Disclosure of Invention
The embodiment of the invention provides a live broadcast room recommending method, electronic equipment and a readable storage medium, which are used for providing a live broadcast room recommending method based on a memory function.
In a first aspect, the present invention provides a live broadcast room recommendation method, including:
under the condition that a live broadcast application program is started, determining a first live broadcast room set viewed by a user within a first preset time range, wherein the first live broadcast room set corresponds to a plurality of second live broadcast room sets, and the second live broadcast room sets are live broadcast room sets similar to the first live broadcast room set;
calculating and obtaining a re-watching probability of each second live broadcast room set in the plurality of second live broadcast room sets based on a memory function, wherein the memory function is used for representing the watching memory of the audience to the first live broadcast room set at the current moment, and the re-watching probability is the probability that the audience watches the first live broadcast room set in the first preset time range and watches the second live broadcast room set in the second preset time range;
determining a second live room set with the largest review probability in the plurality of second live room sets;
and pushing the live broadcast rooms meeting preset conditions in the second live broadcast room set with the maximum watching probability to the user.
Optionally, the obtaining, by calculation, a review probability of each second live broadcast room set in the plurality of second live broadcast room sets based on a memory function includes:
when the review probability of each second live broadcast room set in the second live broadcast room sets is calculated, based on a memory function formula, determining the memory value of the whole network user to the first live broadcast room set at the current moment, determining the number of people watching the second live broadcast room set at the current moment, and determining the number of people watching the second live broadcast room set in the second time range, wherein the review probability of the second live broadcast room set is the difference between the number of people watching the second live broadcast room set at the current moment and the memory value of the whole network user to the first live broadcast room set at the current moment and the number of people watching the second live broadcast room set in the second time range;
the memory function formula is m (u, T, s) ═ md(s) + mu (u, T, s), and represents a watching memory function of the user u to the first live broadcast room set s at the current time T, md(s) ═ N (s, T)/N(s), N(s) is the total number of people watching the first live broadcast room set s in the first preset time range, and N(s) is the total number of people watching the first live broadcast room set s in the first preset time range*T) is the number of people who watch the second live broadcast room set s within the second preset time range T after watching among all users watching the first live broadcast set s within the first preset time range,λ is an attenuation coefficient, T1 is a time point set of the user u watching the first set of live broadcast rooms s in the second time range, and the memory value of the full-network user to the first set of live broadcast rooms at the current moment is
Optionally, the pushing, to the user, the live broadcast room meeting the preset condition in the second live broadcast room set with the largest viewing probability includes:
after the user watches a first live broadcast room in the first live broadcast room set, pushing a second live broadcast room, with the similarity between the second live broadcast room set and the first live broadcast room being greater than a first preset threshold value, in the second live broadcast room set with the maximum watching probability to the user.
Optionally, the pushing, to the user, the live broadcast room meeting the preset condition in the second live broadcast room set with the largest viewing probability includes:
and after the user watches any one live broadcast room in the first live broadcast room set, pushing a second live broadcast room, of which the similarity between the second live broadcast room set with the maximum watching probability and the live broadcast rooms in the first live broadcast room set is greater than a second preset threshold, to the user.
Optionally, the watching duration of each live broadcast room in the first live broadcast room set is greater than a preset duration.
In a second aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes:
the device comprises a first determining unit, a second determining unit and a live broadcast processing unit, wherein the first determining unit is used for determining a first live broadcast room set viewed by a user within a first preset time range under the condition that a live broadcast application program is started, the first live broadcast room set corresponds to a plurality of second live broadcast room sets, and the second live broadcast room sets are live broadcast room sets similar to the first live broadcast room set;
a calculating unit, configured to calculate and obtain a re-watching probability of each second live broadcast room set in the plurality of second live broadcast room sets based on a memory function, where the memory function is used to represent viewing memory of a viewer to the first live broadcast room set at a current time, and the re-watching probability is a probability that the viewer views the first live broadcast room set within the first preset time range and views the second live broadcast room set within the second preset time range;
a second determining unit, configured to determine a second live broadcast room set with a largest re-watching probability in the plurality of second live broadcast room sets;
and the pushing unit is used for pushing the live broadcast rooms meeting preset conditions in the second live broadcast room set with the maximum watching probability to the user.
Optionally, the computing unit is configured to:
when the review probability of each second live broadcast room set in the second live broadcast room sets is calculated, based on a memory function formula, determining the memory value of the whole network user to the first live broadcast room set at the current moment, determining the number of people watching the second live broadcast room set at the current moment, and determining the number of people watching the second live broadcast room set in the second time range, wherein the review probability of the second live broadcast room set is the difference between the number of people watching the second live broadcast room set at the current moment and the memory value of the whole network user to the first live broadcast room set at the current moment and the number of people watching the second live broadcast room set in the second time range;
the memory function formula is m (u, T, s) ═ md(s) + mu (u, T, s), and represents a watching memory function of the user u to the first live broadcast room set s at the current time T, md(s) ═ N (s, T)/N(s), N(s) is the total number of people watching the first live broadcast room set s in the first preset time range, and N(s) is the total number of people watching the first live broadcast room set s in the first preset time range*T) is that all users have watched the first direct broadcast set s within the first preset time rangeThe number of people watching the second live broadcast room set s within a second preset time range T after watching,λ is an attenuation coefficient, T1 is a time point set of the user u watching the first set of live broadcast rooms s in the second time range, and the memory value of the full-network user to the first set of live broadcast rooms at the current moment is
Optionally, the pushing unit is configured to: after the user watches a first live broadcast room in the first live broadcast room set, pushing a second live broadcast room, with the similarity between the second live broadcast room set and the first live broadcast room being greater than a first preset threshold value, in the second live broadcast room set with the maximum watching probability to the user.
Optionally, the pushing unit is configured to: and after the user watches any one live broadcast room in the first live broadcast room set, pushing a second live broadcast room, of which the similarity between the second live broadcast room set with the maximum watching probability and the live broadcast rooms in the first live broadcast room set is greater than a second preset threshold, to the user.
Optionally, the watching duration of each live broadcast room in the first live broadcast room set is greater than a preset duration.
In a third aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes a processor, and the processor is configured to implement, when executing a computer program stored in a memory, the steps of the live broadcast recommendation method in the foregoing first aspect.
In a fourth aspect, an embodiment of the present invention provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the live broadcast recommendation method as described in the foregoing first aspect embodiment.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
in the technical scheme of the embodiment of the invention, under the condition that the live application program is started, a first live room set watched by a user within a first preset time range is determined, wherein the first live room set comprises a plurality of similar second live room sets. And then, accurately measuring the re-watching probability of the user watching the similar second live broadcast room sets after watching the first live broadcast room set through a memory function, after the re-watching probability of each similar second live broadcast room set is calculated, selecting the second live broadcast room set with the maximum re-watching probability, and pushing the live broadcast rooms meeting preset conditions in the second live broadcast room set with the maximum re-watching probability to the user. Therefore, the interest change of the user to the similar live broadcast room after watching the live broadcast room is accurately measured through the memory function, the interest change of the user is fully considered, and the effective and reliable recommended live broadcast room is provided for the user.
Examples
Referring to fig. 1, a first embodiment of the present invention provides a live broadcast room recommendation method, including the following steps:
s101: under the condition that a live broadcast application program is started, determining a first live broadcast room set viewed by a user within a first preset time range, wherein the first live broadcast room set corresponds to a plurality of second live broadcast room sets, and the second live broadcast room sets are live broadcast room sets similar to the first live broadcast room set;
s102: calculating and obtaining a re-watching probability of each second live broadcast room set in the plurality of second live broadcast room sets based on a memory function, wherein the memory function is used for representing the watching memory of the audience to the first live broadcast room set at the current moment, and the re-watching probability is the probability that the audience watches the first live broadcast room set in the first preset time range and watches the second live broadcast room set in the second preset time range;
s103: determining a second live room set with the largest review probability in the plurality of second live room sets;
s104: and pushing the live broadcast rooms meeting preset conditions in the second live broadcast room set with the maximum watching probability to the user.
Specifically, the recommendation method in this embodiment may be applied to a server side of a live application, and when the server determines that a client corresponding to a certain user starts the live application, the server stores history records of the users, and then the server determines, in step S101, a first live room set S viewed by the user within a first preset time range by calling the history record corresponding to the user. Meanwhile, the recommendation method in this embodiment may be applied to a client for installing a live application, where the client may be an electronic device such as a mobile phone, a tablet computer, a desktop computer, or other electronic devices, and the application is not limited herein. When the client starts a live application, a history record corresponding to a user of the client may be requested from the server, and then a first live broadcast room set S viewed by the user within a first preset time range is determined in step S101.
In this embodiment, the first preset time range may be set according to actual needs, for example, may be set to the first 5 days of the closest 10 days from the current time, for example: the current time is 10 days closest to the current time, the current time comprises the 1 st day to the 10 th day from far to near, and the first preset time range is from the 1 st day to the 5 th day. The first set of live rooms s that the user has viewed from day 1 to day 5 are counted. The first live broadcast room set s corresponds to a plurality of similar second live broadcast room sets s, and the second live broadcast room sets s are different from each other.
Further, in step S102, the method in this embodiment measures, by using a memory function, a change in interest of the user in viewing the first live broadcast room set and then similar to each second live broadcast room set S — that is: and calculating the re-watching probability of the user watching the first live broadcasting room set in a first preset time range and watching the second live broadcasting room set s in a second preset time range based on the memory function. Such as: the first live room set s corresponds to 3 similar second live room sets s1, s2, and s3, respectively. It can be obtained based on the memory function that the probability of review Ps1 of the second live broadcast room set s1 is 0.6, the probability of review Ps2 of the second live broadcast room set s2 is 0.8, and the probability of review Ps3 of the second live broadcast room set s3 is 0.2. Wherein the second time range is after the first time range, such as: the method comprises the steps that 10 days closest to the current time exist, the days from 1 st to 10 th are included from far to near from the current time, the first preset time range is from 1 st to 5 th, and the second time range is from 6 th to 10 th. In a specific implementation process, the first time range and the second time range may be set according to actual needs, and the present application is not limited herein.
Further, in step S103, the second live broadcast room set with the highest re-view probability is determined, such as the second live broadcast room set S2 in the above example, among the second live broadcast room set S1, the second live broadcast room set S2, and the second live broadcast room set S3. After the second live broadcast room set with the highest review probability is selected, the fact that the willingness of the user to review the live broadcast rooms in the second live broadcast room set is high is indicated, the live broadcast rooms meeting the preset conditions are selected from the second live broadcast room set with the highest review probability through the step S104 and pushed to the user, and due to the fact that the change of the user interest is considered, the live broadcast rooms recommended to the user can be more effective.
Further, in step S102, when calculating the re-viewing probability of each second live broadcast room set, a memory function is required, where the memory function corresponds to a formula m (u, T, S) ═ md (S) + mu (u, T, S), and represents a viewing memory function of the user u to the first live broadcast room set S at the current time T, and md (S) ═ N (S, T)/N (S), and md (S) is measured by using the historical viewing records of the users over the network, and is a default memory function related only to the first live broadcast room set S, and reflects the potential viewing possibility of the public to the first live broadcast room set S. Wherein N(s) is the total number of people watching s in the first live broadcast room set in the first preset time range, and N(s)*T) is the number of people who watch the second live broadcast room set s within the second preset time range T after watching among all users watching the first live broadcast set s within the first preset time range, and T is the length of the memory time, which can be set according to actual needs, and the application is not limited herein.
Wherein,mu (u, t, s) is the viewing memory of the user u for the first set of live rooms s at the current moment t, reflecting the potential viewing possibilities of the person for the first set of live rooms s. In this formula, λ is an attenuation coefficient, and is a constant greater than 0. T1 is a set of time points in the second time frame T when the user u watches the first set s of live rooms, and since the user's memory retention in the live rooms decays with time, the watching memory is estimated by an exponential distribution.
The memory value of the single user to the first live broadcast room set s by the current time can be obtained by the above formula m (u, t, s) ═ md(s) + mu (u, t, s), and further, the memory value of the whole network user to the first live broadcast room set s at the current time can be obtained asI.e. make statistics onThe sum of the memorized values of all users in a time range for the first inter-session set s. In such a way, the memory value of the current-time full-network user corresponding to each second live broadcast room set to the first live broadcast room set s can be obtained.
Further, when calculating the probability of watching each second live broadcast room set, the number of people watching the second live broadcast room set at the current moment needs to be countedAnd counting the number of people who have viewed the second set of live rooms within a second time frameAnd the watching probability corresponding to the second live broadcast room set is the difference value of the number of people watching the second live broadcast room set at the current moment divided by the memory value of the whole network users to the first live broadcast room set at the current moment and the number of people watching the second live broadcast room set in the second time range. The formula for the probability of viewability for this second set of live rooms can be expressed as:
the calculation of the probability of re-viewing for the second set of live rooms is explained in detail below in a complete example. The method comprises the steps that 10 days closest to the current time exist, the days from 1 st to 10 th are included from far to near from the current time, the first preset time range is from 1 st to 5 th, and the second time range is from 6 th to 10 th. And (3) the users watch the first live broadcast room set s from day 1 to day 5, and the watching records of the second live broadcast room set s4 can be obtained for the second live broadcast room set s4 similar to the first live broadcast room set s from day 6 to day 10.
First, the total number of people who watched the first direct broadcast set s from day 1 to day 5 was counted as 10000, and watched from day 1 to day 5If the number of persons who viewed the second live broadcast room set s4 from day 6 to day 10 after the first live broadcast room set s is 2000, md(s) -2000/10000 is 0.2. A user a who views the first live broadcast room set s from day 1 to day 5 views the second live broadcast room set s4 on the first 2 days and the first 10 days of the current time, and the decay coefficient of the exponential distribution is 0.1, then mu (u, t, s) ═ e-2*0.1+e-10*0.11.186, indicating a remembered value for user a for the first set of live rooms s of 1.186. Assuming that the sum of the memory values of the users in the whole network for the first live broadcast set s at the current time is 20000, 500 people watch the second live broadcast set s4 at the current time, and 19000 people watch the second live broadcast set s4 from the 6 th day to the 10 th day before the current time, the review probability of the second live broadcast set s4 is 500/(20000 19000) and 0.5.
Further, in order to ensure the validity of the statistical history, when counting the number of views, it is necessary to eliminate invalid views, such as: when the watching time length is less than the preset time length (such as 1 minute, 2 minutes and the like), the watching is determined to be invalid, and the record is rejected when the watching times are counted. Meanwhile, for each live broadcast room in the first live broadcast room set, the watching time length of the user is greater than a preset time length (such as 1 minute, 2 minutes and the like).
Specifically, in this embodiment, in step S104, the following two live broadcast push methods can be adopted:
the first method comprises the following steps: after the user watches a first live broadcast room in the first live broadcast room set, pushing a second live broadcast room, with the similarity between the second live broadcast room set and the first live broadcast room being greater than a first preset threshold value, in the second live broadcast room set with the maximum watching probability to the user.
Specifically, in this embodiment, if the user has watched the first live broadcast room a in the first live broadcast room set, because the second live broadcast room set with the largest watching probability is determined in the foregoing manner, the second live broadcast room set with the largest watching probability may include a plurality of second live broadcast rooms B similar to the first live broadcast room a, the live broadcast rooms with similarity greater than the first preset threshold value to the first live broadcast room a selected from the plurality of second live broadcast rooms B are pushed to the user, the first preset threshold value may be set to 0.5, 0.6, and other numerical values may also be set as required, and no limitation is imposed on this application.
And the second method comprises the following steps: and after the user watches any one live broadcast room in the first live broadcast room set, pushing a second live broadcast room, of which the similarity between the second live broadcast room set with the maximum watching probability and the live broadcast rooms in the first live broadcast room set is greater than a second preset threshold, to the user.
Specifically, in this embodiment, if the user has viewed any one live broadcast room in the first live broadcast room set, since the second live broadcast room set with the largest re-viewing probability is determined in the foregoing manner, if the first live broadcast room set includes live broadcast room a1, live broadcast room a2, and live broadcast room A3. The second live broadcast room set with the largest re-watching probability comprises a live broadcast room B1, a live broadcast room B2, a live broadcast room B3, a live broadcast room B4 and a live broadcast room B5, wherein the live broadcast room B1 and the live broadcast room B2 are similar to the live broadcast room a1, the similarity between the live broadcast room B1 and the live broadcast room a1 is 0.4, and the similarity between the live broadcast room B2 and the live broadcast room a1 is 0.7. Live broadcast room B3 and live broadcast room B4 are similar to live broadcast room a2, live broadcast room B3 and live broadcast room a2 have a similarity of 0.65, and live broadcast room B4 and live broadcast room a2 have a similarity of 0.5. Live room B5 is a live room similar to live room A3, and live room B5 has a similarity of 0.75 to live room A3. And selecting live broadcasting rooms with similarity greater than a second preset threshold with the live broadcasting rooms in the first live broadcasting room set from the second live broadcasting room set with the maximum re-watching probability, and pushing the selected live broadcasting rooms to the user, wherein if the second preset threshold is set to be 0.6, the live broadcasting rooms B2, B3 and B5 need to be recommended to the user.
Of course, the recommendation method is not limited to the above two methods, and other methods may also be adopted, such as: and pushing all live broadcast rooms in the second live broadcast room set with the maximum review probability to the user. The application is not limited thereto.
Referring to fig. 2, a third embodiment of the present invention provides an electronic device, including:
a first determining unit 201, configured to determine, when a live broadcast application is started, a first live broadcast room set viewed by a user within a first preset time range, where the first live broadcast room set corresponds to multiple second live broadcast room sets, and the second live broadcast room set is a live broadcast room set similar to the first live broadcast room set;
a calculating unit 202, configured to calculate and obtain a re-watching probability of each second live broadcast room set in the plurality of second live broadcast room sets based on a memory function, where the memory function is used to represent a viewing memory of a viewer to the first live broadcast room set at a current time, and the re-watching probability is a probability that the viewer views the first live broadcast room set within the first preset time range and views the second live broadcast room set within the second preset time range;
a second determining unit 203, configured to determine a second live broadcast room set with a largest re-watching probability in the plurality of second live broadcast room sets;
a pushing unit 204, configured to push, to the user, a live broadcast room that meets a preset condition in the second live broadcast room set with the largest viewing probability.
Specifically, in this embodiment, the electronic device may be a server of a live application, and when the server determines that a client corresponding to a certain user starts the live application, the server stores history records of the users, and then the server calls the history record corresponding to the user through the first determining unit 201 to determine a first live room set S viewed by the user within a first preset time range. Meanwhile, the electronic device in this embodiment may be a client that installs a live application, and the client may be an electronic device such as a mobile phone, a tablet computer, a desktop computer, or other electronic devices, and the application is not limited herein. When the client starts a live application, a history record corresponding to a user of the client may be requested from the server, and a first live broadcast room set s viewed by the user within a first preset time range is determined by the first determining unit 201.
In this embodiment, the first preset time range may be set according to actual needs, for example, may be set to the first 5 days of the closest 10 days from the current time, for example: the current time is 10 days closest to the current time, the current time comprises the 1 st day to the 10 th day from far to near, and the first preset time range is from the 1 st day to the 5 th day. The first set of live rooms s that the user has viewed from day 1 to day 5 are counted. The first live broadcast room set s corresponds to a plurality of similar second live broadcast room sets s, and the second live broadcast room sets s are different from each other.
Further, in the electronic device in this embodiment, the calculating unit 202 measures, by using a memory function, a change in interest of the user in viewing the first live broadcast room set and similar to each second live broadcast room set s, that is: and calculating the re-watching probability of the user watching the first live broadcasting room set in a first preset time range and watching the second live broadcasting room set s in a second preset time range based on the memory function. Such as: the first live room set s corresponds to 3 similar second live room sets s1, s2, and s3, respectively. It can be obtained based on the memory function that the probability of review Ps1 of the second live broadcast room set s1 is 0.6, the probability of review Ps2 of the second live broadcast room set s2 is 0.8, and the probability of review Ps3 of the second live broadcast room set s3 is 0.2. Wherein the second time range is after the first time range, such as: the method comprises the steps that 10 days closest to the current time exist, the days from 1 st to 10 th are included from far to near from the current time, the first preset time range is from 1 st to 5 th, and the second time range is from 6 th to 10 th. In a specific implementation process, the first time range and the second time range may be set according to actual needs, and the present application is not limited herein.
Further, the second live room set with the highest re-view probability, such as the second live room set s1, the second live room set s2, and the second live room set s3 in the above example, is determined by the second determining unit 203, and the second live room set with the highest re-view probability is the second live room set s 2. After the second live broadcast room set with the highest review probability is selected, the fact that the willingness of the user to review live broadcast rooms in the second live broadcast room set is high is indicated, the live broadcast rooms meeting preset conditions are selected from the second live broadcast room set with the highest review probability through the pushing unit 204 and pushed to the user, and due to the fact that the change of user interests is considered, the live broadcast rooms recommended to the user can be more effective.
Further, when calculating the re-viewing probability of each second live broadcast room set, the calculating unit 202 needs to use a memory function, where a formula corresponding to the memory function is m (u, T, s) ═ md(s) + mu (u, T, s), which represents a viewing memory function of the user u to the first live broadcast room set s at the current time T, and md(s) ═ N (s, T)/N(s), and md(s) is measured by using the historical viewing records of the users over the internet, and is a default memory function only related to the first live broadcast room set s, and reflects the potential viewing probability of the public to the first live broadcast room set s. Wherein N(s) is the total number of people watching s in the first live broadcast room set in the first preset time range, and N(s)*T) is the number of people who watch the second live broadcast room set s within the second preset time range T after watching among all users watching the first live broadcast set s within the first preset time range, and T is the length of the memory time, which can be set according to actual needs, and the application is not limited herein.
Wherein,mu (u, t, s) is the viewing memory of the user u for the first set of live rooms s at the current moment t, reflecting the potential viewing possibilities of the person for the first set of live rooms s. In this formula, λ is an attenuation coefficient, and is a constant greater than 0. T1 is a set of time points in the second time frame T when the user u watches the first set s of live rooms, and since the user's memory retention in the live rooms decays with time, the watching memory is estimated by an exponential distribution.
By the above formula m (u, t, s) ═ md(s) + mu (u, t, s), the first live broadcast set of the single user at the current time can be obtainedThe memory value of s is combined, and then the memory value of the whole network user to the first live broadcast room set s at the current moment is obtained asI.e. the sum of the memorized values of all users in the first time range for the first inter-session set s is counted. In such a way, the memory value of the current-time full-network user corresponding to each second live broadcast room set to the first live broadcast room set s can be obtained.
Further, when calculating the probability of watching each second live broadcast room set, the number of people watching the second live broadcast room set at the current moment needs to be countedAnd counting the number of people who have viewed the second set of live rooms within a second time frameAnd the watching probability corresponding to the second live broadcast room set is the difference value of the number of people watching the second live broadcast room set at the current moment divided by the memory value of the whole network users to the first live broadcast room set at the current moment and the number of people watching the second live broadcast room set in the second time range. The formula for the probability of viewability for this second set of live rooms can be expressed as:
the calculation of the probability of re-viewing for the second set of live rooms is explained in detail below in a complete example. The method comprises the steps that 10 days closest to the current time exist, the days from 1 st to 10 th are included from far to near from the current time, the first preset time range is from 1 st to 5 th, and the second time range is from 6 th to 10 th. And (3) the users watch the first live broadcast room set s from day 1 to day 5, and the watching records of the second live broadcast room set s4 can be obtained for the second live broadcast room set s4 similar to the first live broadcast room set s from day 6 to day 10.
First, the total number of people who watched the first live broadcast room set s from day 1 to day 5 was counted as 10000, and the number of people who watched the second live broadcast room set s4 from day 6 to day 10 after watching the first live broadcast room set s from day 1 to day 5 was counted as 2000, and md(s) -2000/10000 was 0.2. A user a who views the first live broadcast room set s from day 1 to day 5 views the second live broadcast room set s4 on the first 2 days and the first 10 days of the current time, and the decay coefficient of the exponential distribution is 0.1, then mu (u, t, s) ═ e-2*0.1+e-10*0.11.186, indicating a remembered value for user a for the first set of live rooms s of 1.186. Assuming that the sum of the memory values of the users in the whole network for the first live broadcast set s at the current time is 20000, 500 people watch the second live broadcast set s4 at the current time, and 19000 people watch the second live broadcast set s4 from the 6 th day to the 10 th day before the current time, the review probability of the second live broadcast set s4 is 500/(20000 19000) and 0.5.
Further, in order to ensure the validity of the statistical history, when counting the number of views, it is necessary to eliminate invalid views, such as: when the watching time length is less than the preset time length (such as 1 minute, 2 minutes and the like), the watching is determined to be invalid, and the record is rejected when the watching times are counted. Meanwhile, for each live broadcast room in the first live broadcast room set, the watching time length of the user is greater than a preset time length (such as 1 minute, 2 minutes and the like).
Further, the push unit 204 can perform live broadcasting in the following two ways:
the first method comprises the following steps: after the user watches a first live broadcast room in the first live broadcast room set, pushing a second live broadcast room, with the similarity between the second live broadcast room set and the first live broadcast room being greater than a first preset threshold value, in the second live broadcast room set with the maximum watching probability to the user.
Specifically, in this embodiment, if the user has watched the first live broadcast room a in the first live broadcast room set, because the second live broadcast room set with the largest watching probability is determined in the foregoing manner, the second live broadcast room set with the largest watching probability may include a plurality of second live broadcast rooms B similar to the first live broadcast room a, the live broadcast rooms with similarity greater than the first preset threshold value to the first live broadcast room a selected from the plurality of second live broadcast rooms B are pushed to the user, the first preset threshold value may be set to 0.5, 0.6, and other numerical values may also be set as required, and no limitation is imposed on this application.
And the second method comprises the following steps: and after the user watches any one live broadcast room in the first live broadcast room set, pushing a second live broadcast room, of which the similarity between the second live broadcast room set with the maximum watching probability and the live broadcast rooms in the first live broadcast room set is greater than a second preset threshold, to the user.
Specifically, in this embodiment, if the user has viewed any one live broadcast room in the first live broadcast room set, since the second live broadcast room set with the largest re-viewing probability is determined in the foregoing manner, if the first live broadcast room set includes live broadcast room a1, live broadcast room a2, and live broadcast room A3. The second live broadcast room set with the largest re-watching probability comprises a live broadcast room B1, a live broadcast room B2, a live broadcast room B3, a live broadcast room B4 and a live broadcast room B5, wherein the live broadcast room B1 and the live broadcast room B2 are similar to the live broadcast room a1, the similarity between the live broadcast room B1 and the live broadcast room a1 is 0.4, and the similarity between the live broadcast room B2 and the live broadcast room a1 is 0.7. Live broadcast room B3 and live broadcast room B4 are similar to live broadcast room a2, live broadcast room B3 and live broadcast room a2 have a similarity of 0.65, and live broadcast room B4 and live broadcast room a2 have a similarity of 0.5. Live room B5 is a live room similar to live room A3, and live room B5 has a similarity of 0.75 to live room A3. And selecting live broadcasting rooms with similarity greater than a second preset threshold with the live broadcasting rooms in the first live broadcasting room set from the second live broadcasting room set with the maximum re-watching probability, and pushing the selected live broadcasting rooms to the user, wherein if the second preset threshold is set to be 0.6, the live broadcasting rooms B2, B3 and B5 need to be recommended to the user.
Of course, the recommendation method is not limited to the above two methods, and other methods may also be adopted, such as: and pushing all live broadcast rooms in the second live broadcast room set with the maximum review probability to the user. The application is not limited thereto.
Referring to fig. 3, a third embodiment of the present invention provides an electronic device, which includes: a processor 301, a memory 302 and a computer program stored in the memory and executable on the processor, for example, a program corresponding to the live broadcast room recommendation method in the first embodiment. The processor implements the steps in the detection of each path in the first embodiment described above when executing the computer program. Alternatively, the processor implements the functions of the modules/units in the electronic device of the second embodiment described above when executing the computer program.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory and executed by the processor to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program in the computer apparatus. For example, the computer program may be divided into a first determining unit, a calculating unit, a second determining unit and a pushing unit, and the specific functions of each unit are as follows:
the device comprises a first determining unit, a second determining unit and a live broadcast processing unit, wherein the first determining unit is used for determining a first live broadcast room set viewed by a user within a first preset time range under the condition that a live broadcast application program is started, the first live broadcast room set corresponds to a plurality of second live broadcast room sets, and the second live broadcast room sets are live broadcast room sets similar to the first live broadcast room set;
a calculating unit, configured to calculate and obtain a re-watching probability of each second live broadcast room set in the plurality of second live broadcast room sets based on a memory function, where the memory function is used to represent viewing memory of a viewer to the first live broadcast room set at a current time, and the re-watching probability is a probability that the viewer views the first live broadcast room set within the first preset time range and views the second live broadcast room set within the second preset time range;
a second determining unit, configured to determine a second live broadcast room set with a largest re-watching probability in the plurality of second live broadcast room sets;
and the pushing unit is used for pushing the live broadcast rooms meeting preset conditions in the second live broadcast room set with the maximum watching probability to the user.
The electronic device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram 3 is merely an example of a computer apparatus and is not intended to limit an electronic device, which may include more or less components than those shown, or some components in combination, or different components, for example, the electronic device may also include input and output devices, network access devices, buses, etc.
The Processor 301 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like which is the control center for the computer device and which connects the various parts of the overall computer device using various interfaces and lines.
The memory 302 may be used to store the computer programs and/or modules, and the processor may implement the various functions of the computer device by running or executing the computer programs and/or modules stored in the memory, as well as by invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Further, the historical time range includes the nearest N days from the current time, where N is an integer greater than 0, and the processor 301 included in the electronic device further has the following functions:
when the review probability of each second live broadcast room set in the second live broadcast room sets is calculated, based on a memory function formula, determining the memory value of the whole network user to the first live broadcast room set at the current moment, determining the number of people watching the second live broadcast room set at the current moment, and determining the number of people watching the second live broadcast room set in the second time range, wherein the review probability of the second live broadcast room set is the difference between the number of people watching the second live broadcast room set at the current moment and the memory value of the whole network user to the first live broadcast room set at the current moment and the number of people watching the second live broadcast room set in the second time range;
the memory function formula is m (u, T, s) ═ md(s) + mu (u, T, s), and represents a watching memory function of the user u to the first live broadcast room set s at the current time T, md(s) ═ N (s, T)/N(s), N(s) is the total number of people watching the first live broadcast room set s in the first preset time range, and N(s) is the total number of people watching the first live broadcast room set s in the first preset time range*T) is the number of people who watch the second live broadcast room set s within the second preset time range T after watching among all users watching the first live broadcast set s within the first preset time range,λ is the attenuation coefficient, T1 is at the secondAnd in a second time range, a user u watches the time point set of the first live broadcast room set s, and the memory value of the whole network user at the current moment to the first live broadcast room set is
Further, the processor 301 included in the electronic device also has the following functions:
after the user watches a first live broadcast room in the first live broadcast room set, pushing a second live broadcast room, with the similarity between the second live broadcast room set and the first live broadcast room being greater than a first preset threshold value, in the second live broadcast room set with the maximum watching probability to the user.
Further, the processor 301 included in the electronic device also has the following functions:
and after the user watches any one live broadcast room in the first live broadcast room set, pushing a second live broadcast room, of which the similarity between the second live broadcast room set with the maximum watching probability and the live broadcast rooms in the first live broadcast room set is greater than a second preset threshold, to the user.
Further, the watching duration of each live broadcast room in the first live broadcast room set is greater than the preset duration.
A fourth embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, and the electronic device integrated functional unit in the second embodiment of the present invention may be stored in one computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, all or part of the flow of the live broadcast recommendation method according to the first embodiment may be implemented by a computer program, which may be stored in a computer-readable storage medium and may be executed by a processor to implement the steps of the above method embodiments. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
In the technical scheme of the embodiment of the invention, under the condition that the live application program is started, a first live room set watched by a user within a first preset time range is determined, wherein the first live room set comprises a plurality of similar second live room sets. And then, accurately measuring the re-watching probability of the user watching the similar second live broadcast room sets after watching the first live broadcast room set through a memory function, after the re-watching probability of each similar second live broadcast room set is calculated, selecting the second live broadcast room set with the maximum re-watching probability, and pushing the live broadcast rooms meeting preset conditions in the second live broadcast room set with the maximum re-watching probability to the user. Therefore, the interest change of the user to the similar live broadcast room after watching the live broadcast room is accurately measured through the memory function, the interest change of the user is fully considered, and the effective and reliable recommended live broadcast room is provided for the user.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.