CHAT SESSION EXTERNAL CONTENT RECOMMENDER

• US 20200134035A1
• Filed: 10/31/2018
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Rakshit, Sarbajit K., Ganci, JR., John M., Keen, Martin G., BOSTICK, JAMES E.
• Granted Patent: US 11,762,864 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9532 Query formulation
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: H04L 51/046 Interoperability with other network applications or services
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads

Abstract

Aspects of the present invention provide devices that identify a question in a text message of a chat session between a plurality of computing devices, wherein each of the plurality of computing devices includes an identifier of a user of a corresponding computing device in the text message, analyze digital data to determine a relationship between the users of the plurality of computing devices, construct search parameters for digital content external to the chat session according to the identified question and determined relationship, search for the digital content over a network according to the constructed search parameters to obtain search results, rank the search results according to the determined relationship, and distribute the ranked search results according to the determined relationship to at least one of the plurality of computing devices in an overlay of the chat session.

Claims

1. A computer-implemented method for generating chat session content, comprising executing on a computer processor:

identifying a question in a text message of a chat session between a plurality of computing devices, wherein each of the plurality of computing devices includes an identifier of a user of a corresponding computing device in the text message;

analyzing digital data to determine a relationship between the users of the plurality of computing devices;

constructing search parameters for digital content external to the chat session according to the identified question and determined relationship;

searching for the digital content over a network according to the constructed search parameters to obtain search results;

ranking the search results according to the determined relationship; and

distributing the ranked search results according to the determined relationship to at least one of the plurality of computing devices in an overlay of the chat session.

2. The method of claim 1, further comprising:

analyzing text messages of the chat session to determine a sentiment value; and

refining the search parameters for the digital content in response to the determined sentiment value.

3. The method of claim 1, wherein analyzing prior digital data includes identifying a decision maker from the users of the plurality of computing devices and a strength of the determined relationships between the users;

wherein ranking the search results includes ranking the search results according to preferences of the decision maker and the strength of the determined relationships; and

wherein distributing the ranked search results includes distributing the search results to the computing device of the decision maker.

4. The method of claim 1, wherein analyzing prior digital data includes identifying a strength of the determined relationships between the users;

wherein ranking the search results includes a plurality of rankings, each ranking according to preferences of the user of a corresponding computing device and the strength of the determined relationships; and

wherein distributing the ranked search results includes distributing the search results to each computing device with an overlay of one of the plurality of rankings corresponding to the preferences of the user of the corresponding computing device.

5. The method of claim 1, wherein the prior digital data comprises digital data selected from a group consisting of all text messages in the chat session, text messages in prior chat sessions, biometric data, calendar data, and social media data.

6. The method of claim 1, wherein the digital content is selected from a group consisting of events, activities, products, and services.

7. The method of claim 1, further comprising:

integrating computer-readable program code into a computer system comprising a processor, a computer readable memory in circuit communication with the processor, and a computer readable storage medium in circuit communication with the processor; and

wherein the processor executes program code instructions stored on the computer readable storage medium via the computer readable memory and thereby identifies a question in a text message of a chat session, analyzes prior digital data to determine a relationship between the users of the chat session, constructs search parameters for digital content external to the chat session, searches for digital content over a network, ranks the search results according to the determined relationship and displays the ranked search results in an overlay of the chat session.

8. The method of claim 7, wherein the computer-readable program code is provided as a service in a cloud environment.

9. A system for generating chat session content, comprising:

a computer processor;

a computer readable memory in circuit communication with the computer processor; and

a computer readable storage medium in circuit communication with the computer processor;

wherein the computer processor executes program instructions stored on the computer readable storage medium via the computer readable memory and thereby;

identifies a question in a text message of a chat session between a plurality of computing devices, wherein each of the plurality of computing devices includes an identifier of a user of a corresponding computing device in the text message;

analyzes digital data to determine a relationship between the users of the plurality of computing devices;

constructs search parameters for digital content external to the chat session according to the identified question and determined relationship;

searches for the digital content over a network according to the constructed search parameters to obtain search results;

ranks the search results according to the determined relationship; and

distributes the ranked search results according to the determined relationship to at least one of the plurality of computing devices in an overlay of the chat session.

10. The system of claim 9, wherein the processor executes program instructions stored on the computer readable storage medium via the computer readable memory and thereby:

analyzes text messages of the chat session to determine a sentiment value; and

refines the search parameters for the digital content as a function of the determined sentiment value.

11. The system of claim 9, wherein the processor executes program instructions stored on the computer readable storage medium via the computer readable memory and thereby:

identifies a decision maker from the users of the plurality of plurality of computing devices and a strength of the determined relationships between the users;

ranks the search results according to preferences of the decision maker and the strength of the determined relationships; and

distributes the search results to the computing device of the decision maker.

12. The system of claim 9, wherein the processor executes program instructions stored on the computer readable storage medium via the computer readable memory and thereby:

ranks the search results with a plurality of rankings, each ranking according to preferences of the user of a corresponding computing device and the strength of the determined relationships; and

distributes the search results to each computing device with an overlay of one of the plurality of rankings corresponding to the preferences of the user of the corresponding computing device.

13. The system of claim 9, wherein the prior digital data comprises digital data selected from a group consisting of all text messages in the chat session, text messages in prior chat sessions, biometric data, calendar data, and social media data.

14. The system of claim 9, wherein the digital content is selected from a group consisting of events, activities, products, and services.

15. A computer program product for generating chat session content, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising instructions for execution by a computer processor that causes the computer processor to;

identify a question in a text message of a chat session between a plurality of computing devices, wherein each of the plurality of computing devices includes an identifier of a user of a corresponding computing device in the text message;

analyze digital data to determine a relationship between the users of the plurality of computing devices;

construct search parameters for digital content external to the chat session according to the identified question and determined relationship;

search for the digital content over a network according to the constructed search parameters to obtain search results;

rank the search results according to the determined relationship; and

distribute the ranked search results according to the determined relationship to at least one of the plurality of computing devices in an overlay of the chat session.

16. The computer program product of claim 15, wherein the instructions for execution cause the computer processor to:

analyze text messages of the chat session to determine a sentiment value; and

refine the search parameters for the digital content as a function of the determined sentiment value.

17. The computer program product of claim 16, wherein the instructions for execution cause the computer processor to:

identify a decision maker from the users of the plurality of computing devices and a strength of the determined relationships between the users;

rank the search results according to preferences of the decision maker and the strength of the determined relationships; and

distribute the search results to the computing device of the decision maker.

18. The computer program product of claim 15, wherein the instructions for execution cause the computer processor to:

rank the search results with a plurality of rankings, each ranking according to preferences of the user of a corresponding computing device and the strength of the determined relationships; and

distribute the search results to each computing device with an overlay of one of the plurality of rankings corresponding to the preferences of the user of the corresponding computing device.

19. The computer program product of claim 15, wherein the prior digital data comprises digital data selected from a group consisting of all text messages in the chat session, text messages in prior chat sessions, biometric data, calendar data, and social media data.

20. The computer program product of claim 15, wherein the digital content is selected from a group consisting of events, activities, products, and services.