Computerized systems and methods for building knowledge bases using context clouds

• US 10,102,291 B1
• Filed: 07/06/2015
• Issued: 10/16/2018
• Est. Priority Date: 07/06/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Steiger, Sebastian, Semturs, Christopher, Grimm, Henrik, Vandevenne, Lode, Sinopalnikov, Danila, Scharli, Nathanael Martin, Lecomte, David, Lyashuk, Alexander
• Primary Examiner(s): Robinson, Greta L
• Application Number:
  US14/792,583
• Time in Patent Office: 1,198 Days
• Field of Search: 707603, 707724, 707727, 707729, 707730, 707750, 707797, 707798, 707800, 707802, 707805, 707811, 707825, 707829, 707830
• CPC Class Codes: G06F 16/289 Object oriented databases
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/953 Querying, e.g. by the use of web search engines
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Computer-implemented systems and methods are disclosed for building knowledge bases, such as knowledge graphs, using context clouds. According to certain embodiments, a target object is identified in a portion of unstructured or semi-structured data in a target document, which does not conform to a predefined structure or pattern. A knowledge server may build a context cloud for the target document. The knowledge server may analyze one or more other documents stored in a networked database, to identify candidate documents that may include a meaning or relationship associated with the target object. The knowledge server may analyze one or more context clouds for the candidate documents to determine a meaning or relationship of the target object based on objects in the candidate document(s). The knowledge server may associate the determined meanings and/or relationships with the target object in the target document, thereby creating a new portion of a knowledge graph.

Claims

1. A computer-implemented system for generating and utilizing knowledge graphs, comprising:

a memory device that stores a set of instructions; and

at least one processor that executes the instructions to;

detect a target data object in a document on the Internet;

detect a second data object, based on the second data object being proximate to the target data object in the document;

identify a third data object associated with the second data object, based on a frequency of co-occurrence of the second data object and the third data object in one or more stored occurrence lists;

determine a relationship associated with the target data object based on the identified third data object;

generate, in a knowledge graph stored in a database, a first entry including the target data object, and the relationship between the target data object and an additional data object in the document;

receive a query;

identify that the generated first entry from the knowledge graph is responsive to the query;

generate a search result based on the first entry from the knowledge graph; and

transmit the search result for presentation in response to the query.

2. The computer-implemented system of claim 1, wherein at least one of the first data object, the second data object, or the third data object is an n-gram.

3. The computer-implemented system of claim 1, wherein the at least one processor is further configured to:

identify a fourth data object proximate to the first data object;

identify a fifth data object associated with the fourth data object based on one or more stored occurrence lists identifying a second predefined relationship between the fourth data object and the fifth data object; and

update the first entry in the knowledge graph to include at least one of the second predefined relationship or the fifth data object.

4. The computer-implemented system of claim 1, wherein the at least one processor is further configured to:

determine, based on the first entry, a context of the first data object.

5. The computer-implemented system of claim 1, wherein the first data object is adjacent to the second data object.

6. A computer-implemented method for generating and utilizing knowledge graphs, comprising:

detecting, by at least one processor, a target data object in a document on the Internet;

detecting, by the at least one processor, a second data object, based on the second data object being proximate to the target data object in the document;

identifying, by the at least one processor, a third data object associated with the second data object, based on a frequency of co-occurrence of the second data object and the third data object in one or more stored occurrence lists;

determining a relationship associated with the target data object based on the identified third data object;

generating in a knowledge graph stored in a database, a first entry including the target data object, and the relationship between the target data object and an additional data object in the document;

receiving a query;

identifying that the generated first entry from the knowledge graph is responsive to the query;

generating a search result based on the first entry from the knowledge graph; and

transmitting the search result for presentation in response to the query.

7. The computer-implemented method of claim 6, wherein at least one of the first data object, the second data object, or the third data object is an n-gram.

8. The computer-implemented method of claim 6, further comprising:

identifying a fourth data object proximate to the first data object;

identifying a fifth data object associated with the fourth data object based on one or more stored occurrence lists identifying a second predefined relationship between the fourth data object and the fifth data object; and

updating the first entry in the knowledge graph to include at least one of the second predefined relationship or the fifth data object.

9. The computer-implemented method of claim 6, further comprising:

determining, based on the first entry, a context of the first data object.

10. The computer-implemented method of claim 6, wherein the first data object is adjacent to the second data object.

11. A non-transitory computer readable medium storing instructions which, when executed, cause at least one processor to perform a method for generating knowledge graphs, the method comprising:

detecting a target data object in a document on the Internet;

detecting a second data object, based on the second data object being proximate to the target data object in the document;

identifying a third data object associated with the second data object, based on a frequency of co-occurrence of the second data object and the third data object in one or more stored occurrence lists;

determining a relationship associated with the target data object based on the identified third data object;

generating in a knowledge graph stored in a database, a first entry including the target data object, and the relationship between the target data object and an additional data object in the document;

receiving a query;

identifying that the generated first entry from the knowledge graph is responsive to the query;

generating a search result based on the first entry from the knowledge graph; and

transmitting the search result for presentation in response to the query.

12. The method of claim 11, wherein at least one of the first data object, the second data object, or the third data object is an n-gram.

13. The method of claim 11, further comprising:

identifying a fourth data object proximate to the first data object;

identifying a fifth data object associated with the fourth data object based on one or more stored occurrence lists identifying a second predefined relationship between the fourth data object and the fifth data object; and

updating the first entry in the knowledge graph to include at least one of the second predefined relationship or the fifth data object.

14. The method of claim 11, further comprising:

determining, based on the first entry, a context of the first data object.

15. The method of claim 11, wherein the first data object is adjacent to the second data object.