Methods, apparatus, and systems for sending information based on user interactions

1. An information sending method performed by an apparatus, the method comprising:

calculating, by the apparatus, a weight of an interaction setting between a first terminal device and a second terminal device;

calculating a relational score based on the weight between the first terminal device and the second terminal device, the second terminal device being one or more second terminal devices;

calculating a service index of the first terminal device based on the relational score;

determining information to send based on the service index; and

sending the determined information to the first terminal device.

2. The method of claim 1 , wherein calculating the weight of the interaction setting between the first terminal device and the second terminal device comprises calculating the weight of the interaction setting between the first terminal device and the second terminal device according to a logistic regression model.

3. The method of claim 2 , wherein calculating the at least one relational score based on the weight among the first terminal device and the at least one second terminal device comprises:

calculating, according to the logistic regression model, a first sum of a plurality of interaction scores corresponding to a plurality of interaction settings;

multiplying the first sum by a time decay value of the first terminal device with respect to the second terminal device, to obtain a first total relational value of the first terminal device with respect to the second terminal device; and

dividing the first total relational value by a second sum of second total relational values of the second terminal device with respect to terminal devices interacting with the second terminal device to obtain the relational score.

4. The method of claim 1 , wherein calculating the service index of the first terminal device based on the relational score comprises calculating the service index of the first terminal device based on iterations with a PageRank algorithm.

5. The method of claim 4 , wherein calculating the service index of the first terminal device based on the iterations with the PageRank algorithm comprises:

iterating for a number of times with the PageRank algorithm, if the number of times is preset; and

iterating until all service indices of all terminal devices interacting with the first terminal device meet a preset convergence condition, if the number of times is not preset.

6. An information sending apparatus, comprising:

a weight calculating unit configured to calculate a weight of an interaction setting between a first terminal device and a second terminal device;

a score calculating unit configured to calculate a relational score based on the weight between the first terminal device and the second terminal device, the second terminal device being one or more second terminal devices;

an index calculating unit configured to calculate a service index of the first terminal device based on the relational score; and

an information sending unit configured to deteii iine what information to send based on the service index and to send the determined information to the first terminal device.

7. The apparatus of claim 6 , wherein the weight calculating unit is further configured to calculate the weight of the interaction setting between the first terminal device and the second terminal device according to a logistic regression model.

8. The apparatus of claim 7 , wherein the score calculating unit is further configured to:

calculate, according to the logistic regression model, a first sum of a plurality of interaction scores corresponding to a plurality of interaction settings;

multiply the first sum by a time decay value of the first terminal device with respect to the second terminal device, to obtain a first total relational value of the first terminal device with respect to the second terminal device; and

divide the first total relational value by a second sum of second total relational values of the second terminal device with respect to terminal devices interacting with the second terminal device to obtain the relational score.

9. The apparatus of claim 6 , wherein the index calculating unit is further configured to calculate the service index of the first terminal device based on iterations with a PageRank algorithm.

10. The apparatus of claim 9 , wherein the index calculating unit is further configured to:

iterate for a number of times with the PageRank algorithm, if the number of times is preset; and

iterate until all service indices of all terminal devices interacting with the first terminal device meet a preset convergence condition, if the number of times is not preset.

11. An information sending apparatus, comprising:

a memory configured to store a set of instructions;

a processor configured to execute the set of instructions to cause the information sending apparatus to:

calculate a weight of an interaction setting between a first terminal device and a second terminal device;

calculate a relational score based on the weight between the first terminal device and the second terminal device, the second terminal device being one or more second terminal devices;

calculate a service index of the first terminal device based on the relational score;

determine information to send based on the service index; and

send the determined information to the first terminal device.

12. The apparatus of claim 11 , wherein the processor is configured to execute the set of instructions to cause the information sending apparatus to calculate the weight of the interaction setting between the first terminal device and the second terminal device according to a logistic regression model.

13. The apparatus of claim 12 , the processor is configured to execute the set of instructions to cause the information sending apparatus to:

calculate, according to the logistic regression model, a first sum of a plurality of interaction scores corresponding to a plurality of interaction settings;

multiply the first sum by a time decay value of the first terminal device with respect to the second terminal device, to obtain a first total relational value of the first terminal device with respect to the second terminal device; and

divide the first total relational value by a second sum of second total relational values of the second terminal device with respect to terminal devices interacting with the second terminal device to obtain the relational score.

14. The apparatus of claim 11 , wherein the processor is configured to execute the set of instructions to cause the information sending apparatus to calculate the service index of the first terminal device based on iterations with a PageRank algorithm.

15. The apparatus of claim 14 , wherein the processor is configured to execute the set of instructions to cause the information sending apparatus to:

iterate for a number of times with the PageRank algorithm, if the number of times is preset; and

iterate until all service indices of all terminal devices interacting with the first terminal device meet a preset convergence condition, if the number of times is not preset.

16. A non-transitory computer readable medium that stores a set of instructions that is executable by at least one processor of an information sending apparatus to cause the information sending apparatus to perform a method for sending information, the method comprising:

calculating a weight of an interaction setting between a first terminal device and a second terminal device;

calculating a relational score based on the weight between the first terminal device and the second terminal device, the second terminal device being one or more second terminal devices;

calculating a service index of the first terminal device based on the relational score;

determining information to send based on the service index; and

sending the determined information to the first terminal device.

17. The computer readable medium according to claim 16 , wherein calculating the weight of the interaction setting between the first terminal device and the second terminal device comprises calculating the weight of the interaction setting between the first terminal device and the second terminal device according to a logistic regression model.

18. The computer readable medium according to claim 17 , wherein calculating the at least one relational score based on the weight among the first terminal device and the at least one second terminal device comprises:

calculating, according to the logistic regression model, a first sum of a plurality of interaction scores corresponding to a plurality of interaction settings;

multiplying the first sum by a time decay value of the first terminal device with respect to the second terminal device, to obtain a first total relational value of the first terminal device with respect to the second terminal device; and

dividing the first total relational value by a second sum of second total relational values of the second terminal device with respect to terminal devices interacting with the second terminal device to obtain the relational score.

19. The computer readable medium according to claim 16 , wherein calculating the service index of the first terminal device based on the relational score comprises calculating the service index of the first terminal device based on iterations with a PageRank algorithm.

20. The computer readable medium according to claim 19 , wherein calculating the service index of the first terminal device based on the iterations with the PageRank algorithm comprises:

iterating for a number of times with the PageRank algorithm, if the number of times is preset; and

iterating until all service indices of all terminal devices interacting with the first terminal device meet a preset convergence condition, if the number of times is not preset.