Method and apparatus for providing information based on artificial intelligence

1. A method for providing information based on artificial intelligence, comprising:

determining a characteristic of interest of a user according to historical access records of the user;

acquiring news data corresponding to the characteristic of interest from a database according to preset extracting rules;

analyzing the news data to obtain key information contained in the news data, wherein analyzing the news data to obtain key information contained in the news data comprises: determining a structure model of core contents corresponding to the news data according to the characteristic of interest; and splitting the news data up into sentences and extracting the key information from the news data according to the structure model;

aggregating the key information to generate an information card matched with the characteristic of interest, wherein, aggregating the key information comprises: performing a deep neural network training on the key information according to the structure model; and

displaying the information card matched with the characteristic of interest in an information displaying interface, the information card comprising core contents of news matched with the characteristic of interest determined by analyzing news in the database.

2. The method according to claim 1 , before determining the characteristic of interest of the user according to historical access records of the user, further comprising:

determining a scenario characteristic when the user accesses the information displaying interface, the scenario characteristic comprising at least one of a type of a terminal device, a location of the user, and a current time;

determining the characteristic of interest of the user according to the scenario characteristic.

3. The method according to claim 1 , wherein, acquiring news data corresponding to the characteristic of interest from the database according to preset extracting rules comprises:

determining an event granularity corresponding to target news data according to the characteristic of interest; and

aggregating news data in conformity with the event granularity from the database by means of clustering, retrieving, and/or signature.

4. The method according to claim 1 , after displaying the information card matched with the characteristic of interest to the user in the information displaying interface, further comprising:

receiving a touch operation performed by the user on the information displaying interface;

updating the information card displayed in the information displaying interface in response to the touch operation.

5. The method according to claim 4 , wherein, the information displaying interface comprises a guide card,

receiving a touch operation performed by the user on the information displaying interface comprises:

receiving an input operation performed by the user on the information displaying interface; or

receiving a touch operation performed by the user on the information card; or

receiving a selecting operation performed by the user on the guide card.

6. The method according to claim 4 , after receiving a touch operation performed by the user on the information displaying interface, further comprising:

optimizing the characteristic of interest of the user in response to the touch operation.

7. An apparatus for providing information based on artificial intelligence, comprising:

a processor;

a memory, configured to store one or more software modules executable by the user,

wherein the one or more software modules comprise:

a first determining module, configured to determine a characteristic of interest of a user according to historical access records of the user;

a displaying module, configured to display an information card matched with the characteristic of interest in an information displaying interface, the information card comprising core contents of news matched with the characteristic of interest determined by analyzing news in a database;

an acquiring module, configured to acquire news data corresponding to the characteristic of interest from the database according to preset extracting rules;

an analyzing module, configured to analyze the news data to obtain key information contained in the news data, wherein analyzing the news data to obtain key information contained in the news data comprises: determining a structure model of core contents corresponding to the news data according to the characteristic of interest; and splitting the news data up into sentences and extracting the key information from the news data according to the structure model; and

an aggregating module, configured to aggregate the key information to generate the information card matched with the characteristic of interest, wherein, aggregating the key information comprises: performing a deep neural network training on the key information according to the structure model.

8. The apparatus according to claim 7 , wherein the one or more software modules further comprise:

a second determining model, configured to determine a scenario characteristic when the user accesses the information displaying interface, the scenario characteristic comprising at least one of a type of terminal device, a location of the user, and a current time;

a third determining model, configured to determine the characteristic of interest the user according to the scenario characteristic.

9. The apparatus according to claim 7 , wherein, the acquiring module is configured to:

determine an event granularity corresponding to target news data according to the characteristic of interest; and

aggregate news data in conformity with the event granularity from the database by means of clustering, retrieving, and/or signature.

10. The apparatus according to claim 7 , wherein the one or more software modules further comprise:

a receiving module, configured to receive a touch operation performed by the user on the information displaying interface; and

an updating module, configured to update the information card displayed in the information displaying interface in response to the touch operation.

11. The apparatus according to claim 10 , wherein, the information displaying interface comprises a guide card, and the receiving module is configured to:

receive an input operation performed by the user on the information displaying interface; or

receive a touch operation performed by the user on the information card; or

receive a selecting operation performed by the user on the pilot card.

12. The apparatus according to claim 10 , wherein the one or more software modules further comprise:

an optimizing module, configured to optimize the characteristic of interest of the user in response to the touch operation.

13. A computer-readable storage medium, stored with computer programs that, when executed by a processor, cause the processor to perform a method for providing information based on artificial intelligence, the method comprising:

determining a characteristic of interest of a user according to historical access records of the user;

acquiring news data corresponding to the characteristic of interest from a database according to preset extracting rules;

analyzing the news data to obtain key information contained in the news data, wherein analyzing the news data to obtain key information contained in the news data comprises: determining a structure model of core contents corresponding to the news data according to the characteristic of interest; and splitting the news data up into sentences and extracting the key information from the news data according to the structure model;

aggregating the key information to generate an information card matched with the characteristic of interest, wherein, aggregating the key information comprises: performing a deep neural network training on the key information according to the structure model; and

displaying an information card matched with the characteristic of interest in an information displaying interface, the information card comprising core contents of news matched with the characteristic of interest determined by analyzing news in a database.

14. The computer-readable storage medium according to claim 13 , before determining the characteristic of interest of the user according to historical access records of the user, the method further comprising:

determining a scenario characteristic when the user accesses the information displaying interface, the scenario characteristic comprising at least one of a type of a terminal device, a location of the user, and a current time;

determining the characteristic of interest of the user according to the scenario characteristic.

15. The computer-readable storage medium according to claim 13 , wherein, acquiring news data corresponding to the characteristic of interest from the database according to preset extracting rules comprises:

determining an event granularity corresponding to target news data according to the characteristic of interest; and

aggregating news data in conformity with the event granularity from the database by means of clustering, retrieving, and/or signature.

16. The computer-readable storage medium according to claim 13 , after displaying the information card matched with the characteristic of interest to the user in the information displaying interface, the method further comprising:

receiving a touch operation performed by the user on the information displaying interface;

updating the information card displayed in the information displaying interface in response to the touch operation.

17. The computer-readable storage medium according to claim 16 , wherein, the information displaying interface comprises a guide card,

receiving a touch operation performed by the user on the information displaying interface comprises:

receiving an input operation performed by the user on the information displaying interface; or

receiving a touch operation performed by the user on the information card; or

receiving a selecting operation performed by the user on the guide card.

18. The computer-readable storage medium according to claim 16 , after receiving a touch operation performed by the user on the information displaying interface, the method further comprising:

optimizing the characteristic of interest of the user in response to the touch operation.