# US 11,443,341 B2 · Method, apparatus, and computer program product for organizing pedestrian movement > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,341 B2 - Document ID: US11443341B2 - Status: Granted - Kind: B2 - Application number: 16/692,772 - Filed: 2019-11-22 - Published: 2021-05-27 - Granted: 2022-09-13 - Earliest claimed: 2019-11-22 - Assignees: HERE Global B.V. - Applicants: HERE Global B.V. - Inventors: James Fowe; Timothy Garcia; Naoko Harada - Web page: https://patentgrep.com/patent/US11443341B2 ## CPC - G06Q 30/0251: Targeted advertisements - G06Q 30/0201: Market modelling; Market analysis; Collecting market data - G06Q 30/0261: {based on user location} - H04W 4/02: Services making use of location information - 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 - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract A method, apparatus, and computer program product are provided for organizing pedestrian movement data. The method includes receiving a set of travel data. The set of travel data includes one or more pedestrian trips including an origin and a destination. The method also includes generating a pedestrian flow matrix. The pedestrian flow matrix has one or more pedestrian flow compartments. The method further includes assigning at least one of the pedestrian trips to one or more of the pedestrian flow compartments based on the origin and the destination of the given pedestrian trip. Corresponding apparatuses and computer program products are also provided. ## Claims ### Claim 1 A method of organizing pedestrian movement data, the method comprising: receiving a set of travel data, wherein the set of travel data comprises one or more pedestrian trips comprising an origin and a destination; generating a pedestrian flow matrix, wherein (i) the pedestrian flow matrix has one or more pedestrian flow compartments, iii) each of the one or more pedestrian flow compartments is uniquely defined by a combination of an origin location and a destination location, (iii) each pedestrian flow compartment is divided based on a first level defined as one of a zip code level, a link level, or a point of interest level and (iv) each pedestrian flow compartment describes one or more characteristics associated with the travel data; generating an additional pedestrian flow matrix, wherein (i) the additional pedestrian flow matrix has one or more pedestrian flow compartments, (ii) each of the one or more pedestrian flow compartments is uniquely defined by a combination of the origin location and the destination location and (iii) each pedestrian flow compartment is divided based on a second level defined as one of a zip code level, a link level, or a point of interest level, wherein the first level and the second level are different; based on the origin and the destination of a given pedestrian trip, assigning at least one of the pedestrian trips to one or more of the pedestrian flow compartments of the pedestrian flow matrix and additional pedestrian flow matrix; predicting a location of a user using a machine learning model, wherein the machine learning model is configured to combine the pedestrian flow matrix and the additional pedestrian flow matrix to predict the location of the user; and causing the transmission of a signal to be provided relating to an advertisement to provide to the user based on the pedestrian flow matrix and the additional pedestrian flow matrix. ### Claim 2 (depends on 1) The method of claim 1, further comprising determining the advertisement to provide to a user based on the pedestrian flow matrix. ### Claim 3 (depends on 1) The method of claim 1, wherein the one or more pedestrian flow compartments are divided based on at least one of zip code level, link level, or point of interest level. ### Claim 4 (depends on 1) The method of claim 1, wherein the one or more pedestrian trips comprises temporal information comprising a time at original and/or a time at destination. ### Claim 5 (depends on 4) The method of claim 4, wherein a plurality of pedestrian flow matrices are each generated with a plurality of time ranges. ### Claim 6 (depends on 1) The method of claim 1, wherein the set of travel data further comprises one or more sub-location points, wherein the sublocation points are intermediate locations between the origin and the destination. ### Claim 7 (depends on 6) The method of claim 6, wherein at least one sublocation point is used as an origin or destination in determining the assignment of the pedestrian tip to the pedestrian flow compartment. ### Claim 8 An apparatus for organizing pedestrian movement data, the apparatus comprising at least one processor and at least one non-transitory memory including computer program code instructions, the computer program code instructions configured to, when executed, cause the apparatus to: receive a set of travel data, wherein the set of travel data comprises one or more pedestrian trips comprising an origin and a destination; generate a pedestrian flow matrix, wherein (i) the pedestrian flow matrix has one or more pedestrian flow compartments, (ii)each of the one or more pedestrian flow compartments is uniquely defined by a combination of an origin location and a destination location, (iii) each pedestrian flow compartment is divided based on a first level defined as one of a zip code level, a link level, or a point of interest level and (iv) each pedestrian flow compartment describes one or more characteristics associated with the travel data; generate an additional pedestrian flow matrix, wherein (i) the additional pedestrian flow matrix has one or more pedestrian flow compartments, (ii) each of the one or more pedestrian flow compartments is uniquely defined by a combination of the origin location and the destination location and (iii) each pedestrian flow compartment is divided based on a second level defined as one of a zip code level, a link level, or a point of interest level, wherein the first level and the second level are different; based on the origin and the destination of a given pedestrian trip, assign at least one of the pedestrian trips to one or more of the pedestrian flow compartments of the pedestrian flow matrix and additional pedestrian flow matrix; predict a location of a user using a machine learning model, wherein the machine learning model is configured to combine the pedestrian flow matrix and the additional pedestrian flow matrix to predict the location of the user; and cause the transmission of a signal to be provided relating to an advertisement to provide to a user based on the pedestrian flow matrix and the additional pedestrian flow matrix. ### Claim 9 (depends on 8) The apparatus of claim 8, wherein the computer program code instructions are further configured to, when executed, cause the apparatus to determine the advertisement to provide to a user based on the pedestrian flow matrix. ### Claim 10 (depends on 8) The apparatus of claim 8, wherein the one or more pedestrian flow compartments are divided based on at least one of zip code level, link level, or point of interest level. ### Claim 11 (depends on 8) The apparatus of claim 8, wherein the one or more pedestrian trips comprises temporal information comprising a time at original and/or a time at destination. ### Claim 12 (depends on 11) The apparatus of claim 11, wherein a plurality of pedestrian flow matrices are each generated with a plurality of time ranges. ### Claim 13 (depends on 8) The apparatus of claim 8, wherein the set of travel data further comprises one or more sub-location points, wherein the sublocation points are intermediate locations between the origin and the destination. ### Claim 14 (depends on 13) The apparatus of claim 13, wherein at least one sublocation point is used as an origin or destination in determining the assignment of the pedestrian tip to the pedestrian flow compartment. ### Claim 15 A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code portions stored therein, the computer-executable program code portions comprising program code instructions configured to: receive a set of travel data, wherein the set of travel data comprises one or more pedestrian trips comprising an origin and a destination; generate a pedestrian flow matrix, wherein (i) pedestrian flow matrix has one or more pedestrian flow compartments, iii) each of the one or more pedestrian flow compartments is uniquely defined by a combination of an origin location and a destination location, (iii) each pedestrian flow compartment is divided based on a first level defined as one of a zip code level, a link level, or a point of interest level and (iv) each pedestrian flow compartment describes one or more characteristics associated with the travel data; generate an additional pedestrian flow matrix, wherein (i) the additional pedestrian flow matrix has one or more pedestrian flow compartments, (ii) each of the one or more pedestrian flow compartments is uniquely defined by a combination of the origin location and the destination location and (iii) each pedestrian flow compartment is divided based on a second level defined as one of a zip code level, a link level, or a point of interest level, wherein the first level and the second level are different; based on the origin and the destination of a given pedestrian trip, assign at least one of the pedestrian trips to one or more of the pedestrian flow compartments of the pedestrian flow matrix and additional pedestrian flow matrix; predict a location of a user using a machine learning model, wherein the machine learning model is configured to combine the pedestrian flow matrix and the additional pedestrian flow matrix to predict the location of the user; and cause the transmission of a signal to be provided relating to an advertisement to provide to a user based on the pedestrian flow matrix and the additional pedestrian flow matrix. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein the program code instructions are further configured to determine the advertisement to provide to a user based on the pedestrian flow matrix. ### Claim 17 (depends on 15) The computer program product of claim 15, wherein the one or more pedestrian flow compartments are divided based on at least one of zip code level, link level, or point of interest level. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein the one or more pedestrian trips comprises temporal information comprising a time at original and/or a time at destination. ### Claim 19 (depends on 18) The computer program product of claim 18, wherein a plurality of pedestrian flow matrices are each generated with a plurality of time ranges. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein the set of travel data further comprises one or more sub-location points, wherein the sublocation points are intermediate locations between the origin and the destination and at least one sublocation point is used as an origin or destination in determining the assignment of the pedestrian tip to the pedestrian flow compartment.