Conversation content generation based on user professional level
AssigneeInternational Business Machines Corporation
InventorsXin Zhou, Qi Cheng Li, Jian Wang, Li Jun Mei, Hao Chen, Shao Chun Li, Ya Bin Dang
Life of this patent
Estimating the term…
Abstract
The present disclosure provides a method, computer system and computer program product facilitating generation of a conversation content. A computer-implemented method comprises: obtaining, by a device operatively coupled to one or more processors, history conversation data of an user; determining, by the device, a professional level of the user based on the history conversation data; and generating, by the device, a conversation content for the user based on the professional level of the user.
Claims17
A computer-implemented method comprising:
- obtaining, by a device operatively coupled to one or more processors, history conversation data of a user;
- determining, by the device, a professional level of the user based on the history conversation data;
- and
- generating, by the device, a conversation content for the user based on the professional level of the user, wherein the determining the professional level of the user based on the history conversation data comprises:
- extracting, by the device, one or more symptoms from the history conversation data;
- determining, by the device, one or more description sections used by the user for describing each of the one or more symptoms;
- assigning, by the device, weights to the one or more description sections;
- and
- calculating, by the device, a score for at least one of the one or more symptoms based on the weights, wherein scores for the one or more symptoms are used to represent the professional level of the user on the one or more symptoms.
A computer system comprising:
- a memory that stores computer executable components;
- and
- a processor, operably coupled to the memory, and that executes the computer executable components stored in the memory, wherein at least one of the computer executable components:
- obtains history conversation data of a user;
- determines a professional level of the user based on the history conversation data;
- and
- generates a conversation content for the user based on the professional level of the user, wherein the determination of the professional level of the user based on the history conversation data comprises:
- extraction of one or more symptoms from the history conversation data;
- determination of one or more description sections used by the user for describing each of the one or more symptoms;
- assigning weights to the one or more description sections;
- and
- calculation of a score for at least one of the one or more symptoms based on the weights, wherein scores for the one or more symptoms are used to represent the professional level of the user on the one or more symptoms.
A computer program product facilitating generation of conversation contents based on user professional levels, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
- obtain, by the processor, history conversation data of a user;
- determine, by the processor, a professional level of the user based on the history conversation data;
- and
- generate, by the processor, a conversation content for the user based on the professional level of the user, wherein a determination of the professional level of the user based on the history conversation data comprises:
- extraction of one or more symptoms from the history conversation data;
- determination of one or more description sections used by the user for describing at least one of the one or more symptoms;
- an assigning of weights to the one or more description sections;
- and
- calculation of a score for at least one of the one or more symptoms based on the weights, wherein scores for the one or more symptoms are used to represent the professional level of the user on the one or more symptoms.
Dependencies are inferred from the claim text.