Method for grouping journeys traveled

Abstract

The present invention relates to a path grouping method, comprising a time-stamped acquisition step (ACQ) of the paths' positioning data, a filtering step (FIL) of outliers, and a grouping step (CST) using a spatiotemporal distance-based agglomerative grouping method. Figure 1 to be published

Description

Title of the invention: Method for grouping traveled paths Technical field

[0001] The present invention relates to the field of grouping journeys traveled, in particular for the purpose of determining the mode of transport, a quantity of pollutants emitted, a vehicle speed and / or a vehicle flow rate.

[0002] The transport sector is an essential aspect of daily life, upon which the global economy is heavily dependent. However, it also plays a major role in the degradation of air quality and the increase in CO2 emissions, particularly in urban areas. According to the World Health Organization (WHO), transport is one of the main sources of air pollution and is directly linked to numerous respiratory and cardiovascular diseases. Furthermore, global transport is responsible for approximately 24% of direct CO2 emissions from fuel combustion, with nearly three-quarters of these emissions coming from cars, trucks, buses, and motorcycles, further exacerbating the phenomenon of global warming. Other types of harmful emissions include nitrogen oxides (NOx), tropospheric ozone (O3), and particulate matter (PM), which generally exceed recommended limits.The importance of transport's role in air quality is also reflected in the increasing number of policy actions undertaken in Europe in recent years, making it a central issue. Strategies aimed at tackling this problem include: standards for vehicle efficiency and low-carbon fuels, development of low-emission vehicles, and tax policies and regimes.

[0003] New mobility data (“Floating Car Data,” which can be translated as tracking vehicle data, GPS-type geolocation sensor data from mobile phones, cell tower data, etc.) presents a largely untapped potential for characterizing mobility patterns within a territory. Indeed, the mobile phone has become one of the essential objects of everyday life. This device is, on the one hand, connected to the network, but more recent technologies also allow it to be connected to and detected by other devices, such as satellites via a geolocation system like the Global Positioning System (GPS), wireless network access points via the Wi-Fi protocol, or other mobile phones via the Bluetooth protocol.This connection data can be used to determine, with varying degrees of accuracy, the position of the mobile device, and therefore presumably that of its owner, and consequently can be useful for characterizing mobility.

[0004] Telephone operators collect connection information from their mobile antennas for all users during data transfers over the mobile network, such as calls, messages, and internet connections, which we will refer to as events hereafter. This data, called Call Detail Records (CDRs), contains, for each recorded event, the user ID, the start and end dates of the event, and the location of the antenna through which the information was transmitted. This type of data offers a very high population penetration rate, as most people now own a mobile phone. However, the generation of this data is often irregular, as it depends on user activity on their mobile phones.It has been observed that a significant portion of this data appears in bursts and during static phases. For this reason, this type of data is widely used for estimating origin-destination matrices of travel patterns, or for dynamically determining the catchment areas of a territory. However, since mobility is repeatable, it is possible to identify recurring patterns in user movement. Some research even aims to supplement data during dynamic phases by utilizing observed patterns. Few solutions, however, focus on determining the trajectory taken by a user to travel from an origin to a destination. Prior art

[0005] Regarding trajectory aggregation in general, there is a great deal of work on GPS data that consists of finding, in real time, which groups of individuals are following the same trajectory in order to group them together, from a more Lagrangian perspective. Most solutions do not simply use GPS data, but also a lot of other information that phones can provide, such as the speed and instantaneous acceleration of the individuals.

[0006] Regarding the aggregation of trajectories with mobile network data, Network Signal Data (NSD), which is generated as soon as a phone connects to an antenna to find a network, is often preferred to CDR data. Since CDR data is a subset of NSD data, everything that can be done with CDR data can be done with NSD data. Origin-destination matrix estimation is possible with NSD data.

[0007] Several solutions have been developed with the aim of categorizing journeys taken from data measured using a mobile phone.

[0008] French patent application FR 3112398 (US 2022 / 0011123) relates to a grouping of trajectories into clusters (groupings) from GPS data, to allow to associate the trajectories of the same cluster with the same mode of transport. To implement this grouping, a spatial distance is used, which does not allow for differentiation between modes of transport that could use the same path but at different speeds. Furthermore, the modified Fréchet distance described in this patent application is not suitable for processing a large set of journeys.

[0009] French patent application FR 3130488 relates to a method for determining a mode of transport using a mobile telephone network. This method, which does not involve grouping the journeys taken, requires significant computation time and substantial computing resources (memory and processor) for processing a large set of journeys.

[0010] The document: “Loïc Bonnetain, Angelo Furno, Nour-Eddin El Faouzi, Marco Fiore, Razvan Stanica, Zbigniew Smoreda, Cezary Ziemlicki, TRANSIT: Fine-grained human mobility trajectory inference at scale with mobile network signaling data, Transportation Research Part C: Emerging Technologies, 2021” describes a method based on a DBSCAN clustering strategy, which allows for the refinement of trajectories for the same user from NSD data, thanks to the repeatability of the trajectories. The goal is to obtain trajectories closely matching GPS data. At the end of the article, the authors overlay trajectories and observe that public transport and road networks stand out with this implementation. They use these operations to observe the catchment areas of certain zones.This method does not take into account the temporal aspect, which makes it impossible to differentiate between journeys using the same route at different speeds (for example, due to a different mode of transport, or due to a congested road).

[0011] US patent application 10073908 describes a spatio-temporal clustering of trajectories using a combination of functional analysis of the trajectories (temporal clustering) followed by spatial clustering of the identified functions. The main problem with this method lies in the computation time, the necessary computing resources (memory and processor), and the parameterization of Functional Data Analysis (FDA) methods for estimating a parametric function for each trajectory, and then of Principal Component Analysis (PCA) to arrive at a subset of parametric functions explaining the majority of the variance of each group of functions. This approach appears poorly suited for handling a large set of trajectories. Summary of the invention

[0012] The present invention aims to group traveled paths, making it possible to separate the speeds of different paths, with a large number of paths, with a Given the limited computing time and resources available, the invention addresses the need to determine the mode of transport, the quantity of pollutants emitted, vehicle speed, and / or vehicle flow rate. To this end, the invention relates to a route grouping method, comprising a step of acquiring time-stamped positioning data for the routes, a step of filtering out aberrant routes, and then a grouping step using an agglomerative clustering method based on spatiotemporal distance. This agglomerative clustering method, based on spatiotemporal distance, allows for the differentiation of speeds and trajectories within the grouped routes in a single step, thereby facilitating the determination of the mode of transport, the quantity of pollutants emitted, speed, and / or flow rate.

[0013] The invention further relates to a method for determining a mode of transport, a method for determining a quantity of pollutants emitted, and a method for determining a speed or flow rate of a vehicle implementing such a method of grouping journeys.

[0014] The invention relates to a method for grouping journeys traveled by at least one user by any means of transport, in which the following steps are implemented: a. We acquire time-stamped positioning data from a plurality of journeys taken; b. Outliers are eliminated from the plurality of acquired routes by a filtering method applied to the time-stamped positioning data; and c. The said plurality of acquired and filtered paths is grouped into at least two groups using an agglomerative grouping method based on a spatiotemporal distance, said spatiotemporal distance being a weighted sum of a spatial distance between two paths and a temporal distance between two paths as a function of the difference in duration between two paths, said spatial distance and said temporal distance being determined from said time-stamped positioning data, the groupings differentiating speeds and trajectories.

[0015] According to one embodiment, the process includes a preprocessing step of said time-stamped positioning data to determine a vector having a predetermined number of path points.

[0016] According to one implementation, the said spatial distance between two paths i and j is determined by means of the following formula: / 7 (Y Y.\-±VN / 7 ((rv W y , v \ \ with the path i, the s pat \ A pj ) hwersine yy J » \ J y J path j, dspat the spatial distance, N the number of path points, dhaversine a distance geodesic between two points, / yy, j the pre-processed coordinates of the k-th point \ of J of path i, / ] the preprocessed coordinates of the k-th point of path i journey j.

[0017] Advantageously, the said time distance between two paths i and j is determined by means of the following formula: . . ( M) )2 with Xj the path i, Xj the path j, dt the distance Xj j — 2 temporal, N the number of path points, the time of the last path point of path i, t[j the time of the first path point of path j, the time of the last path point of path j, tjj the time of the first path point of path j.

[0018] According to one aspect, said spatiotemporal distance is determined by means of the following formula: dspatjemp ~ dspat + ^df with dspatjemp the spatiotemporal distance, dt the temporal distance, 2 a weighting scalar.

[0019] According to one configuration, said time-stamped positioning data of said plurality of journeys are acquired from measurements by means of a geolocation device or from connection measurements to a telephone network.

[0020] According to one embodiment, the method includes a step prior to step b) of filtering in which routes with the same geographical origin area and the same geographical destination area are selected, and the filtering and grouping steps are applied to the selected routes.

[0021] Advantageously, the filtering and grouping steps are repeated for several selections of routes with different geographical origin and / or destination areas.

[0022] According to one embodiment, said outlier paths are filtered using a DBSCAN type data partitioning method, said outlier paths being the paths not grouped by said DBSCAN type data partitioning method.

[0023] The invention also relates to a method for determining a mode of transport for a plurality of journeys, in which the following steps are carried out: a. The grouping of each journey is determined by means of the method according to one of the preceding characteristics; and b. A mode of transport is determined for each grouping based on the speed of the journeys of each grouping and / or by interpolating a known mode of transport from at least one journey belonging to said grouping and / or based on the trajectory of said grouping; and c. Each journey of said grouping is assigned the determined mode of transport said group.

[0024] Furthermore, the invention relates to a method for determining, for a plurality of journeys, an average speed and / or a median speed and / or a vehicle flow rate, in which the following steps are implemented: a. The grouping of each path is determined using the method according to one of the preceding characteristics; and b. The said average and / or median speed and / or vehicle flow of each group is determined by means of the said time-stamped positioning data of the journeys belonging to said group.

[0025] Furthermore, the invention relates to a method for determining the quantity of at least one pollutant emitted by a plurality of paths, in which the following steps are implemented: a. The grouping of each path is determined using the method according to one of the preceding characteristics; and b. For each group, a pollutant emission model is applied, which links the speed and trajectory of said group to a quantity of at least one emitted pollutant; and c. The quantity of at least one pollutant emitted by said plurality of journeys is determined by means of a weighted sum of said quantities of pollutant emitted for each grouping.

[0026] Other features and advantages of the process according to the invention will become apparent from the following description of non-limiting examples of embodiments, with reference to the figures attached and described below. List of figures

[0027] [Fig.1]

[0028] Fig. 1 illustrates the steps of the path grouping process according to a first embodiment of the invention.

[0029] [Fig.2]

[0030] Figure [Fig.2] illustrates the steps of the path grouping process according to a second embodiment of the invention.

[0031] [Fig.3]

[0032] Figure 3 illustrates the steps of the path grouping process according to a third embodiment of the invention.

[0033] [Fig.4]

[0034] Figure 4 illustrates the steps of the process of determining a mode of transport according to an implementation of the invention.

[0035] [Fig.5]

[0036] Figure 5 illustrates the steps in the process of determining the quantity of pollutants. issued according to an implementation of the invention.

[0037] [Fig.6]

[0038] Figure 6 illustrates the steps of the process for determining a speed or flow rate according to an implementation of the invention.

[0039] [Fig.7]

[0040] Figure [Fig.7] illustrates a dendrogram for an example of implementation of the agglomerative grouping step.

[0041] [Fig. 8]

[0042] Figure 8 illustrates, for example, a set of paths between an origin zone and a destination zone.

[0043] [Fig.9]

[0044] Fig.9 illustrates, for example, the aberrant paths identified by the filtering step according to one embodiment of the invention.

[0045] [Fig. 10]

[0046] Fig. 10 illustrates, for example, figures 8 and 9, the trajectories of the groups formed by the grouping process according to one embodiment of the invention.

[0047] [Fig. 11]

[0048] Fig. 11 illustrates, for example, figures 8 to 10, the curves of distance as a function of time for the groupings formed by the grouping process according to an embodiment of the invention. Description of the embodiments

[0049] The present invention relates to a method for clustering journeys. A journey is defined as a trip made by a user between an origin and a destination using any means of transportation (vehicle, bicycle, public transportation: bus, tram, train, metro, walking, etc.). Clustering involves forming groups (clusters) of journeys that share similarities (similar attributes) among the plurality of journeys, specifically similarities in terms of travel speed and trajectories (paths taken). According to one embodiment of the invention, clustering can be used to determine the mode(s) of transportation (i.e., the means(s) of transportation). Alternatively or additionally, clustering can be used to determine the quantity of pollutants emitted.Alternatively or cumulatively, grouping can also be used to determine vehicle speed and / or flow rate. Furthermore, grouping can be used to determine users' preferred routes and itineraries, particularly for navigation assistance purposes (determining a route for a user).

[0050] According to a first embodiment, the process can implement the steps following:

[0051] 1. Acquisition of time-stamped positioning data

[0052] 4. Filtering of aberrant paths

[0053] 5. Grouping of routes

[0054] These steps will be detailed in the remainder of the description. These steps 4 and 5 can be implemented by computer means, in particular a computer or a server, comprising at least a processor and computer memory.

[0055] Figure 1 illustrates, schematically and without limitation, the steps of the path grouping process according to the first embodiment. First, time-stamped positioning data for the plurality of paths is acquired using ACQ. Then, outliers are removed by a FIL filtering method. Finally, the paths are grouped using an agglomerative grouping method based on a spatiotemporal distance CST.

[0056] According to one embodiment of the invention, the method may include a preprocessing step of the time-stamped positioning data, for a homogeneous representation of all paths, which facilitates the calculation of the spatiotemporal distance. Advantageously, this preprocessing may consist of the formation of a vector having a predetermined number of path points, identical for all paths.

[0057] This second embodiment then comprises the following steps:

[0058] 1. Acquisition of time-stamped positioning data

[0059] 3. Preprocessing of time-stamped positioning data

[0060] 4. Filtering of aberrant paths

[0061] 5. Grouping of routes

[0062] These steps will be detailed in the remainder of the description. These steps 3 to 5 can be implemented by computer means, in particular a computer or a server, comprising at least a processor and computer memory.

[0063] Figure 2 illustrates, schematically and in a non-limiting manner, the steps of the A path grouping method according to the second embodiment of the invention. The steps identical to [Fig. 1] are not detailed again. The method further includes a pretreatment step (PRE) before the removal of aberrant paths by filtering (FIL).

[0064] According to one embodiment of the invention, the method may further include a path selection step between a starting zone (also called the origin zone) and an arrival zone (also called the destination zone). In this way, the filtering and grouping steps for path selection are implemented, thereby reducing the volume of paths processed and consequently reducing computation time and the required computing resources (memory and processor). For this embodiment, the various steps can be repeated for several sequences. route selections, for example for several departure zones and / or for several arrival zones. Thus, groupings are built for each selection of routes.

[0065] This third embodiment then comprises the following steps:

[0066] 1. Acquisition of time-stamped positioning data

[0067] 2. Route selection

[0068] 4. Filtering of aberrant paths

[0069] 5. Grouping of routes

[0070] These steps will be detailed in the remainder of the description. These steps 2, 4 and 5 can be implemented by computer means, in particular a computer or a server, comprising at least a processor and computer memory.

[0071] Figure 3 schematically illustrates, without limitation, the steps of the path grouping process according to the third embodiment of the invention (including the second embodiment of the invention in Figure 2). The steps identical to those in Figure 2 are not detailed again. The process further includes an O / D path selection step before the PRE preprocessing step. In addition, the dashed arrow indicates the repetition of steps 2 to 5 for multiple path selections.

[0072] 1. Acquisition of time-stamped positioning data

[0073] During this step, time-stamped positioning data is acquired for a plurality of paths traveled. The time-stamped positioning data includes the location in space of points belonging to the trajectory / path as well as the time associated (timestamp) with this location.

[0074] According to one embodiment, time-stamped positioning data can be acquired by measurements using a geolocation system, for example, GPS (Global Positioning System), the Galileo system, or any similar system. The geolocation system may, in particular, be integrated into a smartphone or a connected device. Alternatively, time-stamped positioning data can be acquired from telephone network connection data. This may be NSD or CDR data, corresponding in particular to the location of the cell towers to which a mobile phone connected during a journey. For this type of data, the recorded geographic coordinates do not correspond to the actual positions of a user but rather to those of the cell towers to which their mobile phone was connected during a telephone event (call, SMS, internet connection).These paths can also contain artifacts such as echo phenomena between antennas when the phone connects to several antennas simultaneously. Therefore, for these various implementations, this measurement step can be carried out using a mobile phone. 2. Route selection

[0075] In this optional step, routes are selected from among the plurality of routes acquired in step 1. Route selection involves collecting routes that have the same starting area (also called the geographical origin area) and the same destination area (also called the geographical destination area). A zone or geographical area is defined as a given territory, for example, a region, a department, a group of municipalities, a city, a district of a city, etc. A geographical area therefore comprises a plurality of points (respectively, a plurality of origin points and a plurality of destination points for trips). By way of example only, this could involve determining trips between a residential geographical area and a professional activity geographical area.The geographical origin zone corresponds to the starting territory of a journey, and the geographical destination zone corresponds to the arrival territory of a journey. For this step, we can select all journeys whose first position is in zone A (origin zone), and whose last position is in zone B (destination zone).

[0076] Following this route selection, filtering and grouping steps can be implemented, increasing the number of routes processed and consequently reducing computation time and computing resource requirements (memory and processor). When this optional step is implemented, the various steps can be repeated for several route selections, for example, for several departure zones and / or several arrival zones. Thus, groupings are created for each route selection, and therefore for each origin-destination zone pair.

[0077] 3. Preprocessing of time-stamped positioning data

[0078] In this optional step, the time-stamped positioning data acquired in step 1 is preprocessed, possibly only for the path selection performed in step 2. This preprocessing converts the time-stamped positioning data for each path into a vector with a predetermined number of path points. In other words, the time-stamped positioning data is converted into a vector with the same number of path points for all paths. This preprocessing, thanks to this homogeneity, facilitates the implementation of the subsequent steps by limiting the computation time and the required computing resources (memory and processor). Indeed, each path, depending on its duration and the measurement method, can have a different number of time-stamped positioning data points.

[0079] According to one embodiment, the number of path points (after preprocessing) can be between 5 and 100, and preferably between 10 and 50. Thus, a a good compromise between accuracy of route representation, calculation time and necessary computer resources.

[0080] For a journey, we can note the time-stamped positioning data acquired at Step 1 as follows: trace: Wi)' ^)] oûtrace is the vector of a path, K the number of positioning data points of the path, x; the longitude of point i, y; the latitude of point i, and f the instant of point i.

[0081] According to an example implementation, the preprocessing can consist of interpolating the time-stamped positioning data onto a predefined length preprocessing time vector (number of path points), denoted p..., with N the number of path points, where the instants are distributed linearly between and ^K, such that:

[0082] - ?!

[0083]

[0084] = 'z+l Wl

[0085] Then, the interpolation can be implemented by forming the new traceinterpolated vector for each path in the following way:

[0086] interpoieé trace ~ yf tr ), ..., ( xN, tN ) ]

[0087] Where ) is an interpolation of the longitude and latitude of the trace vector at time ?;. The interpolation for this preprocessing can be a linear interpolation between the two points of the acquired time-stamped positioning data surrounding the time considered during preprocessing. As an example, for a time ïa of the preprocessing time vector between the acquisition times f and ti+i, we can write respectively for the longitude and for the latitude:

[0088] _ Xi 1 i( L) Xa “ Lr6

[0089] ~ 4. Filtering of aberrant paths

[0090] In this step, outliers are removed from the routes acquired in step 1, possibly selected in step 2, and / or possibly preprocessed in step 3, by means of filtering outliers. An outlier is, for example, a route for which there were measurement errors in the time-stamped positioning data, or which includes portions of outliers: in particular, large detours, loops, etc. This step facilitates spatiotemporal grouping in step 5.

[0091] According to one embodiment of the invention, aberrant paths can be identified by a data partitioning method based on a distance between paths, Specifically, the DBSCAN method (density-based spatial clustering of applications with noise) identifies outliers as those that do not belong to a cluster formed by the data partitioning method. Other similar methods can be implemented for filtering outliers.

[0092] The DBSCAN method allows groups of points into clusters in a hyperspace according to the following rules: • For a new point (in this case a path) X,- which is not assigned to any cluster, we check if there are points belonging to a cluster already identified within a distance s of X( • If yes, X belongs to the nearest cluster as well as all points at a distance less than £ from X; • If not, we look at how many points are located at a distance less than e from X; • If there are more than one, a new cluster is created and all points at a distance less than e from X are assigned to the new cluster. • If there are fewer than Xz, it is assigned to the outlier group and can still be assigned to a cluster as long as points located at a distance less than s from X( are neither assigned to a cluster nor to the outlier group.

[0093] The hyperparameters used to configure a DBSCAN data partitioning method are therefore e, which defines the minimum inter-cluster distance, flmin, which defines the minimum number of samples in a cluster, and the distance measure used. In simplified terms, decreasing the value of e increases the number of clusters and the number of outliers; decreasing the value of flmin increases the number of clusters and decreases the number of outliers. The DBSCAN method is advantageous because it does not require a predetermined number of clusters to be identified, and it allows for grouping all truly similar elements into clusters, provided there is a certain density in the point cloud, while separating anything that resembles nothing else into outliers.

[0094] According to one embodiment of the invention, in order to find the optimal values ​​of the parameters of the DBSCAN method, the silhouette score can be used. This score ensures cohesion of the traces within each cluster and separation from the other clusters. The silhouette score values ​​range from -1 to 1. A value close to 1 indicates that the traces are closer to the traces in their cluster than to the traces forming neighboring clusters. Conversely, a value close to -1 may reveal that some traces have been assigned to the wrong cluster. The silhouette score is calculated from the average intra-cluster distance (a) and the average distance between the nearest clusters (b). It is expressed as:

[0095] Silhouette Score = — max

[0096] Where, a is the average distance between each point within a cluster and b is the distance between a point in a cluster and the nearest cluster of which that point is not a part. In summary, the silhouette score provides a quantitative assessment of the quality of the clustering and allows for clusters with good internal cohesion and separation from other clusters.

[0097] Next, the evaluation of the two parameters s and can be done in two steps. First, the optimal value of s, corresponding to the best silhouette score, can be found by provisionally setting a value of nmm of the same order of magnitude as what is expected. The value e found is then used for calibration to obtain the highest possible silhouette score.

[0098] According to one embodiment of the invention, to efficiently group tracks based on their spatial similarity and thus identify aberrant paths, the Fréchet distance can be used. This distance gives a small distance to two paths that are very close to each other throughout the entire path, and a large distance if the tracks diverge from each other during the path, even if they are very close for almost the entire length of the path. This distance is often illustrated as the minimum leash length required for an owner walking their dog, where one track represents the owner's path and the other the dog's path.

[0099] By way of example, to operate the DBSCAN algorithm, the Fréchet distance between each pair of paths in the plurality of paths (optionally preprocessed and optionally selected) can be calculated. The Fréchet distance can be calculated using dynamic programming or can be approximated by a neural network (as described, for example, in patent application number FR 2307300). 5. Grouping of journeys

[0100] In this step, the filtered routes from step 4 (excluding outliers) are grouped into at least two clusters. In other words, at least two clusters are formed to classify the routes. This is achieved using an agglomerative clustering method, which is a hierarchical clustering method that merges clusters in order of their degree of similarity until a predetermined number of clusters, denoted here as Ni, is reached. This agglomerative clustering is illustrated in Figure 7, which is a dendrogram of a dataset. A dendrogram is a diagram whose x-axis represents the indices N of the samples in the database (the numbers in parentheses indicate the number of data points). in a node (and the numbers without parentheses indicate the data reference), and on the y-axis the minimum distance D between the two clusters, with a tree hierarchically linking the clusters. On the tree, the closest clusters are merged at their minimum distance level, starting with a cluster containing a single sample and going down to a single cluster encompassing all the data. The dendrogram is a tool that provides a visual assessment of the number of relevant clusters to consider and is the basis of hierarchical clustering methods. Agglomerative clustering involves using the dendrogram to merge clusters one after another until the required number of clusters, Nclust^gg, is obtained.

[0101] According to the invention, the agglomerative grouping method is based on a spatiotemporal distance, which is a weighted sum of a spatial distance between two paths and a temporal distance that is a function of the difference in duration between the two paths. The spatial and temporal distances are determined from acquired time-stamped positioning data. Taking into account spatial and temporal data makes it possible to form, in a single step, groupings that differentiate paths with different speeds and trajectories.In other words, each grouping includes journeys following similar paths at similar speeds, which makes it possible to distinguish a bicycle journey from a car journey in congested traffic that would take the same amount of time, but are not carried out at the same pace (the car will go fast in some places and very slowly in others, while the bicycle will be much more regular).

[0102] According to one embodiment, the spatiotemporal distance can be determined using the following formula:

[0103] dspatjemp — dspat .^di with ds paîdemp the spatiotemporal distance, dt the temporal distance, 2 a weighting scalar, which underlines the importance of travel time.

[0104] The hyperparameters to be set for the agglomerative clustering method are the number of clusters required and the weighting factor 2, which allows for varying degrees of importance to be given to travel time in the clustering. The choice of parameter 2 may depend on the type of clustered information desired (primarily temporal, spatial, or spatiotemporal clustering).

[0105] By way of non-limiting example, a weighting of 2 can be chosen between 10⁶ and 10*. For each weighting value, a silhouette score (calculated from the mean intra-cluster distance and the mean distance between the nearest clusters) can then be determined for NciusTjagg — 1 to 40 groupings. The combination of 2 and NciusTjagg giving the best silhouette score can then be chosen.

[0106] For the embodiment in which the time-stamped positioning data is pre-processed, the spatial distance can be determined using the following formula:

[0107] y X}--^YN d H \ , y, H with the path i, the path j, dspat the spatial distance, N the number of path points, dhayersine a geodetic distance between two points, k « j the coordinates of the k-th path point of y ijo J y. y path i, / y « \ 'cs coordinates of the k-th point of path j. V

[0108] For the embodiment in which the time-stamped positioning data is preprocessed, the time distance can be determined using the following formula:

[0109] zx _ ( )2 with Xj the path i, the path j, dt the distance dt\ Xp Xj) — j temporal, N the number of path points, the time of the last path point of path i, the time of the first path point of path j, the time of the last path point of path j, tji the time of the first path point of path j.

[0110] For the embodiment in which groupings are constructed for a selection of routes between an origin zone and a destination zone, steps 2 to 5 can be repeated for at least a second selection of routes, which has a different origin zone and / or destination zone.

[0111] Furthermore, the invention relates to a method for determining a mode of transport for a plurality of journeys. For this method, the following steps are carried out: - The grouping of each journey is determined by means of the grouping method according to any one of the variants or combinations of variants described above; - The mode of transport for each group is determined based on the speed of the journeys within each group and / or by interpolating a known mode of transport from at least one journey belonging to the group (i.e., if the mode of transport for at least one journey belonging to the group is known, then this mode of transport is applied to all journeys in the group) and / or based on the trajectory of the group; and - Each journey in the group is assigned the mode of transport of the group.

[0112] This method has the advantage of determining the mode of transport for a large number of journeys in a simple manner, with reduced computation time, and with limited computing resource requirements (memory and processor). Furthermore, due to the grouping of journeys by trajectory and speed, determining the mode transport is more precise.

[0113] These steps can be implemented by computer means, in particular a computer or a server, comprising at least a processor and computer memory.

[0114] The step of determining the mode of transport for each grouping may consist of: - Compare the speed of each group's journeys (which can be obtained by the distance of the journey path and the average duration of the group's journeys, or by measuring the speed simultaneously with time-stamped positioning data measurements) with a speed representative of the modes of transport: for example, walking approximately 5 km / h, running approximately 10 km / h, cycling approximately 20 km / h, motorized vehicle in the city between 30 and 50 km / h, etc., and / or - Identify at least one route within the group for which the mode of transport is known, for example through a mode of transport acquisition step, and / or - Identify the type of paths taken by the group's trajectory, for example: if it is a highway, the mode of transport is a motorized vehicle, if it is a path, the mode of transport is a mode of soft mobility transport.

[0115] Figure 4 illustrates, schematically and without limitation, the steps of the process for determining a mode of transport according to an embodiment, including the steps of the embodiment of Figure 3. The steps described for Figure 3 are not detailed again. The process further includes a step for determining the mode of transport.

[0116] This figure includes the optional steps of route selection and preprocessing; however, the method of determining the mode of transport can be implemented without these steps.

[0117] The invention also relates to a method for determining an average speed and / or a median speed and / or a flow rate of vehicles on a plurality of journeys. This method involves the following steps: - The grouping of each route is determined using the method according to any of the variants or combinations of variants described above; - An average speed and / or a median speed and / or a vehicle flow rate for each group is determined using time-stamped positioning data of the journeys belonging to the group.

[0118] This method has the advantage of determining an average and / or median speed and / or a vehicle flow rate for a large number of journeys in a simple way, with reduced computation time, and with limited computing resource requirements (memory and processor). Furthermore, due to the grouping of journeys by trajectory and speed, the determination of speed or flow rate is more precise.

[0119] These steps can be implemented by computer means, in particular a computer or a server, comprising at least a processor and computer memory.

[0120] According to one embodiment, the speed of the journeys of each group can be obtained by the distance of the path trajectory, and by the average duration of the journeys of the group.

[0121] Alternatively, a median or average of the speeds of the grouping's journeys can be implemented.

[0122] Alternatively or in addition, the flow rate can be determined based on the number of journeys per grouping and based on the times of the time-stamped positioning data (for example, times of day favorable to congestion or fluid traffic can be identified).

[0123] Figure 6 schematically illustrates, without limitation, the steps of the method for determining a velocity or flow rate according to one embodiment, including the steps of the embodiment of Figure 3. The steps described for Figure 3 are not detailed again. The method further includes a step for determining a velocity or flow rate V / D.

[0124] This figure includes the optional path selection and preprocessing steps; however, the method for determining a velocity or flow rate can be implemented without these steps.

[0125] Furthermore, the invention relates to a method for determining the quantity of pollutants emitted by a plurality of paths. This method involves the following steps: - The grouping of each route is determined using the method according to any of the variants or combinations of variants described above; - For each group, a pollutant emission model is applied, which links the speed and trajectory of the group to a quantity of at least one pollutant emitted, thus obtaining a quantity of pollutant emissions per group; and - The quantity of at least one pollutant emitted by said plurality of journeys is determined by means of a weighted sum of said quantities of pollutant emitted for each grouping.

[0126] This process has the advantage of determining a quantity of pollutants emitted from a A large number of journeys can be easily calculated, with reduced computation time and limited computing resources (memory and processor). Furthermore, by grouping journeys by trajectory and speed, the determination of the quantity of pollutants emitted is more precise.

[0127] These steps can be implemented by computer means, in particular a computer or a server, comprising at least a processor and computer memory.

[0128] The pollutant emission model can notably be written in the form:

[0129] q = f(yo. fraj j with 2 / a quantity of pollutant emissions from group considered, v%ro a speed of the vehicles for the group considered, the trajectory of the group considered, f a function corresponding to the model.

[0130] The speed can be determined as indicated above, or by any similar method. The function f can be obtained from a dynamic vehicle model, or by machine learning, or by any similar means.

[0131] Next, a quantity of pollutants can be determined for the set of journeys using a formula of the type: 101321 e , ^pouoî “ / =0 i^poLgro l

[0133] With Qpoitot the total quantity of pollutants emitted, ^clust.a^ the number of groupings, the weighting of group 1, Qpoigro / the quantity of pollutants emitted for a journey of group 1.

[0134] The weighting of the grouping is advantageously proportional to the number of journeys within the grouping.

[0135] Figure 5 schematically illustrates, without limitation, the steps of the process for determining the quantity of pollutants emitted according to one embodiment, including the steps of the embodiment of Figure 3. The steps described for Figure 3 are not detailed again. The process further includes a step for determining the quantity of pollutants emitted (EPO).

[0136] This figure includes the optional steps of route selection and preprocessing; however, the method of determining the mode of transport can be implemented without these steps.

[0137] Furthermore, the method according to the invention may include a step of displaying the mode of transport and / or the speed and / or the flow rate of vehicles and / or the quantity of pollutants emitted. During this step, the mode of transport and / or the speed and / or the flow rate of vehicles and / or the quantity of pollutants emitted determined on a road map (on a road graph) is displayed. This display may take the form of a note or a This information can be displayed using a color code or a specific thickness to represent the road. It can be displayed on the vehicle itself: on the dashboard, on a portable, standalone device such as a GPS tracking device, or on a smartphone. It is also possible to display the mode of transport, speed, traffic flow, and / or amount of pollutants emitted on a website. Furthermore, this information can be shared with public authorities (e.g., road management companies) and public works companies.Thus, public authorities and public works companies can identify roads with high vehicle traffic, high pollutant emissions, low speeds, and few active mobility trips, and adapt the roads to users (e.g., creation of new lanes, modification of signage, etc.). Examples

[0138] The characteristics and advantages of the method according to the invention will become clearer upon reading the example below.

[0139] For this example, we consider 80 journeys between an origin zone denoted ZO and a destination zone denoted ZD. For these 80 journeys, we acquire time-stamped positioning data measured by connection to the communication network, called CDR data.

[0140] Figure 8 illustrates, schematically and in a non-limiting manner, the paths considered between the origin zone ZO and the destination zone ZD. It can be observed that some paths have portions of the route that are far removed from the vast majority of paths.

[0141] A filtering step is applied, using the DBSCAN method based on a Fréchet distance, to identify aberrant paths. The best silhouette score obtained is 0.53 for the parameters e = 1.98 and nmin = 4. This operation made it possible to filter out the 6 most aberrant tracks.

[0142] Figure 9 illustrates, schematically and in a non-limiting manner, according to the representation in Figure 8, the set of the 6 most aberrant TA tracks. The non-aberrant TNA tracks are schematically represented with a single trajectory.

[0143] It is noted that the filtering makes it possible to identify the most aberrant traces having portions of the route far removed from the vast majority of routes.

[0144] The grouping step of the 74 valid (non-aberrant) paths is then applied using an agglomerative grouping method based on spatiotemporal distance (as exemplified in step 5). The best silhouette score obtained is 0.77 for  — 10 3 and N ci ust^agg — 7. This forms 7 groupings.

[0145] Figure 10 illustrates, schematically and without limitation, according to the representation in Figure 8, the trajectories of the 7 groups. It can be observed that Some overlap.

[0146] Figure 11 illustrates, for these 7 groups, the distance traveled D in km as a function of time T in s. We can observe that the 7 groups have different curves (therefore different speeds).

[0147] Consequently, the method according to the invention makes it possible to differentiate the paths according to their trajectory but also their speed.

Claims

Claims

1. Method for grouping journeys traveled by at least one user by any means of transport, characterized in that the following steps are implemented: a. Time-stamped positioning data of a plurality of journeys traveled are acquired (ACQ); b. Aberrant journeys are eliminated from said plurality of acquired journeys, by a filtering method (FIL) applied to said time-stamped positioning data; and c.Said plurality of acquired and filtered paths are grouped (CST) into at least two groupings using an agglomerative grouping method based on a spatio-temporal distance, said spatio-temporal distance being a weighted sum of a spatial distance between two paths and a temporal distance between two paths depending on the difference in duration between two paths, said spatial distance and said temporal distance being determined from said time-stamped positioning data, the groupings differentiating the speeds and the trajectories.

2. The method of claim 1, wherein the method comprises a step of preprocessing (PRE) said time-stamped positioning data to determine a vector having a predetermined number of path points.

3. Method according to claim 2, wherein said spatial distance between two paths i and j is determined by means of the following formula: si (Y. Y A fl ( ( y., y \ (y., v with A) le U s pat \ A p A j / yy haversiney \ - jj: J ' ( AM' ~j Je, yy path i, Xj the path j, dspat the spatial distance, N the number of path points, a geodesic distance between two points, ( j- y ) the preprocessed coordinates of the k-th path point of path i, / v ) the preprocessed coordinates of the k-th path point of path j.

4. Method according to one of claims 2 or 3, in which said time distance between two paths i and j is determined by means of the following formula: d (X- X -)~ with Xi the Xj the lraJct L d< the time distance, N the number of path points, the time of the last path point of path i, t, ] the time of the first path point of path j, î^y the time of the last path point of path j, t ji the time of the first path point of path j.

5. Method according to one of the preceding claims, in which said spatiotemporal distance is determined by means of the following formula: dspat'temp = dspat + ^dt with ds pattern P the spatiotemporal distance, dt the temporal distance, a weighting scalar.

6. Method according to one of the preceding claims, in which said time-stamped positioning data of said plurality of journeys are acquired (ACQ) from measurements by means of a geolocation device or from measurements of connection to a telephone network.

7. Method according to one of the preceding claims, in which said method comprises a step prior to the filtering step (FIL) in which paths having the same geographical area of ​​origin (ZO) and the same geographical area of ​​destination (ZD) are selected, and the filtering (FIL) and grouping (CST) steps are applied to the selected paths.

8. Method according to claim 7, in which the filtering (FIL) and grouping (CST) steps are repeated for several selections of journeys with different geographical areas of origin (ZO) and / or destination (ZD).

9. Method according to one of the preceding claims, in which said aberrant paths are filtered (FIL) by means of a DBSCAN type data partitioning method, said aberrant paths being the paths not grouped by said DBSCAN type data partitioning method.

10. Method for determining a mode of transport (MDT) of a plurality of journeys, characterized in that the following steps are implemented: a. The grouping of each journey is determined by means of the method according to one of the preceding claims; and b. A mode of transport is determined for each grouping as a function of the speed of the journeys of each grouping and / or by interpolation of a known mode of transport of at least one route belonging to said grouping and / or according to the trajectory of said grouping; and c. Each journey of said group is assigned (MDT) the determined mode of transport of said group.

11. Method for determining, for a plurality of journeys, an average speed and / or a median speed and / or a vehicle flow rate (V / D), characterized in that the following steps are implemented: a. The grouping of each path is determined by means of the method according to one of claims 1 to 9; and b. The said average and / or median speed and / or vehicle flow (V / D) of each grouping is determined by means of the said time-stamped positioning data of the journeys belonging to the said grouping.

12. Method for determining a quantity of at least one pollutant emitted by a plurality of paths (EPO), characterized in that the following steps are implemented: a. The grouping of each path is determined by means of the method according to one of claims 1 to 9; and b. For each grouping, a pollutant emissions model is applied, which links the speed and trajectory of said grouping to a quantity of at least one pollutant emitted; and c. The quantity of at least one pollutant (EPO) emitted by said plurality of paths is determined by means of a weighted sum of said quantities of pollutant emitted for each grouping.

Images