# US 11,113,944 B2 · Walking analysis apparatus and method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,944 B2 - Document ID: US11113944B2 - Status: Granted - Kind: B2 - Application number: 16/687,907 - Filed: 2019-11-19 - Published: 2021-03-25 - Granted: 2021-09-07 - Earliest claimed: 2019-09-20 - Assignees: Electronics and Telecommunications Research Institute - Applicants: Electronics and Telecommunications Research Institute - Inventors: Min Gi Jeong; Jeong Kyun Kim; Myung Nam Bae; Kang Bok Lee; Sang Yeoun Lee - Web page: https://patentgrep.com/patent/US11113944B2 ## CPC - G08B 21/043: {detecting an emergency event, e.g. a fall} - A61B 5/1117: {Fall detection} - A61B 5/747: {in case of emergency, i.e. alerting emergency services} - G08B 21/0446: {worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait} - G06F 2218/12: Classification; Matching - G06V 40/25: {Recognition of walking or running movements, e.g. gait recognition} - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A walking analysis method includes measuring impacts due to floor landing occurring during walking; identifying an impact section before floor landing, a free fall section, and an impact peak section by floor landing in an impact graph over time; analyzing at least one impact-related parameter for the impact section before floor landing, the free fall section, and the impact peak section by floor landing; and determining a walking-related accident type according to a result of analyzing the at least one impact-related parameter. Accordingly, by classifying and detecting a variety of accidents that may actually occur, the main walking characteristics that are dangerous in the actual accident can be extracted. ## Claims ### Claim 1 A walking analysis method comprising: measuring impacts due to floor landing occurring during walking; identifying an impact section before floor landing, a free fall section, and an impact peak section by floor landing in an impact graph over time; analyzing at least one impact-related parameter for each of the impact section before floor landing, the free fall section, and the impact peak section by floor landing; and determining whether a walking-related accident type is a ground-level fall, falling from a high place, or a collision according to the analysis of the at least one impact-related parameter. ### Claim 2 (depends on 1) The walking analysis method according to claim 1, wherein the at least one impact-related parameter includes one or more of a summation of impact in floor landing section (SIF), a free fall duration (FFD), an impact before floor-landing section peak (IBP), and an impact peak section peak by floor-landing (IPP). ### Claim 3 (depends on 2) The walking analysis method according to claim 2, wherein the at least one impact-related parameter includes, for the impact section before floor landing, the free fall section, and the impact peak section by floor landing, one or more of an order of the sections, a time duration of each of the sections, body tilts at a start point and an end point of each of the sections, a body tilt variation for each of the sections, and acceleration variation for each of the sections. ### Claim 4 (depends on 2) The walking analysis method according to claim 2, wherein the determining whether the walking-related accident type is the ground-level fall, the falling from a high place, or the collision is made by comparing each of SIF, FFD, IBP, and IPP with a threshold for each of SIF, FFD, IBP, and IPP. ### Claim 5 (depends on 4) The walking analysis method according to claim 4, wherein, when the walking-related accident type is the ground-level fall, the determining of the walking-related accident type further comprises determining whether the ground-level fall is a stuck fall, a slip fall, or a sit down fall by additionally analyzing a maximum impact of an upper body of a pedestrian before floor landing, a tilt variation of a body of the pedestrian, FFD, and an exposure angle of an insole. ### Claim 6 (depends on 1) The walking analysis method according to claim 1, further comprising calculating a risk level based on the determined walking-related accident type and at least one additional information. ### Claim 7 (depends on 1) The walking analysis method according to claim 1, further comprising: analyzing walking characteristics of a pedestrian after an accident event occurs; comparing the walking characteristics after the accident event occurs with walking characteristics before the accident event occurs; and determining whether the pedestrian is abnormal according to the accident event based on a result of the comparison. ### Claim 8 (depends on 7) The walking analysis method according to claim 7, wherein the analyzing of the walking characteristics comprises: detecting a change in energies of left and right feet during walking; and detecting a walking pattern according to the change of energies in a section of heel-strike (HS) and a section of toe-off (TO). ### Claim 9 (depends on 6) The walking analysis method according to claim 6, wherein the one or more additional information includes a biometric factor, a location factor within a dangerous area, and a user risk group factor. ### Claim 10 A walking analysis apparatus comprising a processor and a memory storing at least one instruction executable by the processor, wherein when executed by the processor, the at least one instruction is configured to: measure impacts due to floor landing occurring during walking; identify an impact section before floor landing, a free fall section, and an impact peak section by floor landing in an impact graph over time; analyze at least one impact-related parameter for each of the impact section before floor landing, the free fall section, and the impact peak section by floor landing; and determine whether a walking-related accident type is a ground-level fall, falling from a high place, or a collision according to the analysis of the at least one impact-related parameter. ### Claim 11 (depends on 10) The walking analysis apparatus according to claim 10, wherein the at least one impact-related parameter includes one or more of a summation of impact in floor landing section (SIF), a free fall duration (FFD), an impact before floor-landing section peak (IBP), and an impact peak section peak by floor-landing (IPP). ### Claim 12 (depends on 11) The walking analysis apparatus according to claim 11, wherein the at least one impact-related parameter includes, for the impact section before floor landing, the free fall section, and the impact peak section by floor landing, one or more of an order of the sections, a time duration of each of the sections, body tilts at a start point and an end point of each of the sections, a body tilt variation for each of the sections, and acceleration variation for each of the sections. ### Claim 13 (depends on 11) The walking analysis apparatus according to claim 11, wherein the at least one instruction is further configured to determine whether the walking-related accident type is the ground-level fall, the falling from a high place, or the collision by comparing each of SIF, FFD, IBP, and IPP with a threshold for each of SIF, FFD, IBP, and IPP. ### Claim 14 (depends on 13) The walking analysis apparatus according to claim 13, wherein the at least one instruction is further configured to, when the walking-related accident type is the ground-level fall, determine whether the ground-level fall is a stuck fall, a slip fall, or a sit down fall by additionally analyzing a maximum impact of an upper body of a pedestrian before floor landing, a tilt variation of a body of the pedestrian, FFD, and an exposure angle of an insole. ### Claim 15 (depends on 10) The walking analysis apparatus according to claim 10, wherein the at least one instruction is further configured to calculate a risk level based on the determined walking-related accident type and at least one additional information. ### Claim 16 (depends on 10) The walking analysis apparatus according to claim 10, wherein the at least one instruction is further configured to: analyze walking characteristics of a pedestrian after an accident event occurs; compare the walking characteristics after the accident event occurs with walking characteristics before the accident event occurs; and determine whether the pedestrian is abnormal according to the accident event based on a result of the comparison. ### Claim 17 (depends on 16) The walking analysis apparatus according to claim 16, wherein the at least one instruction is further configured to: detect a change in energies of left and right feet during walking; and detect a walking pattern according to the change of energies in a section of heel-strike (HS) and a section of toe-off (TO). ### Claim 18 (depends on 15) The walking analysis apparatus according to claim 15, wherein the one or more additional information includes a biometric factor, a location factor within a dangerous area, and a user risk group factor. ### Claim 19 A walking-related accident response service method comprising: identifying an impact section before floor landing, a free fall section, and an impact peak section by floor landing in a graph of impacts due to floor landing occurring during walking, determining whether a walking-related accident type is a ground-level fall, falling from a high place, or a collision by analyzing at least one impact-related parameter for each of the identified sections; calculating an accident risk level based on at least one of the determined walking-related accident type, a biometric factor, a location factor within a dangerous area, and a user risk group factor; and performing an accident response service according to the calculated accident risk level. ### Claim 20 (depends on 19) The walking-related accident response service method according to claim 19, wherein the determining whether the walking-related accident type is the ground-level fall, the falling from a high place, or the collision is made by comparing each of a summation of impact in floor landing section (SIF), a free fall duration (FFD), an impact before floor-landing section peak (IBP), and an impact peak section peak by floor-landing (IPP) with a threshold for each of SIF, FFD, IBP, and IPP.