Context based online advertising

• US 8,326,630 B2
• Filed: 08/18/2008
• Issued: 12/04/2012
• Est. Priority Date: 08/18/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Chandrasekar, Raman, Bai, Tian, Chang, Eric J., Tsang, Michael
• Primary Examiner(s): RIDER, JUSTIN W
• Application Number:
  US12/193,657
• Publication Number:
  US 20100042403A1
• Time in Patent Office: 1,569 Days
• Field of Search: 704/9, 704/270, 704/270.1
• US Class Current: 704/270
• CPC Class Codes: G06F 40/237 Lexical tools
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A software and/or hardware facility for inferring user context and delivering advertisements, such as coupons, using natural language and/or sentiment analysis is disclosed. The facility may infer context information based on a user'"'"'s emotional state, attitude, needs, or intent from the user'"'"'s interaction with or through a mobile device. The facility may then determine whether it is appropriate to deliver an advertisement to the user and select an advertisement for delivery. The facility may also determine an appropriate expiration time and/or discount amount for the advertisement.

Claims

1. A method for managing online advertising, comprising:

determining a mobile device characteristic based on a mobile device context of a mobile device;

determining a user characteristic based at least in part on a user context that includes natural language information based on a user interaction with a mobile device and sentiment information based on the user interaction with the mobile device, the sentiment information including a mood, emotional state or attitude of a user of the mobile device;

determining an advertisement based at least in part on the determined mobile device characteristic and the determined user characteristic;

determining a time, based at least in part on the mood, the emotional state or the attitude, at which the user is expected to desire, need, and/or be predisposed to have a positive response to the advertisement; and

selectively delivering the advertisement at the time to the user of the mobile device.

2. The method of claim 1, further comprising:

extracting the natural language information from the user interaction with the mobile device; and

extracting the sentiment information from the user interaction with the mobile device.

3. The method of claim 1, wherein determining the user characteristic includes:

receiving user speech data; and

extracting at least one of the natural language information or the sentiment information from the received user speech data.

4. The method of claim 1, wherein determining the advertisement includes selecting the advertisement from multiple advertisements based on the determined mobile device characteristic and the determined user characteristic.

5. The method of claim 1, wherein selectively delivering the advertisement includes:

determining at least one of an advertisement expiration time or an advertisement discount amount based on the determined mobile device characteristic and the determined user characteristic.

6. The method of claim 1, wherein determining the mobile device characteristic further includes:

determining ancillary information including at least one of a location of the mobile device, a speed of the mobile device, or a time at the mobile device, and wherein the mobile device context is further based on the determined ancillary information.

7. The method of claim 1, wherein determining the user characteristic further includes:

determining environmental information including at least one of ambient temperature information, body temperature information, heart rate information, humidity information, pressure information, weather information, traffic condition information, or information relating to proximity of the mobile device to other mobile devices, and wherein the user context is further based on the determined environmental information.

8. The method of claim 1, wherein selectively delivering the advertisement is further based on an advertisement effectiveness characteristic.

9. The method of claim 8, wherein the advertisement effectiveness characteristic includes at least one of a redemption rate, response rate, discount amount, community-based feedback, advertiser popularity, product popularity, or service popularity of the selectively delivered advertisement.

10. The method of claim 8, further comprising:

receiving user feedback including a response from a user of the mobile device corresponding to the selectively delivered advertisement;

determining the advertisement effectiveness characteristic based on the received user feedback; and

selectively delivering another advertisement based on the determined advertisement effectiveness.

11. The method of claim 1, further comprising:

estimating a demand for at least one of a product or service based on the selectively delivered advertisement.

12. A processor-readable storage memory containing instructions for executing operations for managing online advertising, the operations comprising:

determining a mobile device characteristic based on a mobile device context of a mobile device, including;

determining ancillary information including at least one of a location of the mobile device, a speed of the mobile device, or a time at the mobile device;

determining a user characteristic based on a user context that includes at least one of natural language information based on a user interaction with a mobile device or sentiment information based at least in part on the user interaction with the mobile device, the user characteristic including a mood, emotional state or attitude of a user of the mobile device;

selecting an advertisement from multiple advertisements based on the determined mobile device characteristic and the determined user characteristic;

determining a time, based at least in part on the mood, the emotional state or the attitude, at which the user is expected to desire, need, and/or be predisposed to have a positive response to the advertisement;

selectively delivering the advertisement at the time to the mobile device;

receiving user feedback including a response from a user of the mobile device corresponding to the selectively delivered advertisement;

determining the advertisement effectiveness characteristic based on the received user feedback; and

selectively delivering another advertisement based on the determined advertisement effectiveness.

13. The processor-readable storage memory of claim 12, wherein determining the user characteristic includes:

receiving user speech data; and

extracting at least one of the natural language information or the sentiment information from the received user speech data.

14. The processor-readable storage memory of claim 12, wherein the method further comprises:

estimating a demand for at least one of a product or service based on the selectively delivered advertisement.

15. The processor-readable storage memory of claim 12, wherein determining the user characteristics further includes:

determining environmental information including at least one of ambient temperature information, body temperature information, heart rate information, humidity information, pressure information, weather information, traffic condition information, or information relating to proximity of the mobile device to other mobile devices, and wherein the user context is further based on the determined environmental information.

16. The processor-readable storage memory of claim 12, wherein the method further comprises determining at least one of an advertisement expiration time or an advertisement discount amount based on the determined mobile device characteristic and the determined user characteristic.

17. A computing system configured to manage online advertising, comprising:

a memory;

a first module configured, when executed in the memory, to determine a mobile device characteristic based at least in part on a mobile device context of a mobile device;

a second module configured, when executed in the memory, to determine a user characteristic of a user of the mobile device based at least in part on a user context that includes at least one of natural language information based at least in part on a user interaction with a mobile device or sentiment information based on the user interaction with the mobile device, the natural language information including at least one of speech transmitted or speech received by the mobile device during a telephonic conversation; and

a third module configured, when executed in the memory, to selectively deliver an advertisement to the user at the mobile device and to the user at a client device that differs from the mobile device based at least in part on the determined mobile device characteristic and the determined user characteristic.

18. The computing system of claim 17, wherein the second module is further configured, when executed in the memory, to:

receive user speech data; and

extract at least one of the natural language information or the sentiment information from the received user speech data.

19. The computing system of claim 17, wherein the third module is further configured, when executed in the memory, to:

select the advertisement from multiple advertisements based on the determined mobile device characteristic and the determined user characteristic;

determine at least one of an advertisement expiration time or an advertisement discount amount based on the determined mobile device characteristic and the determined user characteristic; and

select a time at which to deliver the selected advertisement.

20. The computing system of claim 17, further comprising:

a fourth module configured, when executed in the memory, to receive user feedback corresponding to the selectively delivered advertisement;

a fifth module configured, when executed in the memory, to determine the advertisement effectiveness characteristic based on the received user feedback; and

a sixth module configured, when executed in the memory, to selectively deliver another advertisement based on the determined advertisement effectiveness.