Service recommendation method, apparatus, and device

1. A computer-executed method, comprising:

training, by a computer, a machine-learning model for recommending services based on sample data associated with a plurality of users and a plurality of services;

obtaining, based on historic information associated with a target user, a user feature of the target user and a service-usage feature of the target user for a target service;

inputting the user feature, the service-usage feature, and a service feature of the target service into the trained machine-learning model to determine a service recommendation scheme, wherein the trained machine-learning model outputs a recommendation location;

configuring, based on the service recommendation scheme outputted by the training machine-learning module, a user interface associated with the target service to display a service-upgrade entrance at the recommendation location;

receiving a feedback result of the target user for the service recommendation scheme; and

updating training of the machine-learning model based on the determined feedback result.

2. The method according to claim 1 , wherein the trained machine-learning module further outputs one or more of:

a service type and a recommendation frequency.

3. The method according to claim 1 , wherein the service-usage feature comprises one or more of:

a use time period feature, a use duration feature, a use frequency feature, a used storage space feature, and a used storage quantity feature.

4. The method according to claim 1 , wherein the service feature comprises one or more of:

a storage space feature, a folder quantity feature, a function type feature, a storage quantity feature, a total storage quantity feature, a computation unit peak feature, a total computation amount feature, a network download speed feature, a network upload speed feature, a total network download amount feature, and a total network upload amount feature.

5. The method according to claim 1 , wherein the machine-learning model for recommending services comprises one of: a logistic regression model, a random forest model, a Bayesian method model, a support vector machine model, and a neural network model.

6. A computer system, comprising:

a processer;

a storage device coupled to the processor and storing instructions, which when executed by the processor cause the processor to perform a method, the method comprising:

training, by a computer, a machine-learning model for recommending services based on sample data associated with a plurality of users and a plurality of services;

obtaining, based on historic information associated with a target user, a user feature of the target user and a service-usage feature of the target user for a target service;

inputting the user feature, the service-usage feature, and a service feature of the target service into the trained machine-learning model to determine a service recommendation scheme, wherein the trained machine-learning model outputs a recommendation location;

configuring, based on the service recommendation scheme outputted by the training machine-learning module, a user interface associated with the target service to display a service-upgrade entrance at the recommendation location;

receiving a feedback result of the target user for the service recommendation scheme; and

updating training of the machine-learning model based on the determined feedback result.

7. The computer system according to claim 6 , wherein the trained machine-learning module further outputs one or more of:

a service type and a recommendation frequency.

8. The computer system according to claim 6 , wherein the service-usage feature comprises one or more of:

a use time period feature, a use duration feature, a use frequency feature, a used storage space feature, and a used storage quantity feature.

9. The computer system according to claim 6 , wherein the service feature comprises one or more of:

a storage space feature, a folder quantity feature, a function type feature, a storage quantity feature, a total storage quantity feature, a computation unit peak feature, a total computation amount feature, a network download speed feature, a network upload speed feature, a total network download amount feature, and a total network upload amount feature.

10. The computer system according to claim 6 , wherein the machine-learning model for recommending services comprises one of: a logistic regression model, a random forest model, a Bayesian method model, a support vector machine model, and a neural network model.

11. A non-transitory computer-readable storage 2 medium storing instructions that when executed by a computer cause the computer to perform a method, the method comprising:

training, by a computer, a machine-learning model for recommending services based on sample data associated with a plurality of users and a plurality of services;

obtaining, based on historic information associated with a target user, a user feature of the target user and a service-usage feature of the target user for a target service;

inputting the user feature, the service-usage feature, and a service feature of the target service into the trained machine-learning model to determine a service recommendation scheme, wherein the trained machine-learning model outputs a recommendation location;

configuring, based on the service recommendation scheme outputted by the training machine-learning module, a user interface associated with the target service to display a service-upgrade entrance at the recommendation location;

receiving a feedback result of the target user for the service recommendation scheme; and

updating training of the machine-learning model based on the determined feedback result.

12. The non-transitory computer-readable storage medium according to claim 11 , wherein the trained machine-learning module further outputs one or more of:

a service type and a recommendation frequency.

13. The non-transitory computer-readable storage medium 2 according to claim 11 , wherein the service-usage feature comprises one or more of:

a use time period feature, a use duration feature, a use frequency feature, a used storage space feature, and a used storage quantity feature.

14. The non-transitory computer-readable storage medium according to claim 11 , wherein the service feature comprises one or more of:

a storage space feature, a folder quantity feature, a function type feature, a storage quantity feature, a total storage quantity feature, a computation unit peak feature, a total computation amount feature, a network download speed feature, a network upload speed feature, a total network download amount feature, and a total network upload amount feature.

15. The non-transitory computer-readable storage medium according to claim 11 , wherein the machine-learning model for recommending services comprises one of: a logistic regression model, a random forest model, a Bayesian method model, a support vector machine model, and a neural network model.