Method for predicting user operation and mobile terminal
First Claim
Patent Images
1. A method for predicting a user operation, comprising:
- after training an operation model successfully, a mobile terminal obtaining a call instruction by utilizing acquired environmental factors and the operation model, and at last converting the call instruction into selection information to be displayed to a user;
wherein training the operation model successfully is embodied as counting the error of the operation model, determining whether or not the error of the operation model is lower than a use threshold which is preset, if the error is lower than the use threshold, the training of the operation model is successful;
wherein after training the operation model successfully, the mobile terminal periodically performing storage time length determination for the operation records in the operation record list one by one, if the storage time length of an operation record exceeds a deleting threshold, then the operation record is deleted;
wherein training the operation model is embodied as adjusting the operation model by an operation record list;
wherein adjusting the operation model by the operation record list comprises;
the mobile terminal calling operation records in the operation record list one by one, using the environment factors of the operation records as input information of the operation model, comparing output information of the operation model with the call instruction in the operation record, if the output information and the call instruction are identical, continuing to call a next operation record to perform comparison, and if the output information and the call instruction are different, adding 1 to an error of the operation model and adjusting the operation model, and then calling the next operation record to perform comparison until all operation records in the operation record list are called.
1 Assignment
0 Petitions
Accused Products
Abstract
The disclosure discloses a method for predicting a user operation. The method includes the following steps. After training an operation model successfully, a mobile terminal predicts a call instruction by utilizing environmental factors and the operation model, and finally compiles the call instruction into selection information to be displayed to a user. The disclosure further discloses a mobile terminal. Through the solution provided by the disclosure, a forthcoming operation of the user can be predicted, so that intelligent and detailed services are provided for the user.
-
Citations
11 Claims
-
1. A method for predicting a user operation, comprising:
-
after training an operation model successfully, a mobile terminal obtaining a call instruction by utilizing acquired environmental factors and the operation model, and at last converting the call instruction into selection information to be displayed to a user; wherein training the operation model successfully is embodied as counting the error of the operation model, determining whether or not the error of the operation model is lower than a use threshold which is preset, if the error is lower than the use threshold, the training of the operation model is successful; wherein after training the operation model successfully, the mobile terminal periodically performing storage time length determination for the operation records in the operation record list one by one, if the storage time length of an operation record exceeds a deleting threshold, then the operation record is deleted; wherein training the operation model is embodied as adjusting the operation model by an operation record list; wherein adjusting the operation model by the operation record list comprises;
the mobile terminal calling operation records in the operation record list one by one, using the environment factors of the operation records as input information of the operation model, comparing output information of the operation model with the call instruction in the operation record, if the output information and the call instruction are identical, continuing to call a next operation record to perform comparison, and if the output information and the call instruction are different, adding 1 to an error of the operation model and adjusting the operation model, and then calling the next operation record to perform comparison until all operation records in the operation record list are called. - View Dependent Claims (2, 3, 4, 11)
-
-
5. A mobile terminal, comprising a hardware processor configured to execute following modules:
-
an operation model module, configured to input environmental factors into an operation model after the operation model is trained successfully, and send a call instruction to an output module, wherein the call instruction is calculated and outputted by the operation model; an output module, configured to receive the call instruction sent by the operation model module, convert the call instruction into selection information, and send the selection information to a display interaction module; and the display interaction module, configured to receive the selection information sent by the output module and display the selection information to a user; wherein the operation model module is specifically configured to call operation records in the operation record list one by one, use the environment factors of the operation records as input information of the operation model, compare output information of the operation model with the call instruction in the operation record, if the output information and the call instruction are identical, continue to call a next operation record to perform comparison, and if the output information and the call instruction are different, add 1 to an error of the operation model and adjust the operation model, and then call the next operation record until all operation records in the operation record list are called; wherein the operation model module is further configured to determine whether or not the error of the operation model is lower than a use threshold which is preset, if the error is lower than the use threshold, the training of the operation model is successful; wherein the operation model module is further configured to periodically perform storage time length determination for the operation records in the operation record list one by one after training the operation model successfully, if the storage time length of an operation record exceeds a deleting threshold, then the operation record is deleted. - View Dependent Claims (6, 7, 8, 9, 10)
-
Specification