CN104424210B - A kind of information recommendation method, system and server - Google Patents
A kind of information recommendation method, system and server Download PDFInfo
- Publication number
- CN104424210B CN104424210B CN201310369757.3A CN201310369757A CN104424210B CN 104424210 B CN104424210 B CN 104424210B CN 201310369757 A CN201310369757 A CN 201310369757A CN 104424210 B CN104424210 B CN 104424210B
- Authority
- CN
- China
- Prior art keywords
- information
- recommendation
- list
- data
- user
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
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 Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of information recommendation system, the system includes：Service Processing Unit, relational database and KV databases；The Service Processing Unit, for the historical operating data of described information to be sent to relational database and KV databases in real time；When being additionally operable to receive information recommendation request, the status data of described information is read from the relational database, the historical operating data of described information is read from the KV databases, the recommendation list of described information is calculated according to the historical operating data of described information, the status data of described information and user profile, and returns to the recommendation list；The relational database, for calculating status data according to the historical operating data of described information；The KV databases, for storing the historical operating data of described information.The present invention also discloses a kind of information recommendation method.Using the solution of the present invention, the susceptibility of information recommendation is substantially increased, improves the experience of user.
Description
Technical Field
The invention relates to the Internet technology, in particular to an information recommendation method, an information recommendation system and a server.
Background
With the development of internet applications, the system can recommend information which may be interesting to the user, such as songs, videos or commodities which may be interesting to the user, according to the historical operating records of the user. The current information recommendation service uses a way of calculating an information recommendation list offline: the recommendation system calculates an information recommendation list which may be interested by a user at a fixed time every day according to the total historical operation records of the last three months of the user, fig. 1 is a schematic diagram of a composition structure of the information recommendation system in the prior art, as shown in fig. 1, the information recommendation system in the prior art comprises a client 11, a service system 12 and a relational database 13; based on the existing information system, the recommendation method comprises the following steps:
the client 11 requests the service system 12 for the recommended information, and the service system 12 returns the information recommendation list to the client 11 in response to the recommendation request of the client 11.
Correspondingly, the information historical operation data is reported to the service system 12 in real time, and is imported to the relational database 13 once a day from the service system 12. For example: the client 11 requests to recommend songs, and the service system 12 reports song playing record data of the client 11 to the relational database, and imports relevant information of songs in the playing records, such as information of singers of the songs, genres of the songs, and the like.
The relational database 13 calculates an information recommendation list once a day according to the historical operation data of the information, and imports the information recommendation list into the service system 12 so as to recommend the information recommendation list to the client 11 when the client 11 requests the information recommendation list.
The existing information recommendation method has the following disadvantages:
in the conventional information recommendation process, a general way for the business system 12 to import the information history operation data into the relational database 13 once a day is to report the information history operation records of all users on the previous day every day, which is limited by the performance of the relational database 13, the data reporting process generally takes 2 hours, the relational database 13 calculates an information recommendation list interested by the users, which generally takes 15 hours, and the information recommendation list is imported into the business system 12, which generally takes 3 hours, so that the process of recommending information once may take more than one day, that is, the information requested to be recommended by the users on the current day is likely to be the information interested two days ago, which may result in reduction in recommendation sensitivity. If the relational database fails, the calculation result derivation for a certain day fails, so that the recommendation result seen by the user today is the same as that seen by the user yesterday, and the experience of the user is affected. And each time the recommendation algorithm is updated, the verification period of the effect is long.
In addition, the number of information is limited by the current information recommendation list, at most one hundred information can be recommended every day, and if the number of times of requesting recommendation by the user on the day is too many and all the information in the information recommendation list is already recommended, the information in the information recommendation list can be recommended again, so that the user sees repeated information and the user experience is influenced.
Disclosure of Invention
In view of this, the main objective of the present invention is to provide an information recommendation method, system and server, which can calculate information that a user is interested in real time and return the information to a user recommendation list, thereby improving user experience.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the invention provides an information recommendation system, which comprises: a business processing unit, a relational database and a Key-Value (KV, Key-Value) database; wherein,
the business processing unit is used for sending the historical operation data of the information to the relational database and the KV database in real time; the information recommendation system is also used for reading the state data of the information from the relational database, reading the historical operation data of the information from the KV database, calculating a recommendation list of the information according to the historical operation data of the information, the state data of the information and the user information and returning the recommendation list when receiving an information recommendation request;
the relational database is used for calculating state data according to historical operation data of the information;
and the KV database is used for storing historical operation data of the information.
In the above solution, the system further includes a user information base for storing user information, where the user information includes at least one of: the age of the user, the gender of the user, the location of the user, the occupation of the user, and the hobbies and interests of the user.
In the above solution, the service processing unit includes: the system comprises a business system module, an operation processing module, a state data management module and a real-time recommendation module; wherein,
the business system module is used for sending the historical operation data of the information to the operation processing module; the real-time recommendation module is also used for returning the recommendation list of the information sent by the real-time recommendation module to the client;
the operation processing module is used for respectively sending the historical operation data of the information sent by the service system module to a relational database and a KV database;
the state data management module is used for acquiring the state data of the information from the relational database and sending the state data to the real-time recommendation module;
and the real-time recommendation module is used for reading the historical operation data of the information from the KV database when receiving an information recommendation request, calculating a recommendation list of the information according to the historical operation data, the state data sent by the state data management module and the user information read from the user information base, and returning the recommendation list of the information to the service system module.
In the above scheme, the calculating, by the real-time recommendation module, a recommendation list of the information according to the historical operation data, the status data sent by the status data management module, and the user information read from the user information base includes:
performing scoring operation on the information in the historical operation data according to the operation attenuation coefficient/weight table to obtain a score list of the operation information;
associating the score list of the operation information with the information similarity to obtain a first process list of the recommendation list;
acquiring the associated information of the user according to the user attribute information, adding the associated information to the first process list, and acquiring a second process list of the recommendation list;
and associating the second process list with the information attribute information to obtain a recommendation list of the information.
In the above scheme, the information recommendation system further comprises an effect display module;
the relational database is also used for calculating the recommendation effect data of the information according to the historical operation data of the information and sending the effect data to an effect display module;
and the effect display module is used for receiving the effect data sent by the relational database and displaying the effect data when receiving the effect viewing request.
The invention also provides an information recommendation method, which comprises the following steps:
sending historical operation data of the information to a relational database and a KV database in real time;
when an information recommendation request is received, reading state data of the information from the relational database, and reading historical data of the information from the KV database; the state data of the information is obtained by the relational database through calculation according to the historical operation data of the information;
and calculating a recommendation list of the information according to the historical operation data of the information, the state data of the information and the user information, and returning to the recommendation list.
In the foregoing solution, the status data includes: the attenuation coefficient/weight table, information similarity and information attribute information are manipulated.
In the above solution, the calculating a recommendation list of the information according to the historical operation data of the information, the state data of the information, and the user information includes:
performing scoring operation on the information in the historical operation data according to the operation attenuation coefficient/weight table to obtain a score list of the operation information;
associating the score list of the operation information with the information similarity to obtain a first process list of the recommendation list;
acquiring the associated information of the user according to the user attribute information, adding the associated information to the first process list, and acquiring a second process list of the recommendation list;
and associating the second process list with the information attribute information to obtain a recommendation list of the information.
In the above scheme, the method further comprises:
and the relational database calculates the recommendation effect data of the information according to the historical operation data of the information, and displays the effect data when receiving an effect viewing request.
In the foregoing solution, the recommendation effect data includes: and the operation integrity of the user on the information in the recommendation list.
According to the information recommendation method, the system and the server, the service processing unit sends the historical operation data of the information to the relational database and the KV database in real time; when an information recommendation request is received, calculating a recommendation list of the information according to the state data calculated by the relational database, the historical operation data of the information read from the KV database and the user information, and returning the recommendation list; therefore, the recommendation list can be calculated in real time, and information which is possibly interested by the user can be returned in real time, so that the recommendation sensitivity is greatly improved, and the user experience is improved; by summarizing the historical operation data to the relational database in real time, the data summarizing efficiency is effectively improved, the relational database can quickly calculate the recommendation effect and immediately reflect whether the recommendation algorithm is effective or not, so that the recommendation algorithm is immediately improved, and the algorithm optimization efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of a component structure of an information recommendation system in the prior art;
FIG. 2 is a schematic diagram of a configuration of an information recommendation system according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an information recommendation method according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a calculation method of a recommendation list according to an embodiment of the present invention.
Detailed Description
The basic idea of the invention is: the method comprises the steps of calculating a recommendation list of information in real time after receiving an information recommendation request of a client, separately managing historical operation data and state data, storing the historical operation data in a KV database through reading operation more quickly, storing the state data in a relational database, respectively reading the historical operation data from the KV database when the recommendation list needs to be calculated, reading the state data from the relational database, and calculating the recommendation list according to the historical operation data, the state data and user information.
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Fig. 2 is a schematic diagram of a composition structure of an information recommendation system according to an embodiment of the present invention, and as shown in fig. 2, the information recommendation system mainly includes: a service processing unit 21, a relational database 22 and a KV database 23; wherein,
the service processing unit 21 is configured to send historical operation data of the information to the relational database 22 and the KV database 23 in real time; the information recommendation system is further configured to, when an information recommendation request is received, read the state data of the information from the relational database 22, read the historical operation data of the information from the KV database 23, calculate a recommendation list of the information according to the historical operation data of the information, the state data of the information, and the user information, and return the recommendation list;
the relational database 22 is used for calculating state data according to historical operation data of the information;
the KV database 23 is used for storing historical operation data of the information.
Preferably, the system further comprises a user information repository 24 for storing user information, the user information comprising at least one of: the age, sex, province of the user, occupation of the user, hobbies of the user, and the like.
Preferably, the service processing unit 21 includes: a business system module 211, an operation processing module 212, a state data management module 213 and a real-time recommendation module 214; wherein,
the business system module 211 is configured to send historical operation data of the information to the operation processing module 212; the real-time recommendation module 214 is further configured to return a recommendation list of the information sent by the real-time recommendation module 214 to the client;
the operation processing module 212 is configured to send the historical operation data of the information sent by the service system module 211 to the relational database 22 and the KV database 23, respectively;
the status data management module 213 is configured to obtain status data of the information from the relational database 22, and send the status data to the real-time recommendation module 214;
the real-time recommendation module 214 is configured to, when receiving an information recommendation request, read historical operation data of the information from the KV database 23, calculate a recommendation list of the information according to the historical operation data, the state data sent by the state data management module 213, and the user information read from the user information base 24, and return the recommendation list of the information to the service system module 211.
Preferably, the information recommendation system further comprises an effect display module 25,
the relational database 22 is further configured to calculate recommended effect data of the information according to the historical operation data of the information, and send the effect data to the effect display module 25;
the effect display module 25 is configured to receive the effect data sent by the relational database 22, and display the effect data when receiving the effect viewing request.
In practical application, the service Processing Unit 21 of the information recommendation system may be implemented by a Central Processing Unit (CPU), a Digital Signal Processor (DSP), or a Programmable Gate Array (FPGA); the KV database 23 and the user information database 24 of the information recommendation system can be realized by a memory in the system in practical application; in practical application, the data processing function of the relational database 22 of the information recommendation system can be realized by a CPU, or a DSP, or an FPGA in the system, and the storage function can be realized by a memory; the effect display module 25 of the information recommendation system can be implemented by a display in practical application.
The embodiment of the invention also provides a server, and the server comprises the information recommendation system provided by the embodiment of the invention.
Based on the information recommendation system, an embodiment of the present invention provides an information recommendation method, as shown in fig. 3, fig. 3 is a schematic flow diagram of the information recommendation method according to the embodiment of the present invention, and the method includes the following steps:
step 301: and sending the historical operation data of the information to a relational database in real time.
And the relational database calculates the state data of the information according to the historical operation data of the information. Here, the state data includes: the attenuation coefficient/weight table, information similarity and information attribute information are manipulated.
Specifically, the relational database may set the attenuation coefficient/weight table according to the generation time of data in the historical operation data and the preference of the user, where the earlier the data generation time is, the lower the coefficient/weight value is, and otherwise, the higher the coefficient/weight value is; the more the number of information operations, the higher the coefficient/weight value, otherwise, the lower the coefficient/weight value; the information similarity is a decimal number larger than zero and smaller than one, and is closer to 1, the numerical value of the information similarity can be obtained according to a label preset for the information, the label is set for the information according to the attribute information of the information, and the more the same labels are, the more similar the information is, taking music as an example, the label is set for the music according to the attribute information of the music, for example, the label is set as: 85-95, piano, lyric, etc.; the information attribute information may be obtained according to the historical operation data of the user, for example, obtaining the like and dislike information attributes of the user according to the historical operation data of the user, taking recommended music as an example, and the information attribute information may include attribute information such as genre of music, language of music, and singer of music.
Step 302 to step 303: and when an information recommendation request is received, reading the state data of the information from the relational database, reading the historical data of the information from the KV database, calculating a recommendation list of the information according to the state data of the information, the historical operation data of the information and the user information, and returning the recommendation list.
Preferably, the calculating a recommendation list of information according to state data of the information, historical operation data of the information, and user information includes:
performing scoring operation on the information in the historical operation data according to the operation attenuation coefficient/weight table to obtain a score list of the operation information;
associating the score list of the operation information with the information similarity to obtain a first process list of the recommendation list;
acquiring the associated information of the user according to the user attribute information, adding the associated information to the first process list, and acquiring a second process list of the recommendation list;
and associating the second process list with the information attribute information to obtain a recommendation list of the information.
The following describes in further detail the implementation flow of the information recommendation method according to the embodiment of the present invention by taking an example of a user requesting to recommend a song.
A user logs in a client through a computer or a mobile phone, for example, a QQ music client is logged in, the business system module sends historical operation data of the user to the operation processing module in real time, wherein the historical operation data comprises listened music, searched music and the like, and the operation processing module sends the historical operation data to the relational database and the KV database respectively;
the relational database calculates state data according to the historical operation data and preset rules, and specifically, the state data includes: the attenuation coefficient/weight table, information similarity and information attribute information, etc. are manipulated. The relational database can set the attenuation coefficient/weight table according to the generation time of data in the historical operation data and the preference of a user, wherein the earlier the data generation time is, the lower the coefficient/weight value is, otherwise, the higher the coefficient/weight value is; the more the same music is listened to or searched, the higher the coefficient/weight value is, otherwise, the lower the coefficient/weight value is; the information similarity is a decimal number larger than zero and smaller than one, and is closer to 1, the numerical value of the information similarity can be obtained according to a label preset for the information, the label is set for the information according to the attribute information of the information, and the more the same labels are, the more similar the information is, taking music as an example, the label is set for the music according to the attribute information of the music, for example, the label is set as: 85-95, piano, lyric, etc.; the information attribute information may be obtained according to the historical operation data of the user, for example, the like and dislike information attributes of the user, including attribute information of a genre of music, a language of the music, a singer of the music, and the like, may be obtained according to the historical operation data of the user.
The KV database stores historical operation data of all users;
when a user logs in a client to request for recommending music, the client sends a music recommendation request of the user to a service system module, and a real-time recommendation module calculates a music recommendation list of the user; the state data management module reads the state data of the user from the relational database, wherein the state data comprise an operation attenuation coefficient/weight table, information similarity, information attribute information and the like, and the state data are sent to the real-time recommendation module; and the real-time recommendation module reads the historical operation data of the user from the KV database and calculates a recommendation list according to the historical operation data, the state data and the user information of the user. Specifically, fig. 4 is a schematic diagram of a calculation method of a recommendation list according to an embodiment of the present invention, as shown in fig. 4, including the following steps:
the real-time recommendation module scores songs in the historical operation data according to the operation attenuation coefficient/weight table to obtain a score list of the operation songs; associating the score list of the operation songs with information similarity to obtain a recommendation list 1;
if the recommendation list 1 is empty or the number of songs in the recommendation list 1 is small, acquiring songs that the user may like according to the user attribute information, for example, retrieving other users similar to the current user according to information such as the age of the user, the occupation of the user, the location of the user, and the like, and adding the songs that the other users like to the recommendation list of the current user to obtain a recommendation list 2;
associating the recommendation list 2 with information attribute information, the information attribute information including song attribute information disliked by the current user, including: the genre of music, the language of the music, the singer of the music and other attribute information, if the current user does not like the music of a singer, the music of the singer is deleted from the recommendation list 2; in addition, the music which has been recently operated by the current user is deleted at the same time, so that new music can be recommended to the user; after deleting corresponding music, obtaining a recommendation list 3;
and associating the recommendation list 3 with information attribute information 2, wherein the information attribute information is the same as the information attribute information in the previous step, and the purpose is to perform adjustment operation on the music in the recommendation list 3, adjust at least ten pieces of continuous music in the recommendation list 3 without music of the same singer, and obtain a final recommendation list after the corresponding adjustment operation is finished.
And after the real-time recommendation module calculates and obtains a final recommendation list, returning the recommendation list to the service system module, and timely returning the recommendation list to the client through the service system module.
Preferably, the step further comprises: and the relational database calculates the recommendation effect data of the information according to the historical operation data of the information, and displays the effect data when receiving an effect viewing request.
Preferably, the recommendation effect data includes: and the operation integrity of the user on the information in the recommendation list.
Here, the recommendation effect data may include various data, and the operation integrity of the information in the recommendation list may be, for example, a full listening ratio, an average listening time length, an average listening number, 60% of listening music, 30% of listening music, and the like of the user to music in the music recommendation list; taking a recommended video as an example, the information operation integrity in the recommended list may be data such as the complete watching proportion, the average watching duration, the average watching number, and the like of the video in the video recommended list by the user; from these data, it can be seen whether the recommended information is liked by the user, which can reflect whether the current recommendation algorithm is valid.
Specifically, in a period of time, the relational database calculates recommended effect data of music according to the received historical operation data, sends the effect data to the effect display module, and displays the effect data when maintenance personnel check the effect data. The recommendation effect data is specifically reflected as recommendation effect data of the current recommendation algorithm, such as the complete listening proportion, the average listening duration, the average listening number and the like of the user on the music recommendation page, and from the recommendation effect data, whether the recommended music is liked by the user can be seen, so that whether the current recommendation algorithm is effective can be reflected.
Table 1 is a list of recommended effects obtained by actual calculation, and as shown in table 1, the large disc of the player indicates all song listening behaviors at the QQ music client; the real-time associated recommendation represents feedback for recommended music under the condition that the user has operation history; real-time property recommendations represent feedback to a user about recommended music without historical operational data. It can be seen from table 1 that the indexes of the ratio of completely listening to songs, the ratio of 60% of listening to songs, the ratio of 30% of listening to songs, the average listening duration, the average listening characteristics, etc. can all reflect whether the user likes the recommended music, and the larger the number is, the more the user likes.
TABLE 1
The information recommendation method of the embodiment of the invention can be stored in a computer readable storage medium if the information recommendation method is realized in the form of a software functional module and sold or used as an independent product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. Thus, embodiments of the invention are not limited to any specific combination of hardware and software.
Correspondingly, the embodiment of the invention also provides a computer storage medium, wherein a computer program is stored, and the computer program is used for executing the information recommendation method of the embodiment of the invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present invention are included in the protection scope of the present invention.
Claims (8)
1. An information recommendation system, the system comprising: a service processing unit, a relational database and a key-value (KV) database; wherein,
the business processing unit is used for sending the historical operation data of the information to the relational database and the KV database in real time; the information recommendation system is also used for reading the state data of the information from the relational database, reading the historical operation data of the information from the KV database, calculating a recommendation list of the information according to the historical operation data of the information, the state data of the information and the user information and returning the recommendation list when receiving an information recommendation request;
the relational database is used for calculating state data according to historical operation data of the information;
the KV database is used for storing historical operation data of the information;
the service processing unit is used for reading historical operation data of the information from the KV database when receiving an information recommendation request, and performing scoring operation on the information in the historical operation data according to the operation attenuation coefficient/weight table to obtain a score list of the operation information; associating the score list of the operation information with the information similarity to obtain a first process list of the recommendation list; acquiring the associated information of the user according to the user attribute information, adding the associated information to the first process list, and acquiring a second process list of the recommendation list; and associating the second process list with the information attribute information, obtaining a recommendation list of the information, and returning the recommendation list.
2. The information recommendation system according to claim 1, further comprising a user information repository for storing user information, the user information comprising at least one of: the age of the user, the gender of the user, the location of the user, the occupation of the user, and the hobbies and interests of the user.
3. The information recommendation system according to claim 1, wherein said service processing unit comprises: the system comprises a business system module, an operation processing module, a state data management module and a real-time recommendation module; wherein,
the business system module is used for sending the historical operation data of the information to the operation processing module; the real-time recommendation module is also used for returning the recommendation list of the information sent by the real-time recommendation module to the client;
the operation processing module is used for respectively sending the historical operation data of the information sent by the service system module to a relational database and a KV database;
the state data management module is used for acquiring the state data of the information from the relational database and sending the state data to the real-time recommendation module;
the real-time recommendation module is used for reading historical operation data of the information from the KV database when an information recommendation request is received, and performing scoring operation on the information in the historical operation data according to the operation attenuation coefficient/weight table to obtain a score list of the operation information; associating the score list of the operation information with the information similarity to obtain a first process list of the recommendation list; acquiring the associated information of the user according to the user attribute information, adding the associated information to the first process list, and acquiring a second process list of the recommendation list; and associating the second process list with the information attribute information, obtaining a recommendation list of the information, and returning the recommendation list to the service system module.
4. The information recommendation system according to claim 1, further comprising an effect display module;
the relational database is also used for calculating the recommendation effect data of the information according to the historical operation data of the information and sending the effect data to an effect display module;
and the effect display module is used for receiving the effect data sent by the relational database and displaying the effect data when receiving the effect viewing request.
5. An information recommendation method, characterized in that the method comprises:
sending historical operation data of the information to a relational database and a key-value (KV) database in real time;
when an information recommendation request is received, reading state data of the information from the relational database, and reading historical data of the information from the KV database; the state data of the information is obtained by the relational database through calculation according to the historical operation data of the information;
calculating a recommendation list of the information according to the historical operation data of the information, the state data of the information and the user information, and returning to the recommendation list;
wherein the calculating a recommendation list of the information according to the historical operation data of the information, the state data of the information and the user information comprises: performing scoring operation on the information in the historical operation data according to the operation attenuation coefficient/weight table to obtain a score list of the operation information;
associating the score list of the operation information with the information similarity to obtain a first process list of the recommendation list;
acquiring the associated information of the user according to the user attribute information, adding the associated information to the first process list, and acquiring a second process list of the recommendation list;
and associating the second process list with the information attribute information to obtain a recommendation list of the information.
6. The information recommendation method of claim 5, wherein the status data comprises: the attenuation coefficient/weight table, information similarity and information attribute information are manipulated.
7. The method of claim 5, further comprising:
calculating recommended effect data of the information according to historical operation data of the information, and displaying the effect data when an effect viewing request is received; and the recommendation effect data is obtained by the relational database through calculation according to the historical operation data of the information.
8. The information recommendation method according to claim 7, wherein the recommendation effect data includes: and the operation integrity of the user on the information in the recommendation list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310369757.3A CN104424210B (en) | 2013-08-22 | 2013-08-22 | A kind of information recommendation method, system and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310369757.3A CN104424210B (en) | 2013-08-22 | 2013-08-22 | A kind of information recommendation method, system and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104424210A CN104424210A (en) | 2015-03-18 |
| CN104424210B true CN104424210B (en) | 2017-11-14 |
Family
ID=52973209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310369757.3A Active CN104424210B (en) | 2013-08-22 | 2013-08-22 | A kind of information recommendation method, system and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104424210B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708829B (en) * | 2015-07-31 | 2022-05-10 | 腾讯科技（深圳）有限公司 | Data recommendation method and recommendation system |
| CN105512934A (en) * | 2015-10-22 | 2016-04-20 | 深圳怡化电脑股份有限公司 | Method and device for inputting business parameters |
| CN106803178B (en) * | 2015-11-26 | 2020-09-18 | 阿里巴巴集团控股有限公司 | Method and equipment for processing entity |
| CN106844359A (en) * | 2015-12-04 | 2017-06-13 | 深圳富泰宏精密工业有限公司 | Server and its music service system and method |
| CN105959374B (en) | 2016-05-12 | 2019-05-03 | 腾讯科技（深圳）有限公司 | A data recommendation method and device thereof |
| CN107451141B (en) * | 2016-05-30 | 2021-01-29 | 阿里巴巴集团控股有限公司 | Data recommendation processing interaction method, device and system |
| CN106210127B (en) * | 2016-08-15 | 2019-07-16 | 腾讯科技（深圳）有限公司 | A kind of information processing method, server and client |
| CN107180086A (en) * | 2017-05-09 | 2017-09-19 | 中国石油集团川庆钻探工程有限公司 | Method for rapidly storing and publishing drilling real-time data |
| CN108076353A (en) * | 2017-05-18 | 2018-05-25 | 北京市商汤科技开发有限公司 | Business object recommends method, apparatus, storage medium and electronic equipment |
| CN107547740A (en) * | 2017-08-28 | 2018-01-05 | 江西博瑞彤芸科技有限公司 | The management method and system of station list |
| CN110019925A (en) * | 2017-12-07 | 2019-07-16 | 北京雷客天地科技有限公司 | Batch deletes the method and device of song |
| CN111291018B (en) * | 2018-12-07 | 2023-06-23 | 北京沃东天骏信息技术有限公司 | Data management method, device, equipment and storage medium |
| CN116828535B (en) * | 2023-08-30 | 2023-11-14 | 太一云境技术有限公司 | Audio sharing method and system based on wireless transmission |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332006A (en) * | 2011-08-03 | 2012-01-25 | 百度在线网络技术（北京）有限公司 | Information push control method and device |
| 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 |
| CN103049865A (en) * | 2012-12-17 | 2013-04-17 | 中国农业大学 | Method and system for initiatively recommending product information service |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110125753A1 (en) * | 2009-11-20 | 2011-05-26 | Rovi Technologies Corporation | Data delivery for a content system |
-
2013
- 2013-08-22 CN CN201310369757.3A patent/CN104424210B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102332006A (en) * | 2011-08-03 | 2012-01-25 | 百度在线网络技术（北京）有限公司 | Information push control method and device |
| CN103049865A (en) * | 2012-12-17 | 2013-04-17 | 中国农业大学 | Method and system for initiatively recommending product information service |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104424210A (en) | 2015-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104424210B (en) | A kind of information recommendation method, system and server | |
| CN107729542B (en) | A kind of information scoring method and device and storage medium | |
| US11442948B2 (en) | Optimizing digital video distribution | |
| US10558682B2 (en) | Cross media recommendation | |
| KR101947667B1 (en) | Clustering of viewing time for video search | |
| US8140541B2 (en) | Time-weighted scoring system and method | |
| US9165060B2 (en) | Content creation and management system | |
| US8762413B2 (en) | User data store | |
| US8775471B1 (en) | Representing user behavior information | |
| US9183239B2 (en) | Optimizing a content index for target audience queries | |
| US10169356B2 (en) | Intelligent data caching for typeahead search | |
| US9679018B1 (en) | Document ranking based on entity frequency | |
| US20120072283A1 (en) | Mobile application recommendation system and method | |
| US20080077568A1 (en) | Talent identification system and method | |
| US20090276709A1 (en) | Method and apparatus for providing dynamic playlists and tag-tuning of multimedia objects | |
| WO2011119440A2 (en) | Crowd-sourcing and contextual reclassification of rated content | |
| US20150058417A1 (en) | Systems and methods of presenting personalized personas in online social networks | |
| WO2014144833A2 (en) | Taste profile attributes | |
| US20140122504A1 (en) | Systems and Methods for Collection and Automatic Analysis of Opinions on Various Types of Media | |
| US11568451B2 (en) | Dual-optimization of targeted digital assets under volume and position constraints | |
| US20210406925A1 (en) | Algorithm for identification of trending content | |
| CA2832918C (en) | Systems and methods for ranking document clusters | |
| WO2008032037A1 (en) | Method and system for filtering and searching data using word frequencies | |
| US20250086663A2 (en) | Generating audience lookalike models | |
| CN119513417A (en) | A method, device, equipment and medium for updating user portrait features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20150318 Assignee: Ocean interactive (Beijing) Information Technology Co., Ltd. Assignor: Tencent Technology (Shenzhen) Co., Ltd. Contract record no.: 2016990000422 Denomination of invention: Information recommendation method, information recommendation system and server License type: Common License Record date: 20161009 |
|
| LICC | Enforcement, change and cancellation of record of contracts on the licence for exploitation of a patent or utility model | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |