# US 12,112,740 B2 · Creative work systems and methods thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,112,740 B2 - Document ID: US12112740B2 - Status: Granted - Kind: B2 - Application number: 17/545,815 - Filed: 2021-12-08 - Published: 2022-07-21 - Granted: 2024-10-08 - Earliest claimed: 2021-01-21 - Assignees: Societe BIC - Applicants: Societe Bic - Inventors: David Duffy; Bernadette Elliott-Bowman - Web page: https://patentgrep.com/patent/US12112740B2 ## CPC - G10L 15/01: Assessment or evaluation of speech recognition systems - G10L 25/66: for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B5/00) - A61B 5/165: {Evaluating the state of mind, e.g. depression, anxiety} - A61B 5/4803: {Speech analysis specially adapted for diagnostic purposes} - G09B 5/06: with both visual and audible presentation of the material to be studied - G09B 19/00: Teaching not covered by other main groups of this subclass (teaching or practice apparatus for gun-aiming or gun-laying F41G3/26) - G10L 13/027: Concept to speech synthesisers; Generation of natural phrases from machine-based concepts (generation of parameters for speech synthesis out of text G10L13/08) - G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit - G10L 15/16: using artificial neural networks - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 25/63: for estimating an emotional state - G16H 20/70: relating to mental therapies, e.g. psychological therapy or autogenous training - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/30: for calculating health indices; for individual health risk assessment - A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems} - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 2015/025: {Phonemes, fenemes or fenones being the recognition units} - G10L 2015/027: {Syllables being the recognition units} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A computer-implemented method for measuring cognitive load of a user creating a creative work in a creative work system, may include generating at least one verbal statement capable of provoking at least one verbal response from the user, prompting the user to vocally interact with the creative work system by vocalizing the at least one generated verbal statement to the user via an audio interface of the creative work system, and obtaining the at least one verbal response from the user via the audio interface, and determining the cognitive load of the user based on the at least one verbal response obtained from the user, wherein generating the at least one verbal statement is based on at least one predicted verbal response suitable for determining the cognitive load of the user. ## Claims ### Claim 1 A computer-implemented method for measuring cognitive load of a user creating a creative work in a creative work system, comprising: generating at least one verbal statement capable of provoking at least one verbal response from the user by: applying a candidate verbal statement algorithm configured to generate one or more candidate verbal statements; applying a conversation algorithm configured to generate for each candidate verbal statement one or more predicted verbal responses and corresponding one or more response probabilities, thereby generating, for each candidate verbal statement, a list of predicted verbal responses and a vector of response probabilities RPV; applying a predicted verbal response assessment algorithm configured to assign a response score to each predicted verbal response, thereby generating, for each candidate verbal statement, a vector of response scores; and applying a verbal response selection algorithm configured to select one of the one or more candidate verbal statements based on the one or more vectors of response probabilities and on the one or more vectors of response scores, thereby generating the at least one verbal statement based on the at least one predicted verbal response suitable for determining the cognitive load of the user; prompting the user to vocally interact with the creative work system by vocalizing the at least one generated verbal statement to the user via an audio interface of the creative work system; obtaining the at least one verbal response from the user via the audio interface; and determining the cognitive load of the user based on the at least one verbal response obtained from the user. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein assigning the response score to each predicted verbal response comprises checking for one or more verbal features in each predicted verbal response and computing a feature score for each of the one or more verbal features. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein the one or more verbal feature comprises a verbal feature of a first type comprising: a variety of phoneme use; a variety of pseudo-syllable use; or a response length. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein checking for the one or more verbal features in each predicted verbal response and computing the feature score for each of the one or more verbal features comprises applying each predicted verbal response to a phoneme use algorithm configured for: identifying at least one phoneme of the predicted verbal response based on a predetermined list of phonemes; counting the phonemes of the predicted verbal response; counting unique phonemes of the predicted verbal response; and dividing the count of the unique phonemes of the predicted verbal response by the count of the phonemes of the predicted verbal response, thereby computing a phoneme score, thereby computing the verbal feature score. ### Claim 5 (depends on 2) The computer-implemented method of claim 2, wherein assigning the response score to each predicted verbal response is based on at least one verbal feature score corresponding to at least one verbal feature of the predicted verbal response. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein selecting one of the one or more candidate verbal statements based on the one or more vectors of response probabilities and on the one or more vectors of response scores comprises: multiplying, for each candidate verbal statement, the vector of response probabilities RPV and the vector of response scores, thereby generating, for each candidate verbal statement, a vector of weighted response scores; summing, for each candidate verbal statement, components of the vector of weighted response scores, thereby generating, for each candidate verbal statement, a total selection score; and selecting one of the one or more candidate verbal statements with a highest total selection score. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein determining the cognitive load of the user based on the at least one verbal response obtained from the user comprises assessing at least one vocal feature of the at least one verbal response obtained from the user. ### Claim 8 (depends on 7) The computer-implemented method of claim 7, wherein determining the cognitive load of the user based on the at least one verbal response obtained from the user comprises applying one or more cognitive load feature assessment algorithms, wherein each cognitive load feature assessment algorithm corresponds to a vocal feature and is configured for: generating a vocal feature vector representation of the corresponding vocal feature for the at least one verbal response from the user, thereby generating one or more vocal feature vector representations. ### Claim 9 (depends on 8) The computer-implemented method of claim 8, wherein determining the cognitive load of the user based on the at least one verbal response obtained from the user comprises applying the one or more vocal feature vector representations to a cognitive load score algorithm configured for: comparing each of the one or more vocal feature vector representations to at least one predetermined benchmark for cognitive load, wherein each comparison comprises computing a predetermined criterion based on at least one vocal feature vector representation and the at least one predetermined benchmark for cognitive load; counting the one or more vocal feature vector representations satisfying a corresponding predetermined criteria; counting the one or more vocal feature vector representations; and dividing a count of the one or more vocal feature vector representations satisfying the corresponding predetermined criteria by a count of the one or more vocal feature vector representations, thereby determining the cognitive load of the user. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, further comprising: determining at least one contemporaneous feature of the creative work based on the at least one obtained verbal response from the user, wherein the at least one verbal response from the user is applied to a speech-to-text algorithm, thereby generating a verbal feature string inheriting a further timestamp from a timestamped audio waveform. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, wherein determining the at least one contemporaneous feature of the creative work is based on the obtained at least one verbal response from the user or on an obtained at least one further verbal response from the user, and further comprising: applying the verbal feature string to a feature recognition algorithm configured to identify a noun that most likely relates to the at least one contemporaneous feature of the creative work. ### Claim 12 (depends on 10) The computer-implemented method of claim 10, further comprising: generating at least one tailored response based on the cognitive load and/or corresponding contemporaneous feature. ### Claim 13 (depends on 12) The computer-implemented method of claim 12, wherein the at least one tailored response is based on a tailored response template. ### Claim 14 (depends on 1) The computer-implemented method of claim 1, wherein the creative work comprises a visual artwork. ### Claim 15 (depends on 14) The computer-implemented method of claim 14, wherein the visual artwork comprises one or more of a drawing, a painting, a calligraphy, or a sculpture. ### Claim 16 A system for measuring cognitive load of a user creating a creative work in a creative work system, comprising at least one non-transitory computer readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising: generating at least one verbal statement capable of provoking at least one verbal response from the user by: applying a candidate verbal statement algorithm configured to generate one or more candidate verbal statements; applying a conversation algorithm configured to generate for each candidate verbal statement one or more predicted verbal responses and corresponding one or more response probabilities, thereby generating, for each candidate verbal statement, a list of predicted verbal responses and a vector of response probabilities RPV; applying a predicted verbal response assessment algorithm configured to assign a response score to each predicted verbal response, thereby generating, for each candidate verbal statement, a vector of response scores; and applying a verbal response selection algorithm configured to select one of the one or more candidate verbal statements based on the one or more vectors of response probabilities and on the one or more vectors of response scores, thereby generating the at least one verbal statement based on the at least one predicted verbal response suitable for determining the cognitive load of the user; prompting the user to vocally interact with the creative work system by vocalizing the at least one generated verbal statement to the user via an audio interface of the creative work system; obtaining the at least one verbal response from the user via the audio interface; and determining the cognitive load of the user based on the at least one verbal response obtained from the user. ### Claim 17 (depends on 16) The system of claim 16, wherein assigning the response score to each predicted verbal response comprises checking for one or more verbal features in each predicted verbal response and computing a feature score for each of the one or more verbal features. ### Claim 18 (depends on 17) The system of claim 17, wherein the one or more verbal features comprises a verbal feature of a first type comprising: a variety of phoneme use; a variety of pseudo-syllable use; or a response length. ### Claim 19 (depends on 18) The system of claim 18, wherein checking for the one or more verbal features in each predicted verbal response and computing the feature score for each of the one or more verbal features comprises applying each predicted verbal response to a phoneme use algorithm configured for: identifying at least one phoneme of the predicted verbal response based on a predetermined list of phonemes; counting the phonemes of the predicted verbal response; counting unique phonemes of the predicted verbal response; and dividing the count of unique phonemes of the predicted verbal response by the count of the phonemes of the predicted verbal response, thereby computing a phoneme score, thereby computing the verbal feature score. ### Claim 20 An apparatus comprising: at least one processor; and at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following, generate at least one verbal statement capable of provoking at least one verbal response from a user by: apply a candidate verbal statement algorithm configured to generate one or more candidate verbal statements; apply a conversation algorithm configured to generate for each candidate verbal statement one or more predicted verbal responses and corresponding one or more response probabilities, thereby generating, for each candidate verbal statement, a list of predicted verbal responses and a vector of response probabilities RPV; apply a predicted verbal response assessment algorithm configured to assign a response score to each predicted verbal response, thereby generating, for each candidate verbal statement, a vector of response scores; and apply a verbal response selection algorithm configured to select one of the one or more candidate verbal statements based on the one or more vectors of response probabilities and on the one or more vectors of response scores, thereby generating the at least one verbal statement based on the at least one predicted verbal response suitable for determining a cognitive load of the user; prompt the user to vocally interact with a creative work system by vocalizing the at least one generated verbal statement to the user via an audio interface of the creative work system; obtain the at least one verbal response from the user via the audio interface; and determine a cognitive load of the user based on the at least one verbal response obtained from the user.