Page loading method and electronic device

1. A page loading method, comprising:

collecting history browsing behaviors of a user during using a browser, and obtaining visited pages involved in the history browsing behaviors and browsing manners used by the user;

training a learning model based on the visited pages and the browsing manners used by the user, such that the learning model learns a correspondence relationship between the visited pages and the browsing manners, wherein the browsing manners comprise a manner of browsing in a current tab and a manner of browsing in a new tab;

in response to receiving a page visiting request, determining a target browsing manner for the target page from the manner of browsing in a current tab and the manner of browsing in a new tab by analyzing the target page to be visited based on the trained learning model; and

loading the target page according to the target browsing manner.

2. The method according to claim 1 , wherein training the learning model based on the visited pages and the browsing manner used by the user comprises:

analyzing visited pages involved in a plurality of history browsing behaviors, and obtaining characteristic parameters of a plurality of visited pages;

characterizing the plurality of visited pages with the characteristic parameters, and labeling each of the plurality of visited pages by using a corresponding browsing manner;

generating a training sample set based on the plurality of labeled visited pages; and

training the learning model using the training sample set, wherein the learning model is a binary classification model.

3. The method according to claim 2 , wherein analyzing visited pages involved in the plurality of history browsing behaviors and obtaining characteristic parameters of the plurality of visited pages comprising:

for each history browsing behavior, obtaining a URL of the visited page, content of the visited page, a URL of a related page of the visited page and/or content of the related page, wherein, the related page is a page loaded in the current tab and/or a page loaded in another tab before jumping from the current tab to the visited page; and

generating the characteristic parameters based on the URL of the visited page, the content of the visited page, the URL of the related page of the visited page and/or the content of the related page.

4. The method according to claim 1 , before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, further comprising:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.

5. The method according to claim 2 , before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, further comprising:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.

6. The method according to claim 3 , before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, further comprising:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.

7. An electronic device, comprising a housing, a processor, a memory, a circuit board, and a power circuit, wherein the circuit board is arranged inside a space enclosed by the housing; the processor and the memory are disposed on the circuit board; the power circuit is configured to provide power for respective circuits or components of the electronic device; the memory is configured to store executable program codes; and the processor is configured to run a program corresponding to the executable program codes by reading the executable program codes stored in the memory, so as to perform a page loading method, comprising:

collecting history browsing behaviors of a user during using a browser, and obtaining visited pages involved in the history browsing behaviors and browsing manners used by the user;

training a learning model based on the visited pages and the browsing manners used by the user, such that the learning model learns a correspondence relationship between the visited pages and the browsing manners, wherein the browsing manners comprise a manner of browsing in a current tab and a manner of browsing in a new tab;

in response to receiving a page visiting request, determining a target browsing manner for the target page from the manner of browsing in a current tab and the manner of browsing in a new tab by analyzing the target page to be visited based on the trained learning model; and

loading the target page according to the target browsing manner.

8. The electronic device according to claim 7 , wherein training the learning model based on the visited pages and the browsing manner used by the user comprises:

analyzing visited pages involved in a plurality of history browsing behaviors, and obtaining characteristic parameters of a plurality of visited pages;

characterizing the plurality of visited pages with the characteristic parameters, and labeling each of the plurality of visited pages by using a corresponding browsing manner;

generating a training sample set based on the plurality of labeled visited pages; and

training the learning model using the training sample set, wherein the learning model is a binary classification model.

9. The electronic device according to claim 8 , wherein analyzing visited pages involved in the plurality of history browsing behaviors and obtaining characteristic parameters of the plurality of visited pages comprising:

for each history browsing behavior, obtaining a URL of the visited page, content of the visited page, a URL of a related page of the visited page and/or content of the related page, wherein, the related page is a page loaded in the current tab and/or a page loaded in another tab before jumping from the current tab to the visited page; and

generating the characteristic parameters based on the URL of the visited page, the content of the visited page, the URL of the related page of the visited page and/or the content of the related page.

10. The electronic device according to claim 7 , wherein, before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, the method further comprises:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.

11. The electronic device according to claim 8 , wherein, before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, the method further comprises:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.

12. The electronic device according to claim 9 , wherein, before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, the method further comprises:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.

13. A non-transitory computer-readable storage medium, having stored therein computer programs that, when executed by a processor, perform a page loading method, comprising:

collecting history browsing behaviors of a user during using a browser, and obtaining visited pages involved in the history browsing behaviors and browsing manners used by the user;

training a learning model based on the visited pages and the browsing manners used by the user, such that the learning model learns a correspondence relationship between the visited pages and the browsing manners, wherein the browsing manners comprise a manner of browsing in a current tab and a manner of browsing in a new tab;

in response to receiving a page visiting request, determining a target browsing manner for the target page from the manner of browsing in a current tab and the manner of browsing in a new tab by analyzing the target page to be visited based on the trained learning model; and

loading the target page according to the target browsing manner.

14. The non-transitory computer-readable storage medium according to claim 13 , wherein training the learning model based on the visited pages and the browsing manner used by the user comprises:

analyzing visited pages involved in a plurality of history browsing behaviors, and obtaining characteristic parameters of a plurality of visited pages;

characterizing the plurality of visited pages with the characteristic parameters, and labeling each of the plurality of visited pages by using a corresponding browsing manner;

generating a training sample set based on the plurality of labeled visited pages; and

training the learning model using the training sample set, wherein the learning model is a binary classification model.

15. The non-transitory computer-readable storage medium according to claim 14 , wherein analyzing visited pages involved in the plurality of history browsing behaviors and obtaining characteristic parameters of the plurality of visited pages comprising:

for each history browsing behavior, obtaining a URL of the visited page, content of the visited page, a URL of a related page of the visited page and/or content of the related page, wherein, the related page is a page loaded in the current tab and/or a page loaded in another tab before jumping from the current tab to the visited page; and

generating the characteristic parameters based on the URL of the visited page, the content of the visited page, the URL of the related page of the visited page and/or the content of the related page.

16. The non-transitory computer-readable storage medium according to claim 13 , before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, the method further comprises:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.

17. The non-transitory computer-readable storage medium according to claim 14 , before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, the method further comprises:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.

18. The non-transitory computer-readable storage medium according to claim 15 , before analyzing a target page to be visited based on the trained learning model so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab, the method further comprises:

counting a number of times of browsing the target page in a new tab based on the history browsing behaviors;

in response to determining that the number of times satisfies a preset condition, prompting the user to open a smart multi-tab browsing manner; and

obtaining an instruction for allowing the user to open the smart multi-tab browsing manner.