Data ranking with a Lorentzian fuzzy score

• US 6,701,312 B2
• Filed: 09/12/2001
• Issued: 03/02/2004
• Est. Priority Date: 09/12/2001
• Status: Expired due to Fees

• Current Assignee: Science Applications International Corporation
• Original Assignee: Science Applications International Corporation
• Inventors: Lau, Yun-Tung, Nagy, Marton
• Primary Examiner(s): Mizrahi, Diane D.
• Application Number:
  US09/952,518
• Publication Number:
  US 20030065660A1
• Time in Patent Office: 902 Days
• Field of Search: 707/1, 707/2, 707/5, 707/6, 707/10, 709/100
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2468 Fuzzy queries
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

The present mechanism relates to a method for searching a document database such as the Internet and ranking the results obtained from such a search. The mechanism also relates to ranking of a set of numerical data according to a set of user specified preferences, including target range, fuzziness and bias. A fuzzy score is calculated for each database record satisfying a query and the results ranked according to fuzzy score. The fuzzy score is calculated using a Lorentzian fuzzy score formula.

Claims

1. A method for searching a database comprising at least one record and ranking search results, comprising:

entering a query, wherein the query comprises one or more numerical search terms;

searching the database using the query;

determining whether the at least one record in the database satisfies the query; and

ranking each record of the at least one record that satisfies the query according to a fuzzy score, wherein the fuzzy score is calculated using a Lorentzian fuzzy score formula.

2. The method of claim 1, wherein the query further comprises a fuzziness parameter and a bias parameter.

3. The method of claim 2, wherein at least one of the one or more numerical search terms is a target range having a minimum numeric value and a maximum numeric value.

4. The method of claim 3, wherein the bias parameter is a negative number and wherein the fuzzy score is calculated using the following Lorentzian fuzzy score formula:

$\begin{array}{ccc}\text{\hspace{1em}<br><br>}& \frac{1}{1+{\left(\frac{x-x_{\min }}{\mathrm{a1}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x<<br><br>x_{\min }\\ S<br><br>\left(x\right)=& 1+\frac{\mathrm{\beta <br><br>}*\left(x-x_{\min }\right)}{x_{\max }-x_{\min }}& \text{\hspace{1em}<br><br>}<br><br>x_{\min }\le <br><br>x\le <br><br>x_{\max }\\ \text{\hspace{1em}<br><br>}& \frac{1+\mathrm{\beta <br><br>}}{1+{\left(\frac{x-x_{\max }}{\mathrm{a2}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x_{\max }<<br><br>x\end{array}<br><br>$

where x represents any data values, i.e., x∈

{x₁, . . . , x_k}.

5. The method of claim 3, wherein the bias parameter is a positive number and wherein the fuzzy score is calculated using the following Lorentzian fuzzy score formula:

$\begin{array}{ccc}\text{\hspace{1em}<br><br>}& \frac{1-\mathrm{\beta <br><br>}}{1+{\left(\frac{x-x_{\min }}{\mathrm{a1}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x<<br><br>x_{\min }\\ S<br><br>\left(x\right)=& 1+\frac{\mathrm{\beta <br><br>}*\left(x-x_{\max }\right)}{x_{\max }-x_{\min }}& \text{\hspace{1em}<br><br>}<br><br>x_{\min }\le <br><br>x\le <br><br>x_{\max }\\ \text{\hspace{1em}<br><br>}& \frac{1}{1+{\left(\frac{x-x_{\max }}{\mathrm{a2}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x_{\max }<<br><br>x\end{array}<br><br>$

where x represents any data values, i.e., x∈

{x₁, . . . , x_k}.

6. The method of claim 2, wherein the bias parameter is a negative number and wherein the fuzzy score is calculated using the following Lorentzian fuzzy score formula:

$\begin{array}{ccc}\text{\hspace{1em}<br><br>}& \underset{\_}{\frac{1}{1+{\left(\frac{x-\underset{\_}{x}}{\mathrm{a1}}\right)}^2}}& \text{\hspace{1em}<br><br>}<br><br>x<<br><br>\underset{\_}{x}\\ S<br><br>\left(x\right)=& 1& \text{\hspace{1em}<br><br>}<br><br>x=\underset{\_}{x}\\ \text{\hspace{1em}<br><br>}& \frac{1+\mathrm{\beta <br><br>}}{1+{\left(\frac{x-\underset{\_}{x}}{\mathrm{a2}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x><br><br>\underset{\_}{x}\end{array}<br><br>$

where x represents any data values, i.e., x∈

{x₁, . . . , x_k}.

7. The method of claim 2, wherein the bias parameter is a positive number and wherein the fuzzy score is calculated using the following Lorentzian fuzzy score formula:

$\begin{array}{ccc}\text{\hspace{1em}<br><br>}& \underset{\_}{\frac{1-\mathrm{\beta <br><br>}}{1+{\left(\frac{x-\underset{\_}{x}}{\mathrm{a1}}\right)}^2}}& \text{\hspace{1em}<br><br>}<br><br>x<<br><br>\underset{\_}{x}\\ S<br><br>\left(x\right)=& 1& \text{\hspace{1em}<br><br>}<br><br>x=\underset{\_}{x}\\ \text{\hspace{1em}<br><br>}& \frac{1}{1+{\left(\frac{x-\underset{\_}{x}}{\mathrm{a2}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x><br><br>\underset{\_}{x}\end{array}<br><br>$

where x represents any data values, i.e., x∈

{x₁, . . . , x_k}.

8. A method for ranking a set of data, wherein the set of data comprises a plurality of data elements and wherein the data elements are associated with a query, the method comprising:

setting or presetting a numeric bias parameter and a numeric fuzziness factor;

calculating a fuzzy score for each data element of the plurality of data elements, wherein the fuzzy score is calculated using a Lorentzian fuzzy score formula and

wherein when the numeric bias parameter is set or preset to a negative number and the query comprises a numeric target range, the Lorentzian fuzzy score is;

$\begin{array}{ccc}\text{\hspace{1em}<br><br>}& \frac{1}{1+{\left(\frac{x-x_{\min }}{\mathrm{a1}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x<<br><br>x_{\min }\\ S<br><br>\left(x\right)=& 1+\frac{\mathrm{\beta <br><br>}*\left(x-x_{\min }\right)}{x_{\max }-x_{\min }}& \text{\hspace{1em}<br><br>}<br><br>x_{\min }\le <br><br>x\le <br><br>x_{\max }\\ \text{\hspace{1em}<br><br>}& \frac{1+\mathrm{\beta <br><br>}}{1+{\left(\frac{x-x_{\max }}{\mathrm{a2}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x_{\max }<<br><br>x\end{array}<br><br>$

 

where x represents any data values, i.e., x∈

{x₁, . . . , x_k},

wherein when the numeric bias parameter is set or preset to a positive number and the query comprises a numeric target range, the Lorentzian fuzzy score is;

$\begin{array}{ccc}\text{\hspace{1em}<br><br>}& \frac{1-\mathrm{\beta <br><br>}}{1+{\left(\frac{x-x_{\min }}{\mathrm{a1}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x<<br><br>x_{\min }\\ S<br><br>\left(x\right)=& 1+\frac{\mathrm{\beta <br><br>}*\left(x-x_{\max }\right)}{x_{\max }-x_{\min }}& \text{\hspace{1em}<br><br>}<br><br>x_{\min }\le <br><br>x\le <br><br>x_{\max }\\ \text{\hspace{1em}<br><br>}& \frac{1}{1+{\left(\frac{x-x_{\max }}{\mathrm{a2}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x_{\max }<<br><br>x\end{array}<br><br>$

 

where x represents any data values, i.e., x∈

{x₁, . . . , x_k},

wherein when the numeric bias parameter is set or preset to a negative number and the query comprises a single numeric value, the Lorentzian fuzzy score is;

$\begin{array}{ccc}\text{\hspace{1em}<br><br>}& \underset{\_}{\frac{1}{1+{\left(\frac{x-\underset{\_}{x}}{\mathrm{a1}}\right)}^2}}& \text{\hspace{1em}<br><br>}<br><br>x<<br><br>\underset{\_}{x}\\ S<br><br>\left(x\right)=& 1& \text{\hspace{1em}<br><br>}<br><br>x=\underset{\_}{x}\\ \text{\hspace{1em}<br><br>}& \frac{1+\mathrm{\beta <br><br>}}{1+{\left(\frac{x-\underset{\_}{x}}{\mathrm{a2}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x><br><br>\underset{\_}{x}\end{array}<br><br>$

 

where x represents any data values, i.e., x∈

{x₁, . . . , x_k}, and

wherein when the numeric bias parameter is set or preset to a positive number and the query comprises a single numeric value, the Lorentzian fuzzy score is;

$\begin{array}{ccc}\text{\hspace{1em}<br><br>}& \underset{\_}{\frac{1-\mathrm{\beta <br><br>}}{1+{\left(\frac{x-\underset{\_}{x}}{\mathrm{a1}}\right)}^2}}& \text{\hspace{1em}<br><br>}<br><br>x<<br><br>\underset{\_}{x}\\ S<br><br>\left(x\right)=& 1& \text{\hspace{1em}<br><br>}<br><br>x=\underset{\_}{x}\\ \text{\hspace{1em}<br><br>}& \frac{1}{1+{\left(\frac{x-\underset{\_}{x}}{\mathrm{a2}}\right)}^2}& \text{\hspace{1em}<br><br>}<br><br>x><br><br>\underset{\_}{x}\end{array}<br><br>$

 

where x represents any data values, i.e., x∈

{x₁, . . . , x_k}; and

ranking each data element according to the fuzzy score.

9. A method for searching a database and ranking search results, comprising:

entering a query, wherein the query comprises a plurality of numerical search terms;

searching the database using the query, wherein the database comprises at least one record;

determining whether the at least one record in the database satisfies the query;

calculating a fuzzy score using a Lorentzian fuzzy score formula for each numerical search term of the plurality of numerical search terms for each record of the at least one record that satisfies the query;

summing the fuzzy score of each numerical search term for each record into an aggregate fuzzy score;

ranking each record according to the aggregate fuzzy score.

10. The method of claim 9, wherein after calculating the fuzzy score for each numerical search term for each record, the fuzzy score of at least one numerical search term of the plurality of numerical search terms for each record is multiplied by a weight factor to produce a weighted fuzzy score and wherein the summing of the fuzzy score of each numerical search term for each record comprises the weighted fuzzy score in lieu of the fuzzy score for the at least one numerical search term.