Real-time conversation analysis system

A conversation analysis system, comprising:

• a local system configured to capture conversation data associated with a face-to-face conversation between an individual and a user;
• and
• a backend system electronically connected to the local system, the backend system including a suggestion system configured to:
• receive the conversation data from the local system;
• extract, by an analysis unit, information from the conversation data indicative of a mood of the individual;
• classify, by a classifier unit, the individual based on the extracted information, including determining a mood classification;
• determine, by a suggestion unit, one or more rules based at least on the mood classification and stored information in a knowledge base;
• and
• while the face-to-face conversation is still ongoing:
• provide, by the suggestion unit, a suggestion to the user based on the one or more rules, wherein the suggestion includes changing a topic of the conversation or providing positive news;
• receive, from the local system, updated conversation data captured after the suggestion is provided to the user;
• update, by the classification unit, the mood classification based on the updated conversation data;
• and
• provide, by the suggestion unit, a new suggestion to the user based on a relationship between the mood classification and the updated mood classification, wherein the new suggestion includes providing a new topic of the conversation or providing new positive news.

A computer program product for conversation analysis, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

• receive conversation data captured during a face-to-face conversation between a user and an individual;
• extract information from the conversation data indicative of a mood of the individual;
• classify the individual based on the extracted information, including determining a mood classification;
• determine one or more rules based at least on the mood classification and stored information in a knowledge base;
• and
• while the face-to-face conversation is still ongoing:
• provide a suggestion to the user based on the one or more rules, wherein the suggestion includes changing a topic of the conversation or providing positive news;
• receive updated conversation data captured after the suggestion is provided to the user;
• update the mood classification based on the updated conversation data;
• and
• provide a new suggestion to the user based on a relationship between the mood classification and the updated mood classification, wherein the new suggestion includes providing a new topic of the conversation or providing new positive news.