公开(公告)号：US12136089B2

公开(公告)日：2024-11-05

申请号：US17717880

申请日：2022-04-11

Applicant: SAP SE

Inventor： Jesper Lind ,  Suchitra Sundararaman

IPC: G06Q40/00 ,  G06F18/24 ,  G06F40/284 ,  G06N3/02 ,  G06N3/08 ,  G06N20/00 ,  G06Q20/04 ,  G06Q20/38 ,  G06Q20/40 ,  G06Q40/12 ,  G06T7/00 ,  G06T7/73 ,  G06V30/224 ,  G06V30/413 ,  G06V30/414 ,  G06V30/418 ,  G06F16/2455

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes determining valid pixel-based pattern(s) that are included in valid reference images. Fraudulent pixel-based pattern(s) that are included in fraudulent reference images are determined. A request to classify an image is received. A determination is made as to whether pixel values in the image match a valid pixel-based pattern or a fraudulent pixel-based pattern. In response to determining that the pixel values match a valid pixel-based pattern, a likelihood of classifying the first image as a valid image is increased. In response to determining that the pixel values match a fraudulent pixel-based pattern, a likelihood that the image as a fraudulent image is increased. The image is classified in response to the request as either a valid image or a fraudulent image based on the likelihoods.

公开(公告)号：US11568128B2

公开(公告)日：2023-01-31

申请号：US16906906

申请日：2020-06-19

Applicant: SAP SE

Inventor： Jesper Lind ,  Anupam Dewan

IPC: G06F40/174 ,  G06F16/9035 ,  G06N20/20 ,  G06Q40/02

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program receives from a client device an image and a user identifier associated with a user of the client device. Based on the user identifier, the program further retrieves a set of historical transactions associated with the user, the program also uses a first machine learning model to predict a string based on the image. The program further uses a second machine learning model to predict a set of digits based on the image. Based on the set of historical transaction data, the string, and the set of digits, the program also determines a data value for a field in a form.

公开(公告)号：US20220237604A1

公开(公告)日：2022-07-28

申请号：US17717811

申请日：2022-04-11

Applicant: SAP SE

Inventor： Jesper Lind ,  Suchitra Sundararaman

IPC: G06Q20/40 ,  G06N20/00 ,  G06Q40/00 ,  G06K9/62 ,  G06N3/02 ,  G06F40/284 ,  G06Q20/04 ,  G06Q20/38 ,  G06T7/73 ,  G06N3/08 ,  G06T7/00 ,  G06V30/224 ,  G06V30/413 ,  G06V30/414 ,  G06V30/418

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes determining valid pixel-based pattern(s) that are included in valid reference images. Fraudulent pixel-based pattern(s) that are included in fraudulent reference images are determined. A request to classify an image is received. A determination is made as to whether pixel values in the image match a valid pixel-based pattern or a fraudulent pixel-based pattern. In response to determining that the pixel values match a valid pixel-based pattern, a likelihood of classifying the first image as a valid image is increased. In response to determining that the pixel values match a fraudulent pixel-based pattern, a likelihood that the image as a fraudulent image is increased. The image is classified in response to the request as either a valid image or a fraudulent image based on the likelihoods.

公开(公告)号：US20220237606A1

公开(公告)日：2022-07-28

申请号：US17717880

申请日：2022-04-11

Applicant: SAP SE

Inventor： Jesper Lind ,  Suchitra Sundararaman

IPC: G06Q20/40 ,  G06V30/413 ,  G06V30/414 ,  G06V30/418 ,  G06F40/284 ,  G06K9/62 ,  G06N3/02 ,  G06N3/08 ,  G06N20/00 ,  G06Q20/04 ,  G06Q20/38 ,  G06Q40/00 ,  G06T7/00 ,  G06T7/73 ,  G06V30/224

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes determining valid pixel-based pattern(s) that are included in valid reference images. Fraudulent pixel-based pattern(s) that are included in fraudulent reference images are determined. A request to classify an image is received. A determination is made as to whether pixel values in the image match a valid pixel-based pattern or a fraudulent pixel-based pattern. In response to determining that the pixel values match a valid pixel-based pattern, a likelihood of classifying the first image as a valid image is increased. In response to determining that the pixel values match a fraudulent pixel-based pattern, a likelihood that the image as a fraudulent image is increased. The image is classified in response to the request as either a valid image or a fraudulent image based on the likelihoods.

公开(公告)号：US11282078B2

公开(公告)日：2022-03-22

申请号：US16578016

申请日：2019-09-20

Applicant: SAP SE

Inventor： Michael Stark ,  Jesper Lind

IPC: G06Q20/40 ,  G06N20/00 ,  G06Q40/00 ,  G06K9/18 ,  G06K9/00 ,  G06K9/62 ,  G06N3/02 ,  G06F40/284 ,  G06Q20/04 ,  G06Q20/38 ,  G06T7/73 ,  G06N3/08 ,  G06T7/00 ,  G06F16/2455

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes receiving text submitted with a request. Token values are automatically extracted for selected token types from the text using a machine learning model. Tokens are identified in the text, and for each token, features and a token type of the token are determined, along with a score that indicates a likelihood that the token has the token type. A token value is extracted for the token from the text. Extracted token values are compared to request data values. A request value for the selected token type is identified in the data values for each selected token type. The extracted token value for each selected token type is compared to the request value. An audit alert is generated in response to determining that an extracted token value does not match a corresponding request value.

公开(公告)号：US20210398118A1

公开(公告)日：2021-12-23

申请号：US17464217

申请日：2021-09-01

Applicant: SAP SE

Inventor： Michael Stark ,  Evan Adkins ,  Adithya Kumar ,  Suchitra Sundararaman ,  Jesper Lind

IPC: G06Q20/40 ,  G06N20/00 ,  G06Q40/00 ,  G06K9/18 ,  G06K9/00 ,  G06K9/62 ,  G06N3/02 ,  G06F40/284 ,  G06Q20/04 ,  G06Q20/38 ,  G06T7/73 ,  G06N3/08 ,  G06T7/00

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes receiving receipt data associated with an entity. Policy questions associated with the entity are associated with at least one policy question answer that corresponds to a conformance or a violation of a policy selected by the entity. For each policy question, a machine learning policy model is identified for the policy question that includes, for each policy question answer, receipt data features that correspond to the policy question answer. The machine learning policy model is used to automatically determine a selected policy question answer to the policy question by comparing features of extracted tokens to respective receipt data features of the policy question answers that are included in the machine learning policy model. In response to determining that the selected policy question answer corresponds to a policy violation, an audit alert is generated.

公开(公告)号：US20210326517A1

公开(公告)日：2021-10-21

申请号：US16906906

申请日：2020-06-19

Applicant: SAP SE

Inventor： Jesper Lind ,  Anupam Dewan

IPC: G06F40/174 ,  G06N20/20 ,  G06F16/9035

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program receives from a client device an image and a user identifier associated with a user of the client device. Based on the user identifier, the program further retrieves a set of historical transactions associated with the user, the program also uses a first machine learning model to predict a string based on the image. The program further uses a second machine learning model to predict a set of digits based on the image. Based on the set of historical transaction data, the string, and the set of digits, the program also determines a data value for a field in a form.

公开(公告)号：US20210019511A1

公开(公告)日：2021-01-21

申请号：US17039628

申请日：2020-09-30

Applicant: SAP SE

Inventor： Everaldo Aguiar ,  Ravi Sharma ,  Shivani Patel ,  Jesper Lind ,  Michael Stark ,  Yongjian Bi

IPC: G06K9/00 ,  G06N20/00

Abstract: Embodiments of the present disclosure pertain to systems and method for extracting data from an image. In one embodiment, a method of extracting data from an image comprises receiving, from an optical character recognition (OCR) system, OCR text in response to sending an image to the OCR system. The OCR text comprises a plurality of lines of text. Each line of text is classified as either a line item or not a line item using a machine learning algorithm, and a plurality of data fields are extracted from each line of text classified as a line item.

公开(公告)号：US20190318347A1

公开(公告)日：2019-10-17

申请号：US15951058

申请日：2018-04-11

Applicant: SAP SE

Inventor： Everaldo Aguiar ,  Michael Stark ,  Jesper Lind

IPC: G06Q20/38 ,  G06K9/18 ,  G06Q20/40 ,  G06F15/18

Abstract: Embodiments of the present disclosure pertain to matching transactional data. In one embodiment, the present disclosure includes a computer implemented method comprising receiving transactional data for a first user and second data for the first user, selecting transactional data records for the first user from a data store of transactional data for a plurality of users, determining a plurality of similarities between fields of the transactional data and second data, determining a likelihood of a match between a transactional data field and a second data field based on the plurality of similarities using a machine learning model, and in accordance therewith, identifying one record in the transactional data records for the first user that generates said likelihood of the match above a first threshold, and replacing values second data fields with corresponding values in the one record.

公开(公告)号：US20250054070A1

公开(公告)日：2025-02-13

申请号：US18929850

申请日：2024-10-29

Applicant: SAP SE

Inventor： Michael Stark ,  Evan Adkins ,  Adithya Kumar ,  Suchitra Sundararaman ,  Jesper Lind

IPC: G06Q40/12 ,  G06F16/2455 ,  G06F18/24 ,  G06F40/284 ,  G06N3/02 ,  G06N3/08 ,  G06N20/00 ,  G06Q20/04 ,  G06Q20/38 ,  G06Q20/40 ,  G06T7/00 ,  G06T7/73 ,  G06V30/224 ,  G06V30/413 ,  G06V30/414 ,  G06V30/418

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes receiving receipt data associated with an entity. Policy questions associated with the entity are associated with at least one policy question answer that corresponds to a conformance or a violation of a policy selected by the entity. For each policy question, a machine learning policy model is identified for the policy question that includes, for each policy question answer, receipt data features that correspond to the policy question answer. The machine learning policy model is used to automatically determine a selected policy question answer to the policy question by comparing features of extracted tokens to respective receipt data features of the policy question answers that are included in the machine learning policy model. In response to determining that the selected policy question answer corresponds to a policy violation, an audit alert is generated.