# US 2026/0093784 A1 · Training device, training method, attribute data generation device, attribute data generation method, and program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0093784 A1 - Document ID: US20260093784A1 - Status: Published application - Kind: A1 - Application number: 19/332,472 - Filed: 2025-09-18 - Published: 2026-04-02 - Earliest claimed: 2024-10-01 - Assignees: NEC Corporation - Applicants: NEC Corporation - Inventors: Chenhui HUANG; Kensuke WAGATA; Fumiyuki NIHEY - Web page: https://patentgrep.com/patent/US20260093784A1 ## CPC - G06F 18/2415: based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/047: Probabilistic or stochastic networks - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G16H 50/30: for calculating health indices; for individual health risk assessment - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract In order to generate insufficient attribute data by existing attribute data, a training device uses AI or machine learning models to train an attribute data generation device. An acquisition means acquires first and second attribute data other than the first attribute data. A first encoder converts the second attribute data into a stochastic latent variable. A second encoder projects the stochastic latent variable to a latent space, clusters projection points into clusters, and outputs centroids indicating centers of gravity of the clusters. A decoder reconstructs the second attribute data based on the projection points. An optimization means optimizes the first and second encoders, and the decoder based on relationships between the projection points and the centers of gravity and a relationship between the clusters. An analysis result of a health condition and a disease risk using the attribute data is used for supporting a decision making regarding a subject's activity. ## Claims ### Claim 1 A training device comprising: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: acquire first attribute data and second attribute data other than the first attribute data; convert, a first encoder, the second attribute data into a stochastic latent variable; project, by a second encoder, the stochastic latent variable to a latent space according to a category of the first attribute data, clusters obtained projection points into a plurality of clusters, and outputs centroids indicating centers of gravity of the plurality of clusters; reconstruct, by a decoder, the second attribute data based on the projection points in the latent space; and optimize the first encoder, the second encoder, and the decoder based on relationships between the projection points in the latent space and the centers of gravity of the clusters and a mutual relationship between the plurality of clusters. ### Claim 2 (depends on 1) The training device according to claim 1, wherein the first attribute data and the second attribute data are attribute data related to health. ### Claim 3 A training method executed by a computer, the training method comprising: acquiring first attribute data and second attribute data other than the first attribute data; converting, by using a first encoder, the second attribute data into a stochastic latent variable; projecting, by using a second encoder, the stochastic latent variable to a latent space according to a category of the first attribute data, clustering obtained projection points into a plurality of clusters, and outputting centroids indicating centers of gravity of the plurality of clusters; reconstructing, by using a decoder, the second attribute data based on the projection points in the latent space; and optimizing the first encoder, the second encoder, and the decoder based on relationships between the projection points in the latent space and the centers of gravity of the clusters and a mutual relationship between the plurality of clusters. ### Claim 4 A program for causing a computer to execute processing comprising: acquiring first attribute data and second attribute data other than the first attribute data; converting, by using a first encoder, the second attribute data into a stochastic latent variable; projecting, by using a second encoder, the stochastic latent variable to a latent space according to a category of the first attribute data, clustering obtained projection points into a plurality of clusters, and outputting centroids indicating centers of gravity of the plurality of clusters; reconstructing, by using a decoder, the second attribute data based on the projection points in the latent space; and optimizing the first encoder, the second encoder, and the decoder based on relationships between the projection points in the latent space and the centers of gravity of the clusters and a mutual relationship between the plurality of clusters. ### Claim 5 An attribute data generation device comprising: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: acquire a category of a first attribute; determine determining a projection point that belongs to a cluster corresponding to the category of the first attribute in a latent space obtained by clustering projection points obtained by projecting attribute data into a plurality of clusters; and generate, by a decoder, second attribute data based on the projection point in the latent space. ### Claim 6 (depends on 5) The attribute data generation device according to claim 5, wherein the processor acquires an optional vector, and determines the projection point based on a relationship between the optional vector in the latent space and a centroid of the cluster corresponding to the category of the first attribute. ### Claim 7 (depends on 5) The attribute data generation device according to claim 5, wherein the processor further acquires the second attribute data having an attribute other than the first attribute, and in moving the projection point, the processor is configured to, convert, by a first encoder, the second attribute data into a stochastic latent variable; and project, by a second encoder, the stochastic latent variable to the latent space according to the category of the first attribute and determines a projection point of the second attribute data in the latent space. ### Claim 8 (depends on 7) The attribute data generation device according to claim 7, wherein the category of the first attribute includes a current age and a future age of a subject, and the processor moves a projection point corresponding to the current age in the latent space to a position corresponding to the future age, and determines a projection point corresponding to the future age. ### Claim 9 An attribute data generation method executed by a computer, the attribute data generation method comprising: acquiring a category of a first attribute; determining a projection point that belongs to a cluster corresponding to the category of the first attribute in a latent space obtained by clustering projection points obtained by projecting attribute data into a plurality of clusters; and generating second attribute data based on the projection point in the latent space. ### Claim 10 A non-transitory computer-readable recording medium storing a program causing a computer to execute processing comprising: acquiring a category of a first attribute; determining a projection point that belongs to a cluster corresponding to the category of the first attribute in a latent space obtained by clustering projection points obtained by projecting attribute data into a plurality of clusters; and generating second attribute data based on the projection point in the latent space.