# US 2021/0240926 A1 · Method and apparatus for improved analysis of legal documents

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

- Number: US 2021/0240926 A1
- Document ID: US20210240926A1
- Status: Published application
- Kind: A1
- Application number: 17/235,999
- Filed: 2021-04-21
- Published: 2021-08-05
- Earliest claimed: 2019-06-11
- Inventors: Matthew M. Tonuzi
- Web page: https://patentgrep.com/patent/US20210240926A1

## CPC

- G06F 40/205: Parsing
- G06F 16/11: File system administration, e.g. details of archiving or snapshots (error detection or correction of the data by redundancy in operations G06F11/14)
- G06F 40/109: Font handling; Temporal or kinetic typography
- G06F 40/279: Recognition of textual entities
- G06F 40/30: Semantic analysis
- G10L 13/08: Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
- G06Q 10/10: Office automation; Time management
- G06Q 50/18: Legal services
- G10L 13/00: Speech synthesis; Text to speech systems
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

The present disclosure provides apparatus and method for improving analysis of legal documents. A legal document is parsed to generate a list of desired legal authorities. These legal authorities are then acquired from a trusted repository of authorities and processed through a modified text-to-speech program in a desired order to obtain a brief audio recording of the cited authorities. Citing references to the legal authorities may be filtered as appropriate and added to the generated list of desired legal authorities.

## Claims

### Claim 1

A method for analyzing a legal document comprising one or more legal authorities, the method comprising the steps of:
using an electronic scraper to parse the legal document to generate a list of the legal authorities in a format suitable for input into a repository of legal documents;
wherein the step of parsing the legal document comprises a case law subroutine, which comprises the steps of:
determine a stop condition;
for each text-based line of the legal document;
search text for the character string “v.”;
if “v.” is not italicized, then continue searching;
else, if “v.” is italicized, then search the succeeding words for characters matching character strings associated with a prepopulated list of case reporters to identify the case reporter associated with the case law until the stop condition is met;
extract numerical value preceding the case reporter;
extract numerical value succeeding the case reporter;
generate an entry on the list of legal authorities comprising the numerical value preceding the case reporter, the case reporter, and the numerical value succeeding the case reporter;
transmitting the list of the legal authorities to the repository via a communications device in logical connection with the scraper;
receiving, via the communications device, from the repository documents embodying the legal authorities within the list of the legal authorities;
translating the documents embodying the legal authorities to one or more files comprising an audibly perceptible format, wherein the audibly perceptible format comprises a sound file comprising a spoken version of text associated with the legal authorities; and
audibly broadcasting the files with a sound device.

### Claim 2 (depends on 1)

The method of claim 1, further comprising the step of removing from the files at least a first or a second portion of a citation to a case.

### Claim 3 (depends on 2)

The method of claim 2, wherein the first portion of the citation to the case comprises case reporter information associated with the case.

### Claim 4 (depends on 3)

The method of claim 3, wherein the second portion of the citation to the case comprises an identity of a court associated with the case.

### Claim 5 (depends on 4)

The method of claim 4, wherein a voice synthesizer generates alternative case information to substitute into the files in the place of at least the first or the second portion of the citation to the case.

### Claim 6 (depends on 1)

The method of claim 1, wherein the case law subroutine of parsing the legal document comprises the steps of:
continue searching the text-based line for an additional character string if the additional character string “v.” occurs within the text-based line,
then repeat this loop from the step of if “v.” is not italicized, then continue searching; and
else, if the text-based line does not consist of an additional character string “v.”, then move to a second text-based line.

### Claim 7 (depends on 1)

The method of claim 1, wherein the step of parsing the legal document comprises a treatise subroutine, which comprises the steps of:
for each text-based line of the legal document:
search text-based line for a text string comprising a length of greater than a first predetermined number of characters that uses small caps formatting;
search a second predetermined number of characters after the text string;
if the second predetermined number of characters after the text string does not comprise one or more numerical values, then continue searching the text-based line for an additional character string comprising small caps formatting;
else, if the second predetermined number of characters after the text string does comprise one or more numerical values, then extract the numerical values;
generate an entry on the list of legal authorities comprising the text string that uses small caps formatting and the numerical values;
continue searching the text-based line for an additional character string comprising a length of greater than the first predetermined number of characters that uses small caps formatting;
if the additional character string comprising a length of greater than the first predetermined number of characters that uses small caps formatting, then repeat this loop from the step of search a second predetermined number of characters after the text string; and
else, if the text-based line does not consist of an additional character string comprising a length of greater than the first predetermined number of characters that uses small caps formatting, then move to a second text-based line.

### Claim 8 (depends on 1)

The method of claim 1, further comprising the step of transmitting the files via a communications network to a smart device comprising a processor, an audio output, a memory, and a communications access device in logical connection with the communications network.

### Claim 9 (depends on 8)

The method of claim 8, wherein the step of audibly broadcasting the files occurs via an audio output associated with a smart device.

### Claim 10 (depends on 6)

The method of claim 6, wherein the step of transmitting the list of legal authorities further comprises the execution of a citing references subroutine comprising:
assessing the presence or absence of citing authorities for a given legal authority;
based upon a presence of citing authorities, applying a filter condition to obtain a filtered list of citing authorities; and
adding the filtered list of citing authorities to the list of legal authorities.

### Claim 11

An apparatus for improved analysis of legal documents comprising one or more legal authorities, the apparatus comprising:
a processor;
a communications access device in logical connection with a communications network;
a memory comprising software with instructions executable on command to:
parse the legal document to generate a list of the legal authorities in a format suitable for input into a repository of legal documents, wherein the instructions for parsing the legal document comprises a case law subroutine, which comprises the steps of:
determine a stop condition;
for each text-based line of the legal document:
search text for the character string “v.”;
if “v.” is not italicized, then continue searching;
else, if “v.” is italicized, then search the succeeding words for characters matching character strings associated with a prepopulated list of case reporters to identify the case reporter associated with the case law until the stop condition is met;
extract numerical value preceding the case reporter;
extract numerical value succeeding the case reporter; and
generate an entry on the list of legal authorities comprising the numerical value preceding the case reporter, the case reporter, and the numerical value succeeding the case reporter;
transmit via the communications network the list of the legal authorities to the repository;
download from the repository documents embodying the legal authorities from the list of the legal authorities;
translate the documents embodying the legal authorities to one or more files comprising an audibly perceptible format, wherein the audibly perceptible format comprises a sound file comprising a spoken version of text associated with the legal authorities; and
cause an audio device in logical communication with the apparatus to audibly broadcast the files.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the software is further operable to remove from the files at least a first or a second portion of a citation to a case.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein the first portion of the citation to the case comprises case reporter information associated with the case.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein the second portion of the citation to the case comprises an identity of a court associated with the case.

### Claim 15 (depends on 14)

The apparatus of claim 14, wherein a voice synthesizer in logical connection with the apparatus generates alternative case information to substitute into the files in place of at least the first or the second portion of the citation to the case.

### Claim 16 (depends on 11)

The apparatus of claim 11, wherein the case law subroutine further comprises instructions to:
continue searching the text-based line for an additional character string “v.”;
if the additional character string “v.” occurs within the text-based line, then repeat this loop from the step of if “v.” is not italicized, then continue searching; and
else, if the text-based line does not consist of an additional character string “v.”, then move to a second text-based line.

### Claim 17 (depends on 11)

The apparatus of claim 11, wherein the software is operable to parse the legal document using a treatise subroutine comprising the steps of:
for each text-based line of the legal document:
search text-based line for a text string comprising a length of greater than a first predetermined number of characters that uses small caps formatting;
search a second predetermined number of characters after the text string;
if the second predetermined number of characters after the text string does not comprise one or more numerical values, then continue searching the text-based line for an additional character string comprising small caps formatting;
else, if the second predetermined number of characters after the text string does comprise one or more numerical values, then extract the numerical values;
generate an entry on the list of legal authorities comprising the text string that uses small caps formatting and the numerical values;
continue searching the text-based line for an additional character string comprising a length of greater than the first predetermined number of characters that uses small caps formatting;
if the additional character string comprising a length of greater than the first predetermined number of characters that uses small caps formatting, then repeat this loop from the step of search a second predetermined number of characters after the text string; and
else, if the text-based line does not consist of an additional character string comprising a length of greater than the first predetermined number of characters that uses small caps formatting, then move to a second text-based line.

### Claim 18 (depends on 16)

The apparatus of claim 16, wherein the apparatus comprises a smart device.

### Claim 19 (depends on 18)

The apparatus of claim 18, wherein the audio device comprises speakers in logical connection to the smart device.

### Claim 20 (depends on 16)

The apparatus of claim 16, wherein the instructions to transmit the list of legal authorities further includes a citing authorities subroutine, comprising:
assessing the presence or absence of citing authorities for a given legal authority;
based upon a presence of citing authorities, applying a filter condition to obtain a filtered list of citing authorities; and
adding the filtered list of citing authorities to the list of legal authorities.