Smart communications assistant with audio interface
Methods, systems, and computer programs are presented for a smart communications assistant with an audio interface. One method includes an operation for getting messages addressed to a user. The messages are from one or more message sources and each message comprising message data that includes text. The method further includes operations for analyzing the message data to determine a meaning of each message, for generating a score for each message based on the respective message data and the meaning of the message, and for generating a textual summary for the messages based on the message scores and the meaning of the messages. A speech summary is created based on the textual summary and the speech summary is then sent to a speaker associated with the user. The audio interface further allows the user to verbally request actions for the messages.
1. A method comprising:
getting, by one or more processors, one or more messages from one or more message sources, the one or more messages being addressed to a user, each message comprising message data that includes message text;
analyzing, by the one or more processors, the message data to determine a meaning of the message text in each message;
generating, by the one or more processors, a score for each message based on the respective message data and the meaning of the message;
selecting messages based on the score of each message;
generating, by the one or more processors, a textual summary for the selected messages based on the meaning of the message text;
creating, by the one or more processors, a speech summary for each selected message, based on the textual summary and the meaning of the message text; and
sending, by the one or more processors, the speech summary for the selected messages to a speaker associated with the user.
2. The method as recited in claim 1 , wherein generating the score further includes:
for each message, identifying an attribute value for each of a plurality of attributes based on the message data;
for each attribute, generating an attribute score based on the attribute values; and
generating the score for each message based on the attribute scores of the message.
3. The method as recited in claim 2 , wherein a first attribute is whether the message is from a boss of the user.
4. The method as recited in claim 2 , wherein a second attribute is a work relationship between a sender of the message and the user, the work relationship being based on an organizational chart.
5. The method as recited in claim 2 , wherein a third attribute is detecting in the message text a request for an action to be performed by the user.
6. The method as recited in claim 2 , wherein a fourth attribute is detecting urgency in the message, the urgency being detected based on words in the message text.
7. The method as recited in claim 1 , further comprising:
providing a speech interface to the user for receiving commands from the user, the commands comprising one or more of a request for the speech summary, a request to read a message, a request to forward a message, a request to create a reminder, and a request for a summary of a message.
8. The method as recited in claim 1 , wherein getting one or more messages further comprises one or more of:
getting email messages;
getting text messages;
getting chat messages; and
getting messages from a team-based application.
9. The method as recited in claim 1 , wherein generating the textual summary further comprises:
creating a summary of the meaning of the message text of the selected messages for the textual summary.
10. A system comprising:
a memory comprising instructions; and
one or more computer processors, wherein the instructions, when executed by the one or more computer processors, cause the one or more computer processors to perform operations comprising:
getting one or more messages from one or more message sources, the one or more messages being addressed to a user, each message comprising message data that includes message text;
analyzing the message data to determine a meaning of the message text in each message;
generating a score for each message based on the respective message data and the meaning of the message text in each message;
selecting messages based on the score of each message;
generating a textual summary for the selected messages based on the meaning of the message text;
creating a speech summary for each selected message, based on the textual summary and the meaning of the message text; and
sending the speech summary for the selected messages to a speaker associated with the user.
11. The system as recited in claim 10 , wherein generating the score further includes:
for each message, identifying an attribute value for each of a plurality of attributes based on the message data;
for each attribute, generating an attribute score based on the attribute values; and
generating the score for each message based on the attribute scores of the message.
12. The system as recited in claim 11 , wherein a first attribute is whether the message is from a boss of the user, wherein a second attribute is a work relationship between a sender of the message and the user, the work relationship being based on an organizational chart.
13. The system as recited in claim 11 , wherein a third attribute is detecting in the message text a request for an action to be performed by the user, wherein a fourth attribute is detecting urgency in the message, the urgency being detected based on words in the message text.
14. The system as recited in claim 10 , wherein the instructions further cause the one or more computer processors to perform operations comprising:
providing a speech interface to the user for receiving commands from the user, the commands comprising one or more of a request for the speech summary, a request to read a message, a request to forward a message, a request to create a reminder, and a request for a summary of a message.
15. A non-transitory machine-readable storage medium including instructions that, when executed by a machine, cause the machine to perform operations comprising:
getting one or more messages from one or more message sources, the one or more messages being addressed to a user, each message comprising message data that includes message text;
analyzing the message data to determine a meaning of the message text in each message;
generating a score for each message based on the respective message data and the meaning of the message;
selecting messages based on the score of each message;
generating a textual summary for the selected messages based on the meaning of the message text;
creating a speech summary for each selected message, based on the textual summary and the meaning of the message text; and
sending the speech summary for the selected messages to a speaker associated with the user.
16. The machine-readable storage medium as recited in claim 15 , wherein generating the score further includes:
for each message, identifying an attribute value for each of a plurality of attributes based on the message data;
for each attribute, generating an attribute score based on the attribute values; and
generating the score for each message based on the attribute scores of the message.
17. The machine-readable storage medium as recited in claim 16 , wherein a first attribute is whether the message is from a boss of the user, wherein a second attribute is a work relationship between a sender of the message and the user, the work relationship being based on an organizational chart.
18. The machine-readable storage medium as recited in claim 16 , wherein a third attribute is detecting in the message text a request for an action to be performed by the user, wherein a fourth attribute is detecting urgency in the message, the urgency being detected based on words in the message text.
19. The machine-readable storage medium as recited in claim 15 , wherein the machine further performs operations comprising:
providing a speech interface to the user for receiving commands from the user, the commands comprising one or more of a request for the speech summary, a request to read a message, a request to forward a message, a request to create a reminder, and a request for a summary of a message.