# US 11,113,516 B2 · People flow estimation system and people flow estimation method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,516 B2 - Document ID: US11113516B2 - Status: Granted - Kind: B2 - Application number: 16/490,311 - Filed: 2018-02-26 - Published: 2020-03-05 - Granted: 2021-09-07 - Earliest claimed: 2017-03-01 - Assignees: Carrier Corporation - Applicants: Carrier Corporation - Inventors: Hui Fang; Zhen Jia; Keyu Li; Zhengang Zhu; Xiangbao Li; Mei Chen - Web page: https://patentgrep.com/patent/US11113516B2 ## CPC - G06Q 10/0631: Resource planning, allocation, distributing or scheduling for enterprises or organisations - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G08B 13/196: using television cameras - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS ## Abstract The present invention provides a human flow estimation system and a human flow estimation method. The human flow estimation system comprises: a sensor network comprising a plurality of sensors for collecting data and respectively arranged in each to-be-estimated region and between the to-be-estimated regions; a model building module configured to build a horizontal human flow model and a vertical human flow model based on the plurality of sensors arranged in each to-be-estimated region and/or arranged between the to-be-estimated regions; and a human flow estimation module configured to estimate human flow data based on the horizontal human flow model and the vertical human flow model. The human flow estimation system and the human flow estimation method according to the present invention can realize high-precision estimation of human flow data in a three-dimensional space. ## Claims ### Claim 1 A human flow estimation system comprising: a sensor network comprising a plurality of sensors for collecting data and respectively arranged in each to-be-estimated region and between the to-be-estimated regions; a model building module configured to build a horizontal human flow model and a vertical human flow model based on the plurality of sensors arranged in each to-be-estimated region and/or arranged between the to-be-estimated regions; a human flow estimation module configured to estimate human flow data based on the horizontal human flow model and the vertical human flow model; and an auxiliary information collection module configured to respectively collect first auxiliary information in each to-be-estimated region acquired by a non-sensor and second auxiliary information between the to-be-estimated regions acquired by a non-sensor, wherein the first auxiliary information and the second auxiliary information are used for reflecting changes in the human flow data. ### Claim 2 (depends on 1) The human flow estimation system according to claim 1, wherein the first auxiliary information comprises the usage amount of water and/or electricity in each to-be-estimated region. ### Claim 3 (depends on 2) The human flow estimation system according to claim 2, wherein the usage amount of water and/or electricity is used for defining the human flow data of the to-be-estimated region into a first data interval. ### Claim 4 (depends on 3) The human flow estimation system according to claim 3, wherein the human flow estimation module is configured to modify the estimated human flow data based on the first data interval. ### Claim 5 (depends on 1) The human flow estimation system according to claim 1, wherein the second auxiliary information comprises a load variation value of a passenger transportation device between the to-be-estimated regions. ### Claim 6 (depends on 5) The human flow estimation system according to claim 5, wherein the load variation value of the passenger transportation device is used for reflecting changed human flow data in the to-be-estimated regions when load variation takes place. ### Claim 7 (depends on 6) The human flow estimation system according to claim 6, wherein the human flow estimation module is configured to modify the estimated human flow data based on the load variation value of the passenger transportation device. ### Claim 8 (depends on 1) The human flow estimation system according to claim 1, wherein the sensor network further comprises an auxiliary input end for a user to input human flow data of a specific to-be-estimated region; and the model building module is configured to build the horizontal human flow model and the vertical human flow model based on the plurality of sensors arranged in each to-be-estimated region and/or arranged between the to-be-estimated regions and the auxiliary input end. ### Claim 9 (depends on 8) The human flow estimation system according to claim 8, wherein data from the auxiliary input end has a higher data weight than data from the sensors. ### Claim 10 (depends on 1) The human flow estimation system according to claim 1, wherein the human flow data comprises human flow volume and/or human flow density. ### Claim 11 (depends on 1) The human flow estimation system according to claim 1, wherein the horizontal human flow model and the vertical human flow model respectively comprise a human flow state model and a sensor network model. ### Claim 12 (depends on 11) The human flow estimation system according to claim 11, wherein the model building module is configured to analyze the human flow state model and the sensor network model based on a Kalman filter algorithm, a Bayesian Networks algorithm or a DS evidence algorithm. ### Claim 13 (depends on 11) The human flow estimation system according to claim 11, wherein the model building module comprises a dynamic sensor fusion submodule configured to build the sensor network model based on the data of the plurality of sensors. ### Claim 14 (depends on 1) The human flow estimation system according to claim 1, wherein the sensor divides the to-be-estimated region into a plurality of to-be-estimated subregions; and the sensor is used for detecting human flow data in each to-be-estimated subregion and/or human flow data between adjacent to-be-estimated subregions. ### Claim 15 (depends on 1) The human flow estimation system according to claim 1, wherein the sensor comprises a light beam sensor and/or a PIR sensor and/or a video camera. ### Claim 16 (depends on 1) The human flow estimation system according to claim 1, wherein human flow data change media between the to-be-estimated regions comprise passenger transportation devices and/or stairs. ### Claim 17 (depends on 1) The human flow estimation system according to claim 1, wherein the human flow estimation module is configured to estimate the human flow based on the Kalman filter algorithm, the Bayesian Networks algorithm or the DS evidence algorithm. ### Claim 18 A human flow estimation method, comprising: a data collection step S100, for collecting data in each to-be-estimated region and between the to-be-estimated regions through a sensor network; a model building step S200, for building a horizontal human flow model and a vertical human flow model based on the data in each to-be-estimated region and/or between the to-be-estimated regions; and a human flow estimation step S300, for estimating human flow data based on the horizontal human flow model and the vertical human flow model; wherein the data collection step S100 further comprises collecting first auxiliary information in each to-be-estimated region acquired by a non-sensor and second auxiliary information between the to-be-estimated regions acquired by a non-sensor, wherein the first auxiliary information and the second auxiliary information are used for reflecting changes in the human flow data; and the human flow estimation step S300 further comprises modifying the estimated human flow data based on the first auxiliary information and/or the second auxiliary information. ### Claim 19 (depends on 18) The human flow estimation method according to claim 18, wherein: in the data collection step S100, the first auxiliary information comprises the usage amount of water and/or electricity in each to-be-estimated region, for defining the human flow data of the to-be-estimated region into a first data interval; and in the human flow estimation step S300, the estimated human flow data is modified based on the first data interval. ### Claim 20 (depends on 18) The human flow estimation method according to claim 18, wherein: in the data collection step S100, the second auxiliary information comprises a load variation value of a passenger transportation device between the to-be-estimated regions, for reflecting changed human flow data in the to-be-estimated regions when load variation takes place; and in the human flow estimation step S300, the estimated human flow data is modified based on the load variation value of the passenger transportation device. ### Claim 21 (depends on 18) The human flow estimation method according to claim 18, wherein: the data collection step S100 further comprises: collecting human flow data of a specific to-be-estimated region that is inputted by a user through an auxiliary input end; and in the human flow estimation step S300, the data from the auxiliary input end has a higher data weight than the data from the sensors.