Method, apparatus and storage medium for stay point recognition and prediction model training

A method for training a prediction model, wherein the method comprises:

• constructing training data, each piece of training data corresponding to a positioning point, and each piece of training data comprising:
• a feature vector for the positioning point, and a tag about whether the positioning point is a stay point;
• wherein the feature vector is generated according to obtained features of N predetermined dimensions for the positioning point, N being a positive integer greater than one;
• and
• obtaining the prediction model by training according to the training data constructed, so that for a to-be-recognized positioning point, determining whether the to-be-recognized positioning point is a stay point, based on a feature vector for the to-be-recognized positioning point.

A computer device, comprising a memory, a processor and a computer program which is stored on the memory and runs on the processor, wherein the processor, upon executing the program, implements a method for stay point recognition, wherein the method comprises:

• for a to-be-recognized positioning point, obtaining respectively features of N predetermined dimensions for the to-be-recognized positioning point, N being a positive integer greater than one;
• generating a feature vector for the to-be-recognized positioning point according to the features of N predetermined dimensions;
• and
• determining whether the to-be-recognized positioning point is a stay point based on the feature vector, by using a prediction model obtained by pre-training.

A computer device, comprising a memory, a processor and a computer program which is stored on the memory and runs on the processor, wherein the processor, upon executing the program, implements a method for training a prediction model, wherein the method comprises:

• constructing training data, each piece of training data corresponding to a positioning point, and each piece of training data comprising:
• a feature vector for the positioning point, and a tag about whether the positioning point is a stay point;
• wherein the feature vector is generated according to obtained features of N predetermined dimensions for the positioning point, N being a positive integer greater than one;
• and
• obtaining the prediction model by training according to the training data constructed, so that for a to-be-recognized positioning point, determining whether the to-be-recognized positioning point is a stay point, based on a feature vector for the to-be-recognized positioning point.

A non-transitory computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a method for stay point recognition, wherein the method comprises:

• for a to-be-recognized positioning point, obtaining respectively features of N predetermined dimensions for the to-be-recognized positioning point, N being a positive integer greater than one;
• generating a feature vector for the to-be-recognized positioning point according to the features of N predetermined dimensions;
• and
• determining whether the to-be-recognized positioning point is a stay point based on the feature vector, by using a prediction model obtained by pre-training.

A non-transitory computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a method for training a prediction model, wherein the method comprises:

• constructing training data, each piece of training data corresponding to a positioning point, and each piece of training data comprising:
• a feature vector for the positioning point, and a tag about whether the positioning point is a stay point;
• wherein the feature vector is generated according to obtained features of N predetermined dimensions for the positioning point, N being a positive integer greater than one;
• and
• obtaining the prediction model by training according to the training data constructed, so that for a to-be-recognized positioning point, determining whether the to-be-recognized positioning point is a stay point, based on a feature vector for the to-be-recognized positioning point.