Intelligent interaction method and intelligent interaction system

#This application claims the benefit and priority of Chinese patent application No. 201611093525.X filed on Dec. 1, 2016, the entire contents of which are incorporated herein by reference.

#The present invention relates to artificial intelligence technology, and more particularly to an intelligent interaction method and an intelligent interaction system.

#With the continuous development of artificial intelligence technology and the continuous increase of requirements for interaction experience, intelligent interaction methods have gradually replaced some traditional human-computer interaction methods, and have become a research hotspot. However, the conventional intelligent interaction methods are only capable of performing simple semantic analysis on current request information to acquire approximate intention information and determining response information according to the acquired intention information. Since the current request information which can be used for semantic analysis is limited to standard questions that have been stored in a knowledge base, such an interaction method is rigid and brings poor user experience. In addition, with the conventional intelligent interaction methods, even though the intention information corresponding to the current request information is acquired, it does not mean that the real thoughts of the user are acquired. For example, in a phone intelligent customer service scene about credit card repayment reminding, if the current request information is a standard question “I will repay immediately”, the intention information acquired will be “I'm ready to repay”. However, if the user has poor credit records, it is very likely that the user doesn't want to repay, i.e., the real thought of the user is likely to be not repaying. In this case, if frequency and intensity of reminding is lowered just based on the intention information “I'm ready to repay”, the effect of reminding is not good. Therefore, the response will be too simple if it is based on the acquired intention information only, and thus a good interaction effect cannot be achieved.

#FIG. 1 is a flowchart illustrating an intelligent interaction method according to an embodiment of the present invention.

#FIG. 2 is a flowchart illustrating steps of acquiring intention information in the intelligent interaction method according to an embodiment of the present invention.

#FIG. 3 is a flowchart illustrating steps of acquiring interaction background information according to user static information in the intelligent interaction method according to an embodiment of the present invention.

#Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout. In this regard, the present embodiments may have different forms and should not be construed as being limited to the descriptions set forth herein. It will be understood that various changes and modifications can be made by one ordinary skilled in the art within the spirit and scope of the present invention. Various features of the embodiments can be mixed and matched in any manner, to produce further embodiments consistent with the present invention. Accordingly, the embodiments are merely described below, by referring to the figures, to explain aspects of the present description.

#FIG. 1 is a flowchart illustrating an intelligent interaction method according to an embodiment of the present invention. As shown in FIG. 1, the method comprises the following steps.

#Step 101: acquiring user static information and current request information.