# US 2022/0012749 A1 · Prospective client intake and assignment system

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

- Number: US 2022/0012749 A1
- Document ID: US20220012749A1
- Status: Published application
- Kind: A1
- Application number: 17/304,045
- Filed: 2021-06-14
- Published: 2022-01-13
- Earliest claimed: 2020-07-07
- Assignees: Morgan & Morgan Pa
- Applicants: Morgan & Morgan PA
- Inventors: Yehuda Apfelbaum; Koichi Hirano
- Web page: https://patentgrep.com/patent/US20220012749A1

## CPC

- G06Q 30/018: Certifying business or products
- G06F 40/205: Parsing
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 30/016: After-sales
- G06Q 50/18: Legal services
- G06Q 20/127: {Shopping or accessing services according to a time-limitation}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Methods and systems for automatically interviewing and evaluating prospective clients for engagement by a law firm. Through a virtual agent interface a prospective client is engaged in conversation to elicit information useful in determining whether the prospective client is suitable for an engagement. Information obtained from the prospective client is evaluated to identify likely causes of action, which are scored and assessed against engagement criteria. If the scoring and assessment reveal that the prospective client's likely cause of action is suitable for engagement, an engagement process is initiated, otherwise, the interview continues in an attempt to identify other potential causes of action and/or additional facts for reassessing the initially identified potential cause of action. If one or more potential causes of action score sufficiently high enough to warrant engagement, an engagement process is initiated, otherwise a non-engagement procedure with the prospective client is performed.

## Claims

### Claim 1

A system for automatically interviewing and evaluating prospective clients for engagement with a law firm, the system comprising a virtual agent interface communicatively coupled to predictive case engine, the virtual agent interface configured as a front end for the predictive case engine to engage prospective clients of a law firm in a conversation to elicit facts concerning potential causes of action, said predictive case engine configured to evaluate said facts for assessing engagement of the prospective clients by the law firm using scorings assigned according to stored information concerning prior judicial decisions and settlements.

### Claim 2 (depends on 1)

The system according to claim 1, wherein the virtual agent interface is instantiated at a server and accessible by the prospective clients though a web site or other portal associated with the law firm.

### Claim 3 (depends on 1)

The system according to claim 1, wherein the virtual agent interface is a component of a case management platform offered on a subscription basis.

### Claim 4 (depends on 1)

The system according to claim 1, wherein the virtual agent interface is configured to accept natural language inputs from the prospective client.

### Claim 5 (depends on 4)

The system according to claim 4, wherein, the virtual agent interface includes a natural language processor configured to parse input messages and extract key words and/or strings.

### Claim 6 (depends on 5)

The system according to claim 5, wherein the predictive case engine includes a case matching module configured to identify the potential causes of action from the key words and/or strings extracted from the input messages received via the virtual agent interface.

### Claim 7 (depends on 6)

The system according to claim 6, wherein the predictive case engine further includes one or more machine learning modules configured to train the case matching module to identify factual distinctions associated with the potential causes of action that affect outcomes in judicial decisions and settlements and to engage the prospective clients with specific questions when potential causes of action are recognized from the key words and/or strings included in the prospective clients' input messages.

### Claim 8 (depends on 7)

The system according to claim 7, wherein the machine learning modules comprise a convolutional neural network configured to generate case fact pattern vector representations from prior case information stored in one or more databases accessible by the predictive case engine by pooling results of convolution operations on n-dimension vectors that represent extracted facts from individual cases included in the prior case information.

### Claim 9 (depends on 8)

The system according to claim 8, wherein the case matching module is configured to engage the prospective clients with specific questions by populating a dialog module of the predictive case engine with interrogatories to be presented to the prospective clients through the virtual agent interface.

### Claim 10 (depends on 7)

The system according to claim 7, wherein an identified likely one of the potential causes of action is scored by a case scoring module of the predictive case engine by evaluating a description provided by one of the prospective clients through the conversation with the virtual agent system against stored case information in one or more databases accessible by the predictive case engine.

### Claim 11 (depends on 10)

The system according to claim 10, wherein the stored case information comprises available verdict and settlement information from prior cases.

### Claim 12

A process for automatically interviewing and evaluating prospective clients for engagement by a law firm, said process comprising:
monitoring a virtual agent interface for new conversations,
when a new conversation is detected engaging a prospective client in conversation via the virtual agent interface to elicit information useful in determining whether the prospective client is suitable for an engagement;
evaluating the information obtained from the prospective client to determine if a likely cause of action can be identified, and when a likely cause of action is identified based on the information provided by the prospective client, scoring and assessing the identified cause of action against engagement criteria for causes of action of that kind;
if the scoring and assessment reveal that the prospective client's likely cause of action is suitable for engagement, initiating an engagement process, otherwise, continuing to engage the prospective client in conversation to obtain additional information that may reveal other potential causes of action and/or additional facts pertaining to the initially identified potential cause of action;
as new information is elicited, identifying, scoring, and assessing potential new causes of action and reevaluating previously identified causes of action using the additional information;
continuing the interviewing and assessment until one or more potential causes of action score sufficiently high enough to warrant engagement, or the conversation with the prospective client has exhausted available facts without revealing a potential cause of action with a score sufficiently high enough to warrant engagement, in which instance performing a non-engagement procedure with the prospective client.

### Claim 13 (depends on 12)

The process of claim 12, wherein the cause of action assessment is performed using information stored in a knowledge database.

### Claim 14 (depends on 13)

The process of claim 13, wherein the cause of action assessment comprises evaluating the information obtained from the prospective client against fact patterns and outcomes culled from previously contested cases, both reported and unreported.
