Intelligent automated messaging for computer-implemented devices

• US 9,306,878 B2
• Filed: 02/14/2012
• Issued: 04/05/2016
• Est. Priority Date: 02/14/2012
• Status: Active Grant

• Current Assignee: Salesforce.com, Inc.
• Original Assignee: Salesforce.com, Inc.
• Inventors: Patil, Dipak
• Primary Examiner(s): SALAD, ABDULLAHI ELMI
• Application Number:
  US13/396,447
• Publication Number:
  US 20130212190A1
• Time in Patent Office: 1,512 Days
• Field of Search: 709206-207, 707765-767, 715/206
• US Class Current: 1/1
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

Various computer-implemented systems and methods are provided here for purposes of intelligent predictive messaging. An exemplary system can be operated to obtain message context data associated with a messaging session, process the message context data to obtain suggested message content for the messaging session, and automatically populate a message field of a user device with at least some of the suggested message content. The system may proceed by sending a message from the user device, where the message includes content of the message field.

Claims

1. A computer-implemented method of intelligent predictive messaging, the method comprising:

obtaining, at a messaging server from a user device, message context data indicative of context of a conversation taking place between particular participants during a messaging session, wherein the particular participants are people and wherein the conversation takes place between the people;

processing the message context data, at a message prediction engine, to determine a predicted messaging scenario of the conversation between the particular participants of the conversation based on prior conversation patterns between those particular participants of the conversation, wherein the predicted messaging scenario includes a predicted conversation pattern of the conversation that is taking place between the particular participants of the conversation;

determining, at the message prediction engine based on the predicted conversation pattern, recommended text that indicates suggested language to be included in a message as part of the conversation to complete at least part of the message, wherein the suggested language corresponds to the message context data indicative of the context of the conversation, and wherein the recommended text comprises options for suggested language that are predicted to compete at least part of the message;

displaying the recommended text within a message field at the user device, and automatically populating the message field with at least some of the suggested language; and

thereafter, sending the message from the user device, the message including content of the message field.

2. The method of claim 1, wherein:

the suggested language to be included in the message comprises a plurality of suggested entries for the messaging session, wherein each of the suggested entries comprises;

a different recommended lines of text, wherein each of the different lines of text indicates different suggested language for the message corresponding to the message context data;

the method further comprises providing the plurality of suggested entries for presentation at the user device;

the method further comprises selecting one of the plurality of suggested entries, resulting in a selected entry; and

automatically populating the message field comprises automatically populating the message field with the selected entry.

3. The method of claim 2, wherein:

the plurality of suggested entries is provided at the user device in a user-selectable format; and

the selecting is performed in response to user selection of one of the plurality of suggested entries.

4. The method of claim 3, wherein the plurality of suggested entries is provided by an intelligent auto-fill technique.

5. The method of claim 1, wherein the message context data comprises an identification of at least one participant of the messaging session.

6. The method of claim 1, wherein the message context data comprises a time associated with the messaging session.

7. The method of claim 1, wherein the message context data comprises location information that indicates a location of the user device.

8. The method of claim 1, wherein the message context data comprises historical message content associated with the messaging session.

9. The method of claim 1, wherein the message context data comprises calendar information associated with at least one participant of the messaging session.

10. The method of claim 1, wherein:

processing the message context data is performed by a message prediction engine of the user device; and

the method further comprises;

updating the message prediction engine in response to sending the message.

11. A computer-implemented method of intelligent predictive messaging, the method comprising:

initiating, with a messaging server system, a messaging session between a first user of a first user device and a second user of a second user device that are particular participants of a conversation, wherein the particular participants are people and wherein the conversation takes place between the people;

determining, at the messaging server system based on a characteristic of a conversation taking place between the first user device and the second user device as part of the messaging session, wherein the characteristic of the conversation is indicative of context of the conversation, a predicted messaging scenario during the conversation taking place between the first user device and the second user device during the messaging session based on prior conversation patterns between those particular participants of the conversation, wherein the predicted messaging scenario includes a predicted conversation pattern of the conversation that is taking place between the particular participants of the conversation;

determining, based on the predicted conversation pattern, recommended text that indicates suggested language to be included in a message as part of the conversation to complete at least part of the message, wherein the suggested language corresponds to the characteristic of the conversation indicative of the context of the conversation, and wherein the recommended text comprises options for suggested language that are predicted to compete at least part of the message; and

providing suggested message content to the first user device and/or to the second user device, wherein the suggested message content comprises;

the recommended text that indicates the suggested language for the message as part of the conversation, wherein the suggested language corresponds to the characteristic of the conversation indicative of the context of the conversation, the suggested message content being influenced by the predicted messaging scenario.

12. The method of claim 11, wherein the providing comprises:

displaying the suggested message content within a message field at a user device, and automatically populating the message field of the first user device and/or the second user device with the suggested message content.

13. The method of claim 11, wherein:

determining the predicted messaging scenario is performed by a message prediction engine of the messaging server system; and

the method further comprises;

updating the message prediction engine in response to actual message content associated with the messaging session.

14. The method of claim 11, further comprising:

receiving, at the messaging server system, message context data associated with the messaging session that indicates the characteristic of the conversation, wherein the messaging server system determines the predicted messaging scenario based on the message context data.

15. The method of claim 14, wherein the messaging server system receives the message context data from the first user device and/or the second user device.

16. A computer-implemented system, comprising:

a first user device; and

a messaging server, comprising;

a processor and a memory, wherein the memory comprises a non-transitory computer-readable-medium having computer-executable instructions stored therein that, when executed by the processor, cause the processor to;

initiate a messaging session;

obtain, at the messaging server from the first user device, message context data indicative of context of a conversation taking place between the first user device and a second user device associated with particular participants of the conversation during the messaging session, wherein the particular participants are people and wherein the conversation takes place between the people;

analyze the message context data, at a message prediction engine, to determine, based on prior conversation patterns between those particular participants of the conversation, a predicted messaging scenario during the conversation between the particular participants of the conversation as part of the messaging session, wherein the predicted messaging scenario includes a predicted conversation pattern of the conversation that is taking place between the particular participants of the conversation; and

generate, at the message prediction engine based on the predicted conversation pattern, suggested message content for the predicted messaging scenario, wherein the suggested message content comprises;

recommended text that indicates suggested language to be included in a message as part of the conversation to complete at least part of the message, wherein the suggested language corresponds to the message context data indicative of the context of the conversation, and wherein the recommended text comprises options for suggested language that are predicted to compete at least part of the message,

wherein the recommended text is presented within a message field at the first user device, and automatically populates the message field with at least some of the suggested language to a participant of the messaging session.

17. The system of claim 16, wherein:

the messaging server system obtains the message context data from the first user device that is participating in the messaging session.

18. The system of claim 16, wherein the message context data comprises identification of at least one participant of the messaging session.

19. The system of claim 16, wherein the message context data comprises time, date, and/or calendar information.

20. The system of claim 16, wherein the messaging server is implemented at the first user device.

21. The system of claim 16, further comprising:

a computer that is communicatively coupled to the first user device via a network, wherein the messaging server is implemented at the computer.