# US 2019/0378616 A1 · Natural language processing of a motion alphabet for unsupervised clinical scoring > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0378616 A1 - Document ID: US20190378616A1 - Status: Published application - Kind: A1 - Application number: 16/001,063 - Filed: 2018-06-06 - Published: 2019-12-12 - Earliest claimed: 2018-06-06 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Avner Abrami; Vittorio Caggiano; John Jeremy Rice - Web page: https://patentgrep.com/patent/US20190378616A1 ## CPC - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30) - G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning - G06N 7/00: Computing arrangements based on specific mathematical models - G06N 20/20: Ensemble learning - G16H 40/63: for local operation - G16H 50/30: for calculating health indices; for individual health risk assessment - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/045: Combinations of networks - G06N 3/047: Probabilistic or stochastic networks - G06N 3/08: Learning methods - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 5/02: Knowledge representation; Symbolic representation - G06N 5/04: Inference or reasoning models - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Techniques that facilitate natural language processing of a motion alphabet for unsupervised clinical scoring are provided. In one example, a system converts sensor data from one or more movement capturing devices associated with a user identity into symbolic data indicative of a symbolic representation of the sensor data. The system also analyzes the symbolic data associated with the one or more movement capturing devices based on a symbolic analysis technique. ## Claims ### Claim 1 A system, comprising: a memory that stores computer executable components; a processor that executes computer executable components stored in the memory, wherein the computer executable components comprise: a measurement component that converts sensor data from one or more movement capturing devices associated with a user identity into symbolic data indicative of a symbolic representation of the sensor data; and an analysis component that analyzes the symbolic data associated with the one or more movement capturing devices based on a symbolic analysis technique. ### Claim 2 (depends on 1) The system of claim 1, wherein the analysis component analyzes the symbolic data associated with the one or more movement capturing devices based on a natural language processing technique. ### Claim 3 (depends on 1) The system of claim 1, wherein the analysis component analyzes the symbolic data associated with the one or more movement capturing devices based on a Markov-Chain technique. ### Claim 4 (depends on 1) The system of claim 1, wherein the measurement component converts the sensor data into the symbolic data based on a clustering technique. ### Claim 5 (depends on 1) The system of claim 1, wherein the measurement component converts a data window associated with the sensor data into a symbolic letter to facilitate conversion of the sensor data into the symbolic data. ### Claim 6 (depends on 1) The system of claim 1, wherein the analysis component determines whether the sensor data satisfies a defined criterion associated with a medical condition based on a distance measurement between two or more output values of a natural language processing model associated with the symbolic data. ### Claim 7 (depends on 1) The system of claim 1, wherein the computer executable components comprise: a filter component that filters the sensor data based on filter data indicative of information for a range of movement associated with the user identity. ### Claim 8 (depends on 1) The system of claim 1, wherein the measurement component receives the sensor data from one or more wearable devices. ### Claim 9 (depends on 1) The system of claim 1, wherein the measurement component converts the sensor data into the symbolic data to facilitate improved processing of the sensor data from the one or more movement capturing devices. ### Claim 10 A computer-implemented method, comprising: converting, by a system operatively coupled to a processor, sensor data from one or more sensors associated with a user identity into symbolic data indicative of a symbolic representation of the sensor data; and analyzing, by the system, the symbolic data associated with the one or more sensors based on a natural language processing technique. ### Claim 11 (depends on 10) The method of claim 10, further comprising: receiving, by the system, the sensor data from one or more movement capturing devices associated with the sensor data. ### Claim 12 (depends on 10) The method of claim 10, further comprising: receiving, by the system, the sensor data from one or more wearable devices associated with the sensor data. ### Claim 13 (depends on 10) The method of claim 10, wherein the converting comprises converting the sensor data into the symbolic data based on a clustering technique. ### Claim 14 (depends on 10) The method of claim 10, wherein the converting comprises capturing a set of data windows associated with the sensor data to facilitate conversion of the sensor data into the symbolic data. ### Claim 15 (depends on 10) The method of claim 10, wherein the analyzing comprises analyzing the symbolic data based on a Markov-Chain technique. ### Claim 16 (depends on 10) The method of claim 10, further comprising: determining, by the system, whether the sensor data satisfies a defined criterion associated with a medical condition based on the analyzing the symbolic data associated with the natural language processing technique. ### Claim 17 (depends on 10) The method of claim 10, wherein the analyzing comprises improving processing of the sensor data from the one or more sensors. ### Claim 18 A computer program product facilitating natural language processing of a motion alphabet for unsupervised clinical scoring, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to: convert, by the processor, sensor data from one or more sensors associated with a user identity into symbolic data indicative of a symbolic representation of the sensor data; analyze, by the processor, the symbolic data associated with the one or more sensors based on a natural language processing technique; and determine, by the processor, whether the sensor data satisfies a defined criterion associated with a medical condition based on analysis of the symbolic data associated with the natural language processing technique. ### Claim 19 (depends on 18) The computer program product of claim 18, wherein the program instructions are further executable by the processor to cause the processor to: analyze, by the processor, the symbolic data based on a Markov-Chain technique. ### Claim 20 (depends on 18) The computer program product of claim 18, wherein the program instructions are further executable by the processor to cause the processor to: receive, by the processor, sensor data from one or more wearable devices associated with the one or more sensors.