# US 11,907,872 B2 · Apparatus and methods for success probability determination for a user

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

- Number: US 11,907,872 B2
- Document ID: US11907872B2
- Status: Granted
- Kind: B2
- Application number: 17/690,498
- Filed: 2022-03-09
- Published: 2023-09-14
- Granted: 2024-02-20
- Earliest claimed: 2022-03-09
- Assignees: My Job Matcher, Inc.
- Applicants: My Job Matcher, Inc.
- Inventors: Arran Stewart
- Web page: https://patentgrep.com/patent/US11907872B2

## CPC

- G06Q 10/0631: Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06F 18/24155: {Bayesian classification}
- G06F 18/29: {Graphical models, e.g. Bayesian networks}
- G06Q 10/063112: {Skill-based matching of a person or a group to a task}
- G06Q 10/06398: {Performance of employee with respect to a job function}
- G06Q 10/1053: Employment or hiring
- G06V 10/776: Validation; Performance evaluation
- 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)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An apparatus for success probability determination for a user is provided. Apparatus may include at least a processor and a memory communicatively connected to the processor. The memory may contain instructions configuring the at least a processor to receive a plurality of criteria; generate indicators as a function of the criteria; receive user specifications, the user specifications comprising credentials of a user; and classify the user specifications to a performance category of a plurality of performance categories based on the user specifications and the indicators.

## Claims

### Claim 1

An apparatus for success probability determination for a user, the apparatus comprising:
at least a processor communicatively connected to a user device; and
a memory communicatively connected to the processor, the memory containing instructions configuring the at least a processor to:
receive a plurality of criteria;
generate indicators as a function of the criteria, wherein generating the indicators comprises:
training, iteratively, a machine learning model using training data and a machine learning algorithm, wherein the training data includes criteria data correlated with indicator data;
updating the training data with input and output results from the trained machine learning model and retraining the machine learning model with the updated training data using a feedback loop;
generating the indicators using the retrained machine learning model, wherein the plurality of criteria are provided as an input to the retrained machine learning model to output the indicators; and
determining a weight of the indicators using the machine learning model;
receive user specifications, the user specifications comprising credentials of a user, wherein the user specifications comprise a video record, wherein the video record is processed to generate an audio vector and an image vector, and wherein the audio vector and the image vector are utilized to determine the credentials of the user, wherein utilizing the audio vector and the image vector to determine the credentials of the user further comprises concatenating the audio vector and the image vector into a resultant vector;
classify the user specifications, using a classifier, to a performance category of a plurality of performance categories based on the user specifications and the indicators, wherein the classifier comprises a sub-classifier, and wherein classifying the user specifications further comprises:
representing each category of the plurality of performance categories as performance vectors;
using one or more measures of vector similarity to determine a degree of similarity between the resultant vector and each performance vector; and
classifying the user specifications to the performance category associated with the performance vector with the highest degree of similarity to the resultant vector and the indicators;
determine a success of placement for each of one or more previous entities in one or more previous positions, wherein the success of placement includes at least one commonality between the one or more previous entities and the user specifications, wherein the at least one commonality is modeled as a causative link between at least one of the plurality of criteria and the classified user specifications; and
determine a relevancy of the classified user specifications as a function of qualifications of a job position and the success of placement for each of the one or more previous entities utilizing a second machine learning model.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein generating the indicators comprises utilizing a machine-learning module to generate the indicators.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the indicators are weighted based on the criteria.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the criteria comprise requirements, wherein the indicators are weighted based on the requirements.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to generate a compatibility score, wherein classifying the user specifications is further based on the compatibility score.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the indicators are based on a level of the criteria.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to identify the indicators in the user specifications.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to measure the degree the indicators are satisfied in the user specifications.

### Claim 9

A method for success probability determination for a user, the method comprising:
receiving, at a processor, a plurality of criteria;
generating, by the processor, indicators as a function of the criteria, wherein generating the indicators comprises:
training, iteratively, a machine learning model using training data and a machine learning algorithm, wherein the training data includes criteria data correlated with indicator data;
updating the training data with input and output results from the trained machine learning model and retraining the machine learning model with the updated training data using a feedback loop;
generating the indicators using the retrained machine learning model, wherein the plurality of criteria are provided as an input to the retrained machine learning model to output the indicators; and
determining a weight of the indicators using the machine learning model;
receiving, at the processor, user specifications, the user specifications comprising credentials of a user, wherein the user specifications comprise a video record, wherein the video record is processed to generate an audio vector and an image vector, and wherein the audio vector and the image vector are utilized to determine the credentials of the user, wherein utilizing the audio vector and the image vector to determine the credentials of the user further comprises concatenating the audio vector and the image vector into a resultant vector;
classifying, by the processor using a classifier, the user specifications to a performance category of a plurality of performance categories based on the user specifications and the indicators, wherein the classifier comprises a sub-classifier, and wherein classifying the user specifications further comprises:
representing each category of the plurality of performance categories as performance vectors;
using one or more measures of vector similarity to determine a degree of similarity between the resultant vector and each performance vector; and
classifying the user specifications to the performance category associated with the performance vector with the highest degree of similarity to the resultant vector and the indicators;
determining, by the processor, a success of placement for each of one or more previous entities in one or more previous positions, wherein the success of placement includes at least one commonality between the one or more previous entities and the user specifications, wherein the at least one commonality is modeled as a causative link between at least one of the plurality of criteria and the classified user specifications; and
determining a relevancy of the classified user specifications as a function of qualifications of a job position and the success of placement for each of the one or more previous entities utilizing a second machine learning model.

### Claim 10 (depends on 9)

The method of claim 9, wherein generating the indicators comprises utilizing a machine-learning module to generate the indicators.

### Claim 11 (depends on 9)

The method of claim 9, wherein the indicators are weighted based on the criteria.

### Claim 12 (depends on 9)

The method of claim 9, wherein the criteria comprise requirements, wherein the indicators are weighted based on the requirements.

### Claim 13 (depends on 9)

The method of claim 9, wherein the processor is configured to generate a compatibility score, wherein classifying the user specifications is further based on the compatibility score.

### Claim 14 (depends on 9)

The method of claim 9, wherein the indicators are based on a level of the criteria.

### Claim 15 (depends on 9)

The method of claim 9, wherein the processor is configured to identify the indicators in the user specifications.

### Claim 16 (depends on 9)

The method of claim 9, wherein the processor is configured to measure the degree the indicators are satisfied in the user specifications.

### Claim 17 (depends on 1)

The apparatus of claim 1, wherein the image vector and the audio vector are concatenated to predict speech of the user.

### Claim 18 (depends on 9)

The method of claim 9, wherein receiving the user specifications further comprises concatenating the image vector and the audio vector to predict speech of the user.

### Claim 19 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to classify the user to a higher performance category if the job position has been unfulfilled for greater than a predetermined length of time and if less than a predetermined number of applicants have applied for the job position.

### Claim 20 (depends on 9)

The method of claim 9, wherein the method further comprises classifying the user to a higher performance category if the job position has been unfulfilled for greater than a predetermined length of time and if less than a predetermined number of applicants have applied for the job position.