Computing a group of related companies for financial information systems

• US 7,873,595 B2
• Filed: 02/24/2006
• Issued: 01/18/2011
• Est. Priority Date: 02/24/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Mohan, Bharath Kumar, Narendran, Arungundram C., Loiwal, Navneet, Singh, Amardeep
• Primary Examiner(s): Jalil; Neveen Abel
• Assistant Examiner(s): Hicks; Michael J
• Application Number:
  US11/361,854
• Publication Number:
  US 20070203720A1
• Time in Patent Office: 1,789 Days
• Field of Search: 707/104.1
• US Class Current: 707/603
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Abstract

Techniques are disclosed by which users looking for financial information about publicly traded or private companies may richly and interactively navigate both pricing and material news information about those companies. The techniques facilitate and encourage the user'"'"'s use and understanding of financial information presented. Related company information can also be provided to the user, where related companies are organized by hierarchal categories for a meaningful display.

Claims

1. A method, performed by a computer system, for determining whether a target company and a second company are related, the method comprising:

locating a co-occurrence of a target company name of the target company and a second company name of the second company in a first set of data sources;

identifying a business relationship between the target company and the second company based upon a relationship indicator appearing with the co-occurrence of the target company name and the second company name;

verifying the business relationship using a second set of data sources based upon the target company and the second company having in common at least two of the following features;

an industry type, a geographic location, a type of product provided, and a type of service provided;

determining at least one of a plurality of hierarchical business categories to which the target company and the second company belong;

determining a relationship strength value based on the relationship indicator, the second set of data sources and the determined hierarchical business category, the relationship strength value increasing or decreasing based on a depth of the determined business category in hierarchy; and

identifying the second company as related to the target company when the relationship strength value is over a threshold.

2. The method of claim 1 further comprising:

providing for display the second company as a related company in response to a user request for financial information about the target company.

3. The method of claim 1 wherein locating the co-occurrence further comprises:

identifying proper nouns in the first set of data sources; and

identifying company names included in the identified proper nouns.

4. The method of claim 1 wherein locating the co-occurrence further comprises:

identifying known name variations of the target company;

identifying known aliases of the target company; and

disambiguating ambiguous terms based on co-occurrence context.

5. The method of claim 1 wherein identifying the business relationship further comprises:

determining an overall score for the co-occurrence of the target company name and the second company name; and

indicating the business relationship between the target company and the second company if the overall score satisfies a relationship indicator threshold.

6. The method of claim 5 wherein the overall score is based upon the following:

a number of companies indicated in the co-occurrence;

a location in a document including the co-occurrence of the target company name and the second company;

a source of the document including the co-occurrence of the target company name and the second company;

the features that the target company and the second company have in common; and

a pagerank associated with the document including the co-occurrence of the target company name and the secondary second company.

7. The method of claim 5 wherein verifying the business relationship further comprises:

adjusting the overall score for the business relationship, based on one or more supplemental relationship indicators; and

verifying the business relationship if the adjusted overall score satisfies a verified relationship indicator threshold.

8. The method of claim 1 wherein verifying the business relationship further comprises:

determining an overall score for the business relationship, based on one or more relationship indicators; and

verifying the business relationship if the overall score satisfies a relationship indicator threshold.

9. The method of claim 8 wherein the overall score is based upon one or more of the following:

at least one of competing products and services provided by the target company and the second company;

an overlap of at least one of industries, sectors, and geographies in which the target company and the second company operate;

a correlation between movements of stock prices of the target company and the second company;

a frequency of the co-occurrence of the target company name and the second company name that exceeds a co-occurrence frequency threshold;

co-occurrences of the target company name and the second company name in aggregated user website navigation histories; and

co-occurrences of the target company name and the second company name in aggregated user stock portfolio data.

10. The method of claim 1, further comprising:

identifying a third company name of a third company as related to the target company name when

the third company name co-occurs with the target company name in the first set of data sources,

a third relationship is identified between the target company name and the third company name based upon a third relationship indicator appearing with co-occurrence of the third company name and the target company name,

the third relationship is verified using the second set of sources based upon the target company and the third company having in common at least two of the following features;

an industry type, a geographic location, a type of product provided, and a type of service provided, and

the third company name belongs to at least one of a plurality of hierarchical business categories to which the target company name belongs;

determining a first overall score for the relationship and a second overall score for the third relationship, based on the relationship indicator and the third relationship indicator; and

displaying the second company and the third company in an order based on the first overall score and the second overall score.

11. A machine-readable medium encoded with instructions, that when executed by one or more processors, cause the processor to carry out a process for determining whether a target company and a second company are related, the process comprising:

locating a co-occurrence of a target company name of the target company and a second company name of the second company in a first set of data sources;

identifying a business relationship between the target company and the second company based upon a relationship indicator appearing with the co-occurrence of the target company name and the second company name;

verifying the business relationship using a second set of data sources based upon the target company and the second company having in common at least two of the following features;

an industry type, a geographic location, a type of product provided, and a type of service provided;

determining at least one of a plurality of hierarchical business categories to which the target company and the second company belong;

determining a relationship strength value based on the relationship indicator, the second set of data sources and the determined hierarchical business category, the relationship strength value increasing or decreasing based on a depth of the determined business category in hierarchy; and

identifying the second company as related to the target company when the relationship strength value is over a threshold.

12. The machine-readable medium of claim 11, the process further comprising:

providing for display the second company as related company in response to a user request for financial information about the target company.

13. The machine-readable medium of claim 11 wherein locating the co-occurrence further comprises:

identifying proper nouns in the first set of data sources; and

identifying company names included in the identified proper nouns.

14. The machine-readable medium of claim 11 wherein locating the co-occurrence further comprises:

identifying known name variations of the target company;

identifying known aliases of the target company; and

disambiguating ambiguous terms based on co-occurrence context.

15. The machine-readable medium of claim 11 wherein identifying the business relationship further comprises:

determining an overall score for the co-occurrence of the target company and the second company, based on the relationship indicator appearing in the co-occurrence; and

indicating the business relationship between the target company and the second company if the overall score satisfies a relationship indicator threshold.

16. The machine-readable medium of claim 15 wherein the overall score is based upon the following:

a number of companies indicated in the co-occurrence; and

a location in a document including the co-occurrence of the target company name and the secondary company.

17. The machine-readable medium of claim 15 wherein the overall score is based upon the following:

a source of the document including the co-occurrence of the target company name and the second company.

18. The machine-readable medium of claim 15 wherein the overall score is based upon the following:

a pagerank associated with a document including the co-occurrence of the target company name and the secondary company.

19. The machine-readable medium of claim 15 wherein verifying the business relationship further comprises:

adjusting the overall score for the business relationship, based on one or more supplemental relationship indicators; and

verifying the business relationship if the adjusted overall score satisfies a verified relationship indicator threshold.

20. The machine-readable medium of claim 11 wherein verifying the business relationship further comprises:

determining an overall score for the business relationship, based on one or more relationship indicators; and

verifying the business relationship if the overall score satisfies a relationship indicator threshold.

21. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

business, geography, or stock exchange of the target company and the second company.

22. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

at least one of competing products and services provided by the target company and the second company.

23. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

disparate treatment of the target company and the second company in a document.

24. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

presence of the target company and the second company in one or more similar hierarchical categories.

25. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

the target company and the second company are direct competitors.

26. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

an overlap of at least one of industries, sectors, and geographies in which the target company and the second company operate.

27. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

a correlation between movements of stock prices of the target company and the second company.

28. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

a frequency of the co-occurrence of the target company name and the second company name that exceeds a co-occurrence frequency threshold.

29. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

overlap of products of the target company and the second company.

30. The machine-readable medium of claim 20 wherein the overall score is based upon the following:

co-occurrences of the target company name and the second company name in aggregated user website navigation histories.

31. The machine-readable medium of claim 20 further comprising:

identifying a third company name of a third company as related to the target company name when

the third company name co-occurs with the target company name in the first set of data sources,

a third relationship is identified between the target company name and the third company name based upon a third relationship indicator appearing with co-occurrence of the third company name and the target company name,

the third relationship is verified using the second set of sources based upon the target company and the third company having in common at least two of the following features;

an industry type, a geographic location, a type of product provided, and a type of service provided, and

the third company name belongs to at least one of a plurality of hierarchical business categories to which the target company name belongs;

determining a first overall score for the relationship and a second overall score for the third relationship, based on the relationship indicator and the third relationship indicator; and

displaying the second company and the third company in an order based on the first overall score and the second overall score.

32. A system for determining whether a target company and a second company are related, comprising:

a computer processor for executing programmed instructions;

a program memory, coupled to the processor, for storing program instruction steps for execution by the processor;

a co-occurrence mining module, executable by the processor in accordance with program instructions in the program memory, for locating a co-occurrence of a target company name of the target company and a second company name of the second company in a first set of data sources;

a relationship identifier module, executable by the processor in accordance with program instructions in the program memory, for identifying a business relationship between the target company and the second company based upon a relationship indicator appearing with the co-occurrence of the target company name and the second company name;

a relationship verifier module, executable by the processor in accordance with program instructions in the program memory, for verifying the business relationship using a second set of data sources based upon the target company and the second company having in common at least two of the following features;

an industry type, a geographic location, a type of product provided, and a type of service provided;

a hierarchical category identifier module, executable by the processor in accordance with program instructions in the program memory, for determining at least one of a plurality of hierarchical business categories to which the target company and the second company belong; and

a hierarchical category placer module, executable by the processor in accordance with program instructions in the program memory, for determining a relationship strength value based on the relationship indicator, the second set of data sources and the determined hierarchical business category, the relationship strength value increasing or decreasing based on a depth of the determined business category in hierarchy, and for identifying the second company as related to the target company when the relationship strength value is over a threshold.

33. The system of claim 32 wherein the relationship identifier module is further configured for determining an overall score for the co-occurrence of the target company and the second company, based on the relationship indicator appearing in the co-occurrence, and for indicating the relationship between the target company and the second company if the overall score satisfies a relationship indicator threshold.

34. The system of claim 32 wherein the relationship verifier module is further configured for adjusting the overall score for the business relationship, based on one or more supplemental relationship indicators, and for verifying the business relationship if the adjusted overall score satisfies a verified relationship indicator threshold.

35. The system of claim 32 wherein the relationship verifier module is further configured for determining an overall score for the business relationship, based on one or more relationship indicators, and for verifying the business relationship if the overall score satisfies a relationship indicator threshold.

36. A system for determining whether a target company and a second company are related, the system comprising:

a computer processor for executing programmed instructions;

a program memory, coupled to the processor, for storing program instruction steps for execution by the processor;

means, executable by the processor in accordance with program instructions in the program memory, for locating a co-occurrence of a target company name of the target company and a second company name of the second company in a first set of data sources;

means, executable by the processor in accordance with program instructions in the program memory, for identifying a business relationship between the target company and the second company based upon a relationship indicator appearing with the co-occurrence of the target company name and the second company name;

means, executable by the processor in accordance with program instructions in the program memory, for verifying the business relationship using a second set of data sources based upon the target company and the second company having in common at least two of the following features;

an industry type, a geographic location, a type of product provided, and a type of service provided;

means, executable by the processor in accordance with program instructions in the program memory, for determining at least one of a plurality of hierarchical business categories to which the target company and the second company belong;

means, executable by the processor in accordance with program instructions in the program memory, for determining a relationship strength value based on the relationship indicator, the second set of data sources and the determined hierarchical business category, the relationship strength value increasing or decreasing based on a depth of the determined business category in hierarchy; and

means, executable by the processor in accordance with program instructions in the program memory, for identifying the second company as related to the target company when the relationship strength value is over a threshold.