Crowd assisted query system

• US 10,452,688 B2
• Filed: 11/08/2016
• Issued: 10/22/2019
• Est. Priority Date: 11/08/2016
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Heine, Luke Richard-Ivar, Kiapour, Mohammadhadi
• Primary Examiner(s): Morrison, Jay A
• Application Number:
  US15/345,627
• Publication Number:
  US 20180129724A1
• Time in Patent Office: 1,078 Days
• CPC Class Codes: G06F 16/2423 Interactive query statement specification based on a database schema
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/903 Querying for retrieval from the web G06F16/953
• CPC Class Codes: G06F 16/9032 Query formulation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/045 Combinations of networks

Abstract

Aspects of the present disclosure relate to a network-based crowd assisted query system that includes a client device in communication with an application server executing the crowd assisted query system over a network. For example, the crowd assisted query system may be or include a group of one or more server machines. Users of the crowd assisted query system are presented with a graphical user interface (GUI) configured to receive queries that include data objects, wherein the data objects include representations of unidentified items of interest to the user. The data objects may include media content, such as graphical images as well as audio data, and in some example embodiments may further include text data describing the unidentified items.

Claims

1. A system comprising:

one or more processors; and

a non-transitory memory storing instructions that configure the one or more processors to perform operations comprising;

receiving, from a first client device, a query that includes a request for an identification of an unidentified item, the request including a data object that comprises a text string;

assigning the data object to an item category within a data repository based on the text string of the data object;

receiving, from a second client device, an identification of the item category;

causing display of a representation of the request within a graphical user interface (GUI) at the second client device responsive to the identification of the item category, the GUI comprising a display of a set of graphical elements representative of requests associated with the item category within the data repository;

receiving, from the second client device, an input that selects the representation of the request, the input including a description suggestion to be associated with the data object within the data repository; and

training an artificial intelligence (AI) module to identify the unidentified item based on the description suggestion associated with the data object within data repository.

2. The system of claim 1, wherein the data object further comprises image data.

3. The system of claim 1, wherein the receiving the query includes:

receiving the query as a submission through the GUI, wherein the submission includes the data attributes of the data object, and wherein the data attributes include an indication of the item category of the unidentified item.

4. The system of claim 1, wherein the description suggestion is a first description suggestion, the machine learning database includes a set of description suggestions associated with the data object, and the instructions cause the system to perform operations further comprising:

ranking the first description suggestion among the set of description suggestions associated with the data object based on the data attributes; and

training the AI module based on the data repository and the ranking.

5. The system of claim 4, wherein the receiving the description suggestion to be applied to the data object includes:

retrieving user profile data associated with a user of the second client device;

determining a reliability score of the description suggestion based on the user profile data of the user; and

wherein the ranking the first description suggestion is based on the reliability score.

6. The system of claim 4, wherein the instructions cause the system to perform operations further comprising:

receiving a selection of the first description suggestion from the first client device; and

wherein the ranking the first description suggestion is based on the selection from the first client device.

7. The system of claim 1, wherein the receiving the data object from the first client device includes:

receiving a reward value from the first client device, the reward value offered for an identification of the unidentified item of the data object based on the description suggestion; and

wherein the instructions cause the system to perform operations further comprising;

receiving a selection of the description suggestion from the first client device;

identifying the unidentified item based on the selection of the description suggestion; and

awarding the reward value to the second client device in response to the identifying the unidentified item.

8. The system of claim 7, wherein the receiving the selection of the description suggestion includes:

receiving a search request from the first client device, wherein the search requests includes the description suggestion.

9. The system of claim 1, wherein the data object is a first data object and the instructions cause the system to perform operations further comprising:

receiving a general query from the first client device, the query including a second data object;

determining a specific query based on the general query, the second data object, and the A.I. module; and

retrieving a set of search results based on the specific query.

10. The system of claim 1, wherein the item category comprises a set of data objects, wherein the set of data objects have at least some of the data attributes of the data object.

11. A method comprising:

receiving, from a first client device, a query that includes a request for an identification of an unidentified item, the request including a data object that comprises a text string;

assigning the data object to an item category within a data repository based on the text string of the data object;

receiving, from a second client device, an identification of the item category;

causing display of a representation of the request within a graphical user interface (GUI) at the second client device responsive to the identification of the item category, the GUI comprising a display of a set of graphical elements representative of requests associated with the item category within the data repository;

receiving, from the second client device, an input that selects the representation of the request, the input including a description suggestion to be associated with the data object within the data repository; and

training an artificial intelligence (AI) module to identify the unidentified item based on the description suggestion associated with the data object within the data repository.

12. The method of claim 11, wherein the data object further comprises image data.

13. The method of claim 11, wherein the receiving the query includes:

receiving the query as a submission through the GUI, wherein the submission includes the data attributes of the data object, and wherein the data attributes include an indication of the item category of the unidentified item.

14. The method of claim 11, wherein the description suggestion is a first description suggestion, the machine learning database includes a set of description suggestions associated with the data object, and the method further comprises:

ranking the first description suggestion among the set of description suggestions associated with the data object based on the data attributes; and

training the AI module based on the data repository and the ranking.

15. The method of claim 14, wherein the receiving the description suggestion to be applied to the data object includes:

retrieving user profile data associated with a user of the second client device;

determining a reliability score of the description suggestion based on the user profile data of the user; and

wherein the ranking the first description suggestion is based on the reliability score.

16. The method of claim 14, wherein the method further comprises:

receiving a selection of the description suggestion from the first client device; and

wherein the ranking the first description suggestion is based on the selection by the first client device.

17. The method of claim 11, wherein the receiving the data object from the first client device includes:

receiving a reward value from the first client device, the reward value offered for an identification of the unidentified item of the data object based on the description suggestion; and

wherein the method further comprises;

receiving a selection of the description suggestion from the first client device;

identifying the unidentified item based on the selection of the description suggestion; and

awarding the reward value to the second client device in response to the identifying the unidentified item.

18. The method of claim 17, wherein the receiving the selection of the description suggestion includes:

receiving a search request from the first client device, wherein the search requests includes the description suggestion.

19. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

receiving, from a first client device, a query that includes a request for an identification of an unidentified item, the request including a data object that comprises a text string;

assigning the data object to an item category within a data repository based on the text string of the data object;

receiving, from a second client device, an identification of the item category;

causing display of a representation of the request within a graphical user interface (GUI) at the second client device responsive to the identification of the item category, the GUI comprising a display of a set of graphical elements representative of requests associated with the item category within the data repository;

receiving, from the second client device, an input that selects the representation of the request, the input including a description suggestion to be associated with the data object within the data repository; and

training an artificial intelligence (AI) module to identify the unidentified item based on the description suggestion associated with the data object within the data repository.

20. The non-transitory machine-readable storage medium of claim 19, wherein the data object further comprises image data.