Back to results
US 6,823,333 B2Granted
System, method and apparatus for conducting a keyterm search
AssigneeThe United States of America as represented by the Administrator of the National Aeronautics and Space Administration
InventorMichael W. McGreevy
Life of this patent
Estimating the term…
Abstract
A keyterm search is a method of searching a database for subsets of the database that are relevant to an input query. First, a number of relational models of subsets of a database are provided. A query is then input. The query can include one or more keyterms. Next, a gleaning model of the query is created. The gleaning model of the query is then compared to each one of the relational models of subsets of the database. The identifiers of the relevant subsets are then output.
Claims65
A method of searching a database comprising:
- providing a plurality of relational models, wherein each of the plurality of relational models includes a relational model of at least one subset of a database and a plurality of relations, wherein each of the plurality of relations includes at least one term pair and one or more types of relational summation metrics (RSMs), each RSM type including a summation of values of the corresponding type of relational metric of occurrences of the at least one term pair within at least one context window within the at least one database subset and includes at least one of a right contextual metric (RCM) and a left contextual metric (LCM);
- inputting a first query for the database:
- creating a relational model of the first query;
- comparing the relational model of the first query to each one of the plurality of relational models of the subsets;
- and
- outputting a first plurality of identifiers of the subsets relevant to the first query.
3 more elements
A method of searching a database, the method comprising:
- providing a plurality of relational models, wherein each of the plurality of relational models includes a relational model of at least one subset of a database and a plurality of relations, wherein each of the plurality of relations includes at least one term pair and one or more types of relational summation metrics (RSMs);
- inputting a first query for the database;
- creating a relational model of the first query;
- comparing the relational model of the first query to each one of the plurality of relational models of the subsets by a process comprising:
- determining a plurality of first relevance metrics for a first one of the plurality of relational models of the subsets by a sub-process comprising:
- determining an intersection model of the relational model of the first query and a first one of the plurality of relational models of the subsets by a process comprising:
- determining a plurality of intersection relations, wherein each one of the plurality of intersection relations has:
- a shared term pair, which includes a term pair present in at least one relation in each of the first query relational models and the first one of the plurality of the relational models of the subsets;
- and
- a plurality of intersection metrics (IMs), each one of the plurality of intersection metrics being expressible as IM=fct(RSMQ1, RSMS1), wherein:
- fct is a selected function of at least one of two arguments, RSMQ1 and RSMS1,
- RSMQ1 is a value of a type of relational summation metric in the relational model of the first query, and
- RSMS1 is a value of a corresponding type of relational summation metric in the relational model of the first one of the plurality of relational models of the subsets;
- and
- calculating a first relevance metric value for each type of RSM, equal to a summation of the plurality of corresponding IM values of all intersection relations;
- and
- determining a subsequent plurality of first relevance metric values corresponding to each subsequent one of the plurality of relational models of the subsets;
- and
- outputting a first plurality of identifiers of the subsets relevant to the first query.
16 more elements
The method as recited in ciaim 48, further comprising displaying, for each of said plurality of shared term pairs values, NDCMQ1 and NDCMS1, and a product equal to (ln NDCMQ) * (ln NDCMS1), wherein:
- NDCMQ1 is equal to a non-directional contextual metric value of the shared term pair in said query;
- NDCMS1 is equal to a non-directional contextual metric value of the shared term pair in said subset, wherein
- NDCMS1>1, and
- NDCMQ1>1.
1 more element
A method of producing a model of a database comprising:
- providing a database;
- calculating a plurality of relations wherein, each one of the plurality of relations has a term pair and a plurality of types of relational summation metrics (RSMs), and wherein, each one of the plurality of RSMs includes a summation of the corresponding types of relational metrics of each one of a plurality of occurrences of the term pair within a context window within the database, wherein the types of relational metrics include:
- a non-directional contextual metric;
- a right contextual metric;
- a left contextual metric;
- and
- a directional contextual metric;
- and
- outputting a model of the database.
6 more elements
A method of searching a database comprising:
- providing a plurality of relational models, wherein each of the plurality of relational models includes a relational model of at least one subset of a database and a plurality of relations, wherein each of the plurality of relations includes at least one term pair and one or more types of relational summation metrics (RSMs), each RSM type including a summation of values of a corresponding type of relational metric of occurrences of the at least one term pair within at least one context window within the at least one database subset and includes at least one of a right contextual metric (RCM), a left contextual metric (LCM) and a directional contextual metric (DCM), wherein a DCM value for a single occurrence of a term pair (T1, T2) in the at least one subset is:
- DCM(T1, T2)=RCM(T1, T2)−LCM(T1, T2), wherein:
- T1 is a first term in the term pair;
- T2 is a second term in the term pair;
- RCM(T1, T2) is a right contextual metric value for the single occurrence of the term pair (T1, T2) in the at least one subset;
- LCM(T1, T2) is a left contextual metric value for the single occurrence of a term pair (T1, T2) in the at least one subset;
- and
- RCM(T1, T2)≧LCM(T1, T2);
- inputting a first query for the database;
- creating a relational model of the first query;
- comparing the relational model of the first query to each one of the plurality of relational models of the subsets;
- and
- outputting a first plurality of identifiers of the subsets relevant to the first query.
10 more elements
A method of searching a database comprising:
- providing a plurality of relational models, wherein each of the plurality of relational models includes a relational model of at least one subset of a database and a plurality of relations, wherein each of the plurality of relations includes at least one term pair and one or more types of relational summation metrics (RSMs), each RSM type including a summation of values of a corresponding type of relational metric of occurrences of the at least one term pair within at least one context window within the at least one database subset and includes at least one scaled frequency metric (SFM) that is defined by:
- SFM=(C−1−N) * ((2 FM−F1−F2)/(2 FM));
- C is equal to a number of terms in the context window;
- N is equal to a number of terms occurring between a first term and a second term of the term pair;
- FM is equal to a frequency of occurrences of a most frequent term in the database;
- F1 is equal to a frequency of occurrences of the first term of the term pair in the database;
- and
- F2 is equal to a frequency of occurrences of the second term of the term pair in said database;
- and
- inputting a first query for the database;
- creating a relational model of the first query;
- comparing the relational model of the first query to each one of the plurality of relational models of the subsets;
- and
- outputting a first plurality of identifiers of the subsets relevant to the first query.
11 more elements
A method of searching a database comprising:
- providing a plurality of relational models, wherein each of the plurality of relational models includes a relational model of at least one subset of a database and a plurality of relations, wherein each of the plurality of relations includes at least one term pair and one or more types of relational summation metrics (RSMs), each RSM type including a summation of values of a corresponding type of relational metric of occurrences of the at least one term pair within at least one context window within the at least one database subset and includes at least one of a right contextual metric (RCM), a left contextual metric (LCM) and a non-directional contextual metric (NDCM), wherein an NDCM value for a single occurrence of a term pair (T1, T2) in the at least one subset is
- NDCM(T1, T2)=RCM(T1, T2)+LCM(T1, T2), wherein:
- T1 is a first term in the term pair;
- T2 is a second term in the term pair;
- RCM(T1, T2) is a right contextual metric value for the single occurrence of the term pair (T1, T2) in the at least one subset;
- and
- LCM(T1, T2) is a left contextual metric value for the single occurrence of the term pair (T1, T2) in the at least one subset;
- inputting a first query for the database;
- creating a relational model of the first query;
- comparing the relational model of the first query to each one of the plurality of relational models of the subsets;
- and
- outputting a first plurality of identifiers of the subsets relevant to the first query.
9 more elements
Dependencies are inferred from the claim text.