Patent US5832480A successfully refreshed from Google Patents.
US5832480A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Using canonical forms to develop a dictionary of names in a text
Assignee: International Business Machines Corp
•
Filing: 1996-07-12
•
Granted: 1998-11-03
•
Expires: 2016-07-12
Abstract
Abstract Descriptive canonical forms of entity types are created by scanning one or more documents in a database of a computer system to identify one or more proper names that appear in the documents as raw names. Each of the raw names has zero or more proper names, zero or more medial substrings, zero or more leading substrings, and zero or more trailing substrings. The raw names of one or more documents are "cleaned" and "split" until certain "cleaning and splitting conditions" are no longer met to obtain a list of clean and split candidate names. Anchor names are selected from the list that unambiguously represent an entity type. The anchor names have one or more entity-type attribute values. Variant names, clean and split candidate names having one or more shared attribute (values) with the anchor name, are combined with the anchor name to create an equivalence group of names that refer to the same entity. A canonical form is generated for the group from a subset of the anchor name attributes. A canonical form is created in this manner for all of the clean and split candidate names on the list.
Inventors
- 👤 Roy Jefferson Byrd, Jr.
- 👤 Misook A. Choi
- 👤 Yael Ravin
- 👤 Faye Nina Wacholder
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-29 18:43
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/90; G06F16/903; G06F16/90335; G06F16/90344; Y; Y10; Y10S; Y10S707/00; Y10S707/99931; Y10S707/99933; Y10S707/99935
Claims Analysis
Total Claims: 21
Claim 1
Independent Claim
112 words
A data structure in a memory of a computer, comprising: an equivalence group having a set of a plurality of named elements, each name element having a string and one or more attributes associated with the string, each attribute having an attribute value; an anchor, being one of the name elements, the anchor having a high confidence score of being a member of the entity type; and zero or more variants, each being one of the name elements, each of the variants having an equivalence link that references the anchor and is one of the attribute values, and all of the attribute values in the equivalence group being compatible with one another.
Claim 2
Dependent Claim
112 words
A data structure in a memory of a computer, comprising: an equivalence group having a set of a plurality of named elements, each name element having a string and one or more attributes associated with the string, each attribute having an attribute value; an anchor, being one of the name elements, the anchor having a high confidence score of being a member of the entity type; and zero or more variants, each being one of the name elements, each of the variants having an equivalence link that references the anchor and is one of the attribute values, and all of the attribute values in the equivalence group being compatible with one another.
Claim 3
Dependent Claim
59 words
A data structure, as in claim 1, that further comprises a canonical form being a record containing a set of canonical attributes being a subset of the attributes of the anchor and the variants, a canonical value for each canonical attribute being a most complete value selected from the set of respective attribute values of the anchor and variants.
Claim 4
Independent Claim
80 words
A system of one or more computers, comprising: a database; a plurality of canonical forms, stored on the database as a name dictionary, each canonical form being a record containing a set of canonical attributes being a subset of one or more attributes of an anchor named element record and one or more variants records, a canonical value for each canonical attribute being a most complete value selected from the set of respective attribute values of the anchor and variants.
Claim 5
Independent Claim
80 words
A system of one or more computers, comprising: a database; a plurality of canonical forms, stored on the database as a name dictionary, each canonical form being a record containing a set of canonical attributes being a subset of one or more attributes of an anchor named element record and one or more variants records, a canonical value for each canonical attribute being a most complete value selected from the set of respective attribute values of the anchor and variants.
Claim 6
Dependent Claim
36 words
A system, as in claim 3, where one or more of the computers is a client and one or more of the computers is a server, the clients and servers being in communication over a network.
Claim 7
Independent Claim
189 words
A system of one or more computers, comprising: one or more databases; an equivalence group stored on one or more of the databases, the equivalence group having a set of a plurality of named elements, each named element having a string and one or more attributes associated with the string, each attribute having an attribute value; an anchor, being one of the named elements, the anchor having a confidence score of an entity type; and one or more variants, each being one of the named elements, each of the variants having an equivalence link that references the anchor and is one of the attribute values, and all of the attribute values in the equivalence group being compatible with one another; and a plurality of canonical forms, stored as a name dictionary on one or more of the databases, each of the canonical forms being a record containing a set of canonical attributes being a subset of the attributes of the anchor and the variants, a canonical value for each canonical attribute being a most complete value selected from the set of respective attribute values of the anchor and variants.
Claim 8
Independent Claim
189 words
A system of one or more computers, comprising: one or more databases; an equivalence group stored on one or more of the databases, the equivalence group having a set of a plurality of named elements, each named element having a string and one or more attributes associated with the string, each attribute having an attribute value; an anchor, being one of the named elements, the anchor having a confidence score of an entity type; and one or more variants, each being one of the named elements, each of the variants having an equivalence link that references the anchor and is one of the attribute values, and all of the attribute values in the equivalence group being compatible with one another; and a plurality of canonical forms, stored as a name dictionary on one or more of the databases, each of the canonical forms being a record containing a set of canonical attributes being a subset of the attributes of the anchor and the variants, a canonical value for each canonical attribute being a most complete value selected from the set of respective attribute values of the anchor and variants.
Claim 9
Dependent Claim
14 words
A system, as in claim 5, where the entity type is a proper name.
Claim 10
Dependent Claim
42 words
A system, as in claim 6, where proper name is any of the following: an art work, an economic entities, an events, a legal entities, an organizations, a person, a place, a product, a textual entity, and a residue of proper names.
Claim 11
Dependent Claim
13 words
A system, as in claim 5, where the entity type is a person.
Claim 12
Dependent Claim
45 words
A system, as in claim 8, where the attributes include any of the following: a gender, a personal title, a professional title, a first name, an initial name, a middle name, an initial, a nickname, a name prefix, a last name, and a name suffix.
Claim 13
Dependent Claim
32 words
A system, as in claim 5, where the entity type is a place and the attributes include any of the following: a place and a bigger place in which place is located.
Claim 14
Dependent Claim
31 words
A system, as in claim 5, where the entity type is an organization and the attributes include any of the following: an organization name, an organization tag, and an organization place.
Claim 15
Dependent Claim
22 words
A system, as in claim 5, where the anchor name is unambiguous because the confidence score is a value exceeding a threshold.
Claim 16
Independent Claim
135 words
A method of establishing equivalence links between two or more named elements to form an equivalence group, having a set of a plurality of named elements, each named element having a string and one or more attributes associated with the string, each attribute having an attribute value, the method comprising the steps of: selecting one or more of the named elements as an anchor, the anchor having a high confidence score of having string belonging to an entity type; assigning the entity type to the anchor; performing an entity type equivalence process on the anchor and one or more remaining named elements, the entity type equivalence process determining if the remaining named element is compatible with the anchor; and referencing the remaining named elements that are compatible with the anchor as variants of the anchor.
Claim 17
Independent Claim
135 words
A method of establishing equivalence links between two or more named elements to form an equivalence group, having a set of a plurality of named elements, each named element having a string and one or more attributes associated with the string, each attribute having an attribute value, the method comprising the steps of: selecting one or more of the named elements as an anchor, the anchor having a high confidence score of having string belonging to an entity type; assigning the entity type to the anchor; performing an entity type equivalence process on the anchor and one or more remaining named elements, the entity type equivalence process determining if the remaining named element is compatible with the anchor; and referencing the remaining named elements that are compatible with the anchor as variants of the anchor.
Claim 18
Dependent Claim
62 words
A method, as in claim 13, further comprising the step of: creating a canonical form that is a record containing a set of canonical attributes being a subset of the attributes of the anchor and the variants, a canonical value for each canonical attribute being a most complete value selected from the set of respective attribute values of the anchor and variants.
Claim 19
Dependent Claim
159 words
A method, as in claim 13, where the entity type equivalence process is a person entity-type equivalence process that assigns attribute values to the anchor and variants by performing the following steps: filling in a professional title attribute with a professional title value if a professional title is in the string; filling in a suffix attribute with a suffix value if a name suffix is in the string; filling in a last name attribute with a last name value if a last name is in the string; filling in a personal title attribute with a personal title value if a personal title is in the string; filling in a first name attribute with a first name value if a first name is in the string; filling in a prefix attribute with a prefix value if a name prefix is in the string; and filling in a nickname attribute with a nickname value if a nickname is in a string.
Claim 20
Dependent Claim
90 words
A method, as in claim 13, where the entity type equivalence process is a organization entity-type equivalence process that assigns attribute values to the anchor and variants by performing the following steps: filling in an organization place attribute with an organization place value if an organization place is in the string; filling in an organization tag attribute with an organization tag value if an organization tag is in the string; and filling in an organization name attribute with an organization name value if an organization name is in the string.
Claim 21
Dependent Claim
123 words
A method, as in claim 13, where the entity type equivalence process is a place entity-type equivalence process that assigns attribute values to the anchor and variants by performing the following steps: filling in a bigger place attribute with a bigger place value if a country name is to the right of a comma in the string; filling in a place attribute with a place value if a place name is to the left of the comma in the string; filling in the place attribute with the entire string as the value if the entire string is a place; and filling in the place attribute with a place value if a place name is to the right of a modifier in the string.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-11-02 | 2002-05-04 | 2002-11-03 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-11-02 | 2006-05-04 | 2006-11-03 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-11-02 | 2010-05-04 | 2010-11-03 | $7700.00 | Window Closed / Lapsed |