Recipient based text prediction for electronic messaging

2:

• The method of claim 1, wherein predicting the text comprises:
• predicting the text based on text contained in previous electronic messages sent from the message account that were addressed to the recipient.

3:

• The method of claim 1, wherein receiving the identification of the recipient of the electronic message being composed comprises receiving identifications of a plurality of recipients of the electronic message being composed, and wherein predicting the text comprises predicting the text based on past text used by the user in electronic messages addressed to the plurality of recipients.

4:

• The method of claim 1, wherein predicting the text comprises predicting the text using a machine learning model trained based on text contained in the previous electronic messages sent from the message account that were addressed to the recipient.

5:

• The method of claim 1, wherein predicting the text for the body of the electronic message comprises:
• predicting, by the computing system and based on greetings contained in previous electronic messages sent from the message account, a greeting for the body of the electronic message.

6:

• The method of claim 5, wherein predicting the greeting for the body of the electronic message comprises predicting, by the computing system and based on greetings contained in previous electronic messages sent from the message account that were addressed to the recipient, the greeting for the body of the electronic message.

7:

• The method of claim 5, further comprising:
• identifying, by the computing system and using a machine learning model, the greetings contained in the previous electronic messages sent from the message account.

8:

• The method of claim 5, wherein the predicted greeting does not include a name of the recipient.

9:

• The method of claim 5, wherein the predicted greeting includes one or more words other than a name or a salutation of the recipient.

10:

• The method of claim 5, wherein the greeting is further predicted based on a domain of an e-mail address of the recipient.

11:

• The method of claim 5, wherein outputting the predicted greeting comprises outputting the predicted greeting before receiving user input associated with composition of a body of the electronic message being composed.

(canceled)

14:

• The computing system of claim 12, wherein, to predict the text for the body of the electronic message, the one or more processors are configured to:
• predict, based on greetings contained in previous electronic messages sent from the message account, a greeting for the body of the electronic message.

15:

• The computing system of claim 14, wherein, to predict the greeting for the body of the electronic message, the one or more processors are configured to:
• predict, based on greetings contained in previous electronic messages sent from the message account that were addressed to the recipient, the greeting for the body of the electronic message.

16:

• The computing system of claim 14, wherein the one or more processors are further configured to:
• identify, using a machine learning model, the greetings contained in the previous electronic messages sent from the message account.

17:

• The computing system of claim 14, wherein the predicted greeting does not include a name of the recipient.

18:

• The computing system of claim 14, wherein the predicted greeting includes one or more words other than a name or a salutation of the recipient.

19:

• The computing system of claim 14, wherein the greeting is further predicted based on a domain of an e-mail address of the recipient.

20:

• The computing system of claim 14, wherein, to output the predicted greeting, the one or more processors are configured to:
• output the predicted greeting before receiving user input associated with composition of a body of the electronic message being composed.