# US 2023/0057485 A1 · Multi-Dimensional Table Reproduction From Image

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

- Number: US 2023/0057485 A1
- Document ID: US20230057485A1
- Status: Published application
- Kind: A1
- Application number: 17/408,127
- Filed: 2021-08-20
- Published: 2023-02-23
- Earliest claimed: 2021-08-20
- Assignees: Sap SE
- Applicants: Sap SE
- Inventors: Andreas Doms
- Web page: https://patentgrep.com/patent/US20230057485A1

## CPC

- G06F 40/177: of tables; using ruled lines
- G06F 16/2282: {Tablespace storage structures; Management thereof}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06V 30/10: Character recognition
- G06V 30/147: {Determination of region of interest}
- G06V 30/19093: {Proximity measures, i.e. similarity or distance measures}
- G06V 30/412: Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
- G06F 40/18: of spreadsheets (form-filling G06F40/174)
- G06V 30/19007: {Matching; Proximity measures}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Embodiments facilitate selection and assignment of a known user model, based upon input comprising table images of original data. A table engine receives the image and performs pre-processing (e.g., rasterization, Optical Character Recognition, coordinate representation) thereupon to identify image entities. After filtering original numerical data, a similarity (e.g., a distance) is calculated between an image entity and a dimension member of the known user model. Based upon this similarity, the table engine selects and assigns the known user model to the incoming tables images, generating a file representing table columns and rows. This file is received at the UI of an analytics platform, which in turn populates the model with data of the user (rather than the original data) via an API. Embodiments may be particularly valuable in allowing a user to rapidly generate multi-dimensional tables comprising their own data, based upon raw table images received from an external party.

## Claims

### Claim 1

A method comprising:
receiving an image;
pre-processing the image to identify a first image entity comprising a first word;
calculating a similarity between the first word and a dimension member of a model;
selecting the model based upon the similarity;
generating a file representing the model as a table including the dimension member; and
communicating the file to a user interface of a data analysis platform, such that the data analysis platform populates the table with data stored in a database.

### Claim 2 (depends on 1)

A method as in claim 1 wherein the pre-processing comprises one or more of:
rasterizing the image;
performing Optical Character Recognition (OCR) of the image; and
determining a coordinate location of the first image entity in the image.

### Claim 3 (depends on 1)

A method as in claim 1 wherein the pre-processing further identifies a second image entity comprising a number, the method further comprising:
filtering the second image entity.

### Claim 4 (depends on 1)

A method as in claim 1 wherein:
the pre-processing further identifies a second entity comprising a second word; and
selecting the model is based upon similarity between the second word and the dimension member of the model.

### Claim 5 (depends on 1)

A method as in claim 1 wherein a format of the file identifies a column of the table and a row of the table.

### Claim 6 (depends on 1)

A method as in claim 1 wherein selecting the cube is based upon a first probability between the first image entity and a dimension of the model.

### Claim 7 (depends on 7)

A method as in claim 7 wherein selecting the cube is based upon a second probability between the dimension member and the dimension.

### Claim 8 (depends on 1)

A method as in claim 1 wherein:
the database comprises an in-memory database;
an in-memory database engine of the in-memory database calculates the similarity; and
the in-memory database engine selects the model.

### Claim 9 (depends on 8)

A method as in claim 8 wherein the model is stored in the in-memory database.

### Claim 10 (depends on 1)

A method as in claim 1 wherein the similarity comprises a distance.

### Claim 11

A non-transitory computer readable storage medium embodying a computer program for performing a method, said method comprising:
receiving an image;
pre-processing the image to identify a first image entity comprising a first word and a second image entity comprising a number;
filtering the number;
calculating a similarity between the first word and a dimension member of a model;
selecting the model based upon the similarity;
generating a file representing the model as a table including the dimension member; and
communicating the file to a user interface of a data analysis platform, such that the data analysis platform populates the table with data stored in a database.

### Claim 12 (depends on 11)

A non-transitory computer readable storage medium as in claim 11 wherein the pre-processing comprises at least one of:
rasterizing the image;
performing Optical Character Recognition (OCR) of the image; and
determining a coordinate location of the first image entity in the image.

### Claim 13 (depends on 11)

A non-transitory computer readable storage medium as in claim 11 wherein:
the pre-processing further identifies a second entity comprising a second word; and
selecting the model is based upon similarity between the second word and the dimension member of the model.

### Claim 14 (depends on 11)

A non-transitory computer readable storage medium as in claim 11 wherein selecting the cube is based upon a first probability between the first image entity and a dimension of the model.

### Claim 15 (depends on 11)

A non-transitory computer readable storage medium as in claim 11 wherein the similarity comprises a distance.

### Claim 16

A computer system comprising:
one or more processors;
a software program, executable on said computer system, the software program configured to cause an in-memory database engine of an in-memory database to:
receive an image;
pre-process the image to identify a first image entity comprising a first word;
calculate a similarity between the first word and a dimension member of a model stored in the in-memory database;
store the similarity in the in-memory database;
select the model based upon the similarity;
generate a file representing the model as a table including the dimension member;
store the file in the in-memory database; and
communicate the file to a user interface of a data analysis platform, such that the data analysis platform populates the table with data stored in the in-memory database.

### Claim 17 (depends on 16)

A computer system as in claim 16 wherein the in-memory database engine is configured to pre-process the image by one or more of:
rasterizing the image;
performing Optical Character Recognition (OCR) of the image; and
determining a coordinate location of the first image entity in the image.

### Claim 18 (depends on 16)

A computer system as in claim 16 wherein the pre-processing further identifies a second image entity comprising a number, the in-memory database engine further configured to:
filter the second image entity.

### Claim 19 (depends on 16)

A computer system as in claim 16 wherein pre-processing further identifies a second entity comprising a second word; and
the in-memory database engine is configured to select the model based upon similarity between the second word and the dimension member of the model.

### Claim 20 (depends on 16)

A computer system as in claim 16 wherein the similarity comprises a distance.
