阅读说明：本技术 虚拟礼物列表生成方法、虚拟礼物推荐方法及装置 (Virtual gift list generation method, virtual gift recommendation method and device ) 是由 陈艺天 于 2020-07-24 设计创作，主要内容包括：本发明实施例公开了一种虚拟礼物列表生成方法、虚拟礼物推荐方法及装置,虚拟礼物列表生成方法包括：获取用户的用户信息和用户打赏礼物的历史行为数据；针对每种直播类型的直播间,根据用户信息和历史行为数据确定用户对每个礼物分组的偏好程度,以及确定用户对每个礼物分组中各个礼物的偏好程度；基于每个礼物分组的偏好程度和每个礼物分组中各个礼物的偏好程度生成虚拟礼物列表。结合用户信息和历史行为数据,针对用户对礼物分组的偏好以及对礼物的偏好为不同用户展示不同的礼物打赏界面,使得用户偏好的礼物分组以及礼物分组中礼物排在礼物打赏界面的前面,用户无需对礼物打赏界面翻页或刷新即可以打赏喜欢的礼物,提高了用户打赏礼物的效率。(The embodiment of the invention discloses a virtual gift list generation method, a virtual gift recommendation method and a virtual gift list generation device, wherein the virtual gift list generation method comprises the following steps: acquiring user information of a user and historical behavior data of a user watching gift; aiming at the live broadcast room of each live broadcast type, determining the preference degree of a user to each gift grouping according to user information and historical behavior data, and determining the preference degree of the user to each gift in each gift grouping; a virtual gift list is generated based on the preference level of each gift grouping and the preference levels of the gifts in each gift grouping. By combining the user information and the historical behavior data, different gift appreciation interfaces are shown for different users according to the preference of the users for gift grouping and the preference of the users for gifts, so that the gifts in the gift grouping preferred by the users and the gifts in the gift grouping are arranged in front of the gift appreciation interface, the users can appreciate favorite gifts without turning pages or refreshing the gift appreciation interface, and the efficiency of the users in appreciating the gifts is improved.)

1. A method for generating a virtual gift list, comprising:

acquiring user information of a user and historical behavior data of a gift enjoyed by the user, wherein the historical behavior data comprises behavior data of the gift enjoyed by the user in at least one live broadcast room of a live broadcast type;

for each live broadcast type of live broadcast room, determining the preference degree of the user to each gift group according to the user information and the historical behavior data, and determining the preference degree of the user to each gift in each gift group;

generating a virtual gift list based on the preference degree of each gift group and the preference degree of each gift in each gift group, wherein the virtual gift list is used for showing virtual gifts in live rooms of the live type entered by the user.

2. The method of claim 1, wherein the determining, for each live broadcast type of live broadcast room, the user's preference degree for each gift grouping according to the user information and the historical behavior data, and determining the user's preference degree for each gift in each gift grouping comprises:

and inputting the user information and the historical behavior data into a pre-trained hierarchical Bayesian model to obtain the preference degree of the user to each gift group in the live broadcast rooms of various live broadcast types and the preference degree of the user to each gift in each gift group.

3. The method of claim 2, further comprising, prior to the steps of determining, for each live broadcast type of live broadcast room, a degree of preference of the user for each gift grouping based on the user information and the historical behavior data, and determining a degree of preference of the user for respective gifts in each gift grouping, the steps of:

a priori ranking data for each gift is obtained.

4. The method according to claim 3, wherein the inputting the user information and the historical behavior data into a pre-trained hierarchical Bayesian model to obtain the user preference degree for each gift grouping in the live broadcast rooms of various live broadcast types and the user preference degree for each gift in each gift grouping comprises:

and inputting the user information, the historical behavior data and the prior sequencing data into a pre-trained hierarchical Bayesian model to obtain the preference degree of the user to each gift group in the live broadcast rooms of various live broadcast types and the preference degree of the user to each gift in each gift group.

5. The method of any of claims 1-4, wherein generating the virtual gift list based on the preference level of each gift grouping and the preference levels of the gifts in each gift grouping comprises:

sorting each gift group in a descending order according to the preference degree of the gift group to obtain a gift group sorting result;

for the gifts in each gift group, sorting the gifts in a descending order according to the preference degree of the gifts to obtain a gift sorting result of the gift group;

generating a gift grouping list according to the gift grouping sorting result, and generating a gift list of the gift grouping according to the gift sorting result of the gift grouping;

generating a virtual gift list of the user using the gift grouping list and the gift list;

the gift grouping list is used for displaying gift groups in a live broadcast according to the sorting sequence of each gift group in the gift grouping list, and the gift list is used for displaying gifts in the gift groups in the live broadcast according to the sorting sequence of the gifts in the gift list.

6. The method of claim 5, further comprising, prior to obtaining user information of a user and historical behavior data of the user's enjoyment of a gift:

judging whether historical behavior data of the user for enjoying the gift exists or not;

if yes, executing a step of acquiring user information of a user and historical behavior data of the user appreciation gift;

if not, acquiring the user information of the user;

and determining the virtual gift list of the user according to the user information of the user.

7. The method of claim 6, wherein the user information comprises a user group tag of the user, and wherein determining the virtual gift list of the user based on the user information of the user comprises:

obtaining a gift grouping list of a user with the same user grouping label as the user according to the user information to serve as the gift grouping list of the user;

generating a default gift list of each gift group;

generating a virtual gift list for the user using the gift packet list and a default gift list for each gift packet.

8. The method according to any one of claims 2-4, wherein the hierarchical Bayesian model is trained by:

obtaining user information, historical behavior data and prior sorting data of gifts of a large number of users, wherein the historical behavior data comprise behavior data of the users who enjoy gifts in at least one live broadcast type live broadcast room;

preprocessing the user information, the historical behavior data and the prior sequencing data to obtain training data;

and training the initialized hierarchical Bayesian model by using the training data to obtain a trained hierarchical Bayesian model.

9. The method of claim 8, wherein obtaining user information, historical behavior data, and a priori ranking data of gifts for a plurality of users comprises:

and acquiring prior sorting data of the gifts, and acquiring user information and historical behavior data of the user according to a preset time window.

10. The method of claim 8, wherein the user information comprises a user id and a user group tag, the historical behavior data comprises a live broadcast type, a gift group, a gift id, and a gift appreciation amount, and the preprocessing the user information, the historical behavior data, and the a priori sequencing data to obtain training data comprises:

screening out the appreciation number of the gifts enjoyed by the users with the same user group label in each live broadcast room of each live broadcast type and the gift groups to which the gifts belong from the historical behavior data;

determining the real preference degree of the users with the same user grouping label to each gift grouping in each live broadcast room of each live broadcast type according to the reward quantity;

determining the real preference degree of each user for each gift in each gift group according to the appreciation quantity of the user for enjoying the gifts in the live broadcast room of each live broadcast type and the prior sequencing data;

and taking the user id, the user grouping label, the live broadcast type, the gift grouping, the gift id and the gift appreciation number as training samples, and taking the real preference degree of the gift grouping and the real preference degree of the gift as sample labels to obtain training data.

11. The method of claim 10, wherein training the initialized hierarchical bayesian model using the training data to obtain a trained hierarchical bayesian model comprises:

inputting the user id, the user grouping label, the live broadcast type, the gift grouping, the gift id and the gift appreciation number as training samples into the initialized hierarchical Bayesian model to obtain the prediction preference degree of the users with the same user grouping label to each gift grouping in the live broadcast room of each live broadcast type and the prediction preference degree of each user to each gift in each gift grouping;

calculating a loss rate according to the prediction preference degree of the gift grouping, the prediction preference degree of the gift, the real preference degree of the gift grouping and the real preference degree of the gift;

and adjusting the parameters of the hierarchical Bayesian model according to the loss rate until a training stopping condition is reached.

12. A method for virtual gift recommendation, comprising:

when a gift appreciation interface request in a live broadcast room is received, determining a user identifier of the target user and a live broadcast type of the live broadcast room;

judging whether a preset virtual gift list database has a target virtual gift list matched with the user identification and the live broadcast type;

if so, recommending the target virtual gift list to a client where the target user is located, wherein the client is used for displaying a gift appreciation interface according to the target virtual gift list;

if not, acquiring a default virtual gift list, and recommending the default virtual gift list to a client of the target user, wherein the client is used for displaying a gift appreciation interface according to the default virtual gift list;

wherein the target virtual gift list is generated by the virtual gift list generating method of any one of claims 1-11.

13. A virtual gift list generating apparatus, comprising:

the system comprises a user information and historical behavior data acquisition module, a display module and a display module, wherein the user information and historical behavior data acquisition module is used for acquiring user information of a user and historical behavior data of a gift enjoyed by the user, and the historical behavior data comprises behavior data of the gift enjoyed by the user in at least one live broadcast type live broadcast room;

the user preference determining module is used for determining the preference degree of the user to each gift group according to the user information and the historical behavior data and determining the preference degree of the user to each gift in each gift group aiming at the live broadcast room of each live broadcast type;

and the virtual gift list generating module is used for generating a virtual gift list based on the preference degree of each gift group and the preference degree of each gift in each gift group, and the virtual gift list is used for displaying the virtual gift in the live broadcast room of the live broadcast type entered by the user.

14. A virtual gift recommendation device, comprising:

the system comprises a user identification and live broadcast type determining module, a live broadcast type determining module and a display module, wherein the user identification and live broadcast type determining module is used for determining the user identification of a target user and the live broadcast type of a live broadcast when receiving a gift appreciation interface request in the live broadcast;

the virtual gift list matching module is used for judging whether a preset virtual gift list database has a virtual gift list matched with the user identifier and the live broadcast type;

the virtual gift list recommending module is used for recommending the matched target virtual gift list to a client side where the target user is located, and the client side is used for displaying a gift appreciation interface according to the target virtual gift list;

the system comprises a default virtual gift list recommending module, a client and a virtual gift display module, wherein the default virtual gift list recommending module is used for acquiring a default virtual gift list and recommending the default virtual gift list to a client where a target user is located, and the client is used for displaying a gift appreciation interface according to the default virtual gift list;

wherein the target virtual gift list is generated by the virtual gift list generating method of any one of claims 1-11.

15. An electronic device, characterized in that the electronic device comprises:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the virtual gift list generation method of any one of claims 1-11 and/or the virtual gift recommendation method of claim 12.

16. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the virtual gift list generation method of any one of claims 1-11 and/or the virtual gift recommendation method of claim 12.

Technical Field

The embodiment of the invention relates to the technical field of live broadcast, in particular to a virtual gift list generation method, a virtual gift recommendation method and a virtual gift recommendation device.

Background

Along with the popularization and application of the live broadcast APP, the user plays gifts for the anchor broadcast to become more and more daily interaction with the anchor broadcast, and the play behavior is also one of important revenue sources of a live broadcast platform.

As shown in fig. 1, in the live broadcast, the process of enjoying the gift includes: the method comprises the steps that a user enters a live broadcast room of a live broadcast platform, after gift options are clicked, gifts are displayed in a gift appreciation interface according to gift groups, for example, common gift groups comprise gift groups such as paintings, hot spots, nobility, family battles and pink silk balls, a plurality of gifts under the groups are displayed after each gift group is clicked, when the gift groups have more gifts, the gifts are displayed in pages and provided with buttons such as pages and scroll bars, and after the user refreshes gift appreciation pages through button operations such as the pages and the scroll bars, the gift is clicked to be sent, and the gift is successfully appreciated

However, in the live APP, the gift appreciation interface is static, in which the display positions of the respective gifts under the gift groups and the gift groups are static, that is, the gift appreciation interface is the same for all users. The users come from different countries and regions, the users in each country and region have regional gift preferences, and the preferences of user groups with different genders on the gifts are different; in addition, the gifts are grouped differently, the gifts among different gift groups are significantly different, and under the condition that the user hierarchical structure is different from the gift groups, the preferences of the users for viewing the gifts are different, and all the users adopt the same gift viewing interface to easily cause the gifts preferred by part of the users to be displayed at the back position, so that the efficiency of viewing the gifts by the users is reduced.

Disclosure of Invention

The embodiment of the invention provides a virtual gift list generation method, a virtual gift recommendation method, a virtual gift list generation device, electronic equipment and a storage medium, and aims to solve the problems that all users adopt the same static gift appreciation interface to cause partial gifts preferred by the users to be displayed at the positions behind, and the gift appreciation efficiency of the users is reduced.

In a first aspect, an embodiment of the present invention provides a method for generating a virtual gift list, including:

acquiring user information of a user and historical behavior data of a gift enjoyed by the user, wherein the historical behavior data comprises behavior data of the gift enjoyed by the user in at least one live broadcast room of a live broadcast type;

for each live broadcast type of live broadcast room, determining the preference degree of the user to each gift group according to the user information and the historical behavior data, and determining the preference degree of the user to each gift in each gift group;

generating a virtual gift list based on the preference degree of each gift group and the preference degree of each gift in each gift group, wherein the virtual gift list is used for showing virtual gifts in live rooms of the live type entered by the user.

In a second aspect, an embodiment of the present invention provides a virtual gift recommendation method, including:

when a gift appreciation interface request in a live broadcast room is received, determining a user identifier of the target user and a live broadcast type of the live broadcast room;

judging whether a preset virtual gift list database has a target virtual gift list matched with the user identification and the live broadcast type;

if so, recommending the target virtual gift list to a client where the target user is located, wherein the client is used for displaying a gift appreciation interface according to the target virtual gift list;

if not, acquiring a default virtual gift list, and recommending the default virtual gift list to a client of the target user, wherein the client is used for displaying a gift appreciation interface according to the default virtual gift list;

the target virtual gift list is generated by the virtual gift list generation method according to any embodiment of the invention.

In a third aspect, an embodiment of the present invention provides a virtual gift list generating apparatus, including:

the system comprises a user information and historical behavior data acquisition module, a display module and a display module, wherein the user information and historical behavior data acquisition module is used for acquiring user information of a user and historical behavior data of a gift enjoyed by the user, and the historical behavior data comprises behavior data of the gift enjoyed by the user in at least one live broadcast type live broadcast room;

the user preference determining module is used for determining the preference degree of the user to each gift group according to the user information and the historical behavior data and determining the preference degree of the user to each gift in each gift group aiming at the live broadcast room of each live broadcast type;

and the virtual gift list generating module is used for generating a virtual gift list based on the preference degree of each gift group and the preference degree of each gift in each gift group, and the virtual gift list is used for displaying the virtual gift in the live broadcast room of the live broadcast type entered by the user.

In a fourth aspect, an embodiment of the present invention provides a virtual gift recommendation apparatus, including:

the system comprises a user identification and live broadcast type determining module, a live broadcast type determining module and a display module, wherein the user identification and live broadcast type determining module is used for determining the user identification of a target user and the live broadcast type of a live broadcast when receiving a gift appreciation interface request in the live broadcast;

the virtual gift list matching module is used for judging whether a preset virtual gift list database has a virtual gift list matched with the user identifier and the live broadcast type;

the virtual gift list recommending module is used for recommending the matched target virtual gift list to a client side where the target user is located, and the client side is used for displaying a gift appreciation interface according to the target virtual gift list;

the system comprises a default virtual gift list recommending module, a client and a virtual gift display module, wherein the default virtual gift list recommending module is used for acquiring a default virtual gift list and recommending the default virtual gift list to a client where a target user is located, and the client is used for displaying a gift appreciation interface according to the default virtual gift list;

the target virtual gift list is generated by the virtual gift list generation method according to any embodiment of the invention.

In a fifth aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement a virtual gift list generation method, and/or a virtual gift recommendation method, as described in any of the embodiments of the present invention.

In a sixth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a virtual gift list generation method and/or a virtual gift recommendation method according to any embodiment of the present invention.

The embodiment of the invention determines the preference degree of the user to the gift groups and the preference degree of each gift in the gift groups through the user information and the historical behavior data, and generates the virtual gift list of the user according to the preference degrees, so that when the user enters the gift viewing interface in the live broadcast room, each gift group can be displayed according to the preference degrees of the gift groups, and the gift in each gift group can be displayed according to the preference degrees of the gifts, the problem of low viewing efficiency caused by the fact that all users adopt the same static gift viewing interface is avoided, the user information such as user regions and gender and the historical behavior data are combined, different gift viewing interfaces are displayed for different users according to the preference of the user to the gift groups and the preference of the gift in the gift groups, and the gift groups preferred by the user and the gift in the gift groups are arranged in front, the user can enjoy the favorite gift without turning pages or refreshing the gift watching interface, and the gift watching efficiency of the user is improved.

Drawings

FIG. 1 is a schematic diagram of a gift appreciation interface in a live APP;

fig. 2 is a flowchart illustrating steps of a method for generating a virtual gift list according to an embodiment of the present invention;

fig. 3 is a flowchart illustrating steps of a method for generating a virtual gift list according to a second embodiment of the present invention;

fig. 4 is a flowchart illustrating steps of a method for recommending a virtual gift according to a third embodiment of the present invention;

fig. 5 is a block diagram illustrating a virtual gift list generating apparatus according to a fourth embodiment of the present invention;

fig. 6 is a block diagram illustrating a virtual gift recommendation apparatus according to a fifth embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures. The embodiments and features of the embodiments in the present application may be combined with each other without conflict.