摘要:
Summary generation based on comparison objects can include receiving text descriptions of a target object and at least one comparison object. Semantic vectors from the text descriptions can be obtained, using a deep learning based semantic extraction model. The semantic vectors can be input to a generator model trained using an adversarial machine learning technique, the generator model outputting a text summary of the target object describing only unique characteristics of the target object different from characteristics of the at least one comparison object and excluding the characteristics of the at least one comparison object.
摘要:
Techniques are described with respect to a system, method, and computer product for generating multi-media content based on linguistics. An associated method includes receiving a plurality of linguistic inputs and analyzing the plurality of linguistic inputs. The method further including generating multi-media content for presentation to a user based on the analyzing of the linguistic inputs.
摘要:
Collecting online group chat messages. The method may include receiving a message associated with an online group chat session between chat participants. The method may also include determining the received message satisfies at least one message collection rule. The method may further include recording the received message to at least one message table based on each chat participant mentioned in the received message. The method may also include determining a first chat participant chooses to open a private chat session with at least one second chat participant. The method may further include identifying recorded messages within the message tables associated with the at least one second chat participant. The method may also include displaying the identified recorded messages in a private chat session sub-window.
摘要:
A method includes generating a test model based on at least one of test group dependencies and test group constraints and generating a resource base. the method includes generating a cost model and generating a resource allocation plan based on the test model, the resource base, and the cost model.
摘要:
Detecting a first facial region in a first image. Extracting the detected first facial region. Generating a first facial thumbnail based on the extracted first facial region for use in representing the first image.
摘要:
Detecting a first facial region in a first image. Extracting the detected first facial region. Generating a first facial thumbnail based on the extracted first facial region for use in representing the first image.
摘要:
A method includes generating a test model based on at least one of test group dependencies and test group constraints and generating a resource base. The method includes generating a cost model and generating a resource allocation plan based on the test model, the resource base, and the cost model.
摘要:
Detecting a first facial region in a first image. Extracting the detected first facial region. Generating a first facial thumbnail based on the extracted first facial region for use in representing the first image.
摘要:
Detecting a first facial region in a first image. Extracting the detected first facial region. Generating a first facial thumbnail based on the extracted first facial region for use in representing the first image.
摘要:
Collecting online group chat messages. An embodiment of the invention may include determining a received message satisfies at least one of a plurality of message collection rules. The embodiment may also include recording the received message to at least one of a plurality of message tables based on each of a plurality of chat participants mentioned in the received message. The embodiment may further include determining a first chat participant within the plurality of chat participants chooses to open a private chat session with a second chat participant within the plurality of chat participants. The embodiment may also include identifying a plurality of recorded messages within the plurality of message tables where the first chat participant typed a screen name or a given name for the second chat participant and where the second chat participant typed a screen name or a given name of the first chat participant.