Abstract: A recognition method includes the following steps. A text is analyzed by a language recognition network to generate an entity feature, a relation feature and an overall feature. An input image is analyzed by an object detection network to generate candidate regions. Node features, aggregated edge features and compound features are generated by an enhanced cross-modal graph attention network according to the entity feature, the relation feature, the candidate regions and the overall feature. The entity feature and the relation feature are matched to the node features and the aggregated edge features to generate the first scores. The overall feature is matched to the compound features to generate second scores. Final scores corresponding to the candidate regions are generated according to the first scores and the second scores.

Abstract: A group marketing system, a group marketing device and a group marketing method thereof are provided. The group marketing system includes a data collecting device and a group marketing device. The data collecting device has a connection with the group marketing device and is configured to collect group data. The group marketing device is configured to store specific product customer data, receive the group data, generate group relation data according to the group data, generate group preference analysis data according to the group relation data and the specific product customer data, generate product data according to the group preference analysis data, and transmit the product data to an electronic device.

Abstract: Embodiments disclosed relate to a computer device and a method for predicting market demand of commodities. The method includes: creating multiple-sources data for each of a plurality of commodities, wherein each of the all multiple-sources data comes from a plurality data sources; storing the all multiple-sources data; extracting a plurality of features from a corresponding one of the all multiple-sources data for each of the commodities to build a feature matrix for each of the data sources; performing a tensor decomposition process on the feature matrices to produce at least one latent feature matrix; and performing a deep learning process on the at least one latent feature matrix to build a prediction model and predicting market demand of each of the commodities according to the prediction model.

Abstract: A social activity planning method includes the following operation. A database storing multiple candidate invitees with their geographical locations and interest scores towards a topic, and a social graph including vertices representing the candidate invitees and edges connecting two vertices representing mutual acquaintance of the associated candidate invitees is accessed. A social activity request including an invitation number, information about a social activity, and a familiarity condition for the social activity request is received. At least one feasible solution including the invitation number of the candidate invitees and meeting the familiarity condition is generated. A group of selected invitees are found based on the feasible solution and the information about the social activity.

Abstract: A social activity planning method includes the following operation. A database storing multiple candidate invitees with their geographical locations and interest scores towards a topic, and a social graph including vertices representing the candidate invitees and edges connecting two vertices representing mutual acquaintance of the associated candidate invitees is accessed. A social activity request including an invitation number, information about a social activity, and a familiarity condition for the social activity request is received. At least one feasible solution including the invitation number of the candidate invitees and meeting the familiarity condition is generated. A group of selected invitees are found based on the feasible solution and the information about the social activity.