Action prediction based on interactive history and context between sender and recipient

• US 20080126310A1
• Filed: 11/29/2006
• Published: 05/29/2008
• Est. Priority Date: 11/29/2006
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP AG (SAP SE)
• Inventors: Xu, Tian
• Granted Patent: US 8,200,691 B2
• Time in Patent Office: Days
• US Class Current: 707/3
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

Techniques for action prediction based on interactive history and context between a sender and a recipient are described herein. In one embodiment, a process includes, but is not limited to, in response to a message to be received by a recipient from a sender over a network, determining one or more previous transactions associated with the sender and the recipient, the one or more previous transactions being recorded during course of operations performed within an entity associated with the recipient, and generating a list of one or more action candidates based on the determined one or more previous transactions, wherein the one or more action candidates are optional actions recommended to the recipient, in addition to one or more actions required to be taken in response to the message. Key word identification out of voice applications as well as guided actions has also been applied to generate action prediction candidates interactive history links Other methods and apparatuses are also described.

Claims

1. A machine-implemented method, comprising:

in response to a message to be received by a recipient from a sender over a network, determining one or more previous transactions associated with the sender and the recipient, the one or more previous transactions being recorded during course of operations performed within an entity associated with the recipient; and

generating a list of one or more action candidates based on the determined one or more previous transactions, wherein the one or more action candidates are optional actions recommended to the recipient, in addition to one or more actions required to be taken in response to the message.

2. The method of claim 1, further comprising generating the one or more required actions based on the one or more previous transactions associated with the sender and the recipient.

3. The method of claim 1, wherein determining one or more previous transactions comprises:

accessing a first database to search first previous transactions associated with the sender with respect to the entity; and

substantially concurrently accessing a second database to search second previous transactions associated with the recipient with respect to the sender, wherein the list of action candidates is generated based on at least one of the first and second previous transactions.

4. The method of claim 3, further comprising:

extracting one or more keywords from the message;

identifying one or more transaction objects that are related to the extracted one or more keywords based on the first previous transactions; and

generating one or more guided actions based on the identified one or more transaction objects, wherein one or more action candidates are generated based on the one or more guided actions.

5. The method of claim 4, further comprising adjusting the guided actions to form the recommended actions based on one or more behaviors of the sender derived from the first previous transactions.

6. The method of claim 4, further comprising:

generating a first transaction context representing one or more common tasks performed by the sender based on the first previous transactions and the one or more guided actions; and

generating a second transaction context representing one or more common tasks performed by the recipient based on the second previous transactions, wherein the one or more action candidates are generated based on at least one of the first and second transaction contexts.

7. The method of claim 6, further comprising recording one or more behaviors of the recipient in view of the first and second transaction contexts, wherein the recorded behaviors are used to generate further recommended actions with respect to the sender and/or recipient.

8. The method of claim 1, wherein the entity is an enterprise entity, and wherein information of the previous transactions is provided from an enterprise information system (EIS) associated with the enterprise entity, the EIS system including at least an enterprise resource planning (ERP) system.

9. A machine-readable medium having instructions therein, which when executed by a machine, cause the machine to perform a method, the method comprising:

in response to a message to be received by a recipient from a sender over a network, determining one or more previous transactions associated with the sender and the recipient, the one or more previous transactions being recorded during course of operations performed within an entity associated with the recipient; and

generating a list of one or more action candidates based on the determined one or more previous transactions, wherein the one or more action candidates are optional actions recommended to the recipient, in addition to one or more actions required to be taken in response to the message.

10. The machine-readable medium of claim 9, wherein the method further comprises generating the one or more required actions based on the one or more previous transactions associated with the sender and the recipient.

11. The machine-readable medium of claim 9, wherein determining one or more previous transactions comprises:

accessing a first database to search first previous transactions associated with the sender with respect to the entity; and

substantially concurrently accessing a second database to search second previous transactions associated with the recipient with respect to the sender, wherein the list of action candidates is generated based on at least one of the first and second previous transactions.

12. The machine-readable medium of claim 11, wherein the method further comprises:

extracting one or more keywords from the message;

identifying one or more transaction objects that are related to the extracted one or more keywords based on the first previous transactions; and

generating one or more guided actions based on the identified one or more transaction objects, wherein one or more action candidates are generated based on the one or more guided actions.

13. The machine-readable medium of claim 12, wherein the method further comprises adjusting the guided actions to form the recommended actions based on one or more behaviors of the sender derived from the first previous transactions.

14. The machine-readable medium of claim 12, wherein the method further comprises:

generating a first transaction context representing one or more common tasks performed by the sender based on the first previous transactions and the one or more guided actions; and

generating a second transaction context representing one or more common tasks performed by the recipient based on the second previous transactions, wherein the one or more action candidates are generated based on at least one of the first and second transaction contexts.

15. The machine-readable medium of claim 14, wherein the method further comprises recording one or more behaviors of the recipient in view of the first and second transaction contexts, wherein the recorded behaviors are used to generate further recommended actions with respect to the sender and/or recipient.

16. The machine-readable medium of claim 9, wherein the entity is an enterprise entity, and wherein information of the previous transactions is provided from an enterprise information system (EIS) associated with the enterprise entity, the EIS system including at least an enterprise resource planning (ERP) system.

17. A data processing system, comprising:

a processing logic, in response to a message to be received by a recipient from a sender over a network, to determine one or more previous transactions associated with the sender and the recipient, the one or more previous transactions being recorded during course of operations performed within an entity associated with the recipient;

an action generator coupled to generate one or more actions required to be taken based on the determined one or more previous transactions; and

an action predictor coupled to generate a list of one or more action candidates based on the determined one or more previous transactions, wherein the one or more action candidates are optional actions recommended to the recipient, in addition to the one or more required actions in response to the message.

18. The system of claim 17, further comprising:

a first search engine to search within a first database first previous transactions associated with the sender with respect to the entity; and

a second search engine to substantially concurrently search within a second database second previous transactions associated with the recipient with respect to the sender, wherein the list of action candidates is generated based on at least one of the first and second previous transactions.

19. The system of claim 18, further comprising message analyzer coupled to the first search engine to analyze the message, where the message analyzer comprises:

a keyword recognizer to extract one or more keywords from the message;

a transaction identifier to identify one or more transaction objects that are related to the extracted one or more keywords based on the first previous transactions; and

an action guiding unit to generate one or more guided actions based on the identified one or more transaction objects, wherein one or more action candidates are generated based on the one or more guided actions.

20. The system of claim 19, wherein the keyword recognizer identifies one or more key words out of voice applications and then searches one or more transaction objects based on the identified key words, wherein the action guiding unit generates one or more guided actions based on the one or more transaction objects, and wherein one or more action candidates are generated based on the one or more guided actions.

21. A first context generator to generate a first transaction context representing one or more common tasks performed by the sender based on the first previous transactions and the one or more guided actions;

and a second context generator to generate a second transaction context representing one or more common tasks performed by the recipient based on the second previous transactions, wherein the one or more action candidates are generated based on at least one of the first and second transaction contexts.