公开(公告)号：US11861321B1

公开(公告)日：2024-01-02

申请号：US18344344

申请日：2023-06-29

Applicant: Casetext, Inc.

Inventor： Brian O'Kelly ,  Javed Qadrud-Din ,  Ryan Walker ,  Walter DeFoor ,  Pablo Arredondo

IPC: G06F40/40 ,  G06F40/289 ,  G06F40/186 ,  G06F16/338 ,  G06F40/205 ,  G06F16/33 ,  G06F40/174 ,  G06F40/279

CPC classification number: G06F40/40 ,  G06F16/33 ,  G06F16/338 ,  G06F16/3344 ,  G06F40/174 ,  G06F40/186 ,  G06F40/205 ,  G06F40/279 ,  G06F40/289

Abstract: A regular expression prompt may be determined by combining a regular expression prompt template with input text from an input document. The regular expression prompt template may include a natural language instruction to identify one or more regular expressions from the input text and one or more fillable portions designated for filling with the input text. The regular expression prompt may be sent to a large language model for evaluation, and one or more regular expressions may be identified based on a response received from the large language model. The regular expressions may be used to disaggregate the input text, and the disaggregated text portions may be used to determine a structured document based on the input document. The structured document may be used to determine a response to a query of the input document.

公开(公告)号：US20240289561A1

公开(公告)日：2024-08-29

申请号：US18640591

申请日：2024-04-19

Applicant: Casetext, Inc.

Inventor： Javed Qadrud-Din ,  Brian O'Kelly ,  Alan deLevie ,  Ethan Blake ,  Walter DeFoor ,  Ryan Walker ,  Pablo Arredondo

IPC: G06F40/40 ,  G06F40/226 ,  G06F40/289 ,  G06N3/045 ,  G06N3/0985

CPC classification number: G06F40/40 ,  G06F40/226 ,  G06F40/289 ,  G06N3/045 ,  G06N3/0985

Abstract: Relevance scores may be determined based on text included in a document. The text may be divided into a text portions, with the relevance scores being determined based on a comparison of a text portion of the plurality of text portions with a criterion specified in natural language. A subset of the plurality of text portions may be selected based on the plurality of relevance scores, with each of the subset of the plurality of text portions having a relevance score surpassing a threshold. A criteria evaluation prompt may be sent to a remote text generation modeling system via a communication interface. The criteria evaluation prompts may include an instruction to evaluate one or more of the subset of text portions against the criterion.

公开(公告)号：US11995411B1

公开(公告)日：2024-05-28

申请号：US18329039

申请日：2023-06-05

Applicant: Casetext, Inc.

Inventor： Javed Qadrud-Din ,  Brian O'Kelly ,  Alan deLevie ,  Ethan Blake ,  Walter DeFoor ,  Ryan Walker ,  Pablo Arredondo

IPC: G06F40/20 ,  G06F40/226 ,  G06F40/289 ,  G06F40/40 ,  G06N3/045 ,  G06N3/0985

CPC classification number: G06F40/40 ,  G06F40/226 ,  G06F40/289 ,  G06N3/045 ,  G06N3/0985

Abstract: Relevance scores may be determined based on text included in a document. The text may be divided into a text portions, with the relevance scores being determined based on a comparison of a text portion of the plurality of text portions with a criterion specified in natural language. A subset of the plurality of text portions may be selected based on the plurality of relevance scores, with each of the subset of the plurality of text portions having a relevance score surpassing a threshold. A criteria evaluation prompt may be sent to a remote text generation modeling system via a communication interface. The criteria evaluation prompts may include an instruction to evaluate one or more of the subset of text portions against the criterion.

公开(公告)号：US20250005300A1

公开(公告)日：2025-01-02

申请号：US18515032

申请日：2023-11-20

Applicant: Casetext, Inc.

Inventor： Brian O'Kelly ,  Javed Qadrud-Din ,  Ryan Walker ,  Walter DeFoor ,  Pablo Arredondo

IPC: G06F40/40 ,  G06F16/33 ,  G06F16/338 ,  G06F40/174 ,  G06F40/186 ,  G06F40/205 ,  G06F40/279 ,  G06F40/289

Abstract: A regular expression prompt may be determined by combining a regular expression prompt template with input text from an input document. The regular expression prompt template may include a natural language instruction to identify one or more regular expressions from the input text and one or more fillable portions designated for filling with the input text. The regular expression prompt may be sent to a large language model for evaluation, and one or more regular expressions may be identified based on a response received from the large language model. The regular expressions may be used to disaggregate the input text, and the disaggregated text portions may be used to determine a structured document based on the input document. The structured document may be used to determine a response to a query of the input document.