Abstract: A method, a device and a computer storage medium for promotion displaying are disclosed. The method includes: using user's behavior data to perform intent recognition for the user; under the condition that an intent in a specific class is recognized, determining a target entity corresponding to the recognized intent in the specific class; expanding the recognized intent in the specific class using attribute information of the target entity; and displaying promotional data corresponding to the intent obtained from the expansion to the user. According to the technical solution, promotional data may be displayed to the user according to the user's intent, and thus the displaying efficiency and coverage rate of the promotional data may be improved.

Abstract: A method, a computer device and a readable medium user's intent mining are disclosed. The method includes: obtaining text feature information corresponding to behavior data of a user; extracting an intent information list corresponding to the behavior data by using a pre-trained intent extracting model; and obtaining the target intent information of the user from the intent information list corresponding to the behavior data of the user, according to the text feature information and the intent information list corresponding to the behavior data, and a preset semantic similarity threshold, and adding the target intent information of the user to an intent information queue for advertisement recommendation.

Abstract: A method, a computer device and a readable medium user's intent mining are disclosed. The method includes: obtaining text feature information corresponding to behavior data of a user; extracting an intent information list corresponding to the behavior data by using a pre-trained intent extracting model; and obtaining the target intent information of the user from the intent information list corresponding to the behavior data of the user, according to the text feature information and the intent information list corresponding to the behavior data, and a preset semantic similarity threshold, and adding the target intent information of the user to an intent information queue for advertisement recommendation.

Abstract: A method, a device and a computer storage medium for promotion displaying are disclosed. The method includes: using user's behavior data to perform intent recognition for the user; under the condition that an intent in a specific class is recognized, determining a target entity corresponding to the recognized intent in the specific class; expanding the recognized intent in the specific class using attribute information of the target entity; and displaying promotional data corresponding to the intent obtained from the expansion to the user. According to the technical solution, promotional data may be displayed to the user according to the user's intent, and thus the displaying efficiency and coverage rate of the promotional data may be improved.

Abstract: The present application discloses a method and an apparatus for file identification. The method for file identification comprises: determining a virus family of each malicious file sample in a plurality of the file samples resulting in a plurality of virus families; dividing the plurality of the virus families into at least one sample group based on a number of the malicious files belonging to each of the plurality of virus families; training the malicious file samples in each of the at least one sample group with a different training rule to obtain at least one file identification model; and determining, using the at least one identification model whether a file is a malicious file. The method for file identification of the present application may provide different identification models for various types of malicious files and thus improves the accuracy of the file identification.

Abstract: The present application discloses a method and an apparatus for file identification. The method for file identification comprises: determining a virus family of each malicious file sample in a plurality of the file samples resulting in a plurality of virus families; dividing the plurality of the virus families into at least one sample group based on a number of the malicious files belonging to each of the plurality of virus families; training the malicious file samples in each of the at least one sample group with a different training rule to obtain at least one file identification model; and determining, using the at least one identification model whether a file is a malicious file. The method for file identification of the present application may provide different identification models for various types of malicious files and thus improves the accuracy of the file identification.