# US 12,763,096 B2 · AI-based automated personality and behavior analytic and assessment system and method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,763,096 B2 - Document ID: US12763096B2 - Status: Granted - Kind: B2 - Application number: 18/791,887 - Filed: 2024-08-01 - Published: 2025-02-06 - Granted: 2026-10-13 - Earliest claimed: 2023-08-02 - Applicants: Arche AI, LLC - Inventors: Eric A. Bachura; Michael W. Beadle; Jessica C. Whiting - Web page: https://patentgrep.com/patent/US12763096B2 ## CPC - G10L 25/63: for estimating an emotional state - G10L 15/183: using context dependencies, e.g. language models - G10L 25/27: characterised by the analysis technique - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract An AI-based personality and behavior analytic and assessment system includes an input interface configured for receiving input data containing audio speech, an automatic speech recognition module configured to receive the input data, recognize the spoken words in the input data, and generate an output representing the spoken words attributed to the individual, the output including speaking moments and audio slices, a machine learning text-based feature generation pipeline configured to receive the speaking moments and generate a numerical text-based feature set, a machine learning audio-based feature generation pipeline configured to receive the audio slices and generate a numerical audio-based feature set, a machine learning inference processor configured to receive at least one of the numerical text-based feature set and the numerical audio-based feature set, develop inferences from the feature sets, and generate scores representing the probabilities for a number of personality and behavioral traits of the individual. ## Claims ### Claim 1 An AI-based automated personality and behavior analytic and assessment system, comprising: a machine learning data repository storing unstructured and structured training data; an input interface configured for receiving input data containing signals related to audio speech; an automatic speech recognition, diarization, and transcription module configured to receive the input data, recognize the spoken words in the input data, and generate an output representing the spoken words attributed to the individual, the output including speaking moments and audio slices; a machine learning text-based feature generation pipeline configured to receive the speaking moments and generate a numerical text-based feature set; a machine-learning audio-based feature generation pipeline configured to receive the audio slices, perform Fast Fourier Transform (FFT) spectral and signal analysis on the audio slices to extract spectral features comprising prosodic features to generate a numerical audio-based feature set; a machine learning inference processor configured to receive both of the numerical text-based feature set and the numerical audio-based feature set, develop inferences from both feature sets, and generate a set of scores representing the probabilities for a number of personality and behavioral traits; and a user interface configured to present information related to the generated set of scores to a user. ### Claim 2 (depends on 1) The system of claim 1, wherein at least a portion of the input data comprises real-time speech data. ### Claim 3 (depends on 1) The system of claim 1, wherein at least a portion of the input data comprises a stored file containing audio data. ### Claim 4 (depends on 1) The system of claim 1, wherein the user interface is configured to display the information related to the generated set of scores via the web browser-based interface, via an application programming interface, and in curated final reports in PDF format. ### Claim 5 (depends on 1) The system of claim 1, wherein the system is configured to align problem-relevant features to a inference model's target space. ### Claim 6 (depends on 1) The system of claim 1, wherein the system future comprises a large language model evaluation process configured to have an ensemble of large language models that are a mixture of fine-tuned and retrieval-augmented generative variants. ### Claim 7 (depends on 1) The system of claim 1, wherein the ensemble of large language models is configured to evaluate final inference model assumption requirements. ### Claim 8 (depends on 7) The system of claim 7, wherein the assumption requirements are configured to include an establishment of a cognitive load-inducing situation characterizing the statement being assessed, and an evaluation of inference model appropriateness for statement content. ### Claim 9 An AI-based automated personality and behavior analytic and assessment method, comprising: receiving input data containing signals related to audio speech; receiving the input data, recognizing the spoken words in the input data, and generating an output representing the spoken words attributed to the individual, the output including speaking moments and audio slices; receiving the audio slices, performing Fast Fourier Transform (FFT) spectral and signal analysis on the audio slices to extract spectral features comprising prosodic features for generating a numerical audio-based feature set; receiving the numerical audio-based feature set, developing inferences from the audio-based feature set, and generating a set of scores representing the probabilities that the individual possesses a number of personality and behavioral traits; and presenting information related to the generated set of scores to a user. ### Claim 10 (depends on 9) The method of claim 9, wherein receiving input data comprises receiving real-time speech data. ### Claim 11 (depends on 9) The method of claim 9, wherein receiving input data comprises receiving a stored file containing audio data. ### Claim 12 (depends on 9) The method of claim 9 further comprises displaying the information related to the generated set of scores via the web browser-based interface, via an application programming interface, and in curated final reports in PDF format. ### Claim 13 (depends on 9) The method of claim 9, comprises aligning problem-relevant features to a inference model's target space. ### Claim 14 (depends on 9) The method of claim 9, comprises a large language model evaluation process evaluating an ensemble of large language models based on a mixture of fine-tuned and retrieval-augmented generative variants. ### Claim 15 (depends on 14) The method of claim 14, comprises the ensemble of large language models evaluating final inference model assumption requirements. ### Claim 16 (depends on 15) The method of claim 15, wherein evaluating the assumption requirements comprises evaluating a cognitive load-inducing situation characterizing the statement being assessed and evaluating inference model appropriateness for statement content. ### Claim 17 A non-transitory computer readable medium having encoded thereon instructions for performing an AI-based automated personality and behavior analytic and assessment method, the method comprising: receiving input data containing signals related to audio speech; receiving the input data, recognizing the spoken words in the input data, and generating an output representing the spoken words attributed to the individual, the output including speaking moments and audio slices; receiving the speaking moments and generating a numerical text-based feature set; receiving the audio slices, performing Fast Fourier Transform (FFT) spectral and signal analysis on the audio slices to extract spectral features for generating a numerical audio-based feature set; receiving the numerical text-based feature set and the numerical audio-based feature set, developing inferences from both feature sets, and generating a set of scores representing the probabilities that the individual possesses a number of personality and behavioral traits; and presenting information related to the generated set of scores to a user. ### Claim 18 (depends on 17) The method of claim 17, further comprising performing text analysis, dictionary, and vector model processing on the speaking moments. ### Claim 19 (depends on 17) The method of claim 17 further comprises displaying the information related to the generated set of scores via the web browser-based interface, via an application programming interface, and in curated final reports in PDF format.