Item to vector based categorization

Patent metadata

Field	Value
Publication number	US-10380162-B2
Application number	US-201615334808-A
Country	US
Kind code	B2
Filing date	Oct 26, 2016
Priority date	Oct 26, 2016
Publication date	Aug 13, 2019
Grant date	Aug 13, 2019

Abstract

A device may receive information that identifies an item to be categorized. The device may map the item to a first vector based on the information that identifies the item. The device may compare the first vector to a second vector based on mapping the item to the first vector. The device may determine a similarity value between the first vector and the second vector based on comparing the first vector and the second vector. The device may determine that the similarity value satisfies a threshold. The device may determine a category associated with the item based on the similarity value satisfying the threshold. The second vector may be associated with the category. The device may provide information that identifies the category associated with the item to cause an action to be performed.

First claim

What is claimed is:

1. A device, comprising:
one or more processors to:
receive information that identifies an item to be categorized, the item including a set of first terms;
map the item to a first vector based on the set of first terms, the first vector including a set of first values that correspond to the set of first terms,
a first term, from the set of first terms, being mapped to a first value, from the set of first values, and a second term, from the set of first terms, being mapped to a second value, from the set of first values;

compare the first vector and a second vector associated with a categorized item,
the second vector including a set of second values that correspond to a set of second terms associated with the categorized item,
a first term, from the set of second terms, being mapped to a first value, from the set of second values, and the second term, from the set of second terms, being mapped to a second value, from the set of second values, and

where the one or more processors when comparing the first vector and the second vector, are to:
compare:
the first value, from the set of first values, to the first value, from the set of second values, and
the second value, from the set of first values, to the second value, from the set of second values;

determine an amount of the first values that match the second values based on comparing the first vector and the second vector;
determine a similarity value between the first vector and the second vector based on the amount of the first values that match the second values;
determine that the similarity value satisfies a threshold;
determine a category associated with the item based on the similarity value satisfying the threshold,
the categorized item being associated with the category; and

provide information that identifies the category associated with the item to permit and/or cause an action to be performed.

2. The device of claim 1 , where the one or more processors are further to:
compare a third vector and the first vector,
the third vector being associated with another item to be categorized;

determine that another similarity value between the third vector and the first vector satisfies the threshold;
determine that the other item is associated with the category based on the other similarity value satisfying the threshold; and
where the one or more processors, when providing the information that identifies the category associated with the item, are to:
provide the information that identifies the category associated with the item and the other item.

3. The device of claim 1 , where the one or more processors are further to:
compare the first vector and a first set of vectors,
the first set of vectors including the second vector;

identify a second set of vectors based on comparing the first vector and the first set of vectors,
the second set of vectors including the second vector; and

where the one or more processors, when determining the similarity value between the first vector and the second vector, are to:
determine the similarity value based on identifying the second set of vectors.

4. The device of claim 1 , where the one or more processors are further to:
determine a hamming distance value between the first vector and the second vector; and
where the one or more processors, when determining the similarity value, are to:
determine the similarity value based on the hamming distance value.

5. The device of claim 1 , where the one or more processors are further to:
compare the first vector to a set of other vectors of other items to be categorized, the item and the other items being associated with a same dataset; and
determine that the other items are associated with the category based on comparing the first vector to the set of other vectors.

6. The device of claim 1 , where the item to be categorized is a first item, and
where the similarity value is a first similarity value; and
where the one or more processors are further to:
compare a third vector and a fourth vector,
the third vector being associated with a second item to be categorized, and
the fourth vector being associated with a third item to be categorized;

determine that a second similarity value between the third vector and the fourth vector satisfies the threshold;
determine that a third similarity value between the second vector and the fourth vector does not satisfy the threshold;
determine that a fourth similarity value between the third vector and the first vector satisfies the threshold; and
categorize the third item based on the fourth similarity value satisfying the threshold,
the third item being associated with the category.

7. The device of claim 1 , where the one or more processors, further cause the one or more processors to:
compare the first vector and a first set of vectors using a first technique;
identify a second set of vectors based on the first technique,
the second set of vectors including the second vector; and

where the one or more processors, when comparing the first vector and the second vector, are to:
compare the first vector and the second vector using a second technique that is different than the first technique based on identifying the second set of vectors.

8. A method, comprising:
receiving, by a device, information that identifies a first item to be categorized;
mapping, by the device, the first item to a first vector,
the first vector including a plurality of first values that correspond to a plurality of first terms of the first item,
a first term, from the plurality of first terms, being mapped to a first value, from the plurality of first values, and a second term, from the plurality of first terms, being mapped to a second value, from the plurality of first values;

comparing, by the device, the first vector and a second vector,
the second vector being associated with a second item,
the second vector including a plurality of second values that correspond to a plurality of second terms associated with the second item,
a first term, from the plurality of second terms, being mapped to a first value, from the plurality of second values, and a second term, from the plurality of second terms, being mapped to a second value, from the plurality of second values, and

where comparing the first vector and the second vector, comprises:
comparing:
the first value, from the plurality of first values, to the first value, from the plurality of second values, and
the second value, from the plurality of first values, to the second value, from the plurality of second values;

determining, by the device, a similarity value associated with the first vector and the second vector based on comparing the first vector and the second vector;
determining, by the device, that the similarity value satisfies a threshold;
determining, by the device, a category associated with the first item based on the similarity value satisfying the threshold,
the second item being associated with the category; and

providing, by the device, information that identifies the category associated with the first item to permit an action to be performed.

9. The method of claim 8 ,
where determining that the similarity value satisfies the threshold comprises:
determining that the similarity value satisfies the threshold based on comparing the first value, from the plurality of first values, to the first value, from the plurality of second values, and the second value, from the plurality of first values, to the second value, from the plurality of second values.

10. The method of claim 8 , further comprising:
identifying an amount of the plurality of first terms; a

Assignees

• Accenture Global Solutions Ltd

Inventors

• Jablonski John

Classifications

• G06F40/205

  Parsing · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F16/334

  Query execution (filtering based on additional data G06F16/335) · CPC title

• G06F16/35 Primary

  Clustering; Classification · CPC title

• G06F17/2705

  Physics · mapped topic