Granted Patent B2

US 12,596,512 · App. 19/016,747 · Granted Apr 7, 2026

Inventors: Qi Zhang (Beijing, CN); Yujia Fu (Beijing, CN)

Assignee: Beijing Youzhuju Network Technology Co., Ltd.

G06F3/14

Abstract

Claims (81)

1 . A content rendering method, applied to a terminal device, wherein the method comprises:

obtaining a target content, wherein a plurality of display forms correspond to the target content;

determining state information of the terminal device;

determining, by using a local prediction model, an attribute prediction value of each display form based on the state information, wherein the local prediction model is configured to predict an attribute value of the display form based on the state information; and

determining, from the plurality of display forms, a display form with a highest attribute prediction value as a target display form, and rendering the target content according to the target display form.

2 . The method according to claim 1 , further comprising:

after the rendering the target content according to the target display form, determining interaction information of the target content;

synchronizing the state information and the interaction information to a cloud, such that a cloud prediction model on the cloud performs model training based on the state information and the interaction information to obtain a trained cloud prediction model, wherein the cloud prediction model is configured to predict the attribute value of the display form based on the state information; and

obtaining the trained cloud prediction model, and updating the local prediction model based on the trained cloud prediction model.

3 . The method according to claim 2 , wherein the obtaining the trained cloud prediction model, and updating the local prediction model based on the trained cloud prediction model comprises:

obtaining the trained cloud prediction model once at intervals of a preset duration, and updating the local prediction model based on the trained cloud prediction model that is obtained.

4 . The method according to claim 1 , wherein the determining, by using a local prediction model, an attribute prediction value of each display form based on the state information comprises:

inputting the state information into a first local prediction sub-model to obtain a first attribute prediction value corresponding to each display form, wherein the first local prediction sub-model is configured to predict a first-type attribute for each display form based on the state information;

inputting the state information into a second local prediction sub-model to obtain a second attribute prediction value corresponding to each display form, wherein the second local prediction sub-model is configured to predict a second-type attribute for each display form based on the state information; and

determining, for each display form, the attribute prediction value of the display form based on the first attribute prediction value and the second attribute prediction value that correspond to the display form.

5 . The method according to claim 1 , wherein the determining, by using a local prediction model, an attribute prediction value of each display form based on the state information comprises:

inputting the state information into the local prediction model to obtain the attribute prediction value corresponding to each display form.

6 . The method according to claim 1 , wherein the obtaining a target content comprises:

sending a content request to a content system in response to a content browsing operation; and

obtaining the target content and a plurality of rendering data links that are sent by the content system in response to the content request, wherein the plurality of rendering data links correspond to the plurality of display forms in a one-to-one manner; and

the rendering the target content according to the target display form comprises:

obtaining target rendering data based on a rendering data link corresponding to the target display form; and

rendering the target content based on the target rendering data.

7 . The method according to claim 2 , wherein the obtaining a target content comprises:

sending a content request to a content system in response to a content browsing operation; and

obtaining the target content and a plurality of rendering data links that are sent by the content system in response to the content request, wherein the plurality of rendering data links correspond to the plurality of display forms in a one-to-one manner; and

the rendering the target content according to the target display form comprises:

obtaining target rendering data based on a rendering data link corresponding to the target display form; and

rendering the target content based on the target rendering data.

8 . The method according to claim 4 , wherein the obtaining a target content comprises:

sending a content request to a content system in response to a content browsing operation; and

obtaining the target content and a plurality of rendering data links that are sent by the content system in response to the content request, wherein the plurality of rendering data links correspond to the plurality of display forms in a one-to-one manner; and

the rendering the target content according to the target display form comprises:

obtaining target rendering data based on a rendering data link corresponding to the target display form; and

rendering the target content based on the target rendering data.

9 . The method according to claim 5 , wherein the obtaining a target content comprises:

sending a content request to a content system in response to a content browsing operation; and

obtaining the target content and a plurality of rendering data links that are sent by the content system in response to the content request, wherein the plurality of rendering data links correspond to the plurality of display forms in a one-to-one manner; and

the rendering the target content according to the target display form comprises:

obtaining target rendering data based on a rendering data link corresponding to the target display form; and

rendering the target content based on the target rendering data.

10 . The method according to claim 1 , wherein the determining state information of the terminal device comprises:

determining at least one selected from a group comprising device state information and communication state information of the terminal device, wherein the device state information comprises at least one selected from a group comprising a central processing unit utilization rate and a battery state, and the communication state information comprises at least one selected from a group comprising network bandwidth state information and network delay state information.

11 . The method according to claim 2 , wherein the determining state information of the terminal device comprises:

determining at least one selected from a group comprising device state information and communication state information of the terminal device, wherein the device state information comprises at least one selected from a group comprising a central processing unit utilization rate and a battery state, and the communication state information comprises at least one selected from a group comprising network bandwidth state information and network delay state information.

12 . The method according to claim 4 , wherein the determining state information of the terminal device comprises:

determining at least one selected from a group comprising device state information and communication state information of the terminal device, wherein the device state information comprises at least one selected from a group comprising a central processing unit utilization rate and a battery state, and the communication state information comprises at least one selected from a group comprising network bandwidth state information and network delay state information.

13 . A non-transitory computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, steps of a content rendering method are implemented,

wherein the method is applied to a terminal device, and the steps of the method comprises:

obtaining a target content, wherein a plurality of display forms correspond to the target content;

determining state information of the terminal device;

determining, by using a local prediction model, an attribute prediction value of each display form based on the state information, wherein the local prediction model is configured to predict an attribute value of the display form based on the state information; and

determining, from the plurality of display forms, a display form with a highest attribute prediction value as a target display form, and rendering the target content according to the target display form.

14 . An electronic device, comprising:

a memory, having a computer program stored thereon; and

a processor, configured to execute the computer program in the memory to implement steps of a content rendering method,

wherein the method is applied to a terminal device, and the steps of the method comprises:

obtaining a target content, wherein a plurality of display forms correspond to the target content;

determining state information of the terminal device;

determining, by using a local prediction model, an attribute prediction value of each display form based on the state information, wherein the local prediction model is configured to predict an attribute value of the display form based on the state information; and

determining, from the plurality of display forms, a display form with a highest attribute prediction value as a target display form, and rendering the target content according to the target display form.

15 . The electronic device according to claim 14 , wherein the processor executes the computer program in the memory to further implement following steps:

after the rendering the target content according to the target display form, determining interaction information of the target content;

synchronizing the state information and the interaction information to a cloud, such that a cloud prediction model on the cloud performs model training based on the state information and the interaction information to obtain a trained cloud prediction model, wherein the cloud prediction model is configured to predict the attribute value of the display form based on the state information; and

obtaining the trained cloud prediction model, and updating the local prediction model based on the trained cloud prediction model.

16 . The electronic device according to claim 15 , wherein the obtaining the trained cloud prediction model, and updating the local prediction model based on the trained cloud prediction model comprises:

obtaining the trained cloud prediction model once at intervals of a preset duration, and updating the local prediction model based on the trained cloud prediction model that is obtained.

17 . The electronic device according to claim 14 , wherein the determining, by using a local prediction model, an attribute prediction value of each display form based on the state information comprises:

inputting the state information into a first local prediction sub-model to obtain a first attribute prediction value corresponding to each display form, wherein the first local prediction sub-model is configured to predict a first-type attribute for each display form based on the state information;

inputting the state information into a second local prediction sub-model to obtain a second attribute prediction value corresponding to each display form, wherein the second local prediction sub-model is configured to predict a second-type attribute for each display form based on the state information; and

determining, for each display form, the attribute prediction value of the display form based on the first attribute prediction value and the second attribute prediction value that correspond to the display form.

18 . The electronic device according to claim 14 , wherein the determining, by using a local prediction model, an attribute prediction value of each display form based on the state information comprises:

inputting the state information into the local prediction model to obtain the attribute prediction value corresponding to each display form.

19 . The electronic device according to claim 14 , wherein the obtaining a target content comprises:

sending a content request to a content system in response to a content browsing operation; and

obtaining the target content and a plurality of rendering data links that are sent by the content system in response to the content request, wherein the plurality of rendering data links correspond to the plurality of display forms in a one-to-one manner; and

the rendering the target content according to the target display form comprises:

obtaining target rendering data based on a rendering data link corresponding to the target display form; and

rendering the target content based on the target rendering data.

20 . The electronic device according to claim 14 , wherein the determining state information of the terminal device comprises:

determining at least one selected from a group comprising device state information and communication state information of the terminal device, wherein the device state information comprises at least one selected from a group comprising a central processing unit utilization rate and a battery state, and the communication state information comprises at least one selected from a group comprising network bandwidth state information and network delay state information.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (12)