# US 2023/0274085 A1 · Vector space model for form data extraction

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0274085 A1
- Document ID: US20230274085A1
- Status: Published application
- Kind: A1
- Application number: 18/012,293
- Filed: 2021-06-30
- Published: 2023-08-31
- Earliest claimed: 2020-06-30
- Assignees: National Research Council of Canada
- Applicants: National Research Council of Canada
- Inventors: Jiang SU; Hongyu GUO
- Web page: https://patentgrep.com/patent/US20230274085A1

## CPC

- G06F 40/186: Templates
- G06F 16/28: Databases characterised by their database models, e.g. relational or object models
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F 40/30: Semantic analysis
- G06V 30/413: Classification of content, e.g. text, photographs or tables
- G06F 40/177: of tables; using ruled lines
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A computer-implemented method for detecting attribute value pairs from corpus data using a computer comprising a processor and a computer readable medium comprising instructions executable by the processor to at least: receive the corpus data comprising at least one pair; detect a layout template of the at least one pair; measure the merit of the layout template by determining at least one of (a) relative magnitudes of content probabilities based on a probability of the contents of an attribute cell and a probability of a corresponding value cell, (b) the validity of a name-value pair, or (c) the pointwise mutual information of a frequency matrix M corresponding to a sparse vector capturing context information of a word; and output detected attribute value pairs.

## Claims

### Claim 1

A computer-implemented method for detecting attribute value pairs from corpus data using a computer comprising a processor and a computer readable medium comprising instructions executable by the processor to at least:
receive the corpus data comprising at least one pair;
detect a layout template of the at least one pair;
measure the merit of the layout template by determining at least one of (a) relative magnitudes of content probabilities based on a probability of the contents of an attribute cell and a probability of a corresponding value cell, (b) validity of a name-value pair, or (c) the pointwise mutual information of a frequency matrix M corresponding to a sparse vector capturing context information of a word; and
output detected attribute value pairs.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the relative magnitudes of content probabilities are determined by a scoring function S( ):
S
⁡
(
a
)
=
log
⁢
P
⁡
(
x
att
)
P
⁡
(
x
val
)
where P(xatt) is the probability of the contents of the attribute cell and P(xval) is the probability of the corresponding value cell.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the validity of the name value pair is determined by a step function S( ):
S
⁡
(
a
)
=
{
1
if
⁢
P
⁡
(
x
att
)
>
P
⁡
(
x
val
)
0
otherwise
where P(xatt) is the probability of the contents of the attribute cell and P(xval) is the probability of the corresponding value cell.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the pointwise mutual information is determined by a step function S( ):
S
⁡
(
a
)
=
{
1
if
⁢
PMI
⁡
(
x
att
,
x
val
)
>
0
0
otherwise
where xatt and xval are two table cells being paired.

### Claim 5 (depends on 1, 2, 3, 4)

The computer-implemented method of any one of claims 1 to 4, wherein the attribute value pair corresponds to at least one of a pair of words, table cells and text phrases.

### Claim 6

A computer-implemented method for extracting data from data-bearing tables, using a computer comprising a processor and a computer readable medium comprising instructions executable by the processor to at least:
acquire at least one data-bearing table comprising a plurality of rows and a plurality of columns of data values;
assign at least one table layout template for the at least one data-bearing table;
generate a set of attribute value pairs, Ac, for the at least one table layout template;
compute a content score, Wcontent defining a percentage of likely attribute-value pairs for the at least one table layout template;
compute a template score, Wtemplate based on attribute-value pairs and word frequencies for the at least one table layout template;
determine whether content score, Wcontent is greater than a threshold associated with a percentage of likely attribute value pairs;
when content score, Wcontent is greater than the threshold, identify a most suitable at least one table layout template for the at least one data-bearing table based on the template score, Wtemplate and output a set of attribute value pairs.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein the table layout is at least one of a relation layout, an entity layout and an other layout.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, wherein the relation layout comprises at least one attribute name found in a first row of the plurality of rows.

### Claim 9 (depends on 7)

The computer-implemented method of claim 7, wherein the entity layout comprises at least one attribute name found in a first column of the plurality of columns.

### Claim 10 (depends on 7)

The computer-implemented method of claim 7, wherein the other layout comprises at least one of a matrix and mixed formats.

### Claim 11

A non-transitory computer-readable medium storing computer readable instructions that, when executed by one or more computing devices, cause at least one of the computing devices to:
acquire at least one data-bearing table comprising a plurality of rows and a plurality of columns of data values;
assign at least one table layout template for the at least one data-bearing table;
generate a set of attribute value pairs, Ac, for the at least one table layout template;
compute a content score, Wcontent defining a percentage of likely attribute-value pairs for the at least one table layout template;
compute a template score, Wtemplate based on attribute-value pairs and word frequencies for the at least one table layout template;
determine whether content score, Wcontent is greater than a threshold associated with a percentage of likely attribute value pairs;
when content score, Wcontent is greater than the threshold, identify a most suitable at least one table layout template for the at least one data-bearing table based on the template score, Wtemplate and output a set of attribute value pairs.

### Claim 12 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the table layout is at least one of a relation layout, an entity layout and an other layout.

### Claim 13 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein the relation layout comprises at least one attribute name found in a first row of the plurality of rows.

### Claim 14 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein the entity layout comprises at least one attribute name found in a first column of the plurality of columns.

### Claim 15 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein the other layout comprises at least one of a matrix and mixed formats.

### Claim 16

An apparatus for extracting data from data-bearing tables, the apparatus comprising:
at least one processor;
a computer readable medium comprising instructions executable by the at least one processor to cause the processor to at least:
acquire at least one data-bearing table comprising a plurality of rows and a plurality of columns of data values;
assign at least one table layout template for the at least one data-bearing table;
generate a set of attribute value pairs, Ac, for the at least one table layout template;
compute a content score, Wcontent defining a percentage of likely attribute-value pairs for the at least one table layout template;
compute a template score, Wtemplate based on attribute-value pairs and word frequencies for the at least one table layout template;
determine whether content score, Wcontent is greater than a threshold associated with a percentage of likely attribute value pairs;
when content score, Wcontent is greater than the threshold, identify a most suitable at least one table layout template for the at least one data-bearing table based on the template score, Wtemplate and output a set of attribute value pairs.

### Claim 17

An apparatus for extracting data from data-bearing tables, the apparatus comprising at least one processor, a computer readable medium comprising instructions executable by the at least one processor to cause the processor, the apparatus comprising:
a dataset acquisition module for acquiring at least one data-bearing table from a data source, the at least one data-bearing table comprising a plurality of rows and a plurality of columns of data values;
a categorizer for assigning at least one table layout template for the at least one data-bearing table;
an attribute generator for generating a set of attribute value pairs, Ac, for the at least one table layout template;
a table quality analyzer for computing a content score, Wcontent defining a percentage of likely attribute-value pairs for the at least one table layout template;
for computing a template score, Wtemplate based on attribute-value pairs and word frequencies for the at least one table layout template;
a classification module for identifying a most suitable at least one table layout template for the at least one data-bearing table based on the template score, Wtemplate and a relationship between the content score, Wcontent and a threshold associated with a percentage of likely attribute value pairs, and output a set of attribute value pairs.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the table layout is at least one of a relation layout, an entity layout and an other layout.

### Claim 19 (depends on 17)

The apparatus of claim 17, wherein the relation layout comprises at least one attribute name found in a first row of the plurality of rows.

### Claim 20 (depends on 17)

The apparatus of claim 17, wherein the entity layout comprises at least one attribute name found in a first column of the plurality of columns.

### Claim 21 (depends on 17)

The apparatus of claim 17, wherein the other layout comprises at least one of a matrix and mixed formats.

### Claim 22 (depends on 17, 18, 19, 20, 21)

The apparatus of any one of claims 17 to 21, wherein a merit of the at least one layout template by determining at least one of (a) relative magnitudes of content probabilities based on a probability of the contents of an attribute cell and a probability of a corresponding value cell, (b) validity of a name-value pair, or (c) pointwise mutual information of a frequency matrix M corresponding to a sparse vector capturing context information of a word; and output detected attribute value pairs.

### Claim 23 (depends on 22)

The apparatus of claim 22, wherein the relative magnitudes of content probabilities are determined by a scoring function S( ):
S
⁡
(
a
)
=
log
⁢
P
⁡
(
x
att
)
P
⁡
(
x
val
)
where P(xatt) is the probability of the contents of the attribute cell and P(xval) is the probability of the corresponding value cell.

### Claim 24 (depends on 22)

The apparatus of claim 22, wherein the validity of the name value pair is determined by a step function S( ):
S
⁡
(
a
)
=
{
1
if
⁢
P
⁡
(
x
att
)
>
P
⁡
(
x
val
)
0
otherwise
where P(xatt) is the probability of the contents of the attribute cell and P(xval) is the probability of the corresponding value cell.

### Claim 25 (depends on 22)

The apparatus of claim 22, wherein the pointwise mutual information is determined by a step function S( ):
S
⁡
(
a
)
=
{
1
if
⁢
PMI
⁡
(
x
att
,
x
val
)
>
0
0
otherwise
where xatt and xval are two table cells being paired.

### Claim 26 (depends on 22, 23, 24, 25)

The apparatus of any one of claims 22 to 25, wherein the attribute value pair corresponds to at least one of a pair of words, table cells and text phrases.
