CN107948752B - Ordering method, device and terminal for subscription anchor - Google Patents
Ordering method, device and terminal for subscription anchor Download PDFInfo
- Publication number
- CN107948752B CN107948752B CN201711120851.XA CN201711120851A CN107948752B CN 107948752 B CN107948752 B CN 107948752B CN 201711120851 A CN201711120851 A CN 201711120851A CN 107948752 B CN107948752 B CN 107948752B
- Authority
- CN
- China
- Prior art keywords
- anchor
- subscription
- user
- preset
- days
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- 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
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- 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
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, 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
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a subscription anchor ordering method, which comprises the following steps: acquiring user behavior data of a user on a subscription anchor on a live broadcast platform; obtaining user behavior characteristics according to the user behavior data; the user behavior characteristics comprise at least two characteristic indexes; processing the characteristic index according to normalization to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of the characteristic index in a preset time limit to obtain a weighted normalized characteristic index value; summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor; and sequencing the subscription anchor according to the score of each subscription anchor. The ordering of the subscription anchor can better match with the love degree of the user to the subscription anchor, so that the user has higher live broadcast watching enthusiasm and better product use experience. The invention also provides a subscription anchor ordering device and a terminal.
Description
Technical Field
The invention relates to the technical field of sequencing models, in particular to a subscription anchor sequencing method, a subscription anchor sequencing device and a terminal.
Background
Live webcasting is an emerging social media in the current internet era, and has a huge anchor group and a user group watching live webcasting. The system generally sorts the subscription anchor of the user and displays the top several subscription anchors on the outermost layer of the user subscription anchor entry.
In the prior art, the subscription anchor is generally ordered from large to small number of people who are online at the same time. However, the first few subscription anchor obtained by the sorting method is often not the favorite subscription anchor of the user, the user needs to perform more operations, and the favorite subscription anchor can be found only by entering more pages from the outermost subscription anchor entry, so that the enthusiasm of the user for watching live broadcast and the satisfaction degree of product experience are reduced.
Disclosure of Invention
The present invention aims to solve at least one of the above technical drawbacks, and in particular, to solve the technical drawback that the existing subscription anchor ordering fails to rank the favorite subscription anchor of the user at the top.
The invention provides a subscription anchor ordering method, which comprises the following steps:
acquiring user behavior data of a user on a subscription anchor on a live broadcast platform in a preset period;
obtaining user behavior characteristics according to the user behavior data; the user behavior characteristics comprise at least two characteristic indexes;
processing the characteristic index according to normalization to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of the characteristic index in a preset time limit to obtain a weighted normalized characteristic index value; summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor;
and sequencing the subscription anchor according to the score of each subscription anchor.
Preferably, the characteristic indicator includes:
number of days of distance subscribed and amount of payment;
the number of the subscription distance days is the number of days between the time when the user subscribes the current subscription anchor on the live broadcast platform and the current time;
the payment amount is the payment amount of the user to the current subscription anchor;
the normalization indexes corresponding to the subscription distance days are as follows: 1- (the number of subscription distance days/the preset period);
the normalization indexes corresponding to the payment amount are as follows: the payment amount/the total payment amount of the user on the live broadcast platform.
Further, the characteristic index further includes:
whether the user watches the screen latest or not, watching duration, watching distance days, watching days, screen flipping times, paying days and paying or not;
whether the current subscription anchor live broadcast is watched or not when the user watches the live broadcast on the live broadcast platform in the last day;
the watching duration is the duration for watching the current subscription anchor live broadcast by the user;
the viewing distance days are the days from the time when the user last views the current subscription anchor live broadcast to the current time;
the watching days are days for the user to watch the current subscription anchor live broadcast;
the number of the barrage is the number of the barrage sent by the user in the process of watching the current subscription anchor live broadcast;
the payment days are the days for which the user pays for the current subscription anchor;
the payment is whether the user pays for the current subscription anchor.
Preferably, after the ordering the subscription anchor according to the score of each subscription anchor, the method further includes:
and pushing the subscription anchor to the user according to the ranking from big to small.
Preferably, the pushing the subscription anchor to the user according to the descending order includes:
pushing a preset number of subscription anchor ranked in front to the user according to the ranking from big to small; or
According to the sorting from big to small, pushing a preset number of subscription anchor ranked in front as an outer-layer anchor, pushing the rest subscription anchors pushed by the user as inner-layer anchors, and pushing the outer-layer anchor and the inner-layer anchor to the user; the outer-layer anchor is displayed in a subscription anchor overview window of the user on a live broadcast platform, and the inner-layer anchor is displayed in a subscription anchor overview page entering from the subscription anchor overview window.
Preferably, after the subscription anchor is pushed to the user according to the ranking from large to small, the method further includes:
counting the probability that a user clicks a top subscription anchor in a preset duration;
adjusting the weight coefficient of the characteristic index according to the probability;
the counting of the probability that the user clicks the top subscription anchor in the preset duration comprises the following steps:
acquiring the number of users pushing the top-ranked subscription anchor to the users and the number of users feeding back and clicking the top-ranked subscription anchor, and dividing the number of the users feeding back and clicking the top-ranked subscription anchor by the number of the users pushing the top-ranked subscription anchor to the users to obtain a probability; or
Acquiring the number of users who push and click the top push subscription anchor to users of an extraction group within a preset time length, and dividing the number of the users who click and click the top push subscription anchor by the number of the users who push and click the top push subscription anchor to the users to obtain a probability;
the adjusting the weight coefficient of the characteristic index according to the probability comprises:
confirming that the probability is smaller than a preset value, and replacing the weight coefficient of each characteristic index with another preset weight coefficient; or
And confirming that the probability is smaller than a preset value, and adding the weight coefficient of each characteristic index to the adjustment value of the characteristic index, wherein the adjustment value is a positive value or a negative value.
Preferably, after the adjusting the weight coefficient of the characteristic indicator according to the probability, the method further includes:
comparing the probabilities of different preset durations, and taking the weight coefficient of the preset duration with the maximum probability as the weight coefficient in the preset time efficiency; wherein, the weighting coefficients of different preset durations are different.
Preferably, the acquiring user behavior data of the user on each subscription anchor on the live broadcast platform in the preset period includes:
randomly dividing all users of the whole server into a preset number of user groups; wherein, the characteristic indexes of each user group are different in weight coefficient in the preset time limit;
acquiring user behavior data of each subscription anchor of users of each user group on a live broadcast platform in a preset period;
after the ordering of the subscription anchor according to the score of each subscription anchor, the method further comprises the following steps:
pushing the subscription anchor to the user according to the sequence from big to small;
counting the probability that each user clicks the first subscription anchor in a preset time length of each user group;
and acquiring a weight coefficient of the characteristic index of the user group with the maximum probability, and taking the weight coefficient as the weight coefficient in the preset time efficiency of the whole server.
The present invention also provides a subscription anchor sorting apparatus, which includes:
a user behavior data acquisition module: the method comprises the steps of acquiring user behavior data of a user for subscribing the anchor on a live broadcast platform;
a user behavior feature acquisition module: the user behavior data is used for acquiring user behavior characteristics according to the user behavior data; the user behavior characteristics comprise at least two characteristic indexes;
a subscription anchor score calculation module: the characteristic index is used for carrying out normalization processing on the characteristic index to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of preset timeliness of the characteristic index to obtain a weighted normalized characteristic index value; summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor;
a subscription anchor ordering module: and the system is used for sequencing the subscription anchor according to the score of each subscription anchor.
The present invention also provides a terminal, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the subscription-anchor ordering method described in any of the above preferred embodiments is performed.
According to the ordering method, the ordering device and the ordering terminal of the subscription anchor provided by the invention, the user behavior characteristics are obtained by analyzing the user behavior data in the preset period of the user, the subscription anchor preference model of the user is constructed according to various characteristic indexes capable of effectively reflecting the user preference in the user behavior characteristics, the ordering of the subscription anchor obtained by the subscription anchor preference model can be better matched with the preference degree of the user to the subscription anchor, and further the user has higher live broadcast watching enthusiasm and better product use experience.
Secondly, the subscription anchor ordering method provided by the invention also obtains the weight coefficient in the preset time limit of each characteristic index by regularly adjusting the weight coefficient of each characteristic index in the subscription anchor preference model, ensures the timeliness and the accuracy of the subscription anchor ordering result, further enables the obtained subscription anchor ordering to be better matched with the user's preference degree on the subscription anchor, and further enables the user to have higher live broadcast watching enthusiasm and better product use experience.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart of a subscription anchor sorting method according to a first embodiment of the present invention;
FIG. 2 is a table of criteria definitions according to an embodiment of the present invention;
FIG. 3 is a flowchart of a subscription anchor sorting method according to a second embodiment of the present invention;
FIG. 4 is a flowchart of a subscription anchor sorting method according to a third embodiment of the present invention;
FIG. 5 is a diagram of a subscription anchor sorting apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of the terminal structure of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
The present invention provides a subscription anchor sorting method, as shown in fig. 1, which is a flowchart of a subscription anchor sorting method according to a first embodiment of the present invention, and includes the following steps:
step S101: and acquiring user behavior data of the user on the subscription anchor in the live broadcast platform in a preset period.
Specifically, in the embodiment of the present invention, user behavior data of a user on a subscription anchor on a live platform in the last 30 days is obtained. The subscription anchor is the favorite anchor subscribed by the user on the live platform, and the user behavior data are the actions and corresponding data which are respectively executed by the user on each subscription anchor within the last 30 days recorded by the live platform system.
The preset period is used for limiting the time interval of the acquired user behavior data, so that the data is time-efficient and is convenient to update and manage periodically. It should be explicitly noted that the preset period is not limited by the embodiment, and the preset period may be a time period of one week, one month, 45 days, and the like, and a person skilled in the art can adjust the preset period according to actual application requirements.
Step S102: obtaining user behavior characteristics according to the user behavior data; the user behavior feature comprises at least two feature indicators.
Specifically, the user behavior data of the user subscribing to the anchor within the last 30 days obtained in step S101 is analyzed, and user behavior features corresponding to the user behavior data are obtained by mining, where the user behavior features include at least two characteristic indexes. In the embodiment of the present invention, the obtained user behavior characteristics include the following nine characteristic indexes:
number of days of subscription distance, amount of payment, whether it is the latest to watch, length of watching, number of days of watching distance, number of days of watching, number of bullet screen, number of days of payment, and whether it is payment.
The definition of the nine characteristic indexes is specifically as follows:
the number of the subscription distance days is the number of days from the time when the user subscribes the current subscription anchor on the live broadcast platform to the current day within the last 30 days;
the payment amount is the payment amount of the user to the current subscription anchor within the last 30 days;
whether the latest watching is that whether the user watches the current subscription anchor live broadcast in the live broadcast platform in the last day within the last 30 days;
the watching duration is the duration of watching the current subscription anchor live broadcast by the user within the last 30 days;
the viewing distance days are the days from the last time that the user views the current subscription anchor live broadcast within the last 30 days to the current time;
the watching days are the days that the user has watched the current subscription anchor live broadcast in the last 30 days;
the number of bullet screens is the number of times that a user sends a bullet screen in the process of watching the current subscription anchor live broadcast within the last 30 days;
the payment days are the days for which the user has paid for the current subscription anchor within the last 30 days;
whether to pay is whether the user paid for the current subscription anchor within the last 30 days.
The characteristic indexes can reflect the user's favorite degree of each subscription anchor, in other embodiments, the number of the characteristic indexes obtained by mining the user behavior data can be increased or decreased according to the actual situation, the definition of the characteristic indexes is not limited to the nine characteristic indexes, and the characteristic indexes can also be other effective characteristic indexes which can also feed back the user's favorite degree of the subscription anchor.
Step S103: processing the characteristic index according to normalization to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of the characteristic index in a preset time limit to obtain a weighted normalized characteristic index value; and summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor.
Specifically, as shown in fig. 2, the normalized feature indexes corresponding to the feature indexes and the normalized definitions thereof and the weight coefficients corresponding to the feature indexes in about 30 days are shown in the embodiment of the present invention. In this embodiment, each feature index is normalized according to the normalization index shown in fig. 2 to obtain a normalized feature index value; and multiplying each normalized characteristic index value by a weight coefficient in a preset aging corresponding to the characteristic index, wherein in the embodiment of the invention, the preset aging of the weight coefficient is 30 days, and the weight coefficient proportion of each characteristic index meets the following conditions: the number of days of subscription distance, the payment sum, whether the latest watching is carried out, the watching duration, the number of days of watching, the watching days, the screen popping times, the payment days and whether the payment is 3: 2.5: 2: 1.5: 1.2: 1: 0.8: 0.5; and obtaining weighted normalized feature index values according to the normalized feature index values and the corresponding weight coefficients, and summing the weighted normalized feature index values to obtain a score which can reflect the user's love degree to the subscription anchor.
The preset timeliness is used for limiting the use time interval of the weight coefficient of each characteristic index, so that the weight coefficient has timeliness and is convenient to update and manage periodically. It should be explicitly noted that the preset aging is not limited by the embodiment, the preset aging is generally longer than or equal to the preset period in step S101, and may be a period of one week, one month, 45 days, and the like, and those skilled in the art can adjust the preset aging according to the actual application requirement.
Step S104: and sequencing the subscription anchor according to the score of each subscription anchor.
Specifically, the scores of the respective anchor subscriptions obtained in step S103 are integrated, and the anchor subscriptions are sorted by score. In the embodiment of the present invention, the subscription anchor is ranked in the order of scores from large to small, that is, the subscription anchor with large score is ranked in the top.
According to the ordering method of the subscription anchor, the user behavior characteristics are obtained by analyzing the user behavior data in the preset period of the user, the subscription anchor preference model of the user is constructed according to various characteristic indexes capable of effectively reflecting the user preference in the user behavior characteristics, the ordering of the subscription anchor obtained by the subscription anchor preference model can be better matched with the preference degree of the user to the subscription anchor, and therefore the user has higher live broadcast watching enthusiasm and better product use experience.
As shown in fig. 3, which is a flowchart of a subscription anchor sorting method according to a second embodiment of the present invention, the subscription anchor sorting method provided in this embodiment includes the following steps:
step S201: and acquiring user behavior data of the user on the subscription anchor in the live broadcast platform in a preset period.
Specifically, in the embodiment of the present invention, user behavior data of a user on a subscription anchor on a live platform in the last 30 days is obtained. The subscription anchor is the favorite anchor subscribed by the user on the live platform, and the user behavior data are the actions and corresponding data which are respectively executed by the user on each subscription anchor within the last 30 days recorded by the live platform system.
The preset period is used for limiting the time interval of the acquired user behavior data, so that the data is time-efficient and is convenient to update and manage periodically. It should be explicitly noted that the preset period is not limited by the embodiment, and the preset period may be a time period of one week, one month, 45 days, and the like, and a person skilled in the art can adjust the preset period according to actual application requirements.
Step S202: obtaining user behavior characteristics according to the user behavior data; the user behavior feature comprises at least two feature indicators.
Specifically, the user behavior data of the user subscribing to the anchor within the last 30 days obtained in step S201 is analyzed, and the user behavior characteristics corresponding to the user behavior data are obtained by mining, where the user behavior characteristics include at least two characteristic indexes. In the embodiment of the present invention, the obtained user behavior characteristics include the following nine characteristic indexes:
number of days of subscription distance, amount of payment, whether it is the latest to watch, length of watching, number of days of watching distance, number of days of watching, number of bullet screen, number of days of payment, and whether it is payment.
The definition of the nine characteristic indexes is specifically as follows:
the number of the subscription distance days is the number of days from the time when the user subscribes the current subscription anchor on the live broadcast platform to the current day within the last 30 days;
the payment amount is the payment amount of the user to the current subscription anchor within the last 30 days;
whether the latest watching is that whether the user watches the current subscription anchor live broadcast in the live broadcast platform in the last day within the last 30 days;
the watching duration is the duration of watching the current subscription anchor live broadcast by the user within the last 30 days;
the viewing distance days are the days from the last time that the user views the current subscription anchor live broadcast within the last 30 days to the current time;
the watching days are the days that the user has watched the current subscription anchor live broadcast in the last 30 days;
the number of bullet screens is the number of times that a user sends a bullet screen in the process of watching the current subscription anchor live broadcast within the last 30 days;
the payment days are the days for which the user has paid for the current subscription anchor within the last 30 days;
whether to pay is whether the user paid for the current subscription anchor within the last 30 days.
The characteristic indexes can reflect the user's favorite degree of each subscription anchor, in other embodiments, the number of the characteristic indexes obtained by mining the user behavior data can be increased or decreased according to the actual situation, the definition of the characteristic indexes is not limited to the nine characteristic indexes, and the characteristic indexes can also be other effective characteristic indexes which can also feed back the user's favorite degree of the subscription anchor.
Step S203: processing the characteristic index according to normalization to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of the characteristic index in a preset time limit to obtain a weighted normalized characteristic index value; and summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor.
Specifically, as shown in fig. 2, the normalized feature indexes corresponding to the feature indexes and the normalized definitions thereof and the weight coefficients corresponding to the feature indexes in about 30 days are shown in the embodiment of the present invention. In this embodiment, each feature index is normalized according to the normalization index shown in fig. 2 to obtain a normalized feature index value; and multiplying each normalized characteristic index value by a weight coefficient in a preset aging corresponding to the characteristic index, wherein in the embodiment of the invention, the preset aging of the weight coefficient is 30 days, and the weight coefficient proportion of each characteristic index meets the following conditions: the number of days of subscription distance, the payment sum, whether the latest watching is carried out, the watching duration, the number of days of watching, the watching days, the screen popping times, the payment days and whether the payment is 3: 2.5: 2: 1.5: 1.2: 1: 0.8: 0.5; and obtaining weighted normalized feature index values according to the normalized feature index values and the corresponding weight coefficients, and summing the weighted normalized feature index values to obtain a score which can reflect the user's love degree to the subscription anchor.
The preset timeliness is used for limiting the use time interval of the weight coefficient of each characteristic index, so that the weight coefficient has timeliness and is convenient to update and manage periodically. It should be explicitly noted that the preset aging is not limited by the embodiment, the preset aging is generally longer than or equal to the preset period in step S201, and may be a period of one week, one month, 45 days, and the like, and those skilled in the art can adjust the preset aging according to the actual application requirement.
Step S204: and sequencing the subscription anchor according to the score of each subscription anchor.
Specifically, the scores of the respective anchor subscriptions obtained in step S203 are integrated, and the anchor subscriptions are sorted by score. In the embodiment of the present invention, the subscription anchor is ranked in the order of scores from large to small, that is, the subscription anchor with large score is ranked in the top.
Step S205: and pushing the subscription anchor to the user according to the ranking from big to small.
Specifically, according to the ranking from large to small according to the score obtained in step S204, the subscription anchor is sequentially pushed to the subscription anchor display page of the live broadcast platform of the user.
On a live platform, a user often has more than one presentation page subscribed to the anchor. The user usually sets an overview window of the subscription anchor on a personal data home page of a live broadcast platform, the overview window is used as a subscription anchor inlet of the user, usually, only a plurality of anchor display positions are provided, and the user can directly select a certain subscription anchor displayed in the subscription anchor overview window through the subscription anchor inlet so as to conveniently and quickly enter a home page or a live broadcast room of the subscription anchor; the user may also select to enter a subscription anchor overview page from the subscription anchor entry by further operation to find a subscription anchor not shown in the overview window.
In one embodiment, the top ranked subscription anchor of 5 bits is pushed to the user according to a big to small ranking.
In another embodiment, according to the sorting from big to small, the subscription anchor with 5 pushed bits in front is taken as an outer-layer anchor, the rest subscription anchors pushed by the user are taken as inner-layer anchors, and the outer-layer anchor and the inner-layer anchor are pushed to the user; the outer-layer anchor is displayed in the subscription anchor overview window of the live broadcast platform of the user, and the inner-layer anchor is displayed in a subscription anchor overview page obtained from the subscription anchor overview window.
It should be explicitly noted that the number of the foregoing subscription anchor pushed to the user by the present invention is not limited by the foregoing embodiment, and the pushed number is adjusted according to the actual application, and corresponds to the number of display digits of the subscription anchor overview window, and may be a preset number such as 3, 7, 10, etc.
Step S206: and counting the probability that the user clicks the top subscription anchor in a preset time length.
Specifically, in one embodiment, the number of users pushing the top-ranked subscription anchor to the user and the number of users feeding back and clicking the top-ranked subscription anchor to the user of the whole server within the last 30 days are obtained, and the number of users feeding back and clicking the top-ranked subscription anchor is divided by the number of users pushing the top-ranked subscription anchor to the user, so as to obtain the probability. The probability that the user clicks the first subscription anchor in the preset duration is calculated by taking the user of the whole server as an object, so that the most accurate click probability can be obtained.
In another embodiment, the number of users who push and click the top push and subscribe the anchor to users and the number of users who feed and click the top push and subscribe the anchor to users of the extracted group in the last 30 days are obtained, and the number of users who feed and click the top push and subscribe the anchor to users is divided by the number of users who push and subscribe the anchor to users to obtain the probability; for example, 100 users are sampled from a live platform, the top-ranked subscription anchor obtained by the subscription anchor sorting method provided by the invention is pushed to the 100 users, the number of the users who click on the top-ranked subscription anchor in 30 days is counted, and the number is divided by 100 to obtain the probability. The user is selected in a sampling mode to calculate the probability that the user clicks the first subscription anchor in the preset time length, so that the calculation amount can be reduced, and the accurate click probability can be quickly obtained.
Likewise, the preset duration is used to limit the frequency of the statistical probability, so that the statistical probability is convenient to update and manage periodically. It should be noted that the preset time period is not limited by the embodiment, and the preset time period may be the same as or different from the preset period in step S201, and is usually equal to or shorter than the preset time period in step S203, so as to ensure that the weight coefficient during the statistical probability period is not changed. The preset time duration can be a time duration of one week, one month, 45 days and the like, and a person skilled in the art can adjust the preset time duration according to the actual application requirement.
Step S207: and adjusting the weight coefficient of the characteristic index according to the probability.
Specifically, by counting the probability that the user clicks the top-ranked subscription anchor for a preset duration, it can be known whether the subscription anchor ranking obtained from the weight coefficients of the characteristic indexes of the proportion accurately feeds back the user's preference degree to the subscription anchor. And adjusting the weight coefficient of each characteristic index according to the probability to obtain a new weight coefficient ratio of each characteristic index.
In one embodiment, when the probability is confirmed to be smaller than a preset value, the weight coefficient of each characteristic index is replaced by another preset weight coefficient; for example, when the statistical probability that the user clicks the top subscription anchor is less than 50%, the weight coefficient of each feature index is replaced by another preset weight coefficient as follows:
the number of days of subscription distance, the payment sum, whether the latest watching is watched, the watching duration, the number of days of watching, the number of screen flicking times, the number of days of paying and whether the payment is 2: 3: 2.5: 1.5: 1: 0.2.
In another embodiment, when the probability is determined to be smaller than a preset value, adding the weight coefficient of each characteristic index to an adjustment value of the characteristic index, wherein the adjustment value is a positive value or a negative value; for example, when the statistical probability that the user clicks the top subscription anchor is less than 65%, the weight coefficient of each attribute feature index is added to the corresponding adjustment value, and the weight coefficient ratio of each feature index is as follows:
the subscription distance days, the payment amount, whether the latest watching is carried out, the watching duration, the watching distance days, the watching days, the screen flicking times, the paying days, whether the paying is (3-0.4): (2.5+ 0.5): (2-0.5): (1.5+ 0.2): (1.5-0.3): (1.2+ 0.2): (1+ 0.5): (0.8+ 0.2): (0.5-0.3) or not.
By counting the probability of clicking the top subscription anchor by the user with the preset duration and adjusting the weight coefficient of each characteristic index according to the probability, the subscription anchor sequence obtained by the weight coefficient can be better matched with the love degree of the user to the subscription anchor, so that the user has higher live broadcast watching enthusiasm and better product use experience.
Step S208: and comparing the probabilities of different preset durations, and taking the weight coefficient of the preset duration with the maximum probability as the weight coefficient in the preset duration.
Specifically, the probabilities of a plurality of users with preset time length clicking the top subscription anchor are compared, and the weight coefficient of the preset time length corresponding to the maximum probability is used as the weight coefficient in the preset time period, wherein the weight coefficients in different preset time lengths are different; for example, the probabilities of 6 times of user clicks on the top subscription anchor counted in 30 days in the last 180 days are compared, and if the probability counted in the last 30 days is the maximum value of the 6 groups of probabilities, the weight coefficient adopted in the corresponding subscription anchor sorting method in the time duration is used as the weight coefficient of the next quarter subscription anchor sorting method. By comparing the historical statistical probabilities, the most appropriate weight coefficient proportion of each characteristic index can be quickly obtained, and further the ordering of the subscription anchor matched with the user's preference degree can be quickly obtained.
As shown in fig. 4, which is a flowchart of a subscription anchor sorting method according to a third embodiment of the present invention, the subscription anchor sorting method provided in this embodiment includes the following steps:
step S301: randomly dividing all users of the whole server into a preset number of user groups; wherein, the characteristic indexes of each user group are different in weight coefficient in the preset time limit.
Specifically, all users of the whole server are randomly divided into a preset number of user groups; the characteristic indexes adopted by each user group in the follow-up subscription anchor sequencing are different in weight coefficient within preset time limit; for example, all users of the whole server are randomly divided into 5 user groups, and a weight coefficient different from that of other user groups is preset in the preset time limit of the characteristic index of each user group.
Step S302: and acquiring user behavior data of each user group on each subscription anchor on the live broadcast platform in a preset period.
Specifically, in the embodiment of the present invention, user behavior data of each user group on each subscription anchor in the live platform in the last 30 days is obtained. The subscription anchor is the favorite anchor subscribed by the user on the live platform, and the user behavior data are the actions and corresponding data executed by the user of each user group on each subscription anchor within the last 30 days recorded by the live platform system.
The preset period is used for limiting the time interval of the acquired user behavior data, so that the data is time-efficient and is convenient to update and manage periodically. It should be explicitly noted that the preset period is not limited by the embodiment, and the preset period may be a time period of one week, one month, 45 days, and the like, and a person skilled in the art can adjust the preset period according to actual application requirements.
Step S303: obtaining user behavior characteristics according to the user behavior data; the user behavior feature comprises at least two feature indicators.
Step S304: processing the characteristic index according to normalization to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of the characteristic index in a preset time limit to obtain a weighted normalized characteristic index value; and summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor.
Step S305: and sequencing the subscription anchor according to the score of each subscription anchor.
Step S306: and pushing the subscription anchor to the user according to the ranking from big to small.
The steps S303 to S306 are consistent with the steps S202 to S205 in the subscription anchor sorting method provided in the second embodiment of the present invention, and are not described herein again.
Step S307: and counting the probability that the user clicks the first subscription anchor in the preset time of each user group.
Specifically, the probability that the user clicks the top anchor subscription in the group with the preset duration is counted by taking the respective user in each user group as a unit, and the process of counting the probability is not repeated here, and is consistent with step S206 in the method for ordering the anchor subscriptions provided in the second embodiment of the present invention. In this step, the counted number of probabilities is consistent with the preset number of the user group.
Step S308: and acquiring a weight coefficient of the characteristic index of the user group with the maximum probability, and taking the weight coefficient as the weight coefficient in the preset time efficiency of the whole server.
Specifically, the plurality of probabilities obtained in step S307 are compared to obtain the user group corresponding to the maximum probability, so as to obtain the weight coefficient of the feature index of the user group, and the weight coefficient is used as the weight coefficient in the preset time period of the entire server.
By randomly dividing all users into different user groups, adopting different weight coefficients for the characteristic indexes of the different user groups, quickly obtaining the most appropriate weight coefficient proportion of each characteristic index after a preset time, and using the weight coefficient proportion as the weight coefficient in the preset time limit of the whole server, the ordering of the subscription anchor obtained by the whole server can be well matched with the love degree of the user on the subscription anchor, and further the user has higher live broadcast watching enthusiasm and better product use experience.
As shown in fig. 5, which is a schematic diagram of a subscription anchor sorting apparatus according to an embodiment of the present invention, the subscription anchor sorting apparatus includes a user behavior data obtaining module 501, a user behavior feature obtaining module 502, a subscription anchor score calculating module 503, and a subscription anchor sorting module 504.
The user behavior data acquisition module 501: the method comprises the steps of obtaining user behavior data of a user on a subscription anchor on a live broadcast platform in a preset period;
the user behavior feature obtaining module 502: the user behavior data is used for acquiring user behavior characteristics according to the user behavior data; the user behavior characteristics comprise at least two characteristic indexes;
subscription anchor score calculation module 503: the characteristic index is used for carrying out normalization processing on the characteristic index to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of the characteristic index in a preset time limit to obtain a weighted normalized characteristic index value; summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor;
subscription Anchor ordering Module 504: and the system is used for sequencing the subscription anchor according to the score of each subscription anchor.
Preferably, the characteristic indicator includes:
number of days of distance subscribed and amount of payment;
the number of the subscription distance days is the number of days between the time when the user subscribes the current subscription anchor on the live broadcast platform and the current time;
the payment amount is the payment amount of the user to the current subscription anchor;
the normalization indexes corresponding to the subscription distance days are as follows: 1- (the number of subscription distance days/the preset period);
the normalization indexes corresponding to the payment amount are as follows: the payment amount/the total payment amount of the user on the live broadcast platform.
Further, the characteristic index further includes:
whether the viewing is latest, the viewing duration, the number of viewing distance days, the number of viewing days, the number of bullet screen times, the number of payment days and whether the payment is made;
whether the current subscription anchor live broadcast is watched or not when the user watches the live broadcast on the live broadcast platform in the last day;
the watching duration is the duration for watching the current subscription anchor live broadcast by the user;
the viewing distance days are the days from the time when the user last views the current subscription anchor live broadcast to the current time;
the watching days are days for the user to watch the current subscription anchor live broadcast;
the screen popping times are the times of sending the screen popping when a user watches the current subscription anchor live broadcast;
the payment days are the days for which the user pays for the current subscription anchor;
the payment is whether the user pays for the current subscription anchor.
Preferably, the subscription anchor sorting module 504 further includes a subscription anchor pushing module, and after sorting the subscription anchors according to the scores of the subscription anchors, the subscription anchor pushing module is configured to:
and pushing the subscription anchor to the user according to the ranking from big to small.
Preferably, the subscription anchor push module is specifically configured to:
pushing a preset number of subscription anchor ranked in front to the user according to the ranking from big to small; or
According to the sorting from big to small, pushing a preset number of subscription anchor ranked in front as an outer-layer anchor, pushing the rest subscription anchors pushed by the user as inner-layer anchors, and pushing the outer-layer anchor and the inner-layer anchor to the user; the outer-layer anchor is displayed in a subscription anchor overview window of the user on a live broadcast platform, and the inner-layer anchor is displayed in a subscription anchor overview page obtained from the subscription anchor overview window.
Preferably, the subscription anchor ranking module 504 further includes a weight adjusting module, after the subscription anchor is pushed to the user according to the ranking from large to small, configured to:
counting the probability that a user clicks a top subscription anchor in a preset duration;
and adjusting the weight coefficient of the characteristic index according to the probability.
Preferably, the weight adjusting module is configured to count the probability that the user clicks the top subscription anchor in a preset duration, and specifically configured to:
acquiring the number of users pushing the top-ranked subscription anchor to the users and the number of users feeding back and clicking the top-ranked subscription anchor, and dividing the number of the users feeding back and clicking the top-ranked subscription anchor by the number of the users pushing the top-ranked subscription anchor to the users to obtain a probability; or
Acquiring the number of users who push and click the top push subscription anchor to users of an extraction group within a preset time length, and dividing the number of the users who click and click the top push subscription anchor by the number of the users who push and click the top push subscription anchor to the users to obtain a probability;
the weight adjusting module is specifically configured to adjust the weight coefficient of the characteristic index according to the probability, and is further configured to:
confirming that the probability is smaller than a preset value, and replacing the weight coefficient of each characteristic index with another preset weight coefficient; or
Confirming that the probability is smaller than a preset value, and adding the weight coefficient of each characteristic index to the adjustment value of the characteristic index, wherein the adjustment value is a positive value or a negative value;
the weight adjustment module is further configured to:
after the weight coefficient of the characteristic index is adjusted according to the probability, the probabilities of different preset durations are compared, and the weight coefficient of the preset duration with the maximum probability is used as the weight coefficient in the preset time efficiency; wherein, the weighting coefficients of different preset durations are different.
Preferably, the data obtaining module 501 is further configured to:
randomly dividing all users of the whole server into a preset number of user groups; wherein, the weighting coefficients of the characteristic indexes of each user group are different;
acquiring user behavior data of each subscription anchor of users of each user group on a live broadcast platform in a preset period;
the subscription anchor sorting module 504, after sorting the subscription anchors according to the scores of the subscription anchors, is further configured to:
pushing the subscription anchor to the user according to the sequence from big to small;
counting the probability that each user clicks the first subscription anchor in a preset time length of each user group;
and acquiring a weight coefficient of the characteristic index of the user group with the maximum probability, and taking the weight coefficient as the weight coefficient in the preset time efficiency of the whole server.
According to the subscription anchor ordering device provided by the embodiment of the invention, the user behavior characteristics are obtained by analyzing the user behavior data in the preset period of the user, the subscription anchor preference model of the user is constructed according to various characteristic indexes which can effectively reflect the preference of the user in the user behavior characteristics, and the subscription anchor ordering obtained by the subscription anchor preference model can be better matched with the preference degree of the user to the subscription anchor, so that the user has higher live broadcast watching enthusiasm and better product use experience.
Fig. 6 is a schematic diagram of a terminal structure provided by the present invention. The terminal according to the embodiment of the present invention may include one or more processors 601, and further include a memory 602, a WiFi (wireless fidelity) circuit 603, an RF (Radio Frequency) circuit 604, an audio circuit 605, a sensor 606, an output device 607, an input device 604, and a power supply 609, where the processor 601 is a control center of the terminal and is connected to the above portions by using various interfaces and lines. Those skilled in the art will appreciate that the terminal structure shown in fig. 6 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The WiFi circuitry 603 may provide wireless local area network or internet access for the user; which may include an antenna, a WiFi module, etc. RF circuitry 604 may receive and transmit information, or signals during a call; which may include an antenna, at least one amplifier, a tuner, one or more oscillators, couplers, duplexers, and so forth. The audio circuit 605 can convert the received audio data into an electric signal and transmit the electric signal to a loudspeaker, and can also convert a sound signal collected by a microphone into audio data and send the audio data to the processor 601 for processing; which may be provided with a speaker, microphone, earphone interface, etc. The sensor 606 can be used for sensing external signals and sending the signals to the processor 601 for processing; which may include motion sensors, light sensors, etc. Output device 607 may be used to display various signals; the Display panel may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), and the like. Input device 604 may be used to enter information such as numbers and characters; which may be physical keys, touch panels, etc. The power supply 609 can supply power for each part of the terminal and is logically connected with the processor 609 through a power management system; which may include one or more components of a dc or ac power source, a charging system, a power status indicator, etc. The memory 602 may be used to store software programs and modules; it may be a computer readable storage medium, specifically a hard disk, a flash memory, etc. The processor is a control center of the terminal, and performs various functions of the terminal and processes terminal data by operating or executing software programs and/or modules stored in the memory 602 and calling data stored in the memory 602.
As one embodiment, a terminal includes: one or more processors 601, a memory 602, one or more applications, wherein the one or more applications are stored in the memory 602 and configured to be executed by the one or more processors 601, the one or more programs configured to perform the subscription-based anchor ranking methods provided by the first, second and third embodiments of the present invention described above.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium. The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (8)
1. A method for subscription-anchor ranking, comprising:
randomly dividing all users in the server into a preset number of user groups; wherein the characteristic indexes of each user group in the preset number of user groups have different weight coefficients within a preset time limit;
acquiring user behavior data of each subscription anchor of users of each user group on a live broadcast platform in a preset period;
obtaining user behavior characteristics according to the user behavior data; the user behavior characteristics comprise at least two characteristic indexes;
processing the characteristic index according to normalization to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of the characteristic index in a preset time limit to obtain a weighted normalized characteristic index value; summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor;
sequencing the subscription anchor according to the score of each subscription anchor;
pushing the subscription anchor to the user according to the sequence from big to small;
counting the probability that each user clicks the first subscription anchor in a preset time length of each user group;
and acquiring a weight coefficient of the characteristic index of the user group with the maximum probability, and taking the weight coefficient as the weight coefficient of all users of the whole server in a preset time efficiency.
2. The subscription-anchor ranking method of claim 1, wherein the feature metrics comprise:
number of days of distance subscribed and amount of payment;
the number of the subscription distance days is the number of days between the time when the user subscribes the current subscription anchor on the live broadcast platform and the current time;
the payment amount is the payment amount of the user to the current subscription anchor;
the normalization indexes corresponding to the subscription distance days are as follows: 1- (the number of subscription distance days/the preset period);
the normalization indexes corresponding to the payment amount are as follows: the payment amount/the total payment amount of the user on the live broadcast platform.
3. The subscription-anchor ranking method of claim 2, wherein the feature metrics further comprise:
whether the viewing is latest, the viewing duration, the number of viewing distance days, the number of viewing days, the number of bullet screen times, the number of payment days and whether the payment is made;
whether the current subscription anchor live broadcast is watched or not when the user watches the live broadcast on the live broadcast platform in the last day;
the watching duration is the duration for watching the current subscription anchor live broadcast by the user;
the viewing distance days are the days from the time when the user last views the current subscription anchor live broadcast to the current time;
the watching days are days for the user to watch the current subscription anchor live broadcast;
the number of the barrage is the number of the barrage sent by the user in the process of watching the current subscription anchor live broadcast;
the payment days are the days for which the user pays for the current subscription anchor;
the payment is whether the user pays for the current subscription anchor.
4. The subscription anchor ordering method according to claim 1, wherein said pushing the subscription anchor to the user according to a big-to-small ordering comprises:
pushing a preset number of subscription anchor ranked in front to the user according to the ranking from big to small; or
According to the sorting from big to small, pushing a preset number of subscription anchor ranked in front as an outer-layer anchor, pushing the rest subscription anchors pushed by the user as inner-layer anchors, and pushing the outer-layer anchor and the inner-layer anchor to the user; the outer-layer anchor is displayed in a subscription anchor overview window of the user on a live broadcast platform, and the inner-layer anchor is displayed in a subscription anchor overview page entering from the subscription anchor overview window.
5. The subscription anchor sorting method according to claim 1, wherein after pushing the subscription anchor to the user according to the sort from large to small, further comprising:
counting the probability that a user clicks a top subscription anchor in a preset duration;
adjusting the weight coefficient of the characteristic index according to the probability;
the counting of the probability that the user clicks the top subscription anchor in the preset duration comprises the following steps:
acquiring the number of users pushing the top-ranked subscription anchor to the users and the number of users feeding back and clicking the top-ranked subscription anchor, and dividing the number of the users feeding back and clicking the top-ranked subscription anchor by the number of the users pushing the top-ranked subscription anchor to the users to obtain a probability; or
Acquiring the number of users who push and click the top push subscription anchor to users of an extraction group within a preset time length, and dividing the number of the users who click and click the top push subscription anchor by the number of the users who push and click the top push subscription anchor to the users to obtain a probability;
the adjusting the weight coefficient of the characteristic index according to the probability comprises:
confirming that the probability is smaller than a preset value, and replacing the weight coefficient of each characteristic index with another preset weight coefficient; or
And confirming that the probability is smaller than a preset value, and adding the weight coefficient of each characteristic index to the adjustment value of the characteristic index, wherein the adjustment value is a positive value or a negative value.
6. The method of claim 5, wherein after adjusting the weighting factor of the feature indicator according to the probability, the method further comprises:
comparing the probabilities of different preset durations, and taking the weight coefficient of the preset duration with the maximum probability as the weight coefficient in the preset time efficiency; wherein, the weighting coefficients of different preset durations are different.
7. A subscription-anchor sorting apparatus, comprising:
a user behavior data acquisition module: the system comprises a server, a user group and a user group server, wherein the user group server is used for randomly dividing all users in the server into a preset number of user groups; wherein the characteristic indexes of each user group in the preset number of user groups have different weight coefficients within a preset time limit; acquiring user behavior data of each subscription anchor of users of each user group on a live broadcast platform in a preset period;
a user behavior feature acquisition module: the user behavior data is used for acquiring user behavior characteristics according to the user behavior data; the user behavior characteristics comprise at least two characteristic indexes;
a subscription anchor score calculation module: the characteristic index is used for carrying out normalization processing on the characteristic index to obtain a normalized characteristic index value; multiplying the normalized characteristic index value by a weight coefficient of the characteristic index in a preset time limit to obtain a weighted normalized characteristic index value; summing the weighted normalized feature index values of the feature indexes to obtain the score of the subscription anchor;
a subscription anchor ordering module: the system comprises a database, a user terminal and a user terminal, wherein the database is used for storing the scores of all the subscription anchor; pushing the subscription anchor to the user according to the sequence from big to small; counting the probability that each user clicks the first subscription anchor in a preset time length of each user group; and acquiring a weight coefficient of the characteristic index of the user group with the maximum probability, and taking the weight coefficient as the weight coefficient of all users of the whole server in a preset time efficiency.
8. A terminal, characterized in that it comprises:
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors for performing the subscription-anchor ranking method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711120851.XA CN107948752B (en) | 2017-11-14 | 2017-11-14 | Ordering method, device and terminal for subscription anchor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711120851.XA CN107948752B (en) | 2017-11-14 | 2017-11-14 | Ordering method, device and terminal for subscription anchor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107948752A CN107948752A (en) | 2018-04-20 |
| CN107948752B true CN107948752B (en) | 2021-01-08 |
Family
ID=61935039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711120851.XA Active CN107948752B (en) | 2017-11-14 | 2017-11-14 | Ordering method, device and terminal for subscription anchor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107948752B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086995A (en) * | 2018-08-01 | 2018-12-25 | 广州虎牙信息科技有限公司 | Evaluation method, device, equipment and the storage medium of application program download path |
| CN109168048B (en) * | 2018-08-01 | 2020-12-15 | 广州虎牙信息科技有限公司 | Determination method, device and equipment of anchor grade and storage medium |
| CN109257612B (en) * | 2018-08-09 | 2020-11-20 | 广州虎牙信息科技有限公司 | Game live broadcast potential evaluation method and device, computer storage medium and server |
| CN109168049B (en) * | 2018-09-03 | 2021-03-23 | 广州虎牙信息科技有限公司 | Live program grade evaluation method and device, storage medium and server |
| CN109409983A (en) * | 2018-09-19 | 2019-03-01 | 北京创鑫旅程网络技术有限公司 | A kind of method and device of ticket type sequence |
| CN112312173B (en) * | 2019-07-24 | 2023-03-28 | 广州虎牙科技有限公司 | Anchor recommendation method and device, electronic equipment and readable storage medium |
| CN112714329B (en) * | 2020-12-23 | 2023-09-26 | 广州博冠信息科技有限公司 | Display control method and device for live broadcasting room, storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106131584A (en) * | 2016-07-25 | 2016-11-16 | 北京金山安全软件有限公司 | Live broadcast information display method and device and electronic equipment |
| CN106604044A (en) * | 2016-11-21 | 2017-04-26 | 武汉斗鱼网络科技有限公司 | Direct broadcast room recommendation strategy assessment method, user equipment, and server system |
| CN106878772A (en) * | 2017-02-27 | 2017-06-20 | Ut斯达康(深圳)技术有限公司 | A kind of program commending method and device |
| CN106982381A (en) * | 2017-03-31 | 2017-07-25 | 武汉斗鱼网络科技有限公司 | Homepage recommendation process method and device |
| CN107172452A (en) * | 2017-04-25 | 2017-09-15 | 北京潘达互娱科技有限公司 | Direct broadcasting room recommends method and device |
| CN107205178A (en) * | 2017-04-25 | 2017-09-26 | 北京潘达互娱科技有限公司 | Direct broadcasting room recommends method and device |
-
2017
- 2017-11-14 CN CN201711120851.XA patent/CN107948752B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106131584A (en) * | 2016-07-25 | 2016-11-16 | 北京金山安全软件有限公司 | Live broadcast information display method and device and electronic equipment |
| CN106604044A (en) * | 2016-11-21 | 2017-04-26 | 武汉斗鱼网络科技有限公司 | Direct broadcast room recommendation strategy assessment method, user equipment, and server system |
| CN106878772A (en) * | 2017-02-27 | 2017-06-20 | Ut斯达康(深圳)技术有限公司 | A kind of program commending method and device |
| CN106982381A (en) * | 2017-03-31 | 2017-07-25 | 武汉斗鱼网络科技有限公司 | Homepage recommendation process method and device |
| CN107172452A (en) * | 2017-04-25 | 2017-09-15 | 北京潘达互娱科技有限公司 | Direct broadcasting room recommends method and device |
| CN107205178A (en) * | 2017-04-25 | 2017-09-26 | 北京潘达互娱科技有限公司 | Direct broadcasting room recommends method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107948752A (en) | 2018-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107948752B (en) | Ordering method, device and terminal for subscription anchor | |
| CN109299387B (en) | Message pushing method and device based on intelligent recommendation and terminal equipment | |
| CN108259936B (en) | Question-answering method based on live broadcast technology, server and storage medium | |
| WO2019184111A1 (en) | Push message processing method and apparatus, readable storage medium, and terminal device | |
| CN108153463B (en) | Application interface display control method and device, storage medium and mobile terminal | |
| CN111143697B (en) | Content recommendation method and related device | |
| US20200356572A1 (en) | Search ranking method and apparatus, electronic device and storage medium | |
| CN108322829A (en) | Personalized main broadcaster recommends method, apparatus and electronic equipment | |
| CN109274987B (en) | Video set ordering method, server and readable storage medium | |
| CN111478963B (en) | Message pushing method and device, electronic equipment and computer readable storage medium | |
| US20130167041A1 (en) | Posting activity visualization | |
| WO2016183936A1 (en) | Application icon arrangement method and device, mobile terminal and storage medium | |
| CN111105269B (en) | Advertisement delivery processing method, device, equipment and storage medium | |
| CN105338154A (en) | Method, device and terminal for contact person ordering | |
| CN112445970A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN111428032A (en) | Content quality evaluation method and device, electronic device, and storage medium | |
| CN110956505A (en) | Advertisement inventory estimation method and related device | |
| CN107547646B (en) | Application program pushing method and device, terminal and computer readable storage medium | |
| WO2020147007A1 (en) | Information pushing method and related product | |
| CN112995765B (en) | Network resource display method and device | |
| WO2018202127A1 (en) | Information pushing method and device, storage medium, and electronic device | |
| CN116307552A (en) | Work content matching method based on workload data information | |
| JP6247504B2 (en) | Search formula creation device, search formula creation method, and program | |
| WO2022150573A1 (en) | Providing ambient information based on learned user context and interaction, and associated systems and devices | |
| CN115239356A (en) | Recommended content management method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |