US20070271261A1 - Data ranking with a lorentzian fuzzy score - Google Patents

Data ranking with a lorentzian fuzzy score Download PDF

Info

Publication number
US20070271261A1
US20070271261A1 US11/812,954 US81295407A US2007271261A1 US 20070271261 A1 US20070271261 A1 US 20070271261A1 US 81295407 A US81295407 A US 81295407A US 2007271261 A1 US2007271261 A1 US 2007271261A1
Authority
US
United States
Prior art keywords
max
fuzzy
lorentzian
score
fuzzy score
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US11/812,954
Inventor
Yun-Tung Lau
Marton Nagy
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Science Applications International Corp SAIC
Original Assignee
Science Applications International Corp SAIC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Science Applications International Corp SAIC filed Critical Science Applications International Corp SAIC
Priority to US11/812,954 priority Critical patent/US20070271261A1/en
Assigned to SCIENCE APPLICATIONS INTERNATIONAL CORPORATION reassignment SCIENCE APPLICATIONS INTERNATIONAL CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: NAGY, MARTON, LAU, YUN-TUNG
Publication of US20070271261A1 publication Critical patent/US20070271261A1/en
Abandoned legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2458Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2468Fuzzy queries
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99935Query augmenting and refining, e.g. inexact access
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99936Pattern matching access

Definitions

  • the present invention relates to information retrieval in a data processing system.
  • the present invention further relates to a method for searching a document database such as the Internet and ranking the results obtained from such a search.
  • a computer's logic is both its strength and its weakness; it can only perform what it is told to do. If an alarm clock is set to go off at 6:00 PM, it will go off at exactly that time, even if it was obviously meant to go off at 6:00 AM. People in the real world can solve problems and make decisions relatively easy, but even the simplest decisions are often too difficult to be handled by computer. Fuzzy logic query processing helps to bridge the gap.
  • Databases are strategic tools because they support business processes. In order for a database to be useful, data must be compiled into information using tools such as queries. Queries allow a user to specify what data to retrieve from a database, and in what form. Fuzzy querying provides a way to retrieve data that was intended to be retrieved, without requiring exact parameters to be defined.
  • Non-fuzzy query processing relies on Boolean logic, which limits results to true or false (1 or 0). Fuzzy query processing is a superset of Boolean logic that can handle partial truths. Instead of a search results being limited to return a value of true or false, the query returns values as x % true or x % a member of a subset.
  • Fuzzy queries rely on the use of fuzzy quantifiers.
  • Dr. Lotfi A. Zadeh the founder of fuzzy logic theory, defined two kinds of quantifiers: absolute and relative.
  • An absolute quantifier can be represented as fuzzy subsets of the non-negative numbers and use words such as at least three or about five.
  • Relative qualifiers are represented as fuzzy subsets of the unit interval and use words such as most, at least half, or almost all.
  • Fuzzy queries do not take the place of the more structured queries, but expand the alternatives available.
  • Boolean systems use selection and then ordering as a mechanism, where a fuzzy system relies on a single mechanism of overall membership degree.
  • a fuzzy system allows for compromise between the various criteria, where a Boolean system can produce a subset of previously selected elements. There are times when Boolean logic is too rigid to be meaningful to a user.
  • a fuzzy query allows a user to find elements that satisfy a criterion and ranks the results.
  • FIG. 1 illustrates the typical flow of a fuzzy database query.
  • the user queries a database 110 .
  • the database returns a record, which is matched against predefined criteria 120 to determine the degree to which a match has occurred. The degree is then compared to a threshold value 125 to determine whether the record satisfies the users query 130 or whether the record should be discarded 135 .
  • a fuzzy database query differs from a non-fuzzy query by adding steps to match the data to predefined criteria and compare the value to a threshold specified in the query.
  • An object can be a member of multiple sets with a different degree of membership.
  • the degree of membership is a scale from zero to one. Complete membership has a value of one, and no membership has a value of zero.
  • the output is calculated based on the value of membership a given input has in the configured fuzzy sets.
  • Each combination of sets is configured to have a specified output. The output is based on the weighted sum of the amount of membership in each set.
  • the fuzzy models may be used in conjunction with probabilistic models to find a solution.
  • FIG. 2 shows the three transformations of the system inputs 200 to outputs 205 in a fuzzy system.
  • fuzzyification is a methodology to generalize any specific theory from a precise form to continuous form. It decomposes a system input or output into one or more fuzzy sets. After the decomposition into fuzzy sets, fuzzy rule association 215 applies a set of rules to a combination of inputs. The rules determine the action and relate the variable into a numeric value. Once the numeric value is determined, de-fuzzification 220 converts the fuzzy result into an exact output value.
  • the invention relates to database searching and the ranking of a set of numerical data according to a set of user specified preferences, including target range, fuzziness and bias.
  • data records are returned when certain field data falls into a user specified target range.
  • fuzziness in the present invention extends the returned data set by including records that are “close” to the target range.
  • the addition of a bias also increases the usefulness of the database query by providing a means to rank the results of the query in a specified order.
  • the present invention adapts the Lorentzian function to include variables for fuzziness and bias in order to calculate fuzzy scores, which are used to rank the results of database searches.
  • fuzzy scores are calculated for each query field in each record. The fuzzy scores of each query field in each record are then aggregated into a composite fuzzy score that is then used to rank the results of the database query.
  • FIG. 1 shows the typical flow of a fuzzy database query.
  • FIG. 2 depicts the three main transformations in a fuzzy system.
  • FIG. 3 shows a graph of the Lorentzian function.
  • FIG. 4 shows calculated Lorentzian fuzzy scores where the bias is less than zero.
  • FIG. 5 shows calculated Lorentzian fuzzy scores where the bias is greater than zero.
  • FIG. 6 shows two graphs of calculated Lorentzian fuzzy scores where the fuzziness parameters are set to zero (i.e. there is no fuzziness).
  • FIG. 7 shows two graphs of calculated Lorentzian fuzzy scores in the special case where the target range degenerates into a single value.
  • FIG. 8 shows a table of calculated fuzzy scores for each record based only on selling price.
  • FIG. 9 shows a table of calculated fuzzy scores for each record based only on number of rooms.
  • FIG. 10 shows a table of calculated fuzzy scores for each record based only on number of baths.
  • FIG. 11 shows aggregate fuzzy scores for each record and ranked database records.
  • the preferred embodiments of the present invention are directed to a method for searching a document database such as the Internet according to a set of user specified preferences, including target range, fuzziness and bias and ranking the results obtained from such a search.
  • the basic building block of the fuzzy score is the Lorentzian function: 1 1 + [ x - x ⁇ ⁇ 0 a ] 2
  • the Lorentzian function 300 has a bell-shaped drop off from a central peak.
  • the fuzziness of the score is proportional to the width of the Lorentzian function.
  • the bias is introduced by a linear variation within the target range.
  • the fuzzy score allows a user to rank a set of numerical data according to the user's input.
  • the qualitative behavior of the Lorentzian fuzzy score is described as follows. For data that lies outside the target range, the score is zero without fuzziness and in the range [0, 1] with fuzziness. For data that is inside the target range, the score varies linearly, with a bias (higher score) towards either the lower or upper bound of the target range.
  • the present invention can calculate a fuzzy score for a user defined database query and rank the results of the query.
  • the fuzzy score is calculated based on user specified criteria including, but not limited to, target range (x min , x max ), fuzziness ( ⁇ 1 and ⁇ 2 ) and bias ( ⁇ ).
  • the fuzziness and/or bias is static and set by the software/system performing the search. While the parameters for fuzziness and bias are numeric, it is contemplated in at least one embodiment that these parameters be translated into more easily understood terminology for user selection.
  • the user may select from a list of fuzziness categories (i.e. small, medium, large).
  • the terms small, medium and large would equate to specific values of ⁇ 1 and ⁇ 2 and would be used to calculate a fuzzy score as described herein.
  • the bias parameter, ⁇ the bias parameter
  • the user may select from a list of bias categories (i.e. toward the lower bound, toward the upper bound). These categories would also be equated to specific numeric values and would be used to calculate a fuzzy score as described herein.
  • each example will illustrate how variations in user input parameters (i.e. target values, fuzziness, bias) affect the Lorentzian function as it is used to calculate a fuzzy score.
  • the examples will be based on a user who is shopping for a new home via a web site containing new home data.
  • the web site allows the user to search a database of new homes based on the selling price of the home.
  • the web site allows the user to input fuzziness values, ⁇ 1 and ⁇ 2 , and a bias value, ⁇ .
  • the negative slope of the graph between the target values $200,000 and $250,000 is the result of the negative bias.
  • the negative bias affects the fuzzy score calculated from data values between the target range by biasing those data values closer to the lower end of the target range.
  • the calculated fuzzy scores for the data points that lie outside the target range are a direct result of the incorporation of the fuzziness parameters into the Lorentzian function.
  • Consistent with the Lorentzian function is the rapid drop off of the fuzzy scores for the data points that lie farthest from the target range.
  • the query would have returned records for each of the 12 homes in the database.
  • the addition of the fuzzy scores makes it easy for the user to visualize the records that best conform to the original search parameters.
  • the positive slope of the graph between the target values $200,000 and $250,000 is the result of the positive bias.
  • the positive bias affects the fuzzy score calculated from data values between the target range by biasing those data values closer to the upper end of the target range.
  • the calculated fuzzy scores for the data points that lie outside the target range are a direct result of the incorporation of the fuzziness parameters into the Lorentzian function.
  • Consistent with the Lorentzian function is the rapid drop off of the fuzzy scores for the data points that lie farthest from the target range.
  • the query would have returned records for each of the 12 homes in the database.
  • the addition of the fuzzy scores makes it easy for the user to visualize the records that best conform to the original search parameters.
  • plots 600 and 610 illustrate the effect a negative and positive bias have on the calculated fuzzy scores. As previously stated, a negative bias results in the negative slope of the plot 600 between the target values, while a positive bias results in the positive slope of the plot 610 between the target values.
  • the affect of the bias in plot 700 and 710 is more difficult to discern since there is no target range.
  • a close inspection of plot 700 shows that the negative bias does influence the calculated fuzzy scores for those data values less than the target value and in plot 710 that the positive bias does influence the calculated fuzzy scores for those data values greater than then target value.
  • the home buying database in this example is on the Internet and the user is given the option to search for new homes based on selling price, number of rooms, and number of baths. For this example, it is assumed the database contains the following records: Selling Price $150,000 $170,000 $195,000 $200,000 $225,000 $230,000 $235,000 $260,000 $280,000 Number 3 2 3 3 5 3 4 4 3 of Rooms Number 2.5 2 4 3 3.5 2 3 3 1.5 of Baths
  • the database or search tool/engine may be set up to allow the user to input non-numeric bias and fuzziness parameters that are more intuitive and user friendly. These non-numeric parameters are then equated to specific numeric parameters by the database application, search tool/engine or other system/software.
  • each query field i.e. selling price, number of rooms, number of baths
  • each query field could have its own separate fuzziness parameter.
  • FIG. 10 shows the fuzzy score 1000 for each record based only on number of baths. Since the user has specified a bias toward the upper bound of the target range (as indicated by the user's desire for more baths), and since a single target value is also specified, the same Lorentzian fuzzy score formula used to calculate the fuzzy scores for each record based on number of rooms is used.
  • an aggregate fuzzy score is calculated for each record. In one embodiment, this is accomplished by simply adding the fuzzy scores of each query field together. In another embodiment, an aggregate fuzzy score is calculated by using a weighted sum. By using a weighted sum the results of a specific query field(s) can be given more weight. For example, a user may consider the selling price of a home more important than any of the other query fields. In order to incorporate this into the ranking methodology, the fuzzy scores calculated based only on the selling price of the home are multiplied by some factor so that the selling price of the home has more influence on the aggregate fuzzy scores.
  • the aggregate fuzzy scores 1100 for each record in this example are shown in FIG. 11 .
  • the fuzzy scores of each query field have simply been added together.
  • the database records are ranked according to aggregate fuzzy score.
  • the ranked database records 1110 are also shown in FIG. 11 . With the homes ranked, the user can easily identify those homes that best match the user's query.
  • the home selling for $200,000 with 3 rooms and 3 baths is ranked the highest. While a traditional database search would not have retrieved any records outside the user's input target range of $200,000-$230,000, 3 rooms and 3 baths, the present invention has returned all 9 records. Worth noting is the home selling for $195,000 with 3 rooms and 4 baths and the home selling for $235,000 with 4 rooms and 3 baths. Both of these homes would not have been included within the search results in a traditional database search, but in the present invention are ranked high due to the incorporation of the fuzziness parameters in the Lorentzian fuzzy score formulas.

Abstract

The present invention relates to a method for searching a document database such as the Internet and ranking the results obtained from such a search. The invention 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.

Description

    CROSS-REFERENCE TO RELATED APPLICATIONS
  • This application is a continuation of pending application Ser. No. 10/745,552, filed Dec. 29, 2003, entitled “Data Ranking With A Lorentzian Fuzzy Score”, which is a continuation of application Ser. No. 09/952,518, filed Sep. 12, 2001, entitled “Data Ranking With A Lorentzian Fuzzy Score”, now U.S. Pat. No. 6,701,312, both of which are incorporated herein by reference in their entirety.
  • BACKGROUND OF THE INVENTION
  • 1. Field of the Invention
  • The present invention relates to information retrieval in a data processing system. The present invention further relates to a method for searching a document database such as the Internet and ranking the results obtained from such a search.
  • 2. Description of Related Art
  • A computer's logic is both its strength and its weakness; it can only perform what it is told to do. If an alarm clock is set to go off at 6:00 PM, it will go off at exactly that time, even if it was obviously meant to go off at 6:00 AM. People in the real world can solve problems and make decisions relatively easy, but even the simplest decisions are often too difficult to be handled by computer. Fuzzy logic query processing helps to bridge the gap.
  • Databases are strategic tools because they support business processes. In order for a database to be useful, data must be compiled into information using tools such as queries. Queries allow a user to specify what data to retrieve from a database, and in what form. Fuzzy querying provides a way to retrieve data that was intended to be retrieved, without requiring exact parameters to be defined.
  • Non-fuzzy query processing relies on Boolean logic, which limits results to true or false (1 or 0). Fuzzy query processing is a superset of Boolean logic that can handle partial truths. Instead of a search results being limited to return a value of true or false, the query returns values as x % true or x % a member of a subset.
  • Fuzzy queries rely on the use of fuzzy quantifiers. Dr. Lotfi A. Zadeh, the founder of fuzzy logic theory, defined two kinds of quantifiers: absolute and relative. An absolute quantifier can be represented as fuzzy subsets of the non-negative numbers and use words such as at least three or about five. Relative qualifiers are represented as fuzzy subsets of the unit interval and use words such as most, at least half, or almost all.
  • Fuzzy queries do not take the place of the more structured queries, but expand the alternatives available. Boolean systems use selection and then ordering as a mechanism, where a fuzzy system relies on a single mechanism of overall membership degree. A fuzzy system allows for compromise between the various criteria, where a Boolean system can produce a subset of previously selected elements. There are times when Boolean logic is too rigid to be meaningful to a user. A fuzzy query allows a user to find elements that satisfy a criterion and ranks the results.
  • FIG. 1 illustrates the typical flow of a fuzzy database query. After identifying the need for a report 100, the user queries a database 110. The database returns a record, which is matched against predefined criteria 120 to determine the degree to which a match has occurred. The degree is then compared to a threshold value 125 to determine whether the record satisfies the users query 130 or whether the record should be discarded 135. In general, a fuzzy database query differs from a non-fuzzy query by adding steps to match the data to predefined criteria and compare the value to a threshold specified in the query.
  • An object can be a member of multiple sets with a different degree of membership. The degree of membership is a scale from zero to one. Complete membership has a value of one, and no membership has a value of zero. When running a fuzzy query in a control system, the output is calculated based on the value of membership a given input has in the configured fuzzy sets. Each combination of sets is configured to have a specified output. The output is based on the weighted sum of the amount of membership in each set. The fuzzy models may be used in conjunction with probabilistic models to find a solution.
  • FIG. 2 shows the three transformations of the system inputs 200 to outputs 205 in a fuzzy system. The process of “fuzzification” 210 is a methodology to generalize any specific theory from a precise form to continuous form. It decomposes a system input or output into one or more fuzzy sets. After the decomposition into fuzzy sets, fuzzy rule association 215 applies a set of rules to a combination of inputs. The rules determine the action and relate the variable into a numeric value. Once the numeric value is determined, de-fuzzification 220 converts the fuzzy result into an exact output value.
  • For example, telling a driving student to apply the brakes 74 feet from the crosswalk is too precise to be followed. Vague wording like “apply the brakes soon”, however, can be interpreted and acted upon. The instruction is received in a fuzzy form, the person associates the message using past experiences, then defuzzifies the message in order to actually apply the brakes at the appropriate time. Fuzzy queries expand query capabilities by allowing for ambiguity and partial membership.
  • SUMMARY OF THE INVENTION
  • The invention relates to database searching and the ranking of a set of numerical data according to a set of user specified preferences, including target range, fuzziness and bias.
  • In many database query applications, data records are returned when certain field data falls into a user specified target range. The introduction of fuzziness in the present invention extends the returned data set by including records that are “close” to the target range. The addition of a bias also increases the usefulness of the database query by providing a means to rank the results of the query in a specified order.
  • The present invention adapts the Lorentzian function to include variables for fuzziness and bias in order to calculate fuzzy scores, which are used to rank the results of database searches. In one embodiment, only a single input target range is used in the database query. In another embodiment, however, multiple query fields are used. According to another embodiment, when multiple query fields are used fuzzy scores are calculated for each query field in each record. The fuzzy scores of each query field in each record are then aggregated into a composite fuzzy score that is then used to rank the results of the database query.
  • Other features, advantages, and embodiments of the invention are set forth in part in the description that follows, and in part, will be obvious from this description, or may be learned from the practice of the invention.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • The foregoing and other features and advantages of this invention will become more apparent by reference to the following detailed description of the invention taken in conjunction with the accompanying drawings.
  • FIG. 1 shows the typical flow of a fuzzy database query.
  • FIG. 2 depicts the three main transformations in a fuzzy system.
  • FIG. 3 shows a graph of the Lorentzian function.
  • FIG. 4 shows calculated Lorentzian fuzzy scores where the bias is less than zero.
  • FIG. 5 shows calculated Lorentzian fuzzy scores where the bias is greater than zero.
  • FIG. 6 shows two graphs of calculated Lorentzian fuzzy scores where the fuzziness parameters are set to zero (i.e. there is no fuzziness).
  • FIG. 7 shows two graphs of calculated Lorentzian fuzzy scores in the special case where the target range degenerates into a single value.
  • FIG. 8 shows a table of calculated fuzzy scores for each record based only on selling price.
  • FIG. 9 shows a table of calculated fuzzy scores for each record based only on number of rooms.
  • FIG. 10 shows a table of calculated fuzzy scores for each record based only on number of baths.
  • FIG. 11 shows aggregate fuzzy scores for each record and ranked database records.
  • DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS OF THE INVENTION
  • As embodied and broadly described herein, the preferred embodiments of the present invention are directed to a method for searching a document database such as the Internet according to a set of user specified preferences, including target range, fuzziness and bias and ranking the results obtained from such a search.
  • The basic building block of the fuzzy score is the Lorentzian function: 1 1 + [ x - x 0 a ] 2
    As shown in FIG. 3, the Lorentzian function 300 has a bell-shaped drop off from a central peak. FIG. 3 depicts the Lorentzian function with a=5, x0=0, and x ranging from −10 to 10. The fuzziness of the score is proportional to the width of the Lorentzian function. The bias is introduced by a linear variation within the target range.
  • The fuzzy score allows a user to rank a set of numerical data according to the user's input. The qualitative behavior of the Lorentzian fuzzy score is described as follows. For data that lies outside the target range, the score is zero without fuzziness and in the range [0, 1] with fuzziness. For data that is inside the target range, the score varies linearly, with a bias (higher score) towards either the lower or upper bound of the target range.
  • The following notation and terminology is used throughout the specification:
    Name Symbols Notes
    Data Value x1, x2, . . ., xk The maximal and minimal
    data values are Max(xk) and
    Min(xk), respectively
    Target Range (xmin, xmax) xmax ≧ xmin
    Bias β β may be greater or smaller
    than zero
    Fuzzy Parameters a 1 = α1 * Δ 2 Δ = Max(xk) − Min(xk)
    a 2 = α2 * Δ 2
    Fuzziness or Closeness α1 and α2 α1 ≧ 0 and α2 ≧ 0
  • According to an embodiment of the present invention, the present invention can calculate a fuzzy score for a user defined database query and rank the results of the query. The fuzzy score is calculated based on user specified criteria including, but not limited to, target range (xmin, xmax), fuzziness (α1 and α2) and bias (β). In another embodiment, the fuzziness and/or bias is static and set by the software/system performing the search. While the parameters for fuzziness and bias are numeric, it is contemplated in at least one embodiment that these parameters be translated into more easily understood terminology for user selection. For example, instead of having a user specify a numeric value for each of the fuzziness parameters, α1 and α2, the user may select from a list of fuzziness categories (i.e. small, medium, large). The terms small, medium and large would equate to specific values of α1 and α2 and would be used to calculate a fuzzy score as described herein. The same holds true for the bias parameter, β. Instead of having a user specify a numeric bias value, the user may select from a list of bias categories (i.e. toward the lower bound, toward the upper bound). These categories would also be equated to specific numeric values and would be used to calculate a fuzzy score as described herein.
  • In order to illustrate the application of the Lorentzian function to calculate a fuzzy score, several examples will be given. Each example will illustrate how variations in user input parameters (i.e. target values, fuzziness, bias) affect the Lorentzian function as it is used to calculate a fuzzy score. For consistency, the examples will be based on a user who is shopping for a new home via a web site containing new home data. The web site allows the user to search a database of new homes based on the selling price of the home. For the following examples it is assumed the user is interested in houses between $200,000 and $250,000. Thus, the target range is defined as xmin=200000 and xmax=250000. In addition, the web site allows the user to input fuzziness values, α1 and α2, and a bias value, β.
  • For bias (β) values less than zero (i.e. biased toward the lower bound of the target range), the Lorentzian fuzzy score has the following formula:
    For β<0, S ( x ) = 1 1 + ( x - x min a 1 ) 2 x < x min 1 + β * ( x - x min ) x max - x min x min x x max 1 + β 1 + ( x - x max a 2 ) 2 x max < x
    where x represents any data values, i.e., x ε {x1, . . . , xk}.
  • FIG. 4 shows a sample plot 400 of S(x) with xmin=200000, xmax=250000, α1=2, α2=1, and β=−0.1. The negative slope of the graph between the target values $200,000 and $250,000 is the result of the negative bias. The negative bias affects the fuzzy score calculated from data values between the target range by biasing those data values closer to the lower end of the target range. In addition, worth noting are the calculated fuzzy scores for the data points that lie outside the target range. The non-zero scores for those data points lying outside the target range are a direct result of the incorporation of the fuzziness parameters into the Lorentzian function. Consistent with the Lorentzian function is the rapid drop off of the fuzzy scores for the data points that lie farthest from the target range. In this example, and as illustrated in the table of result rankings 410, the query would have returned records for each of the 12 homes in the database. The addition of the fuzzy scores, however, makes it easy for the user to visualize the records that best conform to the original search parameters.
  • For bias (β) values greater than zero (i.e. biased toward the upper bound of the target range), the Lorentzian fuzzy score has the following formula:
    For β>0, S ( x ) = 1 - β 1 + ( x - x min a 1 ) 2 x < x min 1 + β * ( x - x max ) x max - x min x min x x max 1 1 + ( x - x max a 2 ) 2 x max < x
    where x represents any data values, i.e., x ε {x1, . . . , xk}.
  • FIG. 5 shows a sample plot 500 of S(x) with xmin=200000, xmax=250000, α1=2, α2=1, and β=0.1. The positive slope of the graph between the target values $200,000 and $250,000 is the result of the positive bias. The positive bias affects the fuzzy score calculated from data values between the target range by biasing those data values closer to the upper end of the target range. In addition, worth noting are the calculated fuzzy scores for the data points that lie outside the target range. The non-zero scores for those data points lying outside the target range are a direct result of the incorporation of the fuzziness parameters into the Lorentzian function. Consistent with the Lorentzian function is the rapid drop off of the fuzzy scores for the data points that lie farthest from the target range. In this example, and as illustrated in the table of result rankings 510, the query would have returned records for each of the 12 homes in the database. The addition of the fuzzy scores, however, makes it easy for the user to visualize the records that best conform to the original search parameters.
  • In the case of no fuzziness, α1=0, α2=0, and where the bias (β) value is less than zero (i.e. biased toward the lower bound of the target range), the Lorentzian fuzzy score has the following formula:
    For β<0, α1=0, and α2=0, S ( x ) = 0 x < x min 1 + β * ( x - x min ) x max - x min x min x x max 0 x max < x
    where x represents any data values, i.e., x ε {x1, . . . , xk}.
  • In the case of no fuzziness, α1=0, α2=0, and where the bias (β) value is greater than zero (i.e. biased toward the upper bound of the target range), the Lorentzian fuzzy score has the following formula:
    For β>0, α1=0, and α2=0, S ( x ) = 0 x < x min 1 + β * ( x - x max ) x max - x min x min x x max 0 x max < x
    where x represents any data values, i.e., x ε {x1, . . . , xk}
  • FIG. 6 shows a sample plot 600 of S(x) with xmin=200000, xmax=250000, α1=0, α2=0, and β=−0.1. FIG. 6 also shows another sample plot 610 of S(x) with xmin=200000, xmax=250000, α1=0, α2=0, and β3=0.1. As with plots 400 and 500, plots 600 and 610 illustrate the effect a negative and positive bias have on the calculated fuzzy scores. As previously stated, a negative bias results in the negative slope of the plot 600 between the target values, while a positive bias results in the positive slope of the plot 610 between the target values. Since the fuzziness parameters, α1 and α2, were set to zero in both plot 600 and plot 610, all data values lying outside of the user defined target range are given a fuzzy score of zero. While the same query produced 12 records with fuzziness (as illustrated in FIGS. 4 and 5), without fuzziness only 4 records are retrieved. Moreover, records that would probably be of interest to the user, i.e. the $252,000 home, are never retrieved when the query does not incorporate the fuzziness parameters.
  • In the special case where the target range degenerates into a single value (i.e. xmin=xmax=x) and where the bias (β) value is less than zero (i.e. biased toward the lower bound of the target range), the Lorentzian fuzzy score has the following formula:
    For β<0 and xmin=xmax=x, S ( x ) = 1 1 + ( x - x _ a 1 ) 2 _ x < x _ 1 x = x _ 1 + β 1 + ( x - x _ a 2 ) 2 x > x _
    where x represents any data values, i.e., x ε {x1, . . . , xk}.
  • In the special case where the target range degenerates into a single value (i.e. xmin=xmax=x) and where the bias (β) value is greater than zero (i.e. biased toward the upper bound of the target range), the Lorentzian fuzzy score has the following formula: For β > 0 and x min = x max = x _ , 1 - β 1 + ( x - x _ a 1 ) 2 _ x < x _ S ( x ) = 1 x = x _ 1 1 + ( x - x _ a 2 ) 2 x > x _
    where x represents any data values, i.e., X ε {x1, . . . , xk}.
  • FIG. 7 shows a sample plot 700 of S(x) with x=225000, α1=1, α2=1, and β=−0.1. FIG. 7 also shows another sample plot 710 of S(x) with x=225000, α1=1, α2=1, and β=0.1. The affect of the bias in plot 700 and 710 is more difficult to discern since there is no target range. However, a close inspection of plot 700 shows that the negative bias does influence the calculated fuzzy scores for those data values less than the target value and in plot 710 that the positive bias does influence the calculated fuzzy scores for those data values greater than then target value.
  • While each of the above examples has dealt with single term queries (i.e. where the user is searching based only on the selling price of a home), the present invention is easily extended to include queries with multiple search terms. To illustrate how the Lorentzian function can be used in a multiple-field query a more sophisticated home buying example is explored. The home buying database in this example is on the Internet and the user is given the option to search for new homes based on selling price, number of rooms, and number of baths. For this example, it is assumed the database contains the following records:
    Selling Price
    $150,000 $170,000 $195,000 $200,000 $225,000 $230,000 $235,000 $260,000 $280,000
    Number 3 2 3 3 5 3 4 4 3
    of Rooms
    Number 2.5 2 4 3 3.5 2 3 3 1.5
    of Baths
  • It is further assumed that the user has entered the following query:
    Selling Price: $200,000-$230,000 Bias: Lower Priced Homes
    Number of Rooms: 3 Bias: More Rooms
    Number of Baths: 3 Bias: More Baths
    Fuzziness: Medium
  • As previously discussed, and as illustrated here, the database or search tool/engine may be set up to allow the user to input non-numeric bias and fuzziness parameters that are more intuitive and user friendly. These non-numeric parameters are then equated to specific numeric parameters by the database application, search tool/engine or other system/software. For this example, the following non-numeric user specified bias parameters are equated to the following numeric parameters: Bias Lower Priced Homes=−0.1, More Rooms=0.1, More Baths=0.1. In addition, for this example, the following non-numeric specified fuzziness parameter is equated to the following numeric parameters: Medium→α1=2, α2=2. While the user, in this example, was only allowed to enter a single fuzziness parameter for the entire query, it is contemplated in another embodiment that each query field (i.e. selling price, number of rooms, number of baths) could have its own separate fuzziness parameter.
  • The process for searching the database and ranking the results of the query is straightforward. First, a fuzzy score is calculated for each query field and for each record using the appropriate Lorentzian formula. Second, an aggregate fuzzy score is calculated for each record using the fuzzy scores for each query field. Finally, the results are ranked according to the aggregate calculated fuzzy scores for each record.
  • FIG. 8 shows the fuzzy score 800 for each record based only on selling price. Since the user has specified a bias toward the lower bound of the target range (as indicated by the user's desire for lower priced homes), the following Lorentzian fuzzy score formula is used:
    For β<0, S ( x ) = 1 1 + ( x - x min a 1 ) 2 x < x min 1 + β * ( x - x min ) x max - x min x min x x max 1 + β 1 + ( x - x max a 2 ) 2 x max < x
    where x represents any data values, i.e., x ε {x1, . . . , xk}, xmin=200000, xmax=230000, α1=2, α2=2, and β=−0.1.
  • FIG. 9 shows the fuzzy score 900 for each record based only on number of rooms. Since the user has specified a bias toward the upper bound of the target range (as indicated by the user's desire for more rooms), the following Lorentzian fuzzy score formula is used: For β > 0 and x min = x max = x _ , 1 - β 1 + ( x - x _ a 1 ) 2 _ x < x _ S ( x ) = 1 x = x _ 1 1 + ( x - x _ a 2 ) 2 x > x _
    where x represents any data values, i.e., x ε {x1, . . . , xk}, x=3, α1=2, α2=2, and β=0.1.
  • FIG. 10 shows the fuzzy score 1000 for each record based only on number of baths. Since the user has specified a bias toward the upper bound of the target range (as indicated by the user's desire for more baths), and since a single target value is also specified, the same Lorentzian fuzzy score formula used to calculate the fuzzy scores for each record based on number of rooms is used.
  • Once a fuzzy score is calculated for each query field for each record, an aggregate fuzzy score is calculated for each record. In one embodiment, this is accomplished by simply adding the fuzzy scores of each query field together. In another embodiment, an aggregate fuzzy score is calculated by using a weighted sum. By using a weighted sum the results of a specific query field(s) can be given more weight. For example, a user may consider the selling price of a home more important than any of the other query fields. In order to incorporate this into the ranking methodology, the fuzzy scores calculated based only on the selling price of the home are multiplied by some factor so that the selling price of the home has more influence on the aggregate fuzzy scores.
  • The aggregate fuzzy scores 1100 for each record in this example are shown in FIG. 11. In this example the fuzzy scores of each query field have simply been added together. Once the aggregate fuzzy scores are calculated, the database records are ranked according to aggregate fuzzy score. The ranked database records 1110 are also shown in FIG. 11. With the homes ranked, the user can easily identify those homes that best match the user's query.
  • As would be expected based on the input query, the home selling for $200,000 with 3 rooms and 3 baths is ranked the highest. While a traditional database search would not have retrieved any records outside the user's input target range of $200,000-$230,000, 3 rooms and 3 baths, the present invention has returned all 9 records. Worth noting is the home selling for $195,000 with 3 rooms and 4 baths and the home selling for $235,000 with 4 rooms and 3 baths. Both of these homes would not have been included within the search results in a traditional database search, but in the present invention are ranked high due to the incorporation of the fuzziness parameters in the Lorentzian fuzzy score formulas.
  • Other embodiments and uses of the present invention will be apparent to those skilled in the art from consideration of this application and practice of the invention disclosed herein. The present description and examples should be considered exemplary only, with the true scope and spirit of the invention being indicated by the following claims. As will be understood by those of ordinary skill in the art, variations and modifications of each of the disclosed embodiments, including combinations thereof, can be made within the scope of this invention as defined by the following claims.

Claims (22)

1. A method for ranking a plurality of elements, wherein a plurality of numerical parameters characterizes each element, the method comprising:
prior to ranking receiving an indication of at least one of fuzziness and bias as inputs to ranking;
ranking a plurality of elements based at least in part on an aggregate score;
the aggregate score based at least in part on a plurality of Lorentzian fuzzy scores;
each Lorentzian fuzzy score based at least in part on a numerical parameter characterizing each element, wherein the formula used to calculate each Lorentzian fuzzy score is determined at least in part based on the polarity of the bias input.
2. The method of claim 1, wherein at least one of the numerical parameters is a target range having a minimum numeric value and a maximum numeric value.
3. The method of claim 2, wherein the polarity of the bias input is negative and wherein the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 1 1 + ( x - x min a 1 ) 2 x < x min 1 + β * ( x - x min ) x max - x min x min x x max 1 + β 1 + ( x - x max a 2 ) 2 x max < x
where x represents any data values, i.e., x ε {x1, . . . , xk}.
4. The method of claim 2, wherein the polarity of the bias input is positive and wherein the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 1 - β 1 + ( x - x min a 1 ) 2 x < x min 1 + β * ( x - x max ) x max - x min x min x x max 1 1 + ( x - x max a 2 ) 2 x max < x
where x represents any data values, i.e., x ε {x1, . . . , xk}.
5. The method of claim 1, wherein the polarity of the bias input is negative and wherein the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 1 1 + ( x - x _ a 1 ) 2 x < x _ 1 x = x _ 1 + β 1 + ( x - x _ a 2 ) 2 x > x _
where x represents any data values, i.e., x ε {x1, . . . , xk}.
6. The method of claim 1, wherein the polarity of the bias input is positive and wherein the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 1 - β 1 + ( x - x _ a 1 ) 2 _ x < x _ 1 x = x _ 1 1 + ( x - x _ a 2 ) 2 x > x _
where x represents any data values, i.e., x ε {x1, . . . , xk}.
7. The method of claim 1 wherein the aggregate score is based at least in part on summing the plurality of Lorentzian fuzzy scores.
8. The method of claim 1 wherein after calculating each Lorentzian fuzzy score, the aggregate score is based at least in part on weighted summing of the plurality of Lorentzian fuzzy scores.
9. The method of claim 8 further comprising:
prior to ranking, receiving an indication of weight for at least one parameter.
10. The method of claim 1 wherein at least one indication is quantitative.
11. The method of claim 1 wherein at least one indication is qualitative.
12. The method of claim 11 wherein each qualitative indication is mapped to a quantitative indication.
13. A method for ranking a plurality of elements, wherein a numerical parameter characterizes each element, the method comprising:
prior to ranking receiving an indication of at least one of fuzziness and bias as inputs to ranking;
ranking a plurality of elements based at least in part on a Lorentzian fuzzy score based at least in part on a numerical parameter characterizing each element, wherein the formula used to calculate each Lorentzian fuzzy score is determined at least in part based on the polarity of the bias input.
14. The method of claim 13, wherein at least one of the numerical parameters is a target range having a minimum numeric value and a maximum numeric value.
15. The method of claim 14, wherein the polarity of the bias input is negative and wherein the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 1 1 + ( x - x min a 1 ) 2 x < x min 1 + β * ( x - x min ) x max - x min x min x x max 1 + β 1 + ( x - x max a 2 ) 2 x max < x
where x represents any data values, i.e., x ε {x1, . . . , xk}.
16. The method of claim 14, wherein the polarity of the bias input is positive and wherein the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 1 - β 1 + ( x - x min a 1 ) 2 x < x min 1 + β * ( x - x max ) x max - x min x min x x max 1 1 + ( x - x max a 2 ) 2 x max < x
where x represents any data values, i.e., x ε {x1, . . . , xk}.
17. The method of claim 13, wherein the polarity of the bias input is negative and wherein the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 1 1 + ( x - x _ a 1 ) 2 _ x < x _ 1 x = x _ 1 + β 1 + ( x - x _ a 2 ) 2 x > x _
where x represents any data values, i.e., x ε {x1, . . . , xk}.
18. The method of claim 13, wherein the polarity of the bias input is positive and wherein the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 1 - β 1 + ( x - x _ a 1 ) 2 _ x < x _ 1 x = x _ 1 1 + ( x - x _ a 2 ) 2 x > x _
where x represents any data values, i.e., x ε {x1, . . . , xk}.
19. The method of claim 13, wherein at least one indication is quantitative.
20. The method of claim 13, wherein at least one indication is qualitative.
21. The method of claim 20, wherein each qualitative indication is mapped to a quantitative indication.
22. A method for ranking a plurality of elements, wherein a numerical parameter characterizes each element, the method comprising:
prior to ranking receiving an indication of at least one of fuzziness and bias, and a target range having a minimum numeric value and a maximum numeric value, as inputs to ranking;
ranking a plurality of elements based at least in part on a Lorentzian fuzzy score based at least in part on a numerical parameter characterizing each element, wherein the formula used to calculate each Lorentzian fuzzy score is determined at least in part based on the polarity of the bias input and wherein when the fuzziness indication is set or preset to zero and the polarity of the bias input is positive, the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 0 x < x min 1 + β * ( x - x max ) x max - x min x min x x max 0 x max < x
where x represents any data values, i.e., x ε {x1, . . . , xk},
wherein when the fuzziness indication is set or preset to zero and the polarity of the bias input is negative, the fuzzy score is calculated at least in part by using the following Lorentzian fuzzy score formula:
S ( x ) = 0 x < x min 1 + β * ( x - x min ) x max - x min x min x x max 0 x max < x
where x represents any data values, i.e., X ε {x1, . . . , xk}.
US11/812,954 2001-09-12 2007-06-22 Data ranking with a lorentzian fuzzy score Abandoned US20070271261A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US11/812,954 US20070271261A1 (en) 2001-09-12 2007-06-22 Data ranking with a lorentzian fuzzy score

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US09/952,518 US6701312B2 (en) 2001-09-12 2001-09-12 Data ranking with a Lorentzian fuzzy score
US10/745,552 US7257586B2 (en) 2001-09-12 2003-12-29 Data ranking with a Lorentzian fuzzy score
US11/812,954 US20070271261A1 (en) 2001-09-12 2007-06-22 Data ranking with a lorentzian fuzzy score

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US10/745,552 Continuation US7257586B2 (en) 2001-09-12 2003-12-29 Data ranking with a Lorentzian fuzzy score

Publications (1)

Publication Number Publication Date
US20070271261A1 true US20070271261A1 (en) 2007-11-22

Family

ID=25492981

Family Applications (3)

Application Number Title Priority Date Filing Date
US09/952,518 Expired - Fee Related US6701312B2 (en) 2001-09-12 2001-09-12 Data ranking with a Lorentzian fuzzy score
US10/745,552 Expired - Fee Related US7257586B2 (en) 2001-09-12 2003-12-29 Data ranking with a Lorentzian fuzzy score
US11/812,954 Abandoned US20070271261A1 (en) 2001-09-12 2007-06-22 Data ranking with a lorentzian fuzzy score

Family Applications Before (2)

Application Number Title Priority Date Filing Date
US09/952,518 Expired - Fee Related US6701312B2 (en) 2001-09-12 2001-09-12 Data ranking with a Lorentzian fuzzy score
US10/745,552 Expired - Fee Related US7257586B2 (en) 2001-09-12 2003-12-29 Data ranking with a Lorentzian fuzzy score

Country Status (1)

Country Link
US (3) US6701312B2 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080021875A1 (en) * 2006-07-19 2008-01-24 Kenneth Henderson Method and apparatus for performing a tone-based search
US20130167059A1 (en) * 2011-12-21 2013-06-27 New Commerce Solutions Inc. User interface for displaying and refining search results

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7027987B1 (en) * 2001-02-07 2006-04-11 Google Inc. Voice interface for a search engine
US6701312B2 (en) * 2001-09-12 2004-03-02 Science Applications International Corporation Data ranking with a Lorentzian fuzzy score
US6781464B2 (en) * 2001-10-30 2004-08-24 Kabushiki Kaisha Toshiba Balanced amplifier and filter using the same
EP1532815A1 (en) * 2002-08-29 2005-05-25 Opentv, Inc. Video-on-demand and targeted advertising
US7281005B2 (en) * 2003-10-20 2007-10-09 Telenor Asa Backward and forward non-normalized link weight analysis method, system, and computer program product
JP2005250980A (en) * 2004-03-05 2005-09-15 Oki Electric Ind Co Ltd Document retrieval system, retrieval condition input device, retrieval execution device, document retrieval method and document retrieval program
US7257577B2 (en) * 2004-05-07 2007-08-14 International Business Machines Corporation System, method and service for ranking search results using a modular scoring system
US7493320B2 (en) 2004-08-16 2009-02-17 Telenor Asa Method, system, and computer program product for ranking of documents using link analysis, with remedies for sinks
US7991787B2 (en) * 2004-08-31 2011-08-02 Sap Ag Applying search engine technology to HCM employee searches
US7596555B2 (en) * 2004-08-31 2009-09-29 Sap Ag Fuzzy recipient and contact search for email workflow and groupware applications
US7792811B2 (en) * 2005-02-16 2010-09-07 Transaxtions Llc Intelligent search with guiding info
US20060212341A1 (en) * 2005-03-15 2006-09-21 Powers William D System and method for profiling jurors
US7596556B2 (en) * 2005-09-15 2009-09-29 Microsoft Corporation Determination of useful convergence of static rank
US7536373B2 (en) * 2006-02-14 2009-05-19 International Business Machines Corporation Resource allocation using relational fuzzy modeling
US8495075B2 (en) * 2006-03-08 2013-07-23 Apple Inc. Fuzzy string matching of media meta-data
WO2009032770A2 (en) * 2007-08-29 2009-03-12 Partnet, Inc. Systems and methods for providing a confidence-based ranking algorithm
US8010535B2 (en) * 2008-03-07 2011-08-30 Microsoft Corporation Optimization of discontinuous rank metrics
US20100153370A1 (en) * 2008-12-15 2010-06-17 Microsoft Corporation System of ranking search results based on query specific position bias
US20100169106A1 (en) * 2008-12-30 2010-07-01 William Powers System and method for profiling jurors
US8977627B1 (en) * 2011-11-01 2015-03-10 Google Inc. Filter based object detection using hash functions
US9262541B2 (en) 2013-10-18 2016-02-16 Google Inc. Distance based search ranking demotion
CN115357777B (en) * 2022-08-26 2023-09-01 福建师范大学 Fuzzy theory-based user tag weight evaluation method

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5963940A (en) * 1995-08-16 1999-10-05 Syracuse University Natural language information retrieval system and method
US5983220A (en) * 1995-11-15 1999-11-09 Bizrate.Com Supporting intuitive decision in complex multi-attributive domains using fuzzy, hierarchical expert models
US6014664A (en) * 1997-08-29 2000-01-11 International Business Machines Corporation Method and apparatus for incorporating weights into data combinational rules
US6070160A (en) * 1995-05-19 2000-05-30 Artnet Worldwide Corporation Non-linear database set searching apparatus and method
US6131082A (en) * 1995-06-07 2000-10-10 Int'l.Com, Inc. Machine assisted translation tools utilizing an inverted index and list of letter n-grams
US6202060B1 (en) * 1996-10-29 2001-03-13 Bao Q. Tran Data management system
US6243713B1 (en) * 1998-08-24 2001-06-05 Excalibur Technologies Corp. Multimedia document retrieval by application of multimedia queries to a unified index of multimedia data for a plurality of multimedia data types
US6269368B1 (en) * 1997-10-17 2001-07-31 Textwise Llc Information retrieval using dynamic evidence combination
US6701312B2 (en) * 2001-09-12 2004-03-02 Science Applications International Corporation Data ranking with a Lorentzian fuzzy score
US7076487B2 (en) * 2001-04-11 2006-07-11 The Penn State Research Foundation Single-pass low-storage arbitrary probabilistic location estimation for massive data sets

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6070160A (en) * 1995-05-19 2000-05-30 Artnet Worldwide Corporation Non-linear database set searching apparatus and method
US6131082A (en) * 1995-06-07 2000-10-10 Int'l.Com, Inc. Machine assisted translation tools utilizing an inverted index and list of letter n-grams
US5963940A (en) * 1995-08-16 1999-10-05 Syracuse University Natural language information retrieval system and method
US5983220A (en) * 1995-11-15 1999-11-09 Bizrate.Com Supporting intuitive decision in complex multi-attributive domains using fuzzy, hierarchical expert models
US6202060B1 (en) * 1996-10-29 2001-03-13 Bao Q. Tran Data management system
US6014664A (en) * 1997-08-29 2000-01-11 International Business Machines Corporation Method and apparatus for incorporating weights into data combinational rules
US6269368B1 (en) * 1997-10-17 2001-07-31 Textwise Llc Information retrieval using dynamic evidence combination
US6243713B1 (en) * 1998-08-24 2001-06-05 Excalibur Technologies Corp. Multimedia document retrieval by application of multimedia queries to a unified index of multimedia data for a plurality of multimedia data types
US7076487B2 (en) * 2001-04-11 2006-07-11 The Penn State Research Foundation Single-pass low-storage arbitrary probabilistic location estimation for massive data sets
US6701312B2 (en) * 2001-09-12 2004-03-02 Science Applications International Corporation Data ranking with a Lorentzian fuzzy score

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080021875A1 (en) * 2006-07-19 2008-01-24 Kenneth Henderson Method and apparatus for performing a tone-based search
US20130167059A1 (en) * 2011-12-21 2013-06-27 New Commerce Solutions Inc. User interface for displaying and refining search results

Also Published As

Publication number Publication date
US7257586B2 (en) 2007-08-14
US20030065660A1 (en) 2003-04-03
US20040139068A1 (en) 2004-07-15
US6701312B2 (en) 2004-03-02

Similar Documents

Publication Publication Date Title
US20070271261A1 (en) Data ranking with a lorentzian fuzzy score
Croft et al. A retrieval model incorporating hypertext links
Kacprzyk et al. Linguistic database summaries and their protoforms: towards natural language based knowledge discovery tools
US7346608B2 (en) Method and apparatus for query and analysis
US8407229B2 (en) Systems and methods for aggregating search results
Cross Fuzzy information retrieval
EP1181653A1 (en) Wide-spectrum information search engine
Kacprzyk et al. Fuzzy linguistic summaries of databases for an efficient business data analysis and decision support
Sevastjanov et al. Aggregation of aggregating modes in MCDM: Synthesis of Type 2 and Level 2 fuzzy sets
McQuarrie et al. Using values to measure attitudes toward discontinuous innovation
Maimon et al. Information-theoretic fuzzy approach to data reliability and data mining
Trousse et al. Using user behaviour similarity for recommendation computation: the broadway approach.
US20070043755A1 (en) Ranking of records in a relational database
Aligon et al. A holistic approach to OLAP sessions composition: The falseto experience
Džeroski Data mining in a nutshell
Akritidis et al. An unsupervised distance-based model for weighted rank aggregation with list pruning
Hoppe et al. Towards task models for embedded information retrieval
Resteanu et al. On optimal choice problem solving
Subtil et al. A fuzzy information retrieval and management system and its applications
Achs Computed answer from uncertain knowledge: A model for handling uncertain information
Shea et al. ivmte: An R Package for Extrapolating Instrumental Variable Estimates Away From Compliers
Ferrettini et al. A framework for user assistance on predictive models
Kurniawan et al. Elective Courses Recommendation System using Genetic Algorithm
Boman et al. Eliminating paraconsistencies in 4-valued cooperative deductive multidatabase systems with classical negation
Chen et al. Top-N query: Query language, distance function, and processing strategies

Legal Events

Date Code Title Description
AS Assignment

Owner name: SCIENCE APPLICATIONS INTERNATIONAL CORPORATION, CA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LAU, YUN-TUNG;NAGY, MARTON;REEL/FRAME:019521/0583;SIGNING DATES FROM 20010907 TO 20010910

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION