20 results about "Demographic Accounting" patented technology

The present disclosure provides a system for quantifying drivers of growth of niche categories. The system includes a data collection module configured to receive consumer data collected using surveys, an analysis module configured to identify consumer segments using factor analysis of the received consumer data, a market size estimation module configured to estimate market size for each identified consumer segment based on current consumption, a demographic categorization module configured to create sub-groups based on demographics, a growth potential determination module configured to determine growth potential by regressing consumption behavior on the identified consumer segments and consumer demographics using multinomial regression, and a market size prediction module configured to predict potential market size based on model weights and predicted probability of switching between consumer classes.

The invention relates to an infant asthma three-branch classification auxiliary judgment method and a medium, and relates to the technical field of data processing. The method comprises the following steps: collecting and preprocessing tidal respiration data and demographic data of infants, and performing heterogeneous feature extraction and grouping log-likelihood ratio acquisition on the preprocessed tidal respiration data and demographic data to obtain a log-likelihood ratio corresponding to each group; and performing hierarchical Bayesian fusion on each log-likelihood ratio to obtain a fusion result, and performing asthma risk auxiliary judgment of three-branch classification based on the fusion result. Compared with the prior art, the method can assist in judging the infant asthma more objectively and accurately based on the tidal respiration data.

The subject technology predicts consumer sentiment based on demographics and other static features of the consumer as well as dynamic features generated based on engagement of the consumer with previously presented targeted content. The sentiment predictions are used to recommend and generate new targeted content that is published to the consumer.

Apparatus and associated methods relate to a group specific language application (GSLA). In an illustrative example, a GSLA may, for example, include a slang dictionary configured to store informal expressions (IBs) with metadata such as origin, usage context, and demographic relevance. For example, the GSLA may include a viral threshold engine that evaluates engagement metrics — likes, shares, usage frequency — to determine whether an IE qualifies for inclusion. The GSLA may further include a pronunciation engine that generates voice renderings using selectable voice profiles, and a promotion module that distributes validated IBs across social media platforms based on user selection and demographic targeting. Various embodiments may advantageously enable crowd-validated slang creation and dissemination tailored to particular cultural or generational groups.

A financial planning tool for personalized optimization of retirement income, supported by artificial intelligence, comprising a data acquisition interface configured to collect user-specific and environmental financial data; a knowledge modeling unit designed to identify relationships between financial, demographic, and macroeconomic variables; a predictive simulation module trained to generate probabilistic retirement income trajectories; and a decision optimization unit based on reinforcement learning logic that calculates individual investment strategies and withdrawal policies that maximize retirement income adequacy while minimizing financial risk.

A system and method for determining and managing reputation of an entity or industry includes determining a sample size of the population that provides at least a pre-defined percent confidence interval, and which has the predefined level of familiarity (unique group); determining a measure of likelihood that the targeted population will perform a positive action on behalf of an entity (behavioral connection score), wherein determining the measure of the likelihood that the targeted population will perform a positive action on behalf of an entity comprises: receiving survey ratings from behavioral connection survey questions where each survey rating is provided by a party within the unique group; weighting the received survey ratings to accommodate for at least one of the group consisting of cultural bias and missed demographic quotas; and aggregating the ratings within each individual question to provide a single aggregated behavioral connection score for each behavioral connection survey question.

Methods and apparatus to apply household-level weights to audience measurement data at a household-member level are disclosed. An example method to determine demographics of populations to measure media audiences of populations includes determining demographics for members of a first household of a sub-population. First demographics of a first member of the first household are different than second demographics of a second member of the first household. The example method includes calculating a first household-level weight for the first household based on a demographics distribution of the sub-population and aggregate demographics of a population. The example method includes applying the first household-level weight to the first demographics of the first member, applying the first household-level weight to the second demographics of the second member, and estimating a demographics distribution of the population to measure a media audience of the population based on the weighted first demographics and the weighted second demographics.

Systems and methods for obtaining anonymous demographics from gestures, where the method includes capturing information on one or more gestures performed by a user on a touchscreen of a device, along with motion data of the device. The gesture information and motion data in the form of deltas or deviations is provided to a machine learning (ML) model trained to analyze gestures and motion data and output predicted demographics. The predicted demographics from the ML model are then provided to an advertising provider, which send the device one or more ads targeted to the user based on the demographics. The device then displays the ads. Other embodiments are discussed herein.

A computing system for generating handicap-adjusted health scores processes multi-source health metric data collected from heterogeneous devices and activity modalities. The system normalizes and calibrates unstructured health data using schema-conformant transformation logic and device-specific correction parameters. User-specific baseline values are computed over configurable rolling windows and compared to cohort-level reference parameters derived from demographic and device-based population segmentation. Deviation values are corrected using demographic and device normalization models to generate structured adjustment vectors. The system applies context-aware scoring logic to compute normalized health scores that reflect individual performance patterns relative to statistically similar user cohorts. Scoring outputs are configured for competitive presentation via a user interface and may support leaderboard ranking, team-based scoring, or context-specific evaluations across diverse activity types.

A computer-implemented method is disclosed for detecting advertisement fraud in real-time using a multi-modal analysis framework. The method involves receiving user data and user action data from a media device, including demographic information and sensor-based interaction metrics such as accelerometer, gyroscope, and touch sensor data. These inputs are processed by an advertisement fraud detection system equipped with a processor and hardware-run algorithms, including a multi-modal machine learning model that distinguishes human from non-human interactions. Fraudulent actions are identified by detecting deviations from predefined behavioral baselines enriched with campaign-level intelligence. The system further analyzes historical ad performance to identify downtime periods characterized by low human activity and high fraud probability. During these periods, fake advertisements are adaptively inserted based on contextual mismatches to confirm fraudulent behavior. Upon detection, notifications are dispatched to advertisers via multiple communication mediums.

The present disclosure relates to techniques for generating a ranked list of a set of subjects by predicting their potential health benefit from an intervention to prioritize subjects that may be at a risk of a negative outcome and likely to benefit from a proposed intervention. Additionally, the ranking may further account for potential cost-savings associated with early intervention to avoid acute-care utilization by applying a cost-modeling technique. The disclosed techniques may include analyzing subject-specific data, including demographic, clinical, and historical information, to compute a total net-benefit score by combining a predicted benefit probability with cost and revenue metrics. The benefit probability may be calculated using causal inference models to estimate a potential improvement in health outcomes from the proposed intervention or treatment. The disclosed techniques may further facilitate personalized subject care by dynamically updating rankings based on real-time data, enhancing clinical decision-making, and optimizing resource allocation.

According to the present embodiments, provided are a digital health literacy-based content service device and method, wherein the device receives an input of a demographic factor, a health-related factor, and a digital information-related factor to predict a digital health literacy level, recommends user-customized health information on the basis of a prediction result, performs binary classification of a literacy level of a user by using a classification model and a recommendation model, and provides personalized health information on the basis of metadata and interaction data.

Methods and systems to train and use an ensemble of artificial intelligence / machine learning (AI / ML) models to extract information from social determinants of health (SDoH), including training each of multiple dimensionality reduction models to reduce dimensionality of socio-demographic variables associated with a respective one of multiple SDoH categories, training a predictive model to predict a patient behavior for a geographic region (e.g., risk of non-adherence to treatment regimens) based on dimensionally reduced SDoH (alone or in combination with selected socio-demographic variables and / or other data), training a patient classification model to classify patients based on prescription transactions, and / or training a regional similarity model to determine a measure of similarity between geographic regions based on SDoH and / or dimensionally reduced SDoH. Also disclosed are techniques to visually represent outputs of the models on a user-interactive display.

The embodiment of the invention discloses a multi-mode depression sentiment analysis system based on sensitive attribute tag constraints. The system comprises a feature extraction module which is configured to obtain emotion features in each mode; the feature preprocessing module is configured to output each modal feature by a multi-modal data processing model; the feature alignment module is configured to construct feature pairs with the text modality as the center based on the modal features and calculate the comparison loss of the feature pairs so as to determine the target modal features; the comparison decoupling module is configured to sequentially encode and decode each target modal feature to obtain a sensitive attribute irrelevant feature; and the representation fusion module is configured to perform cross-modal attention fusion on the sensitive attribute irrelevant features to obtain fusion features and determine emotion information according to the fusion features. In the embodiment of the invention, individualized and precise emotion recognition and depression emotion analysis can be carried out according to the social media data of the user under the condition of eliminating generalization influence of demographic deviation.

A method may include obtaining demographic data from multiple households in a cleanroom. The method may include obtaining viewership data associated with displayed content from one or more data sources in the cleanroom. The viewership data may be generated by at least a portion of the multiple households. The method may include generating demographic scores using the viewership data and the demographic data with respect to viewers in the multiple households. The method may include estimating a first count of the viewers and a second count of the viewers of the displayed content. The method may include determining an impression score using the demographic scores and the first count of the viewers. The method may include determining a reach score using the demographic scores and the second count of the viewers. The method may include providing the impression score and the reach score in the cleanroom to a requesting entity.

We provide the system. [Solution] Means for collecting user demographic information and past behavioral data, A means of analyzing user sentiment data in real time, A method for integrating analyzed emotional data with past behavioral data to analyze how specific emotions lead to certain behaviors, A method for selecting advertisements based on user emotional state and behavioral data, A means of displaying selected advertisements to users, A system that includes this.

A system for the automated calculation of the loss of professional service years and the associated economic and labor market-related impairments, comprising: a processor configured to execute machine-readable instructions stored in non-volatile memory; the non-volatile storage, consisting of a hierarchical data set structure that includes demographic reference data sets, occupational pension data sets, wage development data sets, labor force survey data sets, and historical occupational transition data sets; a data acquisition unit configured to receive workplace accident reports via protected wired communication interfaces, authenticated wireless interfaces, and machine-readable optical acquisition interfaces; the processing circuit is configured to validate each received death record through redundancy checking, demographic reconstruction and attribute completion using correlation routines stored in non-volatile memory; a demographic classification unit configured to classify each death record based on age distribution records, historical occupational entry records, and survival distribution records stored in non-volatile memory; a unit for determining retirement age that is configured to retrieve a retirement age value for each classified death, corresponding to the identified occupation and aligned with the temporal context of the death; a service forecasting unit configured to calculate a probability-adjusted professional service time that would have occurred after the death by applying nonlinear progress profiles derived from the historical career transition datasets, the turnover distribution datasets, and the labor force volatility datasets stored in non-volatile memory; an aggregation unit configured to combine the calculated service periods into an aggregated value for loss of professional years of service by applying an age-dependent significance scaling based on the deviation of the age at death from the expected career mean values; an economic analysis unit configured to calculate a long-term economic loss value by propagating wage development data sets, experience-based compensation adjustments, and inflation-indexed income trajectories across the aggregate occupational service loss value; a unit for ensuring workforce sustainability, configured to calculate an attrition rate by comparing the aggregate loss of years of professional service with updated Labour Force Survey data retrieved from authenticated external registers; and a secure output unit configured to digitally sign, encrypt, and record the aggregated value of occupational year loss, the value of economic loss, and the exhaustion rate in an immutable archive area within the non-volatile storage.

The embodiment of the specification discloses a multi-modal depression sentiment analysis system based on sensitive attribute label constraint. The system comprises a feature extraction module configured to obtain sentiment features under each modality; a feature preprocessing module configured to output each modality feature from a multi-modal data processing model; a feature alignment module configured to construct a text modality-centered feature pair based on each modality feature, and calculate the contrastive loss of each feature pair to determine each target modality feature; a contrastive decoupling module configured to sequentially encode and decode each target modality feature to obtain sensitive attribute-independent features; a representation fusion module configured to perform cross-modal attention fusion on the sensitive attribute-independent features to obtain fusion features, and determine sentiment information according to the fusion features. In this embodiment, individualized and accurate emotion recognition and depression sentiment analysis can be performed according to the user's social media data while eliminating the generalization influence of demographic bias.

A method may include obtaining demographic data from multiple households in a cleanroom. The method may include obtaining viewership data associated with displayed content from one or more data sources in the cleanroom. The viewership data may be generated by at least a portion of the multiple households. The method may include generating demographic scores using the viewership data and the demographic data with respect to viewers in the multiple households. The method may include estimating a first count of the viewers and a second count of the viewers of the displayed content. The method may include determining an impression score using the demographic scores and the first count of the viewers. The method may include determining a reach score using the demographic scores and the second count of the viewers. The method may include providing the impression score and the reach score in the cleanroom to a requesting entity.

Various methods and processes, apparatuses or systems, and media for mitigating disparities between outputs of different AI / ML models that are subject to usage constraints are disclosed. The method includes: receiving uncertainty values and model quality-related parameter values that are associated with at least two models that are configured to generate a loan price for a loan applicant; receiving feature weight functions that relate to weights of target metrics; calculating model weights for each model; selecting a customized model based on the model weights; receiving a tabular set of personal data that includes individualized financial information and individualized demographic information associated with loan applicants; training the customized model by using the tabular set of personal data, the target metrics, a set of sensitive labels, and historical information that relates to outputs generated by the models; and using the trained model to generate a customized loan price for a loan applicant.