Weight-coefficient-based hybrid information recommendation

1. A computer-implemented method, comprising:

retrieving, by one or more processors, historical behavioral information of a user of a user device, the historical behavioral information comprising data associated to operations performed by the user device on a server;

determining, by the one or more processors, a plurality of recommended information sets based on a plurality of recommendation algorithms that are different from each other and use as input the historical behavioral information;

generating, by the one or more processors, a plurality of weight coefficients, each weight coefficient of the plurality of weight coefficients being generated for each recommended information set of the plurality of recommended information sets, wherein the plurality of weight coefficients are automatically adjusted through an iterative process based on user inputs using a particle swarm algorithm to match current interests of the user;

determining, by the one or more processors, a recommendation list based on the plurality of weight coefficients;

determining, by the one or more processors, a ratio of (i) a number of items in the recommendation list also included in a reference list extracted from the historical behavioral information of the user, and (ii) a total number of items in the recommendation list, the ratio defining an accuracy of the recommendation list;

determining, by the one or more processors, that the accuracy of the recommendation list is lower than a threshold comprising a percentage of items included both in the recommendation list and the reference list;

updating, by the one or more processors, the recommendation list by adjusting each weight coefficient of each recommended information set of the plurality of recommended information sets;

determining that the accuracy of the recommendation list is greater than the threshold;

generating, by the one or more processors, based on the recommendation list, a recommendation configured to accelerate access to the items included in the recommendation list; and

transmitting, by the one or more processors, the recommendation for display on a graphical user interface to be displayed by a device of the user.

2. The computer-implemented method of claim 1 , further comprising:

categorizing the historical behavioral information into test information and reference information.

3. The computer-implemented method of claim 2 , wherein the test information comprises: results of a portion of the historical behavioral information analyzed by the plurality of recommendation algorithms.

4. The computer-implemented method of claim 2 , further comprising:

determining a reliability of the accuracy of the recommendation list based on a consistency of the recommendation list with the reference information.

5. The computer-implemented method of claim 2 , wherein adjusting each weight coefficient comprises:

determining a value of an adjustment to each coefficient for each recommended information set based on an iteration information that is related to the reference information; and

adjusting each weight coefficient of each recommended information set based on the value of the adjustment.

6. The computer-implemented method of claim 5 , wherein the iteration information comprises at least one of a value of a previous adjustment of each weight coefficient of each recommended information set, an accuracy of a recommendation list that was previously determined, and highest accuracy value of a plurality of accuracy values of previously determined recommendation lists.

7. The computer-implemented method of claim 6 , further comprising:

in response to determining that a number of adjustments reaches an adjustment threshold, determining a most accurate recommendation list from the previously determined recommendation lists based on the plurality of accuracy values; and

generating the recommendation based on the most accurate recommendation list.

8. The computer-implemented method of claim 1 , wherein each weight coefficient of the plurality of weight coefficients comprises a sub-weight coefficient of each piece of information comprised in the recommended information set based on a weight coefficient of the recommended information set and a recommended weight coefficient of each piece of information relative to the recommended information set.

9. The computer-implemented method of claim 8 , further comprising:

determining, for each piece of information, a sum of sub-weight coefficients of the recommended information sets, and using the sum of sub-weight coefficients as a total weight coefficient of each piece of information; and

determining the recommendation list based on the total weight coefficient of each piece of information.

10. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

retrieving historical behavioral information of a user of a user device, the historical behavioral information comprising data associated to operations performed by the user device on a server;

determining a plurality of recommended information sets based on a plurality of recommendation algorithms that are different from each other and are using as input the historical behavioral information;

generating a plurality of weight coefficients, each weight coefficient of the plurality of weight coefficients being generated for each recommended information set of the plurality of recommended information sets, wherein the plurality of weight coefficients are automatically adjusted through an iterative process based on user inputs using a particle swarm algorithm to match current interests of the user;

determining a recommendation list based on the plurality of weight coefficients;

determining a ratio of (i) a number of items in the recommendation list also included in a reference list extracted from the historical behavioral information of the user, and (ii) a total number of items in the recommendation list, the ratio defining an accuracy of the recommendation list;

determining that the accuracy of the recommendation list is lower than a threshold comprising a percentage of items included both in the recommendation list and the reference list;

updating the recommendation list by adjusting each weight coefficient of each recommended information set of the plurality of recommended information sets;

determining that the accuracy of the recommendation list is greater than the threshold;

generating, based on the recommendation list, a recommendation configured to accelerate access to the items included in the recommendation list; and

transmitting the recommendation for display on a graphical user interface to be displayed by a device of the user.

11. The non-transitory, computer-readable medium of claim 10 , the operations further comprising:

categorizing the historical behavioral information into test information and reference information.

12. The non-transitory, computer-readable medium of claim 11 , wherein the test information comprises: results of a portion of the historical behavioral information analyzed by the plurality of recommendation algorithms.

13. The non-transitory, computer-readable medium of claim 11 , the operations further comprising:

determining a reliability of the accuracy of the recommendation list based on a consistency of the recommendation list with the reference information.

14. The non-transitory, computer-readable medium of claim 13 ,

wherein adjusting each weight coefficient of each recommended information set of the plurality of recommended information sets comprises:

determining a value of an adjustment to each coefficient for each recommended information set based on an iteration information that is related to the reference information; and

adjusting each weight coefficient of each recommended information set based on the value of the adjustment.

15. A computer-implemented system, comprising:

one or more computers; and

one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform operations comprising:

retrieving historical behavioral information of a user of a user device, the historical behavioral information comprising data associated to operations performed by the user device on a server;

determining a plurality of recommended information sets based on a plurality of recommendation algorithms that are different from each other and are using as input the historical behavioral information;

generating a plurality of weight coefficients, each weight coefficient of the plurality of weight coefficients being generated for each recommended information set of the plurality of recommended information sets, wherein the plurality of weight coefficients are automatically adjusted through an iterative process based on user inputs using a particle swarm algorithm to match current interests of the user;

determining a recommendation list based on the plurality of weight coefficients;

determining a ratio of (i) a number of items in the recommendation list also included in a reference list extracted from the historical behavioral information of the user, and (ii) a total number of items in the recommendation list, the ratio defining an accuracy of the recommendation list;

determining that the accuracy of the recommendation list is lower than a threshold comprising a percentage of items included both in the recommendation list and the reference list;

updating the recommendation list by adjusting each weight coefficient of each recommended information set of the plurality of recommended information sets;

determining that the accuracy of the recommendation list is greater than the threshold;

generating, based on the recommendation list, a recommendation configured to accelerate access to the items included in the recommendation list; and

transmitting the recommendation for display on a graphical user interface to be displayed by a device of the user.

16. The computer-implemented system of claim 15 , the operations further comprising:

categorizing the historical behavioral information into test information and reference information.

17. The computer-implemented system of claim 16 , wherein the test information comprises: results of a portion of the historical behavioral information analyzed by the plurality of recommendation algorithms.

18. The computer-implemented system of claim 16 , the operations further comprising:

determining a reliability of the accuracy of the recommendation list based on a consistency of the recommendation list with the reference information.

19. The computer-implemented system of claim 18 ,

wherein adjusting each weight coefficient of each recommended information set of the plurality of recommended information sets comprises:

determining a value of an adjustment to each coefficient for each recommended information set based on an iteration information that is related to the reference information; and

adjusting each weight coefficient of each recommended information set based on the value of the adjustment.