Method, device, server and computer storage medium for updating popularity ranking list

Abstract

The present application discloses a method, device, server and computer storage medium for updating a popularity ranking list. The method includes: obtaining user operation information accumulated at the current moment for each media information in the current popularity ranking list at the update time point of the update cycle; obtaining the current popularity of the media information after the popularity calculation, and updating the current popularity ranking list according to the current popularity of each media information in the current popularity ranking list; using the current popularity of each media information in the current popularity ranking list, obtaining the popularity of each media information at multiple future moments after the popularity decay calculation; and updating the expected popularity ranking list corresponding to each future moment according to the target popularity of each media information in the current popularity ranking list. By updating the expected popularity ranking list corresponding to each future moment, the media information whose popularity at the future moment does not meet the demand can be screened out, thereby achieving the purpose of reducing the time for calculating the popularity of the media information.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, server and computer storage medium for updating a popularity ranking list. Background Art

[0002] With the rapid development of Internet information technology, more and more users are keen to use various network platforms to read various media information. Each network platform usually recommends currently popular media information to users through popularity rankings.

[0003] At present, the popularity ranking list usually needs to update the popularity of all current media information at regular intervals, and generate a popularity ranking list based on the popularity of each media information. However, as the amount of media information increases, calculating the current popularity of each media information and then generating a popularity ranking list based on the popularity of each media information increases the pressure on the system for calculating the popularity of media information and also increases the time for calculating the popularity of media information. Summary of the invention

[0004] Based on the above-mentioned deficiencies of the prior art, the present application proposes a method, device, server and computer storage medium for updating the popularity ranking list, so as to reduce the pressure on the system for calculating the popularity of media information and reduce the time for calculating the popularity of media information.

[0005] In order to achieve the above objectives, the proposed solution is as follows:

[0006] The first aspect of the present application discloses a method for updating a popularity ranking list, comprising:

[0007] At an update time point in an update cycle, user operation information accumulated at the current moment for each media information in the current popularity ranking list is obtained; wherein the current popularity ranking list includes a plurality of media information sorted by popularity and whose popularity is greater than a minimum threshold;

[0008] For each piece of media information in the current popularity ranking list, the user operation information accumulated at the current moment of the media information is used to calculate the current popularity of the media information, and the current popularity ranking list is updated according to the current popularity of each piece of media information in the current popularity ranking list;

[0009] Using the current popularity of each piece of media information in the current popularity ranking list, the popularity of each piece of media information at multiple future moments is obtained after the popularity decay calculation;

[0010] According to the target heat of each of the media information in the current heat ranking list, the expected heat ranking list corresponding to each future moment is updated; wherein the target heat refers to the heat of each of the media information at each future moment that satisfies the condition that the heat is greater than the minimum threshold, and each of the expected heat ranking lists includes: multiple media information sorted by heat and whose heat is greater than the minimum threshold.

[0011] Optionally, in the above-mentioned method for updating the popularity ranking list, the current popularity of each piece of the media information in the current popularity ranking list is used to obtain the popularity of each piece of the media information at multiple future moments after the popularity decay calculation, including:

[0012] The current popularity of each piece of media information in the current popularity ranking list is processed according to the principle that popularity decays over time, so as to obtain the popularity of each piece of media information at multiple future moments.

[0013] Optionally, in the above-mentioned method for updating the popularity ranking list, the current popularity of each piece of media information in the current popularity ranking list is processed according to the principle that the popularity decays over time to obtain the popularity of each piece of media information at multiple future moments, including:

[0014] For each piece of media information in the current popularity ranking list, the current popularity of the media information is attenuated by the number of future time intervals between the current moment and each of the future moments, and the attenuated popularity is used as the popularity of the media information at each of the future moments.

[0015] Optionally, in the above-mentioned method for updating the popularity ranking list, the method of using the user operation information accumulated by the media information at the current moment to calculate the popularity and obtain the current popularity of the media information includes:

[0016] Counting the user operation information accumulated by the media information at the current moment, including the amount of each type of user operation;

[0017] According to the statistical amount of each user operation and the weight corresponding to each user operation, the current heat of each user operation corresponding to the media information is obtained after heat calculation;

[0018] The current popularity of the media information corresponding to each user operation is synthesized to obtain the current popularity of the media information.

[0019] Optionally, in the above-mentioned method for updating the popularity ranking list, the current popularity of each piece of the media information in the current popularity ranking list is used to obtain the popularity of each piece of the media information at multiple future moments after the popularity decay calculation, including:

[0020] For each piece of media information in the current popularity ranking list, using the current popularity of each user operation corresponding to the media information, the popularity of the media information corresponding to each user operation at multiple future moments is obtained after the popularity decay calculation;

[0021] The popularity of the media information corresponding to each user operation at each future moment is synthesized to obtain the popularity of the media information at each future moment.

[0022] Optionally, in the above method for updating the popularity ranking list, the following steps are further included:

[0023] When a message indicating that an operation is performed by a user on media information is detected, obtaining behavior information of the user performing the operation;

[0024] For the media information operated by the user, the user operation information accumulated at the time of detecting the message is used to calculate the current heat of the media information operated by the user, and the current heat ranking list is updated according to the current heat of the media information operated by the user;

[0025] Using the current heat of the media information operated by the user, heat decay calculation is performed to obtain the heat of the media information operated by the user at multiple future moments;

[0026] According to the heat at each future moment of the media information operated by the user and satisfying the condition that the heat is greater than the minimum threshold, the expected heat ranking list corresponding to each future moment is updated.

[0027] The second aspect of the present application discloses a device for updating a popularity ranking list, comprising:

[0028] A first acquisition unit is used to acquire, at an update time point in an update cycle, user operation information accumulated at the current moment for each media information in the current popularity ranking list; wherein the current popularity ranking list includes a plurality of media information sorted by popularity and whose popularity is greater than a minimum threshold;

[0029] A first updating unit is used to calculate the heat of each piece of media information in the current heat ranking list by using the user operation information accumulated at the current moment of the media information to obtain the current heat of the media information, and update the current heat ranking list according to the current heat of each piece of media information in the current heat ranking list;

[0030] A first calculation unit is used to obtain the heat of each of the media information at multiple future moments by using the current heat of each of the media information in the current heat ranking list and performing heat decay calculation;

[0031] The second updating unit is used to update the expected heat ranking list corresponding to each future moment according to the target heat of each of the media information in the current heat ranking list; wherein the target heat refers to the heat of each of the media information at each future moment that satisfies the condition that the heat is greater than the minimum threshold, and each of the expected heat ranking lists includes: multiple media information sorted by heat and whose heat is greater than the minimum threshold.

[0032] Optionally, in the above-mentioned device for updating the popularity ranking list, the first calculation unit includes:

[0033] The processing unit is used to process the current popularity of each piece of media information in the current popularity ranking list according to the principle that popularity decays over time, and obtain the popularity of each piece of media information at multiple future moments.

[0034] Optionally, in the above-mentioned device for updating the popularity ranking list, the processing unit includes:

[0035] The processing subunit is used to attenuate the current popularity of each piece of media information in the current popularity ranking list by the number of future time intervals between the current moment and each of the future moments, and use the attenuated popularity as the popularity of the media information at each of the future moments.

[0036] Optionally, in the above-mentioned device for updating the popularity ranking list, the first updating unit includes:

[0037] A statistical unit, used to count the user operation information accumulated by the media information at the current moment, and the amount of each type of user operation;

[0038] A second calculation unit is used to calculate the current heat of each user operation corresponding to the media information according to the statistical amount of each user operation and the weight corresponding to each user operation.

[0039] The first confirmation unit is used to obtain the current popularity of the media information by integrating the current popularity of each user operation of the media information.

[0040] Optionally, in the above-mentioned device for updating the popularity ranking list, the first calculation unit includes:

[0041] A first calculation subunit is used for obtaining the heat of each media information in the current heat ranking list by using the current heat of each user operation corresponding to the media information and performing heat decay calculation to obtain the heat of each media information corresponding to the user operation at multiple future moments.

[0042] The second confirmation unit is used to synthesize the popularity of the media information corresponding to each user operation at each future moment to obtain the popularity of the media information at each future moment.

[0043] Optionally, the above-mentioned device for updating the popularity ranking list further includes:

[0044] A second acquisition unit is used to acquire behavior information of the user performing the operation when a message indicating that the media information is operated by the user is detected;

[0045] A third updating unit is used to calculate the current heat of the media information operated by the user by using the user operation information accumulated at the time of detecting the message, and update the current heat ranking list according to the current heat of the media information operated by the user;

[0046] A third calculation unit is used to obtain the heat of the media information operated by the user at multiple future moments by using the current heat of the media information operated by the user and performing heat decay calculation;

[0047] The fourth updating unit is used to update the expected popularity ranking list corresponding to each future moment according to the popularity of each future moment of the media information operated by the user and satisfying the condition that the popularity is greater than the minimum threshold.

[0048] The third aspect of the present application discloses a server, comprising:

[0049] one or more processors;

[0050] a storage device having one or more programs stored thereon;

[0051] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of the first aspects.

[0052] A fourth aspect of the present application discloses a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method as described in any one of the first aspects is implemented.

[0053] It can be seen from the above technical solution that in the method for updating the popularity ranking list provided by the present application, the popularity of the media information in the current popularity ranking list is greater than the minimum threshold value, so the media information with low popularity is removed from the current popularity ranking list. In this way, for each piece of media information in the current popularity ranking list, the user operation information accumulated by the media information at the current moment is used to calculate the current popularity of the media information, and according to the current popularity of each piece of media information in the current popularity ranking list, in the process of updating the current popularity ranking list, it can be ensured that the media information with low popularity will not be calculated and updated to the current popularity ranking list, which reduces the number of media information calculated during the update of the current popularity ranking list, reduces the system pressure, and reduces the heat calculation time. In addition, the popularity of the media information in the expected popularity ranking list corresponding to each future moment is also greater than the minimum threshold value, so the media information with low popularity is also removed from the expected popularity ranking list corresponding to each future moment. In this way, the current popularity of each media information in the current popularity ranking list is used to obtain the popularity of each media information at multiple future moments after the heat decay calculation. In addition, in the process of updating the expected popularity ranking list corresponding to each future moment according to the target popularity of each media information in the current popularity ranking list, it is also ensured that the media information with low popularity will not be calculated and updated to the expected popularity ranking list, thereby reducing the amount of media information calculated during the update of the expected popularity ranking list, reducing system pressure, and reducing heat calculation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0055] Figure 1 A schematic diagram of a user using a forum, community, etc. disclosed in an embodiment of the present application;

[0056] Figure 2 A schematic diagram of the structure of a system for generating content by a user disclosed in an embodiment of the present application;

[0057] Figure 3 A schematic diagram of a process for updating the expected popularity ranking list corresponding to each future moment disclosed in an embodiment of the present application;

[0058] Figure 4 A flowchart of a method for updating a popularity ranking list disclosed in an embodiment of the present application;

[0059] Figure 5 A schematic diagram of a process for updating the expected popularity ranking list corresponding to each future moment disclosed in an embodiment of the present application;

[0060] Figure 6 This is a schematic diagram of the effect of updating the expected popularity ranking list corresponding to each future moment disclosed in an embodiment of the present application;

[0061] Figure 7 A flowchart of a method for updating a popularity ranking list disclosed in another embodiment of the present application;

[0062] Figure 8 A flowchart of a method for updating a popularity ranking list disclosed in another embodiment of the present application;

[0063] Fig. 9 A schematic diagram of a method for updating a popularity ranking list disclosed in an embodiment of the present application;

[0064] Fig.10 A schematic diagram of the structure of a device for updating a popularity ranking list disclosed in an embodiment of the present application;

[0065] Fig.11 A schematic diagram of a server for implementing a method for updating a popularity ranking list provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0067] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0068] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0069] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0070] See also Figure 1 When using forums and communities, users can act as authors of posts, articles, feeds, etc., and manage their posts, articles, feeds, etc., such as publishing and deleting. They can also act as ordinary users to perform ordinary operations on posts, articles, feeds, etc. posted by other users, such as reading, liking, and commenting. Among them, feed is a data format through which websites can disseminate the latest information to users. The prerequisite for users to subscribe to a website is that the website can provide continuously updated information.

[0071] See also Figure 2 , is a schematic diagram of a user generated content (UGC) system. The UGC system can be but is not limited to forums, communities, etc.; cgi is a universal gateway interface; the work elasticsearch is used to store all works published by all users; the work operation storage REDIS-STRING is used to store users' operations such as likes, comments, and reading of works; the popularity ranking REDIS-ZSET is a list of posts sorted by popularity value; MQ refers to message queue (Message Queue), which is a common way to decouple producers (authors) and consumers (ordinary users) and supports multi-consumer subscription.

[0072] For example, when an author publishes a post, article, feed, etc. on the client, the post, article, feed, etc. will be saved to the work elasticsearch in the storage layer through the publisher cgi. When ordinary users perform ordinary operations on the posts, articles, feeds, etc. published by the author, for example, users use the work details cgi to read posts, articles, feeds, etc.; users use the work operation cgi to like and comment on posts, articles, feeds, etc.; the work operation storage REDIS-STRING will store the ordinary operations of ordinary users, and report the ordinary operations of ordinary users to MQ, and update the hot list REDIS-ZSET at a preset time. Users can pull the hot list REDIS-ZSET at any time by requesting the hottest list cgi.

[0073] Every time an ordinary user performs an ordinary operation on a published post, article, feed, etc., the UGC system will write a message in MQ to indicate that the published post, article, feed and other media information have been operated by the user. At this time, the popularity ranking list can be updated. This update method can be called a message-triggered type of update method for the popularity ranking list.

[0074] like Figure 3 As shown, the method for updating the popularity ranking list of this message trigger type includes:

[0075] S301. When a message indicating that a user performs an operation on media information is detected, obtain behavior information of the user performing the operation.

[0076] The operations performed by the user may include, but are not limited to, liking, following, commenting, searching, reading, etc. the media information such as posts and articles. The behavior information of the user's operation is used to describe the type of operation performed by the user, the object of the operation performed by the user, and the time of the operation performed by the user.

[0077] It should be noted that at the same time point, the behavior information of different users performing operations on different media information may be received. For example, at the current time point, the like operation of user A on media information A, the follow operation of user B on media information A, and the reading operation of user C on media information B are obtained. In this embodiment, an operation performed by a user on a piece of media information is used as an example for description.

[0078] S302. For the media information on which the user performs the operation, the user operation information accumulated at the time when the message is detected is used to calculate the current heat of the media information on which the user performs the operation, and the current heat ranking list is updated according to the current heat of the media information on which the user performs the operation.

[0079] Different user operation information may correspond to different heats, for example, a user performing a reading operation may have a heat of 1 point, a user performing a like operation may have a heat of 3 points, a user performing a follow operation may have a heat of 5 points, etc. Different user operation information may also correspond to the same heat, for example, a user performing a follow operation and a user performing a like operation may both have a heat of 3 points, which is not limited here.

[0080] Specifically, the heat corresponding to the user operation information accumulated at the time of detecting the message may be summed up, but not limited to, to obtain the current heat of the media information operated by the user after heat calculation. The current heat ranking list is updated according to the current heat of the media information operated by the user that meets the minimum threshold.

[0081] It can be understood that updating the current popularity ranking list can be to update the current popularity of the media information in the current popularity ranking list, or it can be that when there is no current popularity ranking list at the beginning, the current popularity of the media information whose popularity is greater than a minimum threshold and the current popularity of the media information whose popularity is greater than a minimum threshold are updated to an initial popularity ranking list, thereby generating a current popularity ranking list.

[0082] It should be noted that, in the case that in step S301, behavior information of different users performing operations on different media information is received at the same time point, for each piece of media information operated on by different users, the user operation information accumulated at the moment of detecting the message indicating that the media information is operated on by the user is used to calculate the current heat of each piece of media information operated on by the user, and the current heat ranking list is updated based on the current heat of each piece of media information operated on by the user.

[0083] S303: Using the current heat of the media information operated by the user, the heat of the media information operated by the user at multiple future moments is obtained after heat decay calculation.

[0084] The current heat of the media information operated by the user is processed according to the principle of heat decay over time, and the heat of each media information at multiple future moments is obtained.

[0085] It should be noted that since the popularity of media information decays over time, many old media information are gradually forgotten by users, and the popularity gradually approaches 0 as time goes by. Therefore, when predicting the popularity of media information on which users perform operations at multiple future moments, the principle of heat decay over time can be used to process it.

[0086] Among them, the principle of time attenuation can be to reduce the current heat by a certain percentage, or to reduce the heat by a fixed value, or to use other methods to attenuate the current heat. The methods are very diverse and are not limited here. And it should be noted that when predicting the heat of each media information in the current heat ranking list at multiple future moments, the degree of attenuation of the first future moment relative to the current moment does not necessarily have to be the same as the degree of attenuation of the second future moment equivalent to the first future moment. For example: the heat at the current moment is 100, the degree of attenuation of the first future moment relative to the current moment is 5%, the degree of attenuation of the second future moment equivalent to the first future moment is 7%, and the degree of attenuation of the third future moment equivalent to the second future moment is 10%.

[0087] S304: Update the expected popularity ranking list corresponding to each future moment according to the popularity of each future moment of the media information operated by the user and satisfying the condition that the popularity is greater than a minimum threshold.

[0088] Specifically, the heat of the media information operated by the user at multiple future moments calculated in step S303 is selected, and the heat of each future moment with a condition that the heat is greater than a minimum threshold is updated to the expected heat ranking list corresponding to each future moment.

[0089] It can be understood that updating the expected heat ranking list corresponding to each future moment may be to update the current heat of the media information in the expected heat ranking list corresponding to each future moment, or may be to update the expected heat ranking list that does not correspond to each future moment to an expected heat ranking list that corresponds to each future moment, that is, to generate an expected heat ranking list corresponding to each future moment.

[0090] Initially, there is no expected heat ranking list corresponding to future moments. After the message indicating that the media information is operated by the user is detected, the heat of the media information operated by the user at each future moment is calculated using the current heat of the media information operated by the user. The heat of the media information at each future moment whose heat is greater than the minimum threshold and the heat of the media information corresponding to the heat at each future moment whose heat is greater than the minimum threshold are updated to the initial expected heat ranking list, thereby generating an expected heat ranking list corresponding to each future moment.

[0091] After the current popularity ranking list and the expected popularity ranking list corresponding to each future moment are generated, they will be updated in an update cycle, and the update process is as described in the following embodiment.

[0092] The present application embodiment discloses a method for updating a popularity ranking list. Figure 4 , specifically including the following steps:

[0093] S401. At an update time point in an update cycle, user operation information accumulated at the current moment for each piece of media information in the current popularity ranking list is obtained.

[0094] Among them, the current popularity ranking list includes multiple media information sorted by popularity and whose popularity is greater than the minimum threshold; media information can be but is not limited to posts, articles, etc. posted on forums, communities, etc., that is, the above-mentioned works, which are not limited here; user behavior information is user operation information on media information, which can be but is not limited to users liking, following, commenting, searching, reading, etc. on posts, articles, etc., which is not limited here; the update cycle can be but is not limited to one day, half a day, three hours, etc., which is also not limited here; the update time point of the update cycle can be understood as the start time point of a cycle.

[0095] It is understandable that the current popularity ranking list will be continuously updated using the update method of the message-triggered popularity ranking list proposed in the above embodiment. Therefore, in step S401, at the update time point of an update cycle, it is necessary to search the system for the current popularity ranking list currently stored, and for each media information in the current popularity ranking list, search for the user operation information accumulated by the media information at the update time point of this update cycle.

[0096] S402. For each piece of media information in the current popularity ranking list, the user operation information accumulated by the media information at the current moment is used to calculate the current popularity of the media information, and the current popularity ranking list is updated according to the current popularity of each piece of media information in the current popularity ranking list.

[0097] It should be noted that the current popularity ranking list in this application is not only updated at the update time point of the update cycle, but also the heat of the media information operated by the user is calculated every time a message indicating that the media information is operated by the user is detected, and the media information is updated to the current popularity ranking list when the heat is greater than the minimum threshold. And the update of the current popularity ranking list at the update time point of the update cycle is independent of the update of the current popularity ranking list every time a message indicating that the media information is operated by the user is detected.

[0098] S403: Using the current popularity of each piece of media information in the current popularity ranking list, the popularity of each piece of media information at multiple future moments is obtained after the popularity decay calculation.

[0099] Among them, the number of future moments can be preset to a certain number, such as 7, 9, 20, etc., and can be set according to actual application conditions, or there can be no upper limit on the number, which is not limited here.

[0100] It should be noted that the update cycle is not necessarily consistent with the unit of the future moment. For example, the update cycle is 1 day, but the future moment can be 1 hour. Take steps S401 to S402 as an example, in which the current popularity ranking is updated with an update cycle of 1 day. For example, if the popularity ranking of July 7 is updated at 0:00 on July 7, then in step S403, the current popularity of each media information in the popularity ranking of July 7 can be used, and the popularity of each media information at 1 o'clock, 2 o'clock, 3 o'clock, etc. on July 7 can be obtained after the heat decay calculation; or the popularity of each media information on July 8, July 9, etc. can be obtained after the heat decay calculation.

[0101] Similarly, taking steps S401 to S402 as an example, in which the current popularity ranking is updated with an update cycle of 1 hour, if the popularity ranking of July 7 is updated at 0:00 on July 7, then in step S403, the current popularity of each media information in the popularity ranking of July 7 can be used, and after the heat decay calculation, the popularity of each media information at 1:00, 2:00, 3:00, etc. on July 7 can be obtained; the popularity of each media information at 0:30, 1:30, 2:30, etc. on July 7; or the heat calculation decays to obtain the popularity of each media information on July 8, July 9, etc.

[0102] Optionally, in a specific embodiment of the present application, an implementation of step S403 includes:

[0103] The current popularity of each media information in the current popularity ranking list is processed according to the principle that popularity decays over time, and the popularity of each media information at multiple future moments is obtained.

[0104] It should be noted that since the popularity of media information decays over time, many old media information are gradually forgotten by users, and the popularity gradually approaches 0 as time goes by. Therefore, when predicting the popularity of each media information in the current popularity ranking at multiple future moments, the principle of heat decay over time can be used.

[0105] Among them, the principle of time attenuation can be to reduce the current heat by a certain percentage, or to reduce the heat by a fixed value, or to use other methods to attenuate the current heat. The methods are very diverse and are not limited here. And it should be noted that when predicting the heat of each media information in the current heat ranking list at multiple future moments, the degree of attenuation of the first future moment relative to the current moment is not necessarily the same as the degree of attenuation of the second future moment equivalent to the first future moment. For example: the heat at the current moment is 100, the degree of attenuation of the first future moment relative to the current moment is 5%, the degree of attenuation of the second future moment is equivalent to 7% of the first future moment, and the degree of attenuation of the third future moment is equivalent to 10% of the second future moment.

[0106] Optionally, in a specific embodiment of the present application, a method of processing the current popularity of each media information in the current popularity ranking list according to the principle of popularity decaying over time to obtain the popularity of each media information at multiple future moments includes:

[0107] For each media information in the current popularity ranking list, the current popularity of the media information is attenuated by the number of future time intervals between the current moment and each future moment, and the attenuated popularity is used as the popularity of the media information at each future moment.

[0108] Specifically, for each media information in the current popularity ranking, the current popularity of the media information is decayed according to the number of future times between the current moment and each future moment. It can also be understood that the greater the number of future times between the current moment and each future moment, the faster the current popularity of the media information decays, and the decayed popularity is used as the popularity of the media information at each future moment.

[0109] Taking the interval between the current moment and the next future moment as 1 day, and the current popularity of the media as 1000 as an example, at the current moment T, that is, the first day, the current popularity of the media information is 1000 / (T+0)=1000, then, on T+1 day, the popularity of the media information is 1000 / (T+1)=1000 / (1+1)=500, then, on T+2 day, the popularity of the media information is 1000 / (T+2)=1000 / (1+2)≈333, then on T+3 day, the popularity of the media information is 1000 / (T+3)=1000 / (1+3)=250, and so on.

[0110] S404: Update the expected popularity ranking list corresponding to each future moment according to the target popularity of each piece of media information in the current popularity ranking list.

[0111] The target heat refers to the heat of each media information at each future moment that satisfies the condition that the heat is greater than the minimum threshold, and each expected heat ranking list includes: multiple media information sorted by heat and whose heat is greater than the minimum threshold.

[0112] One implementation method of this step can be found in Figure 5 , with an update cycle of 1 day (i.e. Figure 5 N = 1), the minimum threshold of heat is 0.05 (i.e. Figure 5 H-MIN=0.05), the future time is 30 days (i.e. Figure 5 Taking N_MAX=30 in the example, it can be seen that the above three parameters can be set by technicians according to actual application conditions, and are not limited here. When starting to process media information, the current time is taken as day T, the initial value of N is 1, and it is determined whether the current value of N of the media information is less than 30. If it is less than 30, the popularity H of the media information on day T+N is calculated. N ; Then determine the popularity of the media information on day T+N H N Is it greater than or equal to 0.05? If the media information is hot on day T+N, H N If it is greater than or equal to 0.05, then the media information and the media information’s popularity H on day T+N are recorded. N , update to the expected popularity ranking list corresponding to T+N day; after the media information and the popularity H of the media information on T+N day N , after updating to the expected popularity ranking corresponding to day T+N, N+1 is used as the latest N, that is, Figure 5 Step N=N+1 in the above step; cyclically calculate the target popularity for each media information until N is greater than or equal to 30, or the popularity H of T+N days N Less than 0.05. It is understandable that when N is greater than or equal to 30, since there is no corresponding expected popularity ranking list, there is no need to continue calculating the popularity of the media information; when the popularity on T+N day is less than 0.05, it can also be understood that most users no longer pay attention to the media information, so there is no need to continue calculating the popularity of the media information and update it to the corresponding expected popularity ranking list.

[0113] See also Figure 6This is a schematic diagram of the effect of step S404, N_MAX=30; H_MIN=0.21; the initial value of N is 0, media information A actually received 1 like on T+0, that is, the actual popularity of media information A on T+0 is 1.0; media information B actually received 1 like on T+1, that is, the actual popularity of media information A on T+0 is 1.0; media information C actually received 1 like on T+2, that is, the actual popularity of media information A on T+0 is 1.0. The popularity of media information A, B and C at each future moment is calculated respectively. Taking media information A as an example, the expected popularity on T+1 is 0.5; the expected popularity on T+2 is 0.33; the expected popularity on T+3 is 0.25; and the expected popularity on T+4 is 0.2. Since the expected popularity of media information A on T+4 is less than H_MIN, media information A will no longer be updated to the T+4 list. The same is true for media information B and media information C, which will not be repeated here.

[0114] It should be noted that, during the process of executing steps S401-S404, if a message indicating that the media information is operated by the user is detected, the above steps can also be executed. Figure 3 The embodiment shown.

[0115] Optionally, see Figure 7 In one embodiment of the present application, an implementation of a method for updating a popularity ranking list includes:

[0116] S701. At an update time point in an update cycle, user operation information accumulated at the current moment for each piece of media information in the current popularity ranking list is obtained.

[0117] S702: For each piece of media information in the current popularity ranking list, statistics are collected on the user operation information accumulated by the media information at the current moment, including the amount of each type of user operation.

[0118] For example: As of the current moment, the media information has been read 10 times, liked 7 times, followed 4 times, etc. by users.

[0119] S703: According to the statistically obtained amount of each user operation and the weight corresponding to each user operation, the heat is calculated to obtain the current heat of the media information corresponding to each user operation.

[0120] The weight corresponding to each user operation is preset by technical personnel and the like, and can be changed according to actual conditions, and is not limited here.

[0121] For example, in step S701, it is obtained that the media information has accumulated 10 reading operations, 7 like operations, and 4 follow operations of the user. The preset weight corresponding to a like operation is 2, the weight corresponding to a reading operation is 1, and the weight corresponding to a follow operation is 3. Then, the current popularity of the reading operation of the media information is 10*1=10; the current popularity of the like operation of the media information is 7*2=14; the current popularity of the follow operation of the media information is 4*3=12.

[0122] It can be understood that in this step, the current heat of the media information corresponding to each user operation can be obtained directly based on the statistical amount of each user operation and the heat calculation. It is not necessary to use the weight corresponding to each user operation. It can be understood that the weight corresponding to each user operation is equal.

[0123] S704 , the current popularity of each user operation corresponding to the media information is integrated to obtain the current popularity of the media information.

[0124] Specifically, the current heat of the media information can be calculated by summing the current heat of each user operation corresponding to the media information in the simplest way. For example, the current heat of the reading operation of the media information obtained in step S503 is 10; the current heat of the like operation of the media information is 14; the current heat of the follow operation of the media information is 12. Then, the current heat of the media information is 10+14+12=36.

[0125] S705: Update the current popularity ranking list according to the current popularity of each piece of media information in the current popularity ranking list.

[0126] S706: Using the current popularity of each piece of media information in the current popularity ranking list, the popularity of each piece of media information at multiple future moments is obtained after the popularity decay calculation.

[0127] S707: Update the expected popularity ranking list corresponding to each future moment according to the target popularity of each piece of media information in the current popularity ranking list.

[0128] In this embodiment, the specific implementation of steps S701, S706 and S707 may refer to the contents of steps S401, S403 and S404 in the above method embodiment, and will not be repeated here.

[0129] Optionally, see Figure 8 In one embodiment of the present application, an implementation of a method for updating a popularity ranking list includes:

[0130] S801. At an update time point in an update cycle, user operation information accumulated at the current moment for each piece of media information in the current popularity ranking list is obtained.

[0131] S802. For each piece of media information in the current popularity ranking list, the user operation information accumulated by the media information at the current moment is used to calculate the current popularity of the media information, and the current popularity ranking list is updated according to the current popularity of each piece of media information in the current popularity ranking list.

[0132] S803 . For each piece of media information in the current popularity ranking list, the current popularity of the media information corresponding to each user operation is used to calculate the popularity of the media information corresponding to each user operation at multiple future moments after the popularity decay calculation.

[0133] In other words, we no longer use the overall current popularity of all user operations corresponding to each media information in the current popularity ranking list, but use the current popularity of each user operation corresponding to each media information separately. After the heat decay calculation, we get the popularity of the media information corresponding to each user operation at multiple future moments.

[0134] For example: you can use the current popularity of the like operation corresponding to each media information in the popularity ranking list on July 7, and after the heat decay calculation, you can get the popularity of the like operation corresponding to each media information at 1 o'clock, 2 o'clock, 3 o'clock, etc. on July 7; or after the heat decay calculation, you can get the popularity of each media information on July 8, July 9, etc.

[0135] It should also be noted that in step S803, for each media information in the current popularity ranking list, the current popularity of a corresponding user operation is used to calculate the heat decay to obtain the heat of the media information corresponding to each user operation at multiple future moments. The principle adopted is also the principle of heat decay over time. The specific method can be found in the content of the above embodiment, which will not be repeated here.

[0136] S804: The popularity of the media information corresponding to each user operation at each future moment is synthesized to obtain the popularity of the media information at each future moment.

[0137] Specifically, in step S803, the current heat of the media information corresponding to each user operation is used respectively, and after the heat decay calculation is performed to obtain the heat of the media information corresponding to each user operation at multiple future moments, the heat of the media information corresponding to each user operation at each future moment can be combined to obtain the heat of the media information at each future moment. For example, the heat of the media information of the user operation at each future moment is weighted and summed up to finally obtain the heat of the media information at each future moment.

[0138] For example, in step S803, the current popularity of the like operation corresponding to the media information is 100, the current popularity of the reading operation corresponding to the media information is 200, and the popularity of the follow operation corresponding to the media information is 70. The preset weights of the like operation are 0.5, the weight of the reading operation is 0.2, and the weight of the follow operation is 0.7. Then, by combining the popularity of the media information corresponding to each user operation at each future moment, the popularity of the media information at each future moment is 100*0.5+200*0.2+70*0.7=139.

[0139] S805: Update the expected popularity ranking list corresponding to each future moment according to the target popularity of each piece of media information in the current popularity ranking list.

[0140] In this embodiment, the specific implementation of steps S801, S802 and S805 can refer to the contents of steps S401, S402 and S404 in the above method embodiment, and will not be repeated here. Figure 7 The implementation methods of steps S702 to 705 proposed in the corresponding embodiment.

[0141] The present application is now described by way of example. Fig. 9 When a user reads a post he likes on the UGC system, he likes it. The UGC system will store the user's like behavior, store it in the storage REDIS-STRING, and send a message to MQ. At this time, the message processing program updates the current popularity ranking list of the media information operated by the user and the expected popularity ranking list corresponding to each future moment according to steps S301 to S304. When the update time point of the update cycle is reached, the timing processing program calculates the popularity of each media information in the current popularity ranking list and updates the current popularity ranking list according to steps S401 to S404. After updating the current popularity ranking list, the popularity of each media information in the current popularity ranking list at multiple future moments is calculated again, and the expected popularity ranking list corresponding to each future moment is updated according to the popularity of each media information in the current popularity ranking list at multiple future moments.

[0142] In the method for updating the popularity ranking list provided in the present application, the popularity of the media information in the current popularity ranking list is greater than the minimum threshold value, therefore, the media information with low popularity is removed from the current popularity ranking list. In this way, for each piece of media information in the current popularity ranking list, the user operation information accumulated by the media information at the current moment is used to calculate the current popularity of the media information, and in the process of updating the current popularity ranking list according to the current popularity of each piece of media information in the current popularity ranking list, it can be ensured that the media information with low popularity will not be calculated and updated to the current popularity ranking list, thereby reducing the amount of media information calculated during the update of the current popularity ranking list, reducing system pressure, and reducing the heat calculation time. In addition, the popularity of the media information in the expected popularity ranking list corresponding to each future moment is also greater than the minimum threshold value, therefore, the media information with low popularity is also removed from the expected popularity ranking list corresponding to each future moment. In this way, the current popularity of each media information in the current popularity ranking list is used to obtain the popularity of each media information at multiple future moments after the heat decay calculation. In addition, in the process of updating the expected popularity ranking list corresponding to each future moment according to the target popularity of each media information in the current popularity ranking list, it is also ensured that the media information with low popularity will not be calculated and updated to the expected popularity ranking list, thereby reducing the amount of media information calculated during the update of the expected popularity ranking list, reducing system pressure, and reducing heat calculation time.

[0143] See also Fig.10 Based on the method for updating the popularity ranking list proposed in the above-mentioned embodiment of the present application, the embodiment of the present application also discloses a corresponding device 1000 for updating the popularity ranking list, including: a first acquisition unit 1001, a first update unit 1002, a first calculation unit 1003 and a second update unit 1004.

[0144] The first acquisition unit 1001 is used to acquire the user operation information accumulated at the current moment for each media information in the current popularity ranking list at an update time point in an update cycle.

[0145] The current popularity ranking list includes a plurality of media information sorted by popularity, and the popularity of each of the media information is greater than a minimum threshold.

[0146] The first updating unit 1002 is used to calculate the current popularity of each media information in the current popularity ranking list by using the user operation information accumulated by the media information at the current moment, and update the current popularity ranking list according to the current popularity of each media information in the current popularity ranking list.

[0147] Optionally, in a specific embodiment of the present application, the first updating unit 1002 includes: a statistical unit, a second calculation unit and a first confirmation unit.

[0148] The statistical unit is used to count the user operation information accumulated by the media information at the current moment, which belongs to the amount of each user operation.

[0149] The second calculation unit is used to obtain the current heat of the media information corresponding to each user operation after heat calculation based on the statistical amount of each user operation and the weight corresponding to each user operation.

[0150] The first confirmation unit is used to obtain the current popularity of the media information by integrating the current popularity of each user operation of the media information.

[0151] The first calculation unit 1003 is used to obtain the heat of each media information at multiple future moments by using the current heat of each media information in the current heat ranking list and performing heat decay calculation.

[0152] Optionally, in a specific embodiment of the present application, the first calculation unit 1003 includes:

[0153] The processing unit is used to process the current popularity of each media information in the current popularity ranking list according to the principle that the popularity decays over time, and obtain the popularity of each media information at multiple future moments.

[0154] Optionally, in a specific embodiment of the present application, the processing unit includes:

[0155] The processing subunit is used to attenuate the current heat of each media information in the current heat ranking list by the number of future time intervals between the current moment and each future moment, and use the attenuated heat as the heat of the media information at each future moment.

[0156] Optionally, in a specific embodiment of the present application, the first calculation unit 1003 includes: a first calculation subunit and a second confirmation unit.

[0157] The first calculation subunit is used to obtain the heat of each media information corresponding to each user operation at multiple future moments after heat decay calculation for each media information in the current heat ranking list using the current heat of the media information corresponding to each user operation.

[0158] The second confirmation unit is used to synthesize the popularity of the media information corresponding to each user operation at each future moment to obtain the popularity of the media information at each future moment.

[0159] The second updating unit 1004 is used to update the expected popularity ranking list corresponding to each future moment according to the target popularity of each media information in the current popularity ranking list.

[0160] The target heat refers to the heat of each media information at each future moment that satisfies the condition that the heat is greater than the minimum threshold, and each expected heat ranking list includes: multiple media information sorted by heat and whose heat is greater than the minimum threshold.

[0161] Optionally, in a specific embodiment of the present application, the device 1000 for updating the popularity ranking list further includes: a second acquisition unit, a third updating unit, a third calculation unit and a fourth updating unit.

[0162] The second acquisition unit is used to acquire the behavior information of the user performing the operation when a message indicating that the media information is operated by the user is detected.

[0163] The third updating unit is used to calculate the current heat of the media information operated by the user after calculating the heat of the media information operated by the user using the user operation information accumulated at the time of detecting the message, and update the current heat ranking list according to the current heat of the media information operated by the user.

[0164] The third calculation unit is used to use the current heat of the media information operated by the user to obtain the heat of the media information operated by the user at multiple future time points after heat decay calculation.

[0165] The fourth updating unit is used to update the expected popularity ranking list corresponding to each future moment according to the popularity of each future moment of the media information operated by the user and satisfying the condition that the popularity is greater than a minimum threshold.

[0166] The specific principles and execution process of the popularity ranking list updating device 1000 disclosed in the above-mentioned embodiment of the present application are the same as the popularity ranking list updating method disclosed in the above-mentioned embodiment of the present application. Please refer to the corresponding part of the popularity ranking list updating method disclosed in the above-mentioned embodiment of the present application, and will not be repeated here.

[0167] In the device for updating the popularity ranking list provided by the present application, the popularity of the media information in the current popularity ranking list is greater than the minimum threshold value, so the media information with low popularity is removed from the current popularity ranking list. In this way, the first updating unit 1002 calculates the current popularity of each media information in the current popularity ranking list using the user operation information accumulated by the media information at the current moment, and in the process of updating the current popularity ranking list according to the current popularity of each media information in the current popularity ranking list, it can be ensured that the media information with low popularity will not be calculated and updated to the current popularity ranking list, thereby reducing the amount of media information calculated during the update of the current popularity ranking list, reducing system pressure, and reducing the heat calculation time. In addition, the popularity of the media information in the expected popularity ranking list corresponding to each future moment is also greater than the minimum threshold value, so the media information with low popularity is also removed from the expected popularity ranking list corresponding to each future moment. In this way, the first calculation unit 1003 uses the current heat of each media information in the current heat ranking list to obtain the heat of each media information at multiple future moments after heat decay calculation, and the second updating unit 1004 updates the expected heat ranking list corresponding to each future moment according to the target heat of each media information in the current heat ranking list. It also ensures that the media information with low heat will not be calculated and updated to the expected heat ranking list, thereby reducing the amount of media information calculated during the update of the expected heat ranking list, reducing system pressure, and reducing heat calculation time.

[0168] Another embodiment of the present application provides a server, such as Fig.11 As shown, including:

[0169] One or more processors 1101.

[0170] The storage device 1102 stores one or more programs.

[0171] When the one or more programs are executed by the one or more processors 1101, the one or more processors 1101 implement the method for updating the popularity ranking list provided by the above method embodiments.

[0172] An embodiment of the present application provides a computer storage medium on which a computer program is stored, wherein when the program is executed by a processor, the method for updating the popularity ranking list provided by the above method embodiments is implemented.

[0173] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0174] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0176] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0177] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0178] Storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0179] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0180] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used, and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. The scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned application concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in this application (but not limited to) to form a technical solution.

Claims

1. A method for updating a popularity ranking list, characterized in that: include: When a message indicating that an operation is performed by a user on media information is detected, obtaining behavior information of the user performing the operation; For the media information operated by the user, the user operation information accumulated at the time of detecting the message is used to calculate the current heat of the media information operated by the user, and the current heat ranking list is updated according to the current heat of the media information operated by the user; Using the current heat of the media information operated by the user, heat decay calculation is performed to obtain the heat of the media information operated by the user at multiple future moments; According to the heat of each future moment of the media information operated by the user and satisfying the condition that the heat is greater than a minimum threshold, updating the expected heat ranking list corresponding to each future moment; At an update time point in an update cycle, user operation information accumulated at the current moment for each media information in the current popularity ranking list is obtained; wherein the current popularity ranking list includes a plurality of media information sorted by popularity and whose popularity is greater than a minimum threshold; For each piece of media information in the current popularity ranking list, the user operation information accumulated at the current moment of the media information is used to calculate the current popularity of the media information, and the current popularity ranking list is updated according to the current popularity of each piece of media information in the current popularity ranking list; Using the current popularity of each piece of media information in the current popularity ranking list, the popularity of each piece of media information at multiple future moments is obtained after the popularity decay calculation; According to the target heat of each of the media information in the current heat ranking list, the expected heat ranking list corresponding to each future moment is updated; wherein the target heat refers to the heat of each of the media information at each future moment that satisfies the condition that the heat is greater than the minimum threshold, and each of the expected heat ranking lists includes: multiple media information sorted by heat and whose heat is greater than the minimum threshold.

2. The updating method according to claim 1, characterized in that: The method of using the current popularity of each piece of media information in the current popularity ranking list to obtain the popularity of each piece of media information at multiple future moments after the popularity decay calculation includes: The current popularity of each piece of media information in the current popularity ranking list is processed according to the principle that popularity decays over time, so as to obtain the popularity of each piece of media information at multiple future moments.

3. The updating method according to claim 2, characterized in that: The processing of the current popularity of each piece of media information in the current popularity ranking list according to the principle of popularity decaying over time to obtain the popularity of each piece of media information at multiple future moments includes: For each piece of media information in the current popularity ranking list, the current popularity of the media information is attenuated by the number of future time intervals between the current moment and each of the future moments, and the attenuated popularity is used as the popularity of the media information at each of the future moments.

4. The updating method according to claim 1, characterized in that: The method of using the user operation information accumulated at the current moment of the media information to calculate the current heat of the media information includes: Counting the user operation information accumulated by the media information at the current moment, including the amount of each type of user operation; According to the statistical amount of each user operation and the weight corresponding to each user operation, the current heat of each user operation corresponding to the media information is obtained after heat calculation; The current popularity of the media information corresponding to each user operation is synthesized to obtain the current popularity of the media information.

5. The updating method according to claim 4, characterized in that: The method of using the current popularity of each piece of media information in the current popularity ranking list to obtain the popularity of each piece of media information at multiple future moments after the popularity decay calculation includes: For each piece of media information in the current popularity ranking list, using the current popularity of each user operation corresponding to the media information, the popularity of the media information corresponding to each user operation at multiple future moments is obtained after the popularity decay calculation; The popularity of the media information corresponding to each user operation at each future moment is synthesized to obtain the popularity of the media information at each future moment.

6. A device for updating a popularity ranking list, characterized in that: include: A second acquisition unit is used to acquire behavior information of the user performing the operation when a message indicating that the media information is operated by the user is detected; A third updating unit is used to calculate the current heat of the media information operated by the user by using the user operation information accumulated at the time of detecting the message, and update the current heat ranking list according to the current heat of the media information operated by the user; A third calculation unit is used to obtain the heat of the media information operated by the user at multiple future moments by using the current heat of the media information operated by the user and performing heat decay calculation; A fourth updating unit, configured to update an expected popularity ranking list corresponding to each future moment according to the popularity of each future moment of the media information operated by the user and satisfying a condition that the popularity is greater than a minimum threshold; A first acquisition unit is used to acquire, at an update time point in an update cycle, user operation information accumulated at the current moment for each media information in the current popularity ranking list; wherein the current popularity ranking list includes a plurality of media information sorted by popularity and whose popularity is greater than a minimum threshold; A first updating unit is used to calculate the heat of each piece of media information in the current heat ranking list by using the user operation information accumulated at the current moment of the media information to obtain the current heat of the media information, and update the current heat ranking list according to the current heat of each piece of media information in the current heat ranking list; A first calculation unit is used to obtain the heat of each of the media information at multiple future moments by using the current heat of each of the media information in the current heat ranking list and performing heat decay calculation; The second updating unit is used to update the expected heat ranking list corresponding to each future moment according to the target heat of each of the media information in the current heat ranking list; wherein the target heat refers to the heat of each of the media information at each future moment that satisfies the condition that the heat is greater than the minimum threshold, and each of the expected heat ranking lists includes: multiple media information sorted by heat and whose heat is greater than the minimum threshold.

7. The updating device according to claim 6, characterized in that: The first computing unit comprises: The processing unit is used to process the current popularity of each piece of media information in the current popularity ranking list according to the principle that popularity decays over time, and obtain the popularity of each piece of media information at multiple future moments.

8. The updating device according to claim 7, characterized in that: The processing unit comprises: The processing subunit is used to attenuate the current popularity of each piece of media information in the current popularity ranking list by the number of future time intervals between the current moment and each of the future moments, and use the attenuated popularity as the popularity of the media information at each of the future moments.

9. The updating device according to claim 6, characterized in that: The first updating unit comprises: A statistical unit, used to count the user operation information accumulated by the media information at the current moment, and the amount of each type of user operation; A second calculation unit is used to calculate the current heat of each user operation corresponding to the media information according to the statistical amount of each user operation and the weight corresponding to each user operation. The first confirmation unit is used to obtain the current popularity of the media information by integrating the current popularity of each user operation of the media information.

10. The updating device according to claim 9, characterized in that: The first computing unit comprises: A first calculation subunit is used for obtaining the heat of each media information in the current heat ranking list by using the current heat of each user operation corresponding to the media information and performing heat decay calculation to obtain the heat of each media information corresponding to the user operation at multiple future moments. The second confirmation unit is used to synthesize the popularity of the media information corresponding to each user operation at each future moment to obtain the popularity of the media information at each future moment.

11. A server, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method according to any one of claims 1 to 5.

12. A computer storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

13. A computer program product, characterized in that The method comprises computer program instructions, which implement the method according to any one of claims 1 to 5 when executed by a processor.

Images