CN110012318B - Method, storage medium, device and system for determining user interest - Google Patents
Method, storage medium, device and system for determining user interest Download PDFInfo
- Publication number
- CN110012318B CN110012318B CN201810012260.9A CN201810012260A CN110012318B CN 110012318 B CN110012318 B CN 110012318B CN 201810012260 A CN201810012260 A CN 201810012260A CN 110012318 B CN110012318 B CN 110012318B
- Authority
- CN
- China
- Prior art keywords
- watching
- probability
- user
- interest
- live broadcast
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims description 47
- 238000004590 computer program Methods 0.000 claims description 10
- 238000009499 grossing Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
- H04N21/4663—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms involving probabilistic networks, e.g. Bayesian networks
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Computer Graphics (AREA)
- Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention discloses a method, a storage medium, equipment and a system for determining user interest, which relate to the technical field of big data recommendation and comprise the following steps: obtaining a first viewing probability, a second viewing probability and a third viewing probability; the first watching probability is the watching probability of a user to be determined watching a specified type of live broadcast room in a single month, the second watching probability is the watching probability of all users aiming at the specified type of live broadcast room in the single month, and the third watching probability is the watching probability of the user to be determined watching all types of live broadcast rooms in the single month; and calculating a first interestingness through the first viewing probability, the second viewing probability and the third viewing probability, wherein the first interestingness is used for expressing the interestingness of the user to be determined in the specified type live broadcast room in a single month. The method and the device can determine the interest of the user, avoid errors caused by less historical data and hot events to the interest mining work, and improve the accuracy of determining the interest result of the user.
Description
Technical Field
The invention relates to the technical field of big data recommendation, in particular to a method, a storage medium, equipment and a system for determining user interest.
Background
At present, most live broadcast rooms with interest can be recommended to users on live broadcast platforms, and the technology of the function is based on the discovery of the interest of the users.
When the interest of a user is excavated, the historical behavior of the user is mostly used as an excavation basis, the historical behavior of the user is directly excavated, and when data excavation is carried out, in order to avoid larger error of an excavation result, a large amount of historical data used by the user is mostly selected to be excavated;
however, when the user is a new user or has only a few historical behaviors, or a hot event occurs when the interest level is determined, the current interest of the user cannot be accurately discovered.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method, a storage medium, equipment and a system for determining the interest of a user, which can determine the interest of the user, avoid errors caused by less historical data and hot events on interest mining work, and improve the accuracy of determining the interest result of the user.
In order to achieve the above purposes, the technical scheme adopted by the invention is as follows:
a method of determining user interest, comprising the steps of:
obtaining a first viewing probability, a second viewing probability and a third viewing probability;
the first watching probability is the watching probability of a user to be determined watching a specified type of live broadcast room in a single month, the second watching probability is the watching probability of all users aiming at the specified type of live broadcast room in the single month, and the third watching probability is the watching probability of the user to be determined watching all types of live broadcast rooms in the single month;
and calculating a first interestingness through the first viewing probability, the second viewing probability and the third viewing probability, wherein the first interestingness is used for expressing the interestingness of the user to be determined in the specified type live broadcast room in a single month.
On the basis of the technical scheme, the method for determining the interest of the user comprises the following steps:
said first viewing probability is denoted as pt(ci| watch), the calculation formula is:
said second viewing probability is denoted as pt(ci) The calculation formula is as follows:
said third viewing probability is denoted as pt(watch), the calculation formula is:
the first interest level is marked as It(ci) The calculation formula is as follows:
wherein,
t is used for representing that the month is t month, i is used for representing that the type of the live broadcast room is ci，
Viewing the interest category c for the user to be determined in the month tiNumber of live broadcast rooms, said
View in month t for all users belonging to interest category ciThe total number of times of the live broadcast room, the RNtIs the total number of viewing rooms of the user to be determined in t months, the RTNtIs the number of rooms all users watch in t months.
On the basis of the technical scheme, the method for determining the user interests further comprises the following steps of:
obtaining a first watching frequency and a second watching frequency;
obtaining a second interestingness through the first watching times and the second watching times;
the first watching times are time periods t0The watching times of all the users in the live broadcast room with the specified type are recorded as
The second watching times is a statistical time period t0The total number of views of all users in the system is recorded as
The second interestingness is used for representing the interestingness of all users for the specified type of live broadcast room and is marked as p0(ci) Said p is0(ci) Is calculated by the formula
The i is used for indicating that the type of the live broadcast room is ci。
On the basis of the technical scheme, the method for determining the interest of the user further comprises the following steps of further determining the current interest of the user to be determined:
obtaining a third interest degree according to the first interest degree and the second interest degree;
the third interestingness is used for representing the time t of the user to be determined0Inner pair ciInterestingness of type live broadcast room, denoted as I0(ci)；
The G is a smoothing factor, and can be obtained according to data analysis and industry experience.
A storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the above-mentioned method of determining a user's interest.
An apparatus for determining user interest, comprising a memory, a processor and a computer program stored on the memory and running on the processor, the processor implementing the steps of the method for determining user interest when executing the computer program.
A system for determining user interest, the system comprising:
the user playing recording module is used for obtaining a first viewing probability and a third viewing probability;
the server playing recording module is used for obtaining a second watching probability;
a user interest calculation module, configured to obtain a first interest degree according to the first viewing probability, the second viewing probability, and the third viewing probability;
the first watching probability is the watching probability of a user to be determined watching a specified type of live broadcast room in a single month, the second watching probability is the watching probability of all users aiming at the specified type of live broadcast room in the single month, and the third watching probability is the watching probability of the user to be determined watching all types of live broadcast rooms in the single month.
On the basis of the technical scheme, the calculation formulas of the first viewing probability and the third viewing probability which are arranged in the user playing recording module of the user interest system are determined, wherein the first viewing probability is marked as pt(ci| watch), the calculation formula is:
said third viewing probability is denoted as pt(watch), the calculation formula is:
the server playing recording module is internally provided with a calculation formula of the second viewing probability, and the second viewing probability is marked as pt(ci) The calculation formula is as follows:
the user interest calculation module is internally provided with a calculation formula of the first interest degree, and the first interest degree is marked as It(ci) The calculation formula is as follows:
wherein,
t is used for representing that the month is t month, i is used for representing that the type of the live broadcast room is ci，
Viewing the interest category c for the user to be determined in the month tiNumber of live broadcast rooms, said
View in month t for all users belonging to interest category ciThe total number of times of the live broadcast room, the RNtIs the total number of viewing rooms of the user to be determined in t months, the RTNtIs the number of rooms all users watch in t months.
On the basis of the technical scheme, the server playing recording module of the user interest system is determined to be used for obtaining the first watching times and the second watching times;
the user interest calculation module is further used for obtaining a second interest degree through the first watching times and the second watching times;
the first watching times are time periods t0The watching times of all the users in the live broadcast room with the specified type are recorded as
The second watching times is a statistical time period t0The total number of views of all users in the system is recorded as
The second interestingness is used for representing the interestingness of all users for the specified type of live broadcast room and is marked as p0(ci) Said p is0(ci) Is calculated by the formula
The i is used for indicating that the type of the live broadcast room is ci。
On the basis of the technical scheme, the user interest calculation module of the user interest system is further used for obtaining a third interest degree according to the first interest degree and the second interest degree;
the third interestingness is used for representing the time t of the user to be determined0Inner pair ciInterestingness of type live broadcast room, denoted as I0(ci)；
The G is a smoothing factor, and can be obtained according to data analysis and industry experience.
Compared with the prior art, the invention has the advantages that:
(1) the method and the device utilize the first watching probability, the second watching probability and the third watching probability to obtain a first interest degree which can represent the interest degree of a user to be determined in a specified type of live broadcast room in a single month;
compared with the prior art, the method for determining the user interest by means of self-definition can effectively avoid errors caused by less user historical data and the influence of hot events on the watching habits of the user, and improve the accuracy of determining the user interest result.
(2) According to the invention, the latest interest condition of the user to be determined can be accurately known by determining the current interest of the user;
compared with the prior art, the interest determination time range is narrower, so that the interest determination method is more accurate.
Drawings
FIG. 1 is a flow chart of a method of determining user interest in an embodiment of the present invention;
FIG. 2 is a block diagram of a device for determining user interest according to an embodiment of the present invention;
fig. 3 is a block diagram illustrating a structure of a system for determining user interest according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, an embodiment of the present invention provides a method for determining a user interest, including the following steps:
obtaining a first viewing probability, a second viewing probability and a third viewing probability;
the first watching probability is the watching probability of a user to be determined watching a specified type of live broadcast room in a single month, the second watching probability is the watching probability of all users aiming at the specified type of live broadcast room in the single month, and the third watching probability is the watching probability of the user to be determined watching all types of live broadcast rooms in the single month;
and calculating a first interestingness through the first viewing probability, the second viewing probability and the third viewing probability, wherein the first interestingness is used for expressing the interestingness of the user to be determined in the specified type live broadcast room in a single month.
According to the method and the device, the viewing probability condition of the user to be determined in the specified type live broadcast room in a single month can be obtained by obtaining the first viewing probability, so that the possibility that the user to be determined in the specified type live broadcast room in the single month can be obtained;
the viewing probability situation of all users aiming at the specified type live broadcast room in a single month can be known by obtaining the second viewing probability, so that the possibility that all users can view the specified type live broadcast room in the single month is known, and the probability is determined by the common viewing behavior of all users;
by obtaining the third viewing probability, the viewing probability condition of the user to be determined for viewing all types of live broadcast rooms in a single month can be known, so that the possibility of the user to be determined for viewing all types of live broadcast rooms in the single month can be known,
the method has the advantages that the possibility that a user to be determined watches the specified type live broadcast room in a single month is combined with the possibility that all users watch the specified type live broadcast room in a single month and the possibility that the user to be determined watches all the types of live broadcast rooms in a single month are combined, the interest degree of the user to be determined in the specified type live broadcast room in the single month can be obtained, the watching conditions of all the users are combined with the single-month watching conditions of the user to be determined, the situations that the watching history of the user to be determined is extremely few and the user to be determined receives the attraction of hot events are avoided, and the determination result of the interest of the user is more accurate;
the interest of the user can be determined, errors caused by less historical data and hot events to interest mining work can be avoided, and the accuracy of determining the interest result of the user is improved.
Although the first viewing probability is the viewing probability of the user to be determined viewing the specified type live broadcast room in a single month, and can represent the possibility of the user to be determined viewing the specified type live broadcast room in the single month, the result is usually used as the interest situation of the user to be determined in the specified type live broadcast room, but the traditional method has a large error when the viewing history of the user to be determined is less, and when a hot event occurs, the viewing situation of the user is influenced during the hot event due to the large attraction of the hot event, so the situation also has a large error.
It should be noted that the third viewing probability is a viewing probability that the user to be determined views all types of live broadcast rooms in a single month, and may also be understood as a viewing probability that the user to be determined views any type of live broadcast room in a single month, that is, a viewing probability that the user to be determined views live broadcast rooms in a single month.
In this embodiment, the first viewing probability is denoted as pt(ci| watch), the calculation formula is:
the second viewing probability is denoted as pt(ci) The calculation formula is as follows:
the third viewing probability is denoted as pt(watch), the calculation formula is:
the first interest level is denoted as It(ci) The calculation formula is as follows:
wherein,
t is used to indicate the month is t month, i is used to indicate the type of the live broadcast room is ci，
View belonging to interest category c in month t for user to be determinediThe number of times of the live broadcast room(s),
view in month t for all users belonging to interest category ciTotal number of live broadcast rooms, RNtIs that the user is to be determined at tTotal number of rooms viewed in the month, RTNtIs the number of rooms all users watch in t months.
In this embodiment, the method for determining user interests further includes the step of further determining all user interests:
obtaining a first watching frequency and a second watching frequency;
obtaining a second interest degree through the first watching times and the second watching times;
the first number of times of watching is a time period t0The watching times of all the users in the live broadcast room with the specified type are recorded as
The second watching times is a statistical time period t0The total number of views of all users in the system is recorded as
The second interestingness is used for representing the interestingness of all users for the specified type of live broadcast room and is marked as p0(ci)，p0(ci) Is calculated by the formula
i is used to indicate that the live room type is ci；
This step may be understood as the step of determining the interestingness of all users, i.e. the public interest, t0The calculation time can be 1 day, 3 days or 7 days, and the calculation time can be set additionally according to the actual requirement.
In this embodiment, the method for determining the interest of the user further includes the step of further determining the current interest of the user to be determined:
obtaining a third interest degree according to the first interest degree and the second interest degree;
the third interestingness is used for representing the time t of the user to be determined0Inner pair ciInterestingness of type live broadcast room, denoted as I0(ci)；
G is a smoothing factor and is obtained according to data analysis and industry experience;
g is a constant, called a smoothing factor, generally taken as 20 in actual business, and the function of the factor is to take public interest as the final interest of the user if the historical behavior of the user is very little; conversely, if the user has a large amount of historical viewing behavior, the ultimate interest of the user is primarily determined by the user's personal interests;
the specific value of G can also be obtained by simulation according to a large number of user watching records in the database;
by determining the current interest of the user, the latest interest condition of the user to be determined can be known more accurately.
It should be noted that the trending event may be a major event, a web trending news event, or the like.
A storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the above-mentioned method of determining user interest.
As shown in fig. 2, an apparatus for determining user interest includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method for determining user interest when executing the computer program.
As shown in fig. 3, a system for determining user interest, the system comprising:
the user playing recording module is used for obtaining a first viewing probability and a third viewing probability;
the server playing recording module is used for obtaining a second watching probability;
the user interest calculation module is used for obtaining a first interest degree through the first viewing probability, the second viewing probability and the third viewing probability;
the first watching probability is the watching probability of a user to be determined watching a specified type of live broadcast room in a single month, the second watching probability is the watching probability of all users aiming at the specified type of live broadcast room in the single month, and the third watching probability is the watching probability of the user to be determined watching all types of live broadcast rooms in the single month.
In this embodiment, the calculation formulas for determining the first viewing probability and the third viewing probability built in the user playing recording module of the user interest system are determined, and the first viewing probability is denoted as pt(ci| watch), the calculation formula is:
the third viewing probability is denoted as pt(watch), the calculation formula is:
the server plays a calculation formula of a second viewing probability which is recorded in the recording module, and the second viewing probability is recorded as pt(ci) The calculation formula is as follows:
a calculation formula of a first interestingness is built in the user interest calculation module, and the first interestingness is marked as It(ci) The calculation formula is as follows:
wherein,
t is used to indicate the month is t month, i is used to indicate the type of the live broadcast room is ci，
View belonging to interest category c in month t for user to be determinediThe number of times of the live broadcast room(s),
view in month t for all users belonging to interest category ciTotal number of live broadcast rooms, RNtIs the total number of rooms watched by the user in the month of t, RTNtIs the number of rooms all users watch in t months.
In this embodiment, the server playing recording module of the system for determining user interest is further configured to obtain a first viewing time and a second viewing time;
the user interest calculation module is also used for obtaining a second interest degree through the first watching times and the second watching times;
the first number of times of watching is a time period t0The watching times of all the users in the live broadcast room with the specified type are recorded as
The second watching times is a statistical time period t0The total number of views of all users in the system is recorded as
The second interestingness is used for representing the interestingness of all users for the specified type of live broadcast room and is marked as p0(ci)，p0(ci) Is calculated by the formula
i is used to indicate that the live room type is ci。
In this embodiment, the user interest calculation module of the system for determining user interest is further configured to obtain a third interest level according to the first interest level and the second interest level;
the third interestingness is used for representing the time t of the user to be determined0Inner pair ciInterestingness of type live broadcast room, denoted as I0(ci)；
G is a smoothing factor and is obtained according to data analysis and industry experience, namely, the system also has a database for storing data.
An example of determining user interestingness according to the present invention is given here:
assuming that the user is a behavioral user in month 1, we now estimate the user's interest level in the tag at the beginning of month 2:
for tag 1, the number of views by the user in 1 month
Number of views in 1 month of the whole network
For tag 2, the number of views by the user in 1 month
Number of views in 1 month of the whole network
The total number of times the user watched in month 1 is
The total number of times of watching in 1 month of the whole network is
The number of times of watching the label 1 in the whole network in nearly 1 day is
The number of views of the label 2 is
The total number of views is
Thus:
p1(c1|watch)＝10/50＝0.2 p1(c2|watch)＝20/50＝0.4
p1(c1)＝400000/5000000＝0.08 p1(c2)＝100000/5000000＝0.02
p0(c1)＝10000/200000＝0.05 p0(c2)＝5000/200000＝0.025
according to the above results, the user's interest level in tag 1 and tag 2 can be calculated:
the interest of tag 1 in nearly 1 day is (10 × 0.2/0.08+20) × 0.05/(20+50) ═ 0.032
The interest of tag 2 was (20 × 0.4/0.02+20) × 0.025/(20+50) ═ 0.15 for nearly 1 day.
It should be noted that: in the system provided by the above embodiment, when the operation of determining the user interest is implemented, only the division of the functional modules is illustrated, and in practical application, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the system is divided into different functional modules, so as to complete all or part of the functions described above.
The present invention is not limited to the above-described embodiments, and it will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and such modifications and improvements are also considered to be within the scope of the present invention.
Those not described in detail in this specification are within the skill of the art.
Claims (8)
1. A method for determining user interest, the method comprising the steps of:
obtaining a first viewing probability, a second viewing probability and a third viewing probability;
the first watching probability is the watching probability of a user to be determined watching a specified type of live broadcast room in a single month, the second watching probability is the watching probability of all users aiming at the specified type of live broadcast room in the single month, and the third watching probability is the watching probability of the user to be determined watching all types of live broadcast rooms in the single month;
calculating a first interestingness through the first viewing probability, the second viewing probability and the third viewing probability, wherein the first interestingness is used for expressing the interestingness of the user to be determined in a specified type of live broadcast room in a single month; wherein,
said first viewing probability is denoted as pt(ci| watch), the calculation formula is:
said second viewing probability is denoted as pt(ci) The calculation formula is as follows:
said third viewing probability is denoted as pt(watch), the calculation formula is:
the first interest level is marked as It(ci) The calculation formula is as follows:
t is used for representing that the month is t month, i is used for representing that the type of the live broadcast room is ci，
Viewing the interest category c for the user to be determined in the month tiNumber of live broadcast rooms, said
View in month t for all users belonging to interest category ciThe total number of times of the live broadcast room, the RNtIs the total number of viewing rooms of the user to be determined in t months, the RTNtIs the number of rooms all users watch in t months.
2. The method of determining user interests of claim 1, further comprising the step of further determining all user interests:
obtaining a first watching frequency and a second watching frequency;
obtaining a second interestingness through the first watching times and the second watching times;
the first watching times are time periods t0The watching times of all the users in the live broadcast room with the specified type are recorded as
The second watching times is a statistical time period t0The total number of views of all users in the system is recorded as
The second interestingness is used for representing the interestingness of all users for the specified type of live broadcast room and is marked as p0(ci) Said p is0(ci) Is calculated by the formula
The i is used for indicating that the type of the live broadcast room is ci。
3. The method of determining user interest according to claim 2, further comprising the step of further determining the current interest of the user to be determined:
obtaining a third interest degree according to the first interest degree and the second interest degree;
the third interestingness is used for representing the time t of the user to be determined0Inner pair ciInterestingness of type live broadcast room, denoted as I0(ci)；
And G is a smoothing factor and is obtained according to data analysis.
4. A storage medium having a computer program stored thereon, characterized in that: the computer program when executed by a processor implements the steps of the method of any of the preceding claims 1 to 3.
5. An apparatus for determining user interest, comprising a memory, a processor, and a computer program stored on the memory and executed on the processor, wherein: the processor, when executing the computer program, realizes the steps of the method of any of the preceding claims 1 to 3.
6. A system for determining user interest, the system comprising:
the user playing recording module is used for obtaining a first viewing probability and a third viewing probability;
the server playing recording module is used for obtaining a second watching probability;
a user interest calculation module, configured to obtain a first interest degree according to the first viewing probability, the second viewing probability, and the third viewing probability;
the first watching probability is the watching probability of a user to be determined watching a specified type of live broadcast room in a single month, the second watching probability is the watching probability of all users aiming at the specified type of live broadcast room in the single month, and the third watching probability is the watching probability of the user to be determined watching all types of live broadcast rooms in the single month; wherein,
the user playing recording module is internally provided with calculation formulas of the first viewing probability and the third viewing probability, and the first viewing probability is recorded as pt(ci| watch), the calculation formula is:
said third viewing probability is denoted as pt(watch)，The calculation formula is as follows:
the server playing recording module is internally provided with a calculation formula of the second viewing probability, and the second viewing probability is marked as pt(ci) The calculation formula is as follows:
the user interest calculation module is internally provided with a calculation formula of the first interest degree, and the first interest degree is marked as It(ci) The calculation formula is as follows:
t is used for representing that the month is t month, i is used for representing that the type of the live broadcast room is ci，
Viewing the interest category c for the user to be determined in the month tiNumber of live broadcast rooms, said
View in month t for all users belonging to interest category ciThe total number of times of the live broadcast room, the RNtIs the total number of viewing rooms of the user to be determined in t months, the RTNtIs the number of rooms all users watch in t months.
7. The system for determining user interest of claim 6, wherein:
the server playing recording module is further used for obtaining the first watching times and the second watching times;
the user interest calculation module is further used for obtaining a second interest degree through the first watching times and the second watching times;
the first watching times are time periods t0The watching times of all the users in the live broadcast room with the specified type are recorded as
The second watching times is a statistical time period t0The total number of views of all users in the system is recorded as
The second interestingness is used for representing the interestingness of all users for the specified type of live broadcast room and is marked as p0(ci) Said p is0(ci) Is calculated by the formula
The i is used for indicating that the type of the live broadcast room is ci。
8. The system for determining user interest of claim 7, wherein: the user interest calculation module is further used for obtaining a third interest degree according to the first interest degree and the second interest degree;
the third interestingness is used for representing the time t of the user to be determined0Inner pair ciInterestingness of type live broadcast room, denoted as I0(ci)；
And G is a smoothing factor and is obtained according to data analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810012260.9A CN110012318B (en) | 2018-01-05 | 2018-01-05 | Method, storage medium, device and system for determining user interest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810012260.9A CN110012318B (en) | 2018-01-05 | 2018-01-05 | Method, storage medium, device and system for determining user interest |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110012318A CN110012318A (en) | 2019-07-12 |
| CN110012318B true CN110012318B (en) | 2021-05-28 |
Family
ID=67164627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810012260.9A Active CN110012318B (en) | 2018-01-05 | 2018-01-05 | Method, storage medium, device and system for determining user interest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110012318B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103546778A (en) * | 2013-07-17 | 2014-01-29 | Tcl集团股份有限公司 | Television program recommendation method and system, and implementation method of system |
| CN105224699A (en) * | 2015-11-17 | 2016-01-06 | Tcl集团股份有限公司 | A kind of news recommend method and device |
| CN106294800A (en) * | 2016-08-16 | 2017-01-04 | 武汉斗鱼网络科技有限公司 | Method and system recommended by direct broadcasting room based on weighting k neighbour scoring |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103748871A (en) * | 2012-08-17 | 2014-04-23 | 弗莱克斯电子有限责任公司 | Interactive channel navigation and switching |
-
2018
- 2018-01-05 CN CN201810012260.9A patent/CN110012318B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103546778A (en) * | 2013-07-17 | 2014-01-29 | Tcl集团股份有限公司 | Television program recommendation method and system, and implementation method of system |
| CN105224699A (en) * | 2015-11-17 | 2016-01-06 | Tcl集团股份有限公司 | A kind of news recommend method and device |
| CN106294800A (en) * | 2016-08-16 | 2017-01-04 | 武汉斗鱼网络科技有限公司 | Method and system recommended by direct broadcasting room based on weighting k neighbour scoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110012318A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI702844B (en) | Method, device, apparatus, and storage medium of generating features of user | |
| US20210304229A1 (en) | Methods and apparatus to generate electronic mobile measurement census data | |
| CN102487456B (en) | Method for providing visit rate of online video and device thereof | |
| CN102740140B (en) | For estimating the method for the local market spectators of media content, equipment and manufacture | |
| KR102378855B1 (en) | Methods and apparatus to estimate demographics of users employing social media | |
| JP6689515B2 (en) | Method and apparatus for identifying the type of user geographic location | |
| US20120221563A1 (en) | Social Weight of Social Media Content | |
| US10977670B2 (en) | Method and system for determining and monitoring brand performance based on paid expenditures | |
| CN107026892B (en) | Message recommendation method and device | |
| CN105843876B (en) | Quality evaluation method and device for multimedia resources | |
| CN108965951B (en) | Advertisement playing method and device | |
| CN114747227A (en) | Method, system, and apparatus for estimating census-level audience size and total impression duration across demographic groups | |
| CN110941738A (en) | Recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN111158999B (en) | Formatting time calculation method and device | |
| CN110121088B (en) | User attribute information determination method and device and electronic equipment | |
| CN108564404A (en) | A kind of method and device of prediction investment in advertising return rate | |
| US9811595B2 (en) | Missed media system and method | |
| CN110012318B (en) | Method, storage medium, device and system for determining user interest | |
| CN110717653B (en) | Risk identification method and apparatus, and electronic device | |
| CN112312173B (en) | Anchor recommendation method and device, electronic equipment and readable storage medium | |
| CN104268189B (en) | Evaluate the method and device of application | |
| CN109561350B (en) | User interest degree evaluation method and system | |
| US10943175B2 (en) | Methods, systems and apparatus to improve multi-demographic modeling efficiency | |
| CN110188277A (en) | A kind of recommended method and device of resource | |
| CN112235564B (en) | Data processing method and device based on delivery channel |
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 |