Method and system for providing personalized on-location information exchange

• US 10,706,290 B2
• Filed: 10/11/2018
• Issued: 07/07/2020
• Est. Priority Date: 10/13/2017
• Status: Active Grant

• Current Assignee: Midea Group Co., Ltd
• Original Assignee: Midea Group Co., Ltd
• Inventors: Wang, Dongyan, Mani, Suresh, Yang, Mingyi, Lichteveld, Edwin
• Primary Examiner(s): Allison, Andrae S
• Application Number:
  US16/158,027
• Publication Number:
  US 20190163985A1
• Time in Patent Office: 635 Days
• Field of Search: None
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion

Abstract

A method includes: deploying a frontend system (FIES); activating input streams from on-site cameras located at a current deployment location of the FIES; in accordance with the respective input stream of a first camera, registering an inspection event of a user in association with a first sample product on display; detecting a close-proximity interaction between the user and the FIES; automatically generating a first product recommendation, including: if the inspection event meets enhanced inspection criteria, which are met when a second inspection event of the first user exists in previously stored inspection events associated with the respective first sample product, automatically adding a product-specific description of the first sample product in the first product recommendation; and otherwise, forgoing including the product-specific description of the first sample product in the first product recommendation; and providing, through the frontend information exchange system, the first product recommendation to the first user.

Claims

1. A method, comprising:

at an electronic device having one or more processors, and memory;

deploying a frontend information exchange system, wherein the frontend information exchange system provides an input user interface configured to detect one or more in-person close-proximity interactions between a user and the frontend information exchange system;

activating respective input streams from one or more on-site cameras located at a current deployment location of the frontend information exchange system, wherein each of the one or more on-site cameras is located in proximity to a respective sample product on display at the current deployment location of the frontend information exchange system;

in accordance with the respective input stream of a first camera of the one or more on-site cameras, registering a first inspection event of a first user in association with a first sample product on display at the current deployment location of the frontend information exchange system;

detecting a first in-person close-proximity interaction between the first user and the frontend information exchange system at the current deployment location of the frontend information exchange system;

in response to the first in-person close-proximity interaction between the first user and the frontend information exchange system, automatically generating a first product recommendation, including;

in accordance with a determination that the first inspection event of the first user that has been registered in association with the first sample product meets enhanced inspection criteria, wherein the enhanced inspection criteria include a criterion that is met when at least a second inspection event of the first user exists in a plurality of previously stored inspection events associated with the respective first sample product, automatically adding a product-specific description of the first sample product in the first product recommendation; and

in accordance with a determination that the first inspection event of the first user that has been registered in association with the first sample product does not meet the enhanced inspection criteria, forgoing including the product-specific description of the first sample product in the first product recommendation; and

providing, through the frontend information exchange system, the first product recommendation to the first user.

2. The method of claim 1, comprising:

for each of a plurality of sample products on display at the current deployment location of the frontend information exchange system, determining a respective inspection time that the first user is within a respective inspection zone of said each sample product in accordance with the respective input stream of one or more on-site cameras located in proximity to said each sample product; and

selecting, from the plurality of sample products, a sample product for which the first user has the longest inspection time as the first sample product.

3. The method of claim 1, including:

for each of a plurality of sample products on display at the current deployment location of the frontend information exchange system, determining whether the first user is within a respective inspection zone of said each sample product concurrently with one or more other users as a first recognized group; and

from the plurality of sample products, selecting, as the first sample product, a respective sample product of which the first user is found to be concurrently present within the respective inspection zone with the one or more other users as the first recognized group.

4. The method of claim 3, including:

for each of a plurality of sample products of which the first user is found to be concurrently present within the respective inspection zone with one or more other users as the first recognized group, calculating a respective aggregated satisfaction score for the first user and the one or more other users in the first recognized group based on analysis of the respective input streams of the one or more on-site cameras; and

selecting, from the plurality of sample products of which the first user is found to be concurrently present within the respective inspection zone, a sample product for which the first user and the one or more other users in the first recognized group has the highest aggregated satisfaction score, as the first sample product.

5. The method of claim 1, wherein providing, through the frontend information exchange system, the first product recommendation to the first user includes:

providing at least one natural language statement that includes one or more key words each describing a respective factor used to generate the first product recommendation.

6. The method of claim 1, including:

determining a set of selection factors that are relevant to the first user;

identifying two or more alternative models for generating product recommendations for the first user based on the set of selection factors that are determined to be relevant to the first user, wherein the first product recommendation is generated based on a first model of the two or more alternative models;

after providing the first product recommendation to the first user, detecting a second in-person close-proximity interaction between the first user and the frontend information exchange system at the current deployment location of the frontend information exchange system, wherein the second in-person close-proximity includes a rejection of the first product recommendation; and

in accordance with a determination that the second in-person close-proximity interaction between the first user and the frontend information exchange system includes a rejection of the first product recommendation, automatically generating a second product recommendation using a second model of the two or more alternative models based on the set of selection factors that are determined to be relevant to the first user.

7. The method of claim 6, including:

in accordance with a determination that the second in-person close-proximity interaction between the first user and the frontend information exchange system includes a rejection of the first product recommendation, analyzing the second in-person close-proximity interaction to determine one or more additional factors that are relevant to the first user that modifies or adds to the set of selection factors; and

automatically generating the second product recommendation using the second model based on the one or more additional factors in combination with the set of selection factors that are determined to be relevant to the first user.

8. A system, comprising:

one or more processors; and

memory storing instructions which when executed by one or more processors, cause the processors to perform operations comprising;

deploying a frontend information exchange system, wherein the frontend information exchange system provides an input user interface configured to detect one or more in-person close-proximity interactions between a user and the frontend information exchange system;

activating respective input streams from one or more on-site cameras located at a current deployment location of the frontend information exchange system, wherein each of the one or more on-site cameras is located in proximity to a respective sample product on display at the current deployment location of the frontend information exchange system;

in accordance with the respective input stream of a first camera of the one or more on-site cameras, registering a first inspection event of a first user in association with a first sample product on display at the current deployment location of the frontend information exchange system;

detecting a first in-person close-proximity interaction between the first user and the frontend information exchange system at the current deployment location of the frontend information exchange system;

in response to the first in-person close-proximity interaction between the first user and the frontend information exchange system, automatically generating a first product recommendation, including;

in accordance with a determination that the first inspection event of the first user that has been registered in association with the first sample product meets enhanced inspection criteria, wherein the enhanced inspection criteria include a criterion that is met when at least a second inspection event of the first user exists in a plurality of previously stored inspection events associated with the respective first sample product, automatically adding a product-specific description of the first sample product in the first product recommendation; and

in accordance with a determination that the first inspection event of the first user that has been registered in association with the first sample product does not meet the enhanced inspection criteria, forgoing including the product-specific description of the first sample product in the first product recommendation; and

providing, through the frontend information exchange system, the first product recommendation to the first user.

9. The system of claim 8, wherein the operations include:

for each of a plurality of sample products on display at the current deployment location of the frontend information exchange system, determining a respective inspection time that the first user is within a respective inspection zone of said each sample product in accordance with the respective input stream of one or more on-site cameras located in proximity to said each sample product; and

selecting, from the plurality of sample products, a sample product for which the first user has the longest inspection time as the first sample product.

10. The system of claim 8, wherein the operations include:

for each of a plurality of sample products on display at the current deployment location of the frontend information exchange system, determining whether the first user is within a respective inspection zone of said each sample product concurrently with one or more other users as a first recognized group; and

from the plurality of sample products, selecting, as the first sample product, a respective sample product of which the first user is found to be concurrently present within the respective inspection zone with the one or more other users as the first recognized group.

11. The system of claim 10, wherein the operations include:

for each of a plurality of sample products of which the first user is found to be concurrently present within the respective inspection zone with one or more other users as the first recognized group, calculating a respective aggregated satisfaction score for the first user and the one or more other users in the first recognized group based on analysis of the respective input streams of the one or more on-site cameras; and

selecting, from the plurality of sample products of which the first user is found to be concurrently present within the respective inspection zone, a sample product for which the first user and the one or more other users in the first recognized group has the highest aggregated satisfaction score, as the first sample product.

12. The system of claim 10, wherein providing, through the frontend information exchange system, the first product recommendation to the first user includes:

providing at least one natural language statement that includes one or more key words each describing a respective factor used to generate the first product recommendation.

13. The system of claim 8, wherein the operations include:

determining a set of selection factors that are relevant to the first user;

identifying two or more alternative models for generating product recommendations for the first user based on the set of selection factors that are determined to be relevant to the first user, wherein the first product recommendation is generated based on a first model of the two or more alternative models;

after providing the first product recommendation to the first user, detecting a second in-person close-proximity interaction between the first user and the frontend information exchange system at the current deployment location of the frontend information exchange system, wherein the second in-person close-proximity includes a rejection of the first product recommendation; and

in accordance with a determination that the second in-person close-proximity interaction between the first user and the frontend information exchange system includes a rejection of the first product recommendation, automatically generating a second product recommendation using a second model of the two or more alternative models based on the set of selection factors that are determined to be relevant to the first user.

14. The system of claim 13, wherein the operations include:

in accordance with a determination that the second in-person close-proximity interaction between the first user and the frontend information exchange system includes a rejection of the first product recommendation, analyzing the second in-person close-proximity interaction to determine one or more additional factors that are relevant to the first user that modifies or adds to the set of selection factors; and

automatically generating the second product recommendation using the second model based on the one or more additional factors in combination with the set of selection factors that are determined to be relevant to the first user.

15. A non-transitory computer-readable storage medium storing instructions, the instructions, when executed by one or more processors, cause the processors to perform operations comprising:

deploying a frontend information exchange system, wherein the frontend information exchange system provides an input user interface configured to detect one or more in-person close-proximity interactions between a user and the frontend information exchange system;

activating respective input streams from one or more on-site cameras located at a current deployment location of the frontend information exchange system, wherein each of the one or more on-site cameras is located in proximity to a respective sample product on display at the current deployment location of the frontend information exchange system;

in accordance with the respective input stream of a first camera of the one or more on-site cameras, registering a first inspection event of a first user in association with a first sample product on display at the current deployment location of the frontend information exchange system;

detecting a first in-person close-proximity interaction between the first user and the frontend information exchange system at the current deployment location of the frontend information exchange system;

in response to the first in-person close-proximity interaction between the first user and the frontend information exchange system, automatically generating a first product recommendation, including;

in accordance with a determination that the first inspection event of the first user that has been registered in association with the first sample product meets enhanced inspection criteria, wherein the enhanced inspection criteria include a criterion that is met when at least a second inspection event of the first user exists in a plurality of previously stored inspection events associated with the respective first sample product, automatically adding a product-specific description of the first sample product in the first product recommendation; and

in accordance with a determination that the first inspection event of the first user that has been registered in association with the first sample product does not meet the enhanced inspection criteria, forgoing including the product-specific description of the first sample product in the first product recommendation; and

providing, through the frontend information exchange system, the first product recommendation to the first user.

16. The computer-readable storage medium of claim 15, wherein the operations include:

for each of a plurality of sample products on display at the current deployment location of the frontend information exchange system, determining a respective inspection time that the first user is within a respective inspection zone of said each sample product in accordance with the respective input stream of one or more on-site cameras located in proximity to said each sample product; and

selecting, from the plurality of sample products, a sample product for which the first user has the longest inspection time as the first sample product.

17. The computer-readable storage medium of claim 15, wherein the operations include:

for each of a plurality of sample products on display at the current deployment location of the frontend information exchange system, determining whether the first user is within a respective inspection zone of said each sample product concurrently with one or more other users as a first recognized group; and

from the plurality of sample products, selecting, as the first sample product, a respective sample product of which the first user is found to be concurrently present within the respective inspection zone with the one or more other users as the first recognized group.

18. The computer-readable storage medium of claim 17, wherein the operations include:

for each of a plurality of sample products of which the first user is found to be concurrently present within the respective inspection zone with one or more other users as the first recognized group, calculating a respective aggregated satisfaction score for the first user and the one or more other users in the first recognized group based on analysis of the respective input streams of the one or more on-site cameras; and

selecting, from the plurality of sample products of which the first user is found to be concurrently present within the respective inspection zone, a sample product for which the first user and the one or more other users in the first recognized group has the highest aggregated satisfaction score, as the first sample product.

19. The computer-readable storage medium of claim 18, wherein providing, through the frontend information exchange system, the first product recommendation to the first user includes:

providing at least one natural language statement that includes one or more key words each describing a respective factor used to generate the first product recommendation.

20. The computer-readable storage medium of claim 15, wherein the operations include:

determining a set of selection factors that are relevant to the first user;

identifying two or more alternative models for generating product recommendations for the first user based on the set of selection factors that are determined to be relevant to the first user, wherein the first product recommendation is generated based on a first model of the two or more alternative models;

after providing the first product recommendation to the first user, detecting a second in-person close-proximity interaction between the first user and the frontend information exchange system at the current deployment location of the frontend information exchange system, wherein the second in-person close-proximity includes a rejection of the first product recommendation; and

in accordance with a determination that the second in-person close-proximity interaction between the first user and the frontend information exchange system includes a rejection of the first product recommendation, automatically generating a second product recommendation using a second model of the two or more alternative models based on the set of selection factors that are determined to be relevant to the first user.