Together, i.e., whether match, if result is yes, using the text message similar to popular text message as with displaying live view information
Similar text message, uploads to online data services module 110
This embodiment achieves upload and the history text message that to browse information similar.
In one exemplary embodiment, online data services module 110 is further used for:
According to the popular degree of the text message similar to popular text message, determine that the display of text message puts in order.
Wherein, the number of times of text message is collected according to clicking rate and user, the popular degree of text message is judged.According to text
The popular degree of this information, determines that the display of text message puts in order, so as to ensure that user browses to popular degree most first
High text message, it is ensured that the accuracy that text message is recommended.
This embodiment achieves the popular degree according to text message, determine that the display of text message puts in order, it is ensured that
The function for the accuracy that text message is recommended.
Fig. 4 is block diagram of the online real-time computing module in one embodiment of Fig. 1 correspondence embodiments.As shown in figure 4, being somebody's turn to do
The real-time computing module 170 of line includes but is not limited to:Computing unit 171 and uploading unit 173.
Computing unit 171 is used for the text for calculating the corresponding text mathematics vector sum displaying live view information of popular text message
The similarity of mathematic vector.
Wherein, computing unit 171 gets the corresponding text preface vector of popular text message.Calculate popular text message
The cosine value of angle between the text mathematic vector of corresponding text mathematics vector sum displaying live view information, so as to obtain text mathematics
Similarity between vector.The cosine value of angle is bigger, i.e., angle is smaller, and similarity is higher.
Uploading unit 173 is connected with computing unit 171, and uploading unit 173 is used for the maximum popular text of similarity
Information uploads to online data services module 110 as the text message similar to displaying live view information.
Wherein, uploading unit 173 is used for the maximum heat of the cosine value of angle between similarity highest, i.e. text mathematic vector
Door text message uploads to online data services module 110 as the text message similar to displaying live view information.
This embodiment is realized when popular text message fails with displaying live view information match, is obtained and is believed with displaying live view
Text message as manner of breathing.
In one exemplary embodiment, natural language processing unit 153 is further used for:
The text mathematic vector of displaying live view information is calculated, and the text mathematic vector of displaying live view information is uploaded in line number
According to service module 110.
Wherein, natural language processing unit 153 calculates the text mathematic vector of the displaying live view information of storage, and will be real
When browse the text mathematic vector of information and be uploaded to online data services module 110 so that computing unit 171 can obtain reality
When browse the text mathematic vector of information.
This embodiment achieves calculate the text mathematic vector of displaying live view information.
In one exemplary embodiment, computing unit 171 is further used for:
The text mathematic vector of displaying live view information is read from online data services module 110.
Wherein, the natural language processing unit 153 that the reading online data services of computing unit 171 module 110 is obtained is calculated
The text mathematic vector of the displaying live view information gone out, so as to realize that the corresponding text mathematics vector sum of the popular text message of calculating is real
When browse information text mathematic vector similarity.
This embodiment achieves the text mathematic vector that computing unit obtains displaying live view information.
Fig. 5 is a kind of method flow diagram for realizing text message real-time recommendation according to an exemplary embodiment.Such as
Shown in Fig. 5, this realizes that the method for text message real-time recommendation may comprise steps of.
In step 210, according to user behavior of the user to text message, displaying live view of the storage user to text message
Information.
In step 230, the text message similar to popular text message is prestored, and in popular text message and reality
When browsing information match, regard text message as the text message similar to displaying live view information.
In step 250, when the popular text message prestored fails with displaying live view information match, calculate
The most like text message with displaying live view information, regard popular text message as the text envelope similar to displaying live view information
Breath.
In step 270, the text message similar to displaying live view information is returned to user.
It should be appreciated that the invention is not limited in the precision architecture for being described above and being shown in the drawings, and
And various modifications and changes can be being performed without departing from the scope.The scope of the present invention is only limited by appended claim.
Claims (8)
1. a kind of system for realizing text message real-time recommendation, it is characterised in that the system includes:
Online data services module, for according to displaying live view information of the user to text message, being returned and the reality to user
When browse the similar text message of information;
User's displaying live view behavior collection module, it is connected with the online data services module, user's displaying live view
Behavior collection module is used for according to user behavior of the user to text message, and storage user is believed the displaying live view of text message
Breath;
Off-line data computing module, it is connected with the online data services module, and the off-line data computing module is used for
The text message similar to popular text message is prestored, and in the popular text message and the displaying live view information phase
During matching, the text message is uploaded to the online data services module as the text similar to the displaying live view information
This information;
Online computing module in real time, it is connected with the online data services module, and the online computing module in real time is used for
When the popular text message stored in the off-line data computing module fails with the displaying live view information match, meter
Calculate the popular text message most like with the displaying live view information, and the popular text message uploaded to described
Online data services module is used as the text message similar to the displaying live view information.
2. system according to claim 1, it is characterised in that user's displaying live view behavior collection module includes:
User behavior clears up unit, for according to user behavior of the user to text message, obtaining reality of the user to text message
When browse information;
User browse data unit, it is connected with user behavior cleaning unit, and the user browse data unit is used for
Store displaying live view information of the user to text message.
3. system according to claim 1, it is characterised in that the off-line data computing module includes:
Corpus of text training unit, for choosing popular text message in advance;
Natural language processing unit, it is connected with the corpus of text training unit, and the natural language processing unit is used for
The corresponding text mathematic vector of the popular text message is generated according to the popular text message;
Similar Text computing unit, it is connected with the natural language processing unit, and the Similar Text computing unit is used for
According to the text mathematic vector, find the text message similar to the popular text message and stored;
Judge uploading unit, it is connected with the Similar Text computing unit, the judgement uploading unit is used to judge described
Whether popular text message and the displaying live view information match, if it has, then by the text similar to the popular text message
This information uploads to the online data services module as the text message similar to the displaying live view information.
4. system according to claim 3, it is characterised in that the online data services module is further used for:
According to the popular degree of the text message similar to the popular text message, the display arrangement of the text message is determined
Sequentially.
5. system according to claim 1, it is characterised in that the online computing module in real time includes:
Computing unit, the text for calculating displaying live view information described in the corresponding text mathematics vector sum of the popular text message
The similarity of this mathematic vector;
Uploading unit, it is connected with the computing unit, and the uploading unit is used for the maximum hot topic text of the similarity
This information uploads to the online data services module as the text message similar to the displaying live view information.
6. system according to claim 5, it is characterised in that the natural language processing unit is further used for:
The text mathematic vector of the displaying live view information is calculated, and the text mathematic vector of the displaying live view information is uploaded
To the online data services module.
7. system according to claim 6, it is characterised in that the computing unit is further used for:
The text mathematic vector of the displaying live view information is read from the online data services module.
8. a kind of method for realizing text message real-time recommendation, it is characterised in that methods described includes:
According to user behavior of the user to text message, displaying live view information of the storage user to text message;
The text message similar to popular text message is prestored, and is believed in the popular text message and the displaying live view
When manner of breathing is matched, the text message is regard as the text message similar to the displaying live view information;
When the popular text message prestored fails with the displaying live view information match, calculate and the reality
When browse the most like text message of information, using the popular text message as similar to the displaying live view information
Text message;
The text message similar to the displaying live view information is returned to user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710413824.5A CN107239545A (en) | 2017-06-05 | 2017-06-05 | Realize the system and method for text message real-time recommendation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710413824.5A CN107239545A (en) | 2017-06-05 | 2017-06-05 | Realize the system and method for text message real-time recommendation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107239545A true CN107239545A (en) | 2017-10-10 |
Family
ID=59984858
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710413824.5A Pending CN107239545A (en) | 2017-06-05 | 2017-06-05 | Realize the system and method for text message real-time recommendation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107239545A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108416006A (en) * | 2018-02-28 | 2018-08-17 | 百度在线网络技术(北京)有限公司 | Information off-line recommends method, apparatus, client, server and storage medium |
CN113627559A (en) * | 2021-08-19 | 2021-11-09 | 腾讯音乐娱乐科技(深圳)有限公司 | Potential money-exploding song mining method, device, equipment and medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术(北京)有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
CN102708174A (en) * | 2012-05-04 | 2012-10-03 | 奇智软件(北京)有限公司 | Method and device for displaying rich media information in browser |
CN103198120A (en) * | 2013-04-02 | 2013-07-10 | 百度在线网络技术(北京)有限公司 | Webpage presenting method and device and webpage content providing method and system |
CN103678647A (en) * | 2013-12-20 | 2014-03-26 | Tcl集团股份有限公司 | Method and system for recommending information |
CN104778271A (en) * | 2015-04-24 | 2015-07-15 | 无锡天脉聚源传媒科技有限公司 | Video data caching method and device |
CN105138541A (en) * | 2015-07-08 | 2015-12-09 | 腾讯科技(深圳)有限公司 | Audio fingerprint matching query method and device |
CN106294595A (en) * | 2016-07-29 | 2017-01-04 | 海尔优家智能科技(北京)有限公司 | A kind of document storage, search method and device |
-
2017
- 2017-06-05 CN CN201710413824.5A patent/CN107239545A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术(北京)有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
CN102708174A (en) * | 2012-05-04 | 2012-10-03 | 奇智软件(北京)有限公司 | Method and device for displaying rich media information in browser |
CN103198120A (en) * | 2013-04-02 | 2013-07-10 | 百度在线网络技术(北京)有限公司 | Webpage presenting method and device and webpage content providing method and system |
CN103678647A (en) * | 2013-12-20 | 2014-03-26 | Tcl集团股份有限公司 | Method and system for recommending information |
CN104778271A (en) * | 2015-04-24 | 2015-07-15 | 无锡天脉聚源传媒科技有限公司 | Video data caching method and device |
CN105138541A (en) * | 2015-07-08 | 2015-12-09 | 腾讯科技(深圳)有限公司 | Audio fingerprint matching query method and device |
CN106294595A (en) * | 2016-07-29 | 2017-01-04 | 海尔优家智能科技(北京)有限公司 | A kind of document storage, search method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108416006A (en) * | 2018-02-28 | 2018-08-17 | 百度在线网络技术(北京)有限公司 | Information off-line recommends method, apparatus, client, server and storage medium |
CN113627559A (en) * | 2021-08-19 | 2021-11-09 | 腾讯音乐娱乐科技(深圳)有限公司 | Potential money-exploding song mining method, device, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110046304B (en) | User recommendation method and device | |
CN109299994B (en) | Recommendation method, device, equipment and readable storage medium | |
CN112214685A (en) | Knowledge graph-based personalized recommendation method | |
Rahmatullah Imon | Identifying multiple influential observations in linear regression | |
CN107492008A (en) | Information recommendation method, device, server and computer-readable storage medium | |
CN108182621A (en) | The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium | |
CN104731861B (en) | Multi-medium data method for pushing and device | |
CN106599226A (en) | Content recommendation method and content recommendation system | |
Paquet et al. | A hierarchical model for ordinal matrix factorization | |
CN105512180B (en) | A kind of search recommended method and device | |
CN112966091B (en) | Knowledge map recommendation system fusing entity information and heat | |
CN109472305A (en) | Answer quality determines model training method, answer quality determination method and device | |
CN111008336A (en) | Content recommendation method, device and equipment and readable storage medium | |
CN109993583A (en) | Information-pushing method and device, storage medium and electronic device | |
CN109903127A (en) | Group recommendation method and device, storage medium and server | |
CN106411683B (en) | A kind of determination method and device of key social information | |
CN111984824A (en) | Multi-mode-based video recommendation method | |
CN110489574A (en) | A kind of multimedia messages recommended method, device and relevant device | |
CN112116426A (en) | Method and device for pushing article information | |
CN103020221A (en) | Social search method based on multi-mode self-adaptive social relation strength excavation | |
CN104572915B (en) | One kind is based on the enhanced customer incident relatedness computation method of content environment | |
CN112597389A (en) | Control method and device for realizing article recommendation based on user behavior | |
CN107239545A (en) | Realize the system and method for text message real-time recommendation | |
CN108268519A (en) | A kind of method and apparatus of recommendation network object | |
Umaashankar et al. | Atlas: A dataset and benchmark for e-commerce clothing product categorization |
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 | ||
CB02 | Change of applicant information |
Address after: 361000 Area 1F-D1, Huaxun Building A, Software Park, Xiamen Torch High-tech Zone, Xiamen City, Fujian Province Applicant after: Xiamen Meishao Co., Ltd. Address before: Unit G03, Room 102, 22 Guanri Road, Phase II, Xiamen Software Park, Fujian Province Applicant before: XIAMEN MEIYOU INFORMATION SCIENCE & TECHNOLOGY Co.,Ltd. |
|
CB02 | Change of applicant information | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171010 |
|
RJ01 | Rejection of invention patent application after publication |