A method, system, storage medium and device for allocating electronic resources

Abstract

The present invention discloses a method for allocating electronic resources. First, the first batch of electronic resources is allocated to multiple active users to obtain a target user set; then, based on the active users and the target user set, a first target parameter representing the similarity between the active users and the users in the target user set is obtained; based on the first target parameter, a second target parameter representing the similarity between the active users and the target user set is obtained; based on the second target parameter and a target parameter threshold, a target active user whose second target parameter is greater than or equal to the target parameter threshold is obtained; finally, a second batch of electronic resources is allocated to the target active user. Through the two allocations, the accuracy of electronic resource allocation can be improved.

Description

Technical Field

[0001] The present invention relates to the field of network live broadcast technology, and in particular to a method and system for allocating electronic resources, a storage medium, and a device. Background Art

[0002] On the live streaming platform, in order to promote user participation in live streaming interaction, the platform often has some activities, such as issuing electronic resources (e.g., coupons) to users so that users can use the coupons to actively participate in platform interaction. However, issuing coupons to users has costs and cannot be issued blindly. It is necessary to expect to distribute them to target users as much as possible to obtain a better promotion effect. Therefore, the existing electronic resource allocation is too blind, so that electronic resources are allocated to many non-target users, which causes the live streaming platform to allocate electronic resources lag. Summary of the invention

[0003] In view of the above problems, the present invention is proposed to provide a method and system, storage medium, and device for allocating electronic resources that overcome the above problems or at least partially solve the above problems.

[0004] On the one hand, the present application provides the following technical solution through an embodiment of the present application:

[0005] A method for allocating electronic resources, used in a live broadcast platform, comprising:

[0006] Allocating a first batch of electronic resources to a plurality of active users, wherein the active users are users who have participated in the interaction on the live webcast platform within a first preset time;

[0007] obtaining a target user set, wherein the target user set includes the active users who have used the first batch of electronic resources;

[0008] Based on the active user and the target user set, obtaining a first target parameter representing the similarity between the active user and the users in the target user set;

[0009] Based on the first target parameter, obtaining a second target parameter representing the similarity between the active user and the target user set;

[0010] Based on the second target parameter and the target parameter threshold, obtaining target active users whose second target parameter is greater than or equal to the target parameter threshold;

[0011] A second batch of electronic resources is allocated to the target active users.

[0012] Optionally, obtaining, based on the active user and the target user set, a first target parameter representing the similarity between the active user and users in the target user set specifically includes:

[0013] Based on the log data of the network live broadcast platform, a set of live broadcast rooms in which the active users and the target user set users jointly participate in the interaction within the first preset time is obtained;

[0014] Based on the live broadcast room set, a third target parameter representing the proportion of the active user's interaction time in the live broadcast room set and a fourth target parameter representing the proportion of the target user set's interaction time in the live broadcast room set are obtained;

[0015] Based on the third target parameter and the fourth target parameter, a fifth target parameter is obtained that characterizes the difference in degree of participation of the active user and the target user set in the live broadcast room set interaction;

[0016] Based on the fifth target parameter, a first target parameter characterizing the similarity between the active user and users in the target user set is obtained.

[0017] Optionally, based on the live broadcast room set, obtaining a third target parameter representing a proportion of the interaction time of the active users with the live broadcast room set and a fourth target parameter representing a proportion of the interaction time of users in the target user set with the live broadcast room set specifically includes:

[0018] The third target parameter is obtained according to the following formula:

[0019]

[0020] Among them, P uR is a third target parameter representing the proportion of interaction time of the live broadcast room set R in which the active user u and the target user v jointly participate in the second preset time period; r is the live broadcast room in which active user u and concentrated user v in the live broadcast room set R participate in the interaction, w ur is the duration of interaction of active user u in live broadcast room r during the second preset time period, is the total duration of the active user u's interaction in all live broadcast rooms in the live broadcast room set R during the second preset time period;

[0021] The fourth target parameter is obtained according to the following formula:

[0022]

[0023] Among them, P vR is a fourth target parameter representing the proportion of interaction time of the live broadcast room set R in which the user v in the target user set and the active user u participated in the second preset time period; r is the live broadcast room in which active user u and concentrated user v in the live broadcast room set R participate in the interaction, w vris the duration of user v's interaction with live broadcast room r during the second preset time period, It is the total duration of user v's interaction in all live broadcast rooms in the live broadcast room set R during the second preset time period.

[0024] Optionally, obtaining a fifth target parameter characterizing the difference in degree of participation of the active user and the target user set in the live broadcast room set interaction based on the third target parameter and the fourth target parameter specifically includes:

[0025] The fifth target parameter is obtained according to the following formula:

[0026]

[0027] Among them, p' ur is the normalized p ur , p' vr is the normalized p vr .

[0028] Optionally, obtaining, based on the fifth target parameter, a first target parameter characterizing the similarity between the active user and users in the target user set specifically includes:

[0029] The first target parameter is obtained according to the following formula:

[0030]

[0031] Among them, s uv The first target parameter that characterizes the similarity between active user u and user v, w is the weight coefficient, ranging from 0 to 1, |R u ∪R v | is the number of live broadcast rooms in which active users u and v interact;

[0032] min d u is the minimum fifth target parameter of active user u and users in the target user set, max d u It is the maximum fifth target parameter of active user u and users in the target user set.

[0033] Optionally, obtaining, based on the first target parameter, a second target parameter characterizing the similarity between the active user and the target user set specifically includes:

[0034] The second target parameter is obtained according to the following formula:

[0035]

[0036] Among them, ss(u,C) is the second target parameter that represents the similarity between the active user u and the target user set C;

[0037] C u are the N users with the highest similarity to u in the target user set C, and N is a constant.

[0038] Optionally, allocating the first batch of electronic resources to multiple active users specifically includes:

[0039] Based on the log data of the live webcast platform, an active user set is obtained, where the active user set includes users who participate in the interaction of the live webcast platform within the first preset time;

[0040] A plurality of active users are selected from the active user set, and a first batch of electronic resources are allocated to the plurality of active users.

[0041] On the other hand, the present application provides a system for allocating electronic resources through another embodiment of the present application, which is used for a live broadcast platform, and the system includes:

[0042] A first allocation module is used to allocate a first batch of electronic resources to multiple active users, wherein the active users are users who participate in the interaction of the live broadcast platform within a first preset time;

[0043] A first obtaining module, configured to obtain a target user set, wherein the target user set includes the active users who have used the first batch of electronic resources;

[0044] A second obtaining module is used to obtain a first target parameter representing the similarity between the active user and the user in the target user set based on the active user and the target user set;

[0045] A third obtaining module, configured to obtain, based on the first target parameter, a second target parameter representing the similarity between the active user and the target user set;

[0046] a fourth obtaining module, configured to obtain, based on the second target parameter and the target parameter threshold, target active users whose second target parameter is greater than or equal to the target parameter threshold;

[0047] The second allocation module is used to allocate a second batch of electronic resources to the target active users.

[0048] The present invention discloses a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0049] The present invention discloses an electronic device, comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor executes the steps of the method.

[0050] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0051] In one or more embodiments of the present invention, the method for allocating electronic resources first allocates the first batch of electronic resources to multiple active users, wherein the active users are users who participate in the interaction of the live broadcast platform within a first preset time; then obtains a target user set composed of the active users who have used the first batch of electronic resources; then, based on the active users and the target user set, obtains a first target parameter representing the similarity between the active users and the users in the target user set; based on the first target parameter, obtains a second target parameter representing the similarity between the active users and the target user set; based on the second target parameter and the target parameter threshold, obtains a target active user whose second target parameter is greater than or equal to the target parameter threshold; finally, allocates the second batch of electronic resources to the target active user. It can be seen that since the second batch of electronic resources is allocated to target active users similar to the active users who have used the first batch of electronic resources, the active users who have used the first batch of electronic resources are the target users of the platform, and the target active users similar to them are also very likely to be the target users of the platform. Therefore, through two allocations, the accuracy of electronic resource allocation can be improved, making the electronic resource allocation process of the live broadcast platform efficient and smooth. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 is a flow chart of a method for allocating electronic resources in one embodiment of the present invention;

[0054] Figure 2 It is a system architecture diagram for allocating electronic resources in one embodiment of the present invention. DETAILED DESCRIPTION

[0055] The embodiments of the present application improve the accuracy of electronic resource allocation on a live broadcast platform by providing a method and system, storage medium, and device for allocating electronic resources.

[0056] The technical solution of the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0057] A method for allocating electronic resources is used in a network live broadcast platform. First, the first batch of electronic resources is allocated to multiple active users, and the active users are users who participate in the interaction of the network live broadcast platform within a first preset time; then a target user set consisting of the active users who have used the first batch of electronic resources is obtained; then, based on the active users and the target user set, a first target parameter representing the similarity between the active users and users in the target user set is obtained; based on the first target parameter, a second target parameter representing the similarity between the active users and the target user set is obtained; based on the second target parameter and a target parameter threshold, a target active user whose second target parameter is greater than or equal to the target parameter threshold is obtained; finally, a second batch of electronic resources is allocated to the target active users.

[0058] It can be seen from this that since the second batch of electronic resources is allocated to target active users who are similar to the active users who have used the first batch of electronic resources, the active users who have used the first batch of electronic resources are the target users of the platform, and the target active users similar to them are also very likely to be the target users of the platform. Therefore, through two allocations, the accuracy of electronic resource allocation can be improved.

[0059] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0060] First of all, the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0061] Embodiment 1

[0062] This implementation provides a method for allocating electronic resources for a live webcast platform, see Figure 1 , the method of this embodiment includes the following steps:

[0063] S101, allocating a first batch of electronic resources to multiple active users, wherein the active users are users who participate in the interaction on the live broadcast platform within a first preset time;

[0064] S102, obtaining a target user set, wherein the target user set includes the active users who have used the first batch of electronic resources;

[0065] S103, based on the active user and the target user set, obtaining a first target parameter representing the similarity between the active user and the users in the target user set;

[0066] S104: Based on the first target parameter, obtain a second target parameter representing the similarity between the active user and the target user set;

[0067] S105. Based on the second target parameter and the target parameter threshold, obtain target active users whose second target parameter is greater than or equal to the target parameter threshold;

[0068] S106: Allocate a second batch of electronic resources to the target active users.

[0069] It should be noted that the user or active user in this embodiment can be a person participating in the live broadcast interaction, or an electronic device participating in the live broadcast interaction, such as an intelligent robot, etc. The electronic resource in this embodiment can be an electronic resource such as a coupon, a consumption voucher, etc.

[0070] The method for allocating electronic resources provided in this embodiment can be applied to the scenario of allocating electronic resources to live broadcast users on a live broadcast platform. The method can be performed by an electronic resource allocation device, which can be implemented by software and / or hardware, and is usually integrated into a terminal, such as a server corresponding to the live broadcast platform.

[0071] See also Figure 1 The execution process of the method in this embodiment is as follows:

[0072] First, S101 is executed to distribute the first batch of electronic resources to multiple active users, where the active users are users who participate in the interaction on the live broadcast platform within a first preset time.

[0073] In the specific implementation process, the allocation in this embodiment can also be called delivery; the first preset time can be set as needed, for example, the past 7 days or the past 30 days, etc. The first batch of electronic resources in this embodiment refers to the electronic resources delivered for the first time, and its quantity is not limited and can be set as needed. However, as an optional embodiment, in order to ensure that the number of target user sets obtained later after the first batch of electronic resources are distributed can be used as the basis for similarity comparison and not to waste too many electronic resources, the number of the first batch of electronic resources can be selected to be 10,000-100,000. Since the allocation of the first batch of electronic resources is not targeted, but only to obtain the subsequent target user set as the basis for similarity comparison, therefore, allocating as few first batch of electronic resources as possible is more conducive to avoiding ineffective delivery of electronic resources.

[0074] As an optional embodiment, allocating the first batch of electronic resources to multiple active users specifically includes: obtaining an active user set based on the log data of the live broadcast platform, the active user set including users who participated in the interaction of the live broadcast platform within the first preset time; screening out multiple active users from the active user set, and allocating the first batch of electronic resources to the multiple active users.

[0075] In the specific implementation process, log data refers to objective data left by live broadcast activities on the live broadcast platform, and is not selected by human subjective factors. From the log data, active users can be obtained based on whether the user participates in the interaction on the live broadcast platform within the first preset time, thereby forming an active user set. Multiple active users can be randomly selected from the active user set, and this embodiment does not limit their number, but.

[0076] Next, S102 is executed to obtain a target user set, where the target user set includes the active users who have used the first batch of electronic resources.

[0077] In the specific implementation process, after the first batch of electronic resources are released, multiple active users receive the electronic resources and may or may not use the electronic resources to participate in the live broadcast interaction. The active users who use the electronic resources to participate in the live broadcast interaction may be users who are interested in the electronic resources. Therefore, the active users who have used the first batch of electronic resources can be considered as high-quality target users.

[0078] Next, S103 is executed to obtain, based on the active user and the target user set, a first target parameter representing the similarity between the active user and the users in the target user set.

[0079] In the specific implementation process, after obtaining the target user set, in order to subsequently allocate the second batch of electronic resources, it is necessary to first obtain the target active users. To this end, it is first necessary to obtain a first target parameter that represents the similarity between the active users and the users in the target user set.

[0080] As an optional embodiment, obtaining, based on the active user and the target user set, a first target parameter representing the similarity between the active user and the users in the target user set specifically includes:

[0081] S113, based on the log data of the network live broadcast platform, obtaining a set of live broadcast rooms in which the active users and the target user set users jointly participate in the interaction within the first preset time;

[0082] S123, based on the live broadcast room set, obtaining a third target parameter representing a proportion of the active user's interaction time in the live broadcast room set and a fourth target parameter representing a proportion of the target user set's interaction time in the live broadcast room set;

[0083] S133, based on the third target parameter and the fourth target parameter, obtaining a fifth target parameter representing the difference in degree of participation of the active user and the target user set in the live broadcast room set interaction;

[0084] S143: Based on the fifth target parameter, obtain a first target parameter representing the similarity between the active user and the users in the target user set.

[0085] In the specific implementation process, in S123, as an optional embodiment, the third target parameter may be obtained according to the following formula:

[0086]

[0087] Among them, P uR is a third target parameter representing the proportion of interaction time of the live broadcast room set R in which the active user u and the target user v jointly participate in the second preset time period; r is the live broadcast room in which active user u and concentrated user v in the live broadcast room set R participate in the interaction, w ur is the duration of interaction of active user u in live broadcast room r during the second preset time period, is the total duration of the active user u's interaction in all live broadcast rooms in the live broadcast room set R during the second preset time period;

[0088] in, represents the interaction time w of active user u in live broadcast room r ur Total interaction time The larger the proportion, the more active users u invest in the live broadcast room r, then p ur The larger it is, the larger the third target parameter representing the proportion of the interaction time of active user u in the live broadcast room set R within the second preset time period.

[0089] The fourth target parameter is obtained according to the following formula:

[0090]

[0091] Among them, P vR is a fourth target parameter representing the proportion of interaction time of the live broadcast room set R in which the user v in the target user set and the active user u participated in the second preset time period; r is the live broadcast room in which active user u and concentrated user v in the live broadcast room set R participate in the interaction, wvr is the duration of user v's interaction with live broadcast room r during the second preset time period, It is the total duration of user v's interaction in all live broadcast rooms in the live broadcast room set R during the second preset time period.

[0092] The principle of this formula can be referred to P uR , I will not go into details here.

[0093] The second preset time can be set as needed, for example, the past 30 days or the past 60 days.

[0094] In S133, as an optional embodiment, the fifth target parameter may be obtained according to the following formula:

[0095]

[0096] Among them, p' ur is the normalized p ur , p' vr is the normalized p vr .

[0097] The principle of this formula is: the difference in the degree of interaction between active users and target users in the live broadcast room set consists of two parts: one is the relative viewing difference between active users u and user v for each live broadcast room in the live broadcast room set R. The other part is the absolute value of the difference between the third target parameter and the fourth target parameter

[0098] The reason why both parts need to be considered at the same time is that the relative viewing difference between the live broadcast rooms represents the viewing difference for a single live broadcast room, while the absolute value of the difference between the third target parameter and the fourth target parameter represents the overall difference in the viewing set R. Comprehensive consideration of these two parts can more accurately reflect the viewing difference between users u and v.

[0099] In S143, as an optional embodiment, the first target parameter may be obtained according to the following formula:

[0100]

[0101] Among them, s uv The first target parameter that characterizes the similarity between active user u and user v, w is the weight coefficient, ranging from 0 to 1, |R u ∪R v | is the number of live broadcast rooms in which active users u and v interact;

[0102] in, min d uis the minimum fifth target parameter of active user u and users in the target user set, max d u It is the maximum fifth target parameter of active user u and users in the target user set.

[0103] It should be noted that the principle of the above formula is: the final similarity between u and v consists of two parts, one is the interaction similarity sd between u and v uv , which represents the difference between the distribution of interaction time between u and v in the live broadcast modification room; the other part is It represents the overlap of the interaction of the live broadcast room set. The value of w can be determined based on the average similarity of the two parts of the target users identified in the historical data in the recent period. If the first part (i.e., the interaction similarity sd uv ) has a tendency to increase, then increase the value of w, otherwise, decrease the value of w.

[0104] The reason why these two parts need to be considered at the same time is that the overlap of the set of live broadcast rooms can most directly indicate the similarity of the interactions between users u and v. However, even if users u and v participate in similar live broadcast rooms, but the absolute value and distribution of the interaction time are very different, their similarity will not be that high.

[0105] Next, S104 is executed to obtain a second target parameter representing the similarity between the active user and the target user set based on the first target parameter.

[0106] In the specific implementation process, since the first target parameter can only characterize the similarity between the active user u and the user v in the target user set, in order to obtain the subsequent target active user to allocate the second batch of electronic resources, this embodiment first obtains the second target parameter characterizing the similarity between the active user and the target user set as the basis for determining the target active user.

[0107] Exemplarily, the second target parameter may be obtained according to the following formula:

[0108]

[0109] Among them, ss(u,C) is the second target parameter that represents the similarity between the active user u and the target user set C;

[0110] C u are the N users with the highest similarity to u in the target user set C, and N is a constant.

[0111] It should be noted that the principle of the second target parameter calculation formula is: the similarity between the active user u and the target user set C as a whole can be calculated by the user in C whose similarity is closest to the active user. Therefore, in the formula, the N users with the highest similarity to u are first found, and the average similarity of these users with u is calculated.

[0112] Next, execute S105 to obtain target active users whose second target parameter is greater than or equal to the target parameter threshold based on the second target parameter and the target parameter threshold.

[0113] In the specific implementation process, the target parameter threshold can be set as needed. For example, for the users in the target user set, ss(u,C) is calculated according to the method of S101-S104, and sorted from large to small, and the 95% quantile is taken as the threshold. If it is necessary to increase the coverage rate and deploy more users, the threshold can be lowered, otherwise the threshold can be increased.

[0114] Since the second target parameter represents the similarity between the active users and the target user set, the active users whose second target parameter is greater than or equal to the target parameter threshold have a higher similarity with the target user set. These active users are more likely to actively participate in the interaction using electronic resources. Selecting them as target active users and allocating the second batch of electronic resources is conducive to improving the accuracy of electronic resource allocation.

[0115] In addition, it should be noted that in this embodiment, the number of the second batch of electronic resources is not limited and can be determined as needed. However, since the first batch of electronic resources is randomly allocated only to determine the target active users, the second batch of electronic resources is accurately allocated with a purpose. Therefore, in order to improve the accuracy of allocation, the number of the second batch of electronic resources can be set to be greater than the number of the first batch of electronic resources.

[0116] Next, S106 is executed to allocate a second batch of electronic resources to the target active users.

[0117] During the specific implementation process, there may be multiple target active users. After determining the target active users, the online live broadcast platform directly allocates the second batch of electronic resources to the target active users.

[0118] The following is a practical example to illustrate the process of obtaining the first target parameter of the method of this embodiment:

[0119] Assume that active user u watched live broadcast rooms a, b, and c, and user v watched live broadcast rooms a, b, and d, so the set of live broadcast rooms watched by u and v together is a and b.

[0120] u's viewing time for live broadcast rooms a, b, and c is 100s, 50s, and 50s respectively, and user v's viewing time for live broadcast rooms a, b, and d is 30s, 60s, and 60s respectively. Therefore, the interaction time of u and v in each live broadcast room is w ur Total interaction time The proportion of:

[0121]

[0122]

[0123]

[0124]

[0125]

[0126]

[0127] calculate

[0128] After normalization, we get:

[0129]

[0130]

[0131]

[0132]

[0133] calculate

[0134] therefore,

[0135] Assume max d u =0.14,min d u =0.0

[0136]

[0137] The weight coefficient w = 0.35, so the first target parameter is:

[0138]

[0139] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0140] The method of this embodiment first allocates the first batch of electronic resources to multiple active users, wherein the active users are users who participate in the interaction of the live broadcast platform within the first preset time; then obtains the target user set composed of the active users who have used the first batch of electronic resources; then obtains the first target parameter representing the similarity between the active users and the users in the target user set based on the active users and the target user set; obtains the second target parameter representing the similarity between the active users and the target user set based on the first target parameter; obtains the target active users whose second target parameter is greater than or equal to the target parameter threshold based on the second target parameter and the target parameter threshold; and finally allocates the second batch of electronic resources to the target active users. It can be seen that since the second batch of electronic resources is allocated to the target active users who are similar to the active users who have used the first batch of electronic resources, the active users who have used the first batch of electronic resources are the target users of the platform, and the target active users who are similar to them are also very likely to be the target users of the platform. Therefore, through two allocations, the accuracy of electronic resource allocation can be improved, making the electronic resource allocation process of the live broadcast platform efficient and smooth.

[0141] Embodiment 2

[0142] Based on the same inventive concept as the first embodiment, this embodiment provides a system for distributing electronic resources for a live broadcast platform, see Figure 2 , the system comprising:

[0143] A first allocation module is used to allocate a first batch of electronic resources to multiple active users, wherein the active users are users who participate in the interaction of the live broadcast platform within a first preset time;

[0144] A first obtaining module, configured to obtain a target user set, wherein the target user set includes the active users who have used the first batch of electronic resources;

[0145] A second obtaining module is used to obtain, based on the active user and the target user set, a first target parameter representing the similarity between the active user and the user in the target user set;

[0146] A third obtaining module, configured to obtain, based on the first target parameter, a second target parameter representing the similarity between the active user and the target user set;

[0147] a fourth obtaining module, configured to obtain, based on the second target parameter and the target parameter threshold, target active users whose second target parameter is greater than or equal to the target parameter threshold;

[0148] The second allocation module is used to allocate a second batch of electronic resources to the target active users.

[0149] Since the system for allocating electronic resources introduced in this embodiment is a system used to implement a method for allocating electronic resources in an embodiment of the present application, based on the method for allocating electronic resources introduced in the first embodiment of the present application, those skilled in the art can understand the specific implementation of the system of the present embodiment and its various variations, so how to use the system in this embodiment to implement the method in the first embodiment will not be described in detail here. As long as the system used by those skilled in the art to implement the method for allocating electronic resources in the embodiment of the present application is adopted, it belongs to the scope of protection of this application.

[0150] Based on the same inventive concept as in the aforementioned embodiment, an embodiment of the present invention further provides a readable storage medium having a computer program stored thereon, which implements the steps of any of the aforementioned methods when executed by a processor.

[0151] Based on the same inventive concept as in the aforementioned embodiments, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the aforementioned methods are implemented.

[0152] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0153] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these 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 these modifications and variations.

Claims

1. A method for allocating electronic resources, used in a live broadcast platform, characterized in that: The method comprises: Allocating a first batch of electronic resources to a plurality of active users, wherein the active users are users who have participated in the interaction on the live webcast platform within a first preset time; obtaining a target user set, wherein the target user set includes the active users who have used the first batch of electronic resources; Based on the active user and the target user set, obtaining a first target parameter representing the similarity between the active user and the users in the target user set; Based on the first target parameter, a second target parameter representing the similarity between the active user and the target user set is obtained; the similarity is calculated by using the user in the target user set whose similarity is closest to the active user; Based on the second target parameter and the target parameter threshold, obtaining target active users whose second target parameter is greater than or equal to the target parameter threshold; allocating a second batch of electronic resources to the target active users; The obtaining, based on the active user and the target user set, a first target parameter representing the similarity between the active user and the users in the target user set specifically includes: Based on the log data of the network live broadcast platform, a set of live broadcast rooms in which the active users and the target user set users jointly participate in the interaction within the first preset time is obtained; Based on the live broadcast room set, a third target parameter representing the proportion of the active user's interaction time in the live broadcast room set and a fourth target parameter representing the proportion of the target user set's interaction time in the live broadcast room set are obtained; Based on the third target parameter and the fourth target parameter, a fifth target parameter is obtained that characterizes the difference in degree of participation of the active user and the target user set in the live broadcast room set interaction; Based on the fifth target parameter, a first target parameter characterizing the similarity between the active user and users in the target user set is obtained.

2. The method according to claim 1, characterized in that The obtaining, based on the live broadcast room set, of a third target parameter representing the proportion of the interaction time of the active users with the live broadcast room set and a fourth target parameter representing the proportion of the interaction time of users in the target user set with the live broadcast room set specifically includes: The third target parameter is obtained according to the following formula: Among them, P uR is a third target parameter representing the proportion of interaction time of the live broadcast room set R in which the active user u and the target user v jointly participate in the second preset time period; r is the live broadcast room in which active user u participates in the interaction in the live broadcast room set R*, w ur is the duration of interaction of active user u in live broadcast room r during the second preset time period, is the total duration of the active user u's interaction in all live broadcast rooms in the live broadcast room set R* during the second preset time period; The fourth target parameter is obtained according to the following formula: Among them, P vR is a fourth target parameter representing the proportion of interaction time of the live broadcast room set R in which the user v in the target user set and the active user u participated in the second preset time period; r is the live broadcast room in the live broadcast room set R* where user v participates in the interaction, w vr is the duration of user v's interaction with live broadcast room r during the second preset time period, It is the total duration of user v's interaction in all live broadcast rooms in the live broadcast room set R* during the second preset time period.

3. The method according to claim 2, characterized in that The obtaining, based on the third target parameter and the fourth target parameter, of a fifth target parameter characterizing the difference in degree of participation of the active user and the target user set in the live broadcast room set interaction specifically includes: The fifth target parameter is obtained according to the following formula: Among them, p' ur is the normalized p ur , p' vr is the normalized p vr .

4. The method according to claim 3, characterized in that The obtaining, based on the fifth target parameter, a first target parameter characterizing the similarity between the active user and the users in the target user set specifically includes: The first target parameter is obtained according to the following formula: Among them, s uv The first target parameter that characterizes the similarity between active user u and user v, w is the weight coefficient, ranging from 0 to 1, |R u ∪R v | is the number of live broadcast rooms in which active users u and v interact; mind u is the minimum fifth target parameter of the active user u and the target user set, maxd u It is the maximum fifth target parameter of active user u and users in the target user set.

5. The method according to claim 4, characterized in that The obtaining, based on the first target parameter, a second target parameter characterizing the similarity between the active user and the target user set specifically includes: The second target parameter is obtained according to the following formula: Among them, ss(u,C) is the second target parameter that represents the similarity between active user u and target user set C; C u are the N users with the highest similarity to u in the target user set C, and N is a constant.

6. The method according to claim 1, characterized in that The allocating the first batch of electronic resources to multiple active users specifically includes: Based on the log data of the live broadcast platform, an active user set is obtained, where the active user set includes users who participate in the interaction of the live broadcast platform within the first preset time; A plurality of active users are selected from the active user set, and a first batch of electronic resources are allocated to the plurality of active users.

7. A system for distributing electronic resources, used in a live broadcast platform, characterized in that: The system comprises: A first allocation module is used to allocate a first batch of electronic resources to multiple active users, wherein the active users are users who participate in the interaction of the live broadcast platform within a first preset time; A first obtaining module, configured to obtain a target user set, wherein the target user set includes the active users who have used the first batch of electronic resources; A second obtaining module is used to obtain a first target parameter representing the similarity between the active user and the user in the target user set based on the active user and the target user set; The obtaining, based on the active user and the target user set, a first target parameter representing the similarity between the active user and the user in the target user set specifically includes: Based on the log data of the network live broadcast platform, a set of live broadcast rooms in which the active users and the target user set users jointly participate in the interaction within the first preset time is obtained; Based on the live broadcast room set, a third target parameter representing the proportion of the active user's interaction time in the live broadcast room set and a fourth target parameter representing the proportion of the target user set's interaction time in the live broadcast room set are obtained; Based on the third target parameter and the fourth target parameter, a fifth target parameter is obtained that characterizes the difference in degree of participation of the active user and the target user set in the live broadcast room set interaction; Based on the fifth target parameter, obtaining a first target parameter representing the similarity between the active user and users in the target user set; A third obtaining module is used to obtain a second target parameter representing the similarity between the active user and the target user set based on the first target parameter; the similarity is calculated by using the user in the target user set whose similarity is closest to the active user; a fourth obtaining module, configured to obtain, based on the second target parameter and the target parameter threshold, target active users whose second target parameter is greater than or equal to the target parameter threshold; The second allocation module is used to allocate a second batch of electronic resources to the target active users.

8. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images