method for determining user flow and / or pollutant emissions on at least one strand of a network

Abstract

The invention relates to a method for determining the number of uses of each mode of transport on a strand of a transport network in a predetermined space, for which: a) spatial and temporal training data (STD) are acquired, b) the predetermined space is discretized into zones (ZD / ZA); c) for each route defined by an origin zone (ZD) and a destination zone (ZA), c1) training trajectories (Traj) are determined; c2) For each learning path (Traj), the path traveled on the transport network and the mode of transport are determined (MDT); d) From the results of step c2, a model (Mod) of the number of uses of each mode of transport on the strand is created (Real); e) A data matrix (Mat) is acquired and applied (App) to the model (Mod) to determine the number of uses (Nb_mdt) of each mode of transport on the strand. Figure 1 to be published

Description

Title of the invention: Method for determining user flow and / or pollutant emissions on at least one strand of a network technical field

[0001] The present invention relates to the field of determining traffic of different types of vehicles or users for a transport network, where different modes of transport are possible. In particular, the invention relates to a method for determining the number of uses (or users) of different modes of transport on at least one segment of a transport network. Thus, it is possible to determine the throughput of each type of transport mode (or the utilization rate or frequency of use of each mode of transport).

[0002] The invention also relates to the field of determining pollutant emissions emitted on at least one strand of the road network, taking into account different modes of transport.

[0003] Today, metropolitan areas and road managers have travel modeling tools at their disposal to plan and simulate the impact of future traffic regulations and works, in order to reduce congestion or improve air quality. However, these models are very difficult to implement (requiring very expensive population survey data and a significant calibration effort), difficult to maintain (maintenance is delegated to consulting firms, making it difficult to develop the tool quickly), and difficult to update (population surveys are conducted every 5 to 10 years).

[0004] There is therefore a strong need for tools to determine vehicle flow rates within a transport network without having to use overly expensive and difficult-to-obtain data as input, such as mobility surveys, which are also static and unsuitable for predicting rapid changes in mobility, or actual usage data, such as "floating car data" (FCD), which is dynamic but not necessarily available for all segments of a transport network. Furthermore, these alternative tools should be easy for non-experts to use, quick to run in order to easily evaluate and compare several case studies, and reliable by reproducing recent traffic count data on the road network under consideration as accurately as possible.

[0005] Moreover, according to the World Health Organization (WHO), approximately 18,000 deaths per day are attributable to poor air quality, which raises the estimate to Air pollution causes approximately 6.5 million deaths per year. It also represents a significant financial burden: a Senate inquiry commission estimated that the total cost of air pollution in France is between €68 and €97 billion per year, according to an assessment published in July 2015. This assessment included both the health damage caused by pollution and its impact on buildings, ecosystems, and agriculture. The transport sector remains one of the largest sources of pollutants, despite numerous measures implemented by public authorities and technological advancements in the field. Transport, across all modes, is responsible for approximately 50% of global nitrogen oxide (NOx) emissions and about 10% of PM2.5 emissions (particles with a diameter of less than 2.5 microns).Road transport alone accounts for a considerable share of this transport-related contribution, with 58% of NOx emissions and 73% of PM2.5 emissions. These emissions are primarily due to three factors: exhaust emissions, abrasion emissions, and evaporation emissions. While heavy goods vehicles are the main emitters of pollutants, it is private vehicles, more prevalent in densely populated urban areas, that have the greatest impact on citizens' exposure to poor air quality.

[0006] Measures implemented at the local level to manage transport use (such as improved transport planning and measures to encourage modal shift, i.e., changing modes of transport), as well as the gradual renewal of the vehicle fleet, have helped to limit exhaust emissions from road transport in cities and urban areas. Indeed, worldwide, road transport activity has increased by a quarter over the last decade, while NOx emissions have increased by 5% and particulate emissions have decreased by 6%. Despite these improvements, pollution levels still exceed the limits set by the WHO in many cities.

[0007] To significantly improve air quality within their territories, French urban communities must take action to reduce transport-related emissions. For example, currently, the road sector accounts for two-thirds of total nitrogen oxide (NOx) emissions and one-third of total PM10 emissions (i.e., particles with a diameter of less than 10 microns) in the Lyon metropolitan area. However, to date, the teams in the Roads and Urban Mobility department of this local authority lack the tools to determine the impact on air quality of the development of the various transport networks and / or the characteristics of the vehicles operating on these networks. Consequently, decisions related to these issues do not take into account the impact on pollutant emissions due to the lack of such tools.

[0008] Consequently, it proves difficult for cities to make sound decisions regarding the development of transport network infrastructure and legislation, for example concerning the characteristics of vehicles authorized to circulate on the networks, without having access to precise tools for assessing and projecting the impact of the proposed measures on pollutant emissions from different modes of transport and air quality. Ideally, these new tools should make it possible to assess the impact of measures on very fine temporal and spatial scales (on the order of one minute and ten meters), taking into account the different means of transport, the different types of vehicles, and the journeys made by the various users of these networks. Previous technique

[0009] The mobile phone has become one of the essential objects in everyday life for many people. While designed to connect to the mobile phone network, newer technologies allow it to also connect to and be detected by other devices, such as satellites via the Global Positioning System (GPS) protocol, 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, in principle, that of its owner (hereafter referred to as the user).

[0010] It is known, notably from the publication by Loïc Bonnetain, Angelo Fumo, Nour-Eddin El Faouzi, Marco Fiore, Razvan Stanica, Zbigniew Smoreda, and Cezary Ziemlicki; 2021. “TRANSIT: Fine-grained human mobility trajectory inference at scale with mobile network signaling data” - Transportation Research Part C: Emerging Technologies, to use NSD (Network Signal Data) to illustrate travel patterns on major routes of a large city's transportation network. However, this method does not allow for determining the number of users of each type of transportation mode, let alone determining pollutant emissions, on any given segment of the transportation network.

[0011] We also know of the document by Manon Seppecher, 2022, “Exploration of mobile telephony data for the reconstruction of global patterns of urban mobility for large-scale emission calculation, Thesis manuscript,” which describes a method that, after analyzing user trajectories, seeks to estimate the total distance traveled by users in regions of a territory on the one hand, and to estimate the average speed of users in the same regions on the other. Then, emissions per region are estimated with a COPERT model for “COmputer The term "Program to Calculate Emissions from Road Transport" refers to a computer program designed to calculate emissions from road transport. However, this method does not allow for the identification of the specific mode of transport. Consequently, it cannot discretize the emissions from each mode of transport on each network segment, and therefore, it does not apply an emission model that is dependent on the identified mode of transport.

[0012] Patent application CN105426636 uses a traffic model to obtain flow rates on the strands of a road network and estimates pollutant emissions from a COPERT model. This application does not identify the mode of transport associated with each trajectory.

[0013] Patent application CN112767686 uses GPS data for "Global Positioning System." However, the use of GPS data is less representative of the population than spatial and temporal data from a phone to a mobile network because this data is only possible when the user uses their phone's GPS. Furthermore, each trajectory is considered individually, which imposes significant computation time and computer memory requirements.

[0014] Patent application CN108682156 also uses GPS taxi data, which limits the type of transport mode used in this method. It also uses GIS (Geographic Information System) data, but it does not allow for determining the number of uses of each type of transport mode on a segment of the network, nor for precisely determining polluting emissions. Summary of the invention

[0015] The technical problem of the invention consists in designing a method for determining traffic flows on a strand of road network within a predetermined space, that is to say the number of uses of each type of mode of transport (or the number of users of each mode of transport), or the flow rate of each type of mode of transport, or the frequency of use of each type of mode of transport, on the strand considered.

[0016] We preferably seek to minimize the computation time and the computer memory and / or the number of processors required.

[0017] Furthermore, the method may also seek to enable the rapid assessment, in terms of user flow and / or pollutant emissions, of modifications to be made to the transport network (infrastructure modifications, such as the addition of a road lane, speed limits, the addition of a traffic light or a roundabout, the development of a soft mobility lane, the addition of bus lines or tram or metro etc...) or decisions to restrict certain vehicles to certain areas to limit congestion and polluting emissions.

[0018] Furthermore, the invention seeks to use data based on a high rate of population penetration (i.e. a very large proportion of mobile phone users), even if this data is of low resolution.

[0019] The invention relates to a method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space, using telephones and a mobile telephone network to which said telephones can connect, and using at least one transport network comprising strands. Furthermore, at least the following steps are carried out by computer means, such as a computer: a) Spatial and temporal training data are acquired for the connection of phones to said mobile telephone network, the spatial and temporal training data comprising the positions of the mobile telephone network antennas to which each phone connected and the times at which these connections of each phone to the antennas took place, preferably the spatial and temporal training data being CDR or NSD data b) the predetermined space is discretized into zones; (c) for each path defined by an origin zone and a destination zone, each origin zone and each destination zone being among said zones of the predetermined discretized space, cl) learning trajectories are determined for said path, from the acquired spatial and temporal learning data, each learning trajectory corresponding to the succession of antenna positions to which one of said phones has connected and the times of these connections; c2) For each determined learning trajectory, the path traveled on the transport network and the associated mode of transport are determined, the path traveled being a succession of strands of the transport network at times of passage; d) from the paths and modes of transport determined in step c2), a model is created of the number of uses of each mode of transport on said at least one strand of the transport network linking the trajectories to a number of uses of each mode of transport on said at least one strand of the transport network; e) we acquire a data matrix and we apply said data matrix to said model of the number of uses for each mode of transport on said at least one strand of the transport network to determine the number of uses of each mode of transport on said at least one strand of the transport network from said data matrix.

[0020] Advantageously, in step d), to realize the model of the number of uses of

[0021]

[0022]

[0023]

[0024] For each mode of transport on said at least one strand of the transport network, the following sub-steps are carried out: dl) for each journey, we identify a first number of learning trajectories linked to each mode of transport; d2) for each journey, we identify a second number of learning trajectories linked to each mode of transport and passing through said at least one strand u transport network; d3) then for each journey, we determine the proportion of learning trajectories linked to each mode of transport and passing through said at least one strand of the transport network, this proportion being, for each mode of transport, the ratio between the second number and the first number; d4) We create a model of the number of uses of each mode of transport on at least one strand of the transport network using the following equation: f — V ynf with f the number of uses of the mode of J ABM J predetermined transport mode M passing through said at least one strand bi of the transport network the proportion calculated in step d3) for each journey from the origin zone A to the destination zone B of the predetermined transport mode M passing through said at least one strand bi of the transport network abm 'C nom^re of trajectories of the journey from the origin zone A to the destination zone B for the predetermined mode of transport F being the space of the transport network considered. Preferably, pre-processing and / or filtering of the spatial and temporal training data is performed. Advantageously, a first adjustment coefficient is assigned to said learning trajectories based on the users of the phones for which the spatial and temporal learning data were acquired in step a). Preferably, second spatial and temporal connection data of phones to said mobile telephone network are acquired, the second spatial and temporal data including the positions of the mobile telephone network antennas to which each phone connected and the times at which these connections of each phone to the antennas took place, and second trajectories are determined so as to form said data matrix acquired from the second spatial and temporal data and preferably a second rectification coefficient is assigned to said second trajectories as a function of the users of the phones for which the second spatial and temporal data were acquired. According to one configuration of the invention, the second trajectories are grouped into clusters of second trajectories, preferably by means of a re-grouping method. agglomeration grouping based on a spatio-temporal distance, said spatio-temporal distance being a weighted sum of a spatial distance between two second trajectories and a temporal distance as a function of the difference in duration between the two second trajectories, said spatial distance and temporal distance being determined from the second spatial and temporal data, the groupings differentiating the speeds and the trajectories.

[0025] Preferably, at step cl), different learning trajectories determined are grouped into learning trajectory clusters.

[0026] Advantageously, the learning trajectories are grouped by means of an agglomerative grouping method based on a spatio-temporal distance, said spatio-temporal distance being a weighted sum of a spatial distance between two learning trajectories and a temporal distance as a function of the difference in duration between the two learning trajectories), said spatial distance and temporal distance being determined from the spatial and temporal learning data, the groupings differentiating the speeds and the trajectories.

[0027] According to one aspect of the invention, in steps c1) and c2), at least the following substeps are carried out: - Transport graphs are constructed for each mode of transport, each transport graph comprising nodes, road segments connecting the different nodes and the average travel speeds on each road segment, each road segment of the transport graph representing the possible routes by the associated mode of transport, the superposition of the transport graphs forming the transport network, each strand of the transport network corresponding to one of said road segments of at least one of said transport graphs, and at least the following steps are implemented: (i) from the acquired spatial and temporal learning data, a succession of location-time pairs is determined, defined by locations corresponding to said antenna positions from the acquired spatial and temporal learning data and by the times corresponding to these locations, and at least one sub-route is formed linking two successive location-time pairs, a succession of sub-routes determining a learning trajectory; ii) For each transport graph, the successive positions of the telephone on successive identified nodes of the transport graph are determined from the location-time pairs, the successive identified nodes being positioned as close as possible to each location; iii) Then, for each transport graph and for each sub-route, a predetermined number of paths are determined through shortest path optimizations. possible paths allowing the different successive identified nodes to be linked by sections of road, each possible path including the passage nodes linking all the sections of road of the possible path, and the time of passage of each passage node is calculated from the average speeds associated with each section of road, each possible path being determined by the list of all pairs of passage nodes - times of passage of said possible path; (iv) a correlation index is determined between each of the possible paths identified and the learning trajectory, the correlation index being representative of the spatial and / or temporal proximity of each successive identified node with the locations of the learning trajectory; and (v) We determine the mode of transport of each learning trajectory, by determining the mode of transport which optimizes the correlation index of the learning trajectory, and the path taken corresponding to the possible path optimizing the correlation index.

[0028] Advantageously, a subgraph is extracted from each transport graph, the subgraph being a part of the transport graph limited to a predetermined width around each subroute determined in step i) and the subgraph is used instead of the transport graph for each of steps ii) to v).

[0029] According to a variant of the invention, the number of uses of each mode of transport passing through at least one strand of the transport network, preferably through at least one group of strands of the transport network and even more preferably through all strands of the transport network, is displayed on a map representing the transport network.

[0030] The invention also relates to a method for determining pollutant emissions on at least one strand of a transport network within a predetermined space, in which the method described above is implemented and the pollutant emissions due to each mode of transport of each learning trajectory and / or of the data matrix passing through said strand are determined for at least one strand of the transport network.

[0031] According to one embodiment of the invention, the pollutant emissions of each mode of transport are determined by multiplying a pollutant emission value of each mode of transport on said at least one strand of the transport network and the number of uses of each associated mode of transport on said at least one strand of the transport network.

[0032] According to a variant of the invention, the determined pollutant emissions are displayed on a map representing the transport network.

[0033] Preferably, a vehicle fleet is used to determine pollutant emissions, said vehicle fleet identifying a distribution of different types of vehicles and a pollutant emission value depending on the different types of vehicles.

[0034] The invention also relates to a method for managing the infrastructure of a transport network within a predetermined space, in which at least the following steps are implemented: 1) The number of uses and / or pollutant emissions of each mode of transport are determined for at least one strand of the transmission network using the method for determining the number of uses of each mode of transport on at least one strand of the transmission network within the predetermined space according to one of the variants or combinations of variants described above, or the method for determining pollutant emissions according to one of the variants or combinations of variants described above. 2) At least one transport network infrastructure is modified according to the number of uses of each mode of transport or polluting emissions, preferably an infrastructure for which the number of uses is greater than a predetermined threshold. List of figures

[0035] Other features and advantages of the methods 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. [Fig 1]

[0036] Fig. 1 represents a first embodiment of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention. [Fig 2]

[0037] Fig. 2 represents an example of an embodiment of the model of the number of uses of each mode of transport on said at least one strand of the transport network of the method of determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention. [Fig 3]

[0038] Fig. 3 represents a second embodiment of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention. [Fig 4]

[0039] Figure 4 represents a third embodiment of the method for determining the number of uses of different transport modes on at least one strand of a transport network within a predetermined space according to the invention. [Fig 5]

[0040] Figure 5 represents a fourth embodiment of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention. [Fig 6]

[0041] Fig. 6 represents an example of a mode of transport identification step and path of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention. [Fig 7]

[0042] Figure 7 represents an example of the application of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a metropolis according to the invention. Description of the implementation methods

[0043] The invention relates to a method for determining the number of uses of different modes of transport on at least one segment of a transport network within a predetermined area. The predetermined area may be, for example, an urban agglomeration, such as a metropolis, a region, or a country. The transport network then considers all the roads and transport lines of the different modes of transport connecting points within the predetermined area.

[0044] Alternatively, the number of uses (or users) of different modes of transport can be the user throughput, that is, the number of users over a predetermined period (for example, an hour, a day, or a month), also called the frequency, or the utilization rate of each mode of transport. The rate gives the proportion of the use (or number of users) of each mode of transport. Hereafter, the number of uses can be replaced by "the number of users," or "the user throughput," or "the number of trips," or "the frequency of uses," or "the utilization rate."

[0045] The different modes of transport may, for example, include bicycle, scooter, walking, car, heavy goods vehicles, motorcycle, bus, tram, metro, and / or train.

[0046] Thus, the method makes it possible to determine, on a particular segment of the transport network, the number of passages (a passage being linked to a user and therefore to a use) associated with each mode of transport. When considering the number of passages over a predetermined period, it is thus possible to determine the variability of the number of passages and therefore of the congestion. The method according to the invention can, in particular, make it possible to determine the number of uses of different modes of transport over different periods, for example on weekdays or weekends, during peak periods or outside peak periods.

[0047] This process can in particular be used to modify transport network infrastructure (adding lanes, constructing specific lanes for particular modes of transport, such as bicycles or scooters), to modify the speed limits of certain strands (at least one strand) of the transport network or to prohibit the circulation of certain vehicles on certain strands (at least one strand) of the transport network by evaluating the impact of these modifications on traffic congestion or on air quality.

[0048] The method according to the invention uses mobile phones (hereafter referred to as phones) and a mobile telephone network to which the mobile phones can connect, as well as at least one transport network comprising interconnected strands. The transport network combines different means of transport, and on the same strand of the transport network, different means of transport (bus, tram, car, motorcycle, truck, bicycle, walking, for example) can be possible.

[0049] In addition, at least the following steps are carried out: a) acquisition of spatial and temporal learning data for connecting phones to the mobile phone network;

[0050] b) discretization of the predetermined space into zones;

[0051] c) determination of learning trajectories for each route defined by an origin zone (also called "departure zone") and a destination zone (also called "arrival zone"), and determination of the path and mode of transport for each learning trajectory

[0052] d) realization of a model of the number of uses of each mode of transport on the strand of the transport network;

[0053] e) acquisition of a data matrix (also called a "path matrix") and application of the data matrix to the model of the number of uses for each mode of transport on the strand of the transport network.

[0054] At least some of the preceding steps (steps b), c), d) and / or the part of e) where the model is applied (for example) can be implemented by computer means, such as a computer. Preferably, all the steps are implemented by computer means.

[0055] Fig. 1 illustrates, schematically and without limitation, a first embodiment of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention.

[0056] In this figure, spatial and temporal DSP training data are acquired from Tel phones (mobile phones, also called portable phones) and a mobile telephony Res network.

[0057] The predetermined space Z is discretized into zones (which will serve as origin zones ZD and destination zones ZA in the following step) from a transport network RT in the predetermined space and possibly from the spatial and temporal learning data DSP.

[0058] In the figure, the elements in dotted lines represent the elements that are optional.

[0059] From the spatial and temporal training data DSP and paths defined by an origin zone ZD and a destination zone ZA among the zones resulting from the discretization Z of the predetermined space, we determine For of the learning trajectories Traj.

[0060] MDT is then determined to have an output data Ch, the output data Ch including the mode of transport and the path of each learning trajectory Traj.

[0061] We can then carry out step d) of the process, that is to say the construction Real of a model Mod of determining the number of uses of each mode of transport on a strand of the transport network from the output data Ch of the different learning trajectories Traj.

[0062] We can then apply App the Mod model to a data matrix Mat to determine the number of uses Nb_mdt of each transport mode on the transport network strand.

[0063] Optionally, we can then calculate Cale the pollutant emissions Pol on the transmission network strand from the number of uses Nb_mdt of each mode of transport on the transmission network strand.

[0064] Of course, all the steps described can be carried out on several strands of the transport network, or even on all strands of the transport network.

[0065] Fig. 3 illustrates, schematically and without limitation, a second embodiment of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention.

[0066] In this figure, the elements and references identical to [Fig.1] correspond to the same elements and references as [Fig.1] and are therefore not detailed again.

[0067] In this embodiment, before determining the learning trajectories Traj directly from the raw (i.e., directly acquired) spatial and temporal training data DSP, a pre-processing step Pre and / or a Filtering step Fil can be performed. The pre-processing step Pre can be performed before the Fil filtering step as illustrated in [Fig.3], or in reverse order.

[0068] When using DSP training spatial and temporal data to discretize Z the predetermined space into zones, used as origin zones ZD and destination zones ZA, this data is preferably used after the preprocessing Pre and / or filtering Fil steps.

[0069] Of course, all the steps described can be carried out on several strands of the transport network, or even on all strands of the transport network.

[0070] Step a): Acquisition of spatial and temporal learning data for connecting phones to the mobile phone network

[0071] During this step, spatial and temporal training data on telephone connections to the mobile network are acquired (or measured or recorded). This spatial and temporal data consists of events recorded by the mobile network (by the mobile network operators) detecting a connection between the telephone and the mobile network (to an antenna of that network). The spatial and temporal training data includes the positions of the mobile network antennas to which each telephone connects and the times at which these connections of each telephone to the antennas occur.

[0072] Preferably, the spatial and temporal training data can be NSD data for "Network Signal Data" or CDR data for "Call Detail Records".

[0073] NSD data is generated as soon as a phone connects to an antenna to find a network, whatever the reason: therefore, NSD data is recorded almost continuously from the moment the phone is not in airplane mode.

[0074] CDR data is a subset of NSD data. CDR data is what enables billing the user based on their phone usage via the mobile network. Therefore, CDR data preferably includes exclusively telephone transaction recording data consisting of an identifier allowing recognition of the user's phone, the type of connection event (call, SMS and / or Internet data exchange), the time of the connection event (possibly the start and end times of the event) as well as the position of the antenna to which the phone was connected at the time the event occurred (i.e. the position of the antenna through which the event passed).Compared to NSD data, CDR data is very weak spatial and temporal data because it only considers events necessary for billing by operators, whereas the data. NSD includes other additional information.

[0075] Being qualitatively very weak in terms of spatial accuracy of the telephone and temporal frequency, these CDR data are generally excluded from methods for determining user trajectories and a fortiori for determining modes of transport or paths on these trajectories.

[0076] Nevertheless, these CDR and NSD data offer a very interesting population penetration rate, especially compared to the GPS data generally used, that is to say that they allow the recovery of data from a larger number of users since today most of the population owns a mobile phone and no particular application needs to be used by the user to access this data.

[0077] Advantageously, preprocessing and / or filtering of the spatial and temporal training data can be performed. Filtering can, for example, include the removal of outliers (also called "outliers"). This filtering involves removing outliers from the spatial and temporal training data acquired in step 1 by means of an outlier filtering. An outlier is, for example, a movement for which there were measurement errors in the time-stamped positioning data, or which includes outlier portions of the movement: in particular, large detours, loops, etc. This step facilitates spatiotemporal grouping.

[0078] The term displacement refers to the succession of antenna positions over time for the same phone during its network connections. These displacements are therefore derived from the spatial and temporal training data.

[0079] According to one embodiment of the invention, outliers can be identified by a data partitioning method based on the distance between the spatial and temporal training data, in particular the DBSCAN method (density-based spatial clustering of applications with noise), with outliers being those that do not belong to a cluster formed by the data partitioning method. Other similar methods can be implemented for this type of filtering.

[0080] The DBSCAN method allows groups of displacement sets into clusters in a hyperspace according to the following rules: • For a new displacement Xt that is not assigned to any cluster, we check if there are displacements belonging to a cluster already identified within a distance e of X, • If so, Xj belongs to the nearest cluster as well as all the de- placements at a distance less than s from Xj • If not, we look at how many displacements are located at a distance less than £ from Xj • If there are more than nmn, a new cluster is created and all movements less than e from Xi are assigned to the new cluster. • If there are fewer than nmû^ Xj is assigned to the group of outliers and can still be assigned to a cluster as long as displacements located at a distance less than £ from X{ are neither assigned to a cluster, nor to the group of outliers.

[0081] The hyperparameters used to configure a DBSCAN data partitioning method are therefore e, which defines the minimum inter-cluster distance, nmm, which defines the minimum number of samples in a cluster, and the distance measurement used. In simplified terms, decreasing the value of s increases the number of clusters and the number of outliers; decreasing the value of nmm 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 data into clusters, provided there is a certain density in the cloud of displacements, while separating what is unlike anything else into outliers.

[0082] According to one embodiment of the invention, in order to find the optimal values ​​of the DBSCAN method parameters, the silhouette score can be used. This score ensures cohesion of displacements within each cluster and separation from other clusters. Silhouette score values ​​range from -1 to 1. A value close to 1 indicates that the displacements are closer to the displacements of their cluster than to the displacements forming neighboring clusters. Conversely, a value close to -1 may reveal that some displacements have been attributed 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:

[0083] Silhouette Score = — inax (aj?)

[0084] Such that, a is the average distance between each displacement within a cluster and b is the distance between a displacement from a cluster and the nearest cluster of which the displacement 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.

[0085] Next, the evaluation of the two parameters Σ and >lmm 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 of s found is used for calibration in order to obtain the highest possible silhouette score.

[0086] According to one embodiment of the invention, to efficiently group movements based on their spatial similarity and thus identify aberrant movements, the Fréchet distance can be used. This distance gives a small distance to two movements that are very close to each other throughout their entire path, and a large distance if the movements move away from each other, even if they are very close for almost the entire duration of the movement. This distance is often illustrated as the minimum leash length required for an owner walking their dog, where one movement represents the owner's path and the other the dog's path.

[0087] By way of example, to operate the DBSCAN algorithm, the Fréchet distance between each pair of displacements in the plurality of displacements (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).

[0088] The pre-processing may, for example, include steps to limit noise and / or to improve the accuracy of the learning. This step is particularly useful for improving the accuracy of the results of the process and the model produced in step d).

[0089] Preprocessing can improve the homogeneity of different learning trajectories. To achieve this, preprocessing can consist of creating a vector with a predetermined number of points representing the learning trajectories, identical for all learning trajectories, in order to limit the computation time and computing resources (memory and processors) required. This preprocessing is particularly advantageous when the learning trajectories are grouped into clusters. The preprocessing of the learning trajectories can then be carried out

[0090] For preprocessing, the spatial and temporal training data (corresponding to each phone) can, for example, be converted into a vector with a predetermined number of points. In other words, the spatial and temporal training data for each phone are converted into a vector with the same number of points for all considered movements. This preprocessing, thanks to this homogeneity, limits the computation time as well as the computing resources (memory and processor) required. Indeed, each device placement depending on its duration and the method of measurement can have a different amount of spatial and temporal training data.

[0091] According to one embodiment, the number of points of the displacement (after preprocessing) can be between 5 and 100, and preferably between 10 and 50. Thus, a good compromise is obtained between the accuracy of the representation of the displacements, computation time and the necessary computing resources.

[0092] For a displacement, the spatial and temporal training data acquired can be noted as follows: trace := Vj y fj ) y WHERE trace is the vector of a displacement, K the number of spatial and temporal data for learning the displacement, x; the longitude of point i, y; the latitude of point i, and t; the time of point i.

[0093] According to an example implementation, the preprocessing can consist of an interpolation of the spatial and temporal training data on a predefined length preprocessing time vector (number of displacement points), denoted pj, ..., with N the number of displacement points, where the instants are distributed linearly between li and such that:

[0094] =

[0095] tK = ~tN

[0096] f li+] '1 jV-1

[0097] Then, the interpolation can be implemented by forming the new traceinterpolated vector for each displacement in the following way:

[0098] traceinîerpoiee := [ ( ■ ?i ), • • ■, ( Av, tN ) ]

[0099] Where / yy, ) is an interpolation of the longitude and latitude of the vector lrace to \ 7 jy At time t, the interpolation for this preprocessing can be a linear interpolation between the two points of the acquired spatial and temporal training data surrounding the time considered during preprocessing. For example, for a time t of the preprocessing time vector between the acquisition times t and ti+i, we can write respectively for longitude and latitude:

[0100] Y- _ Xi ( ) +¾ i ( )

[0101] ~ _ y(LA)+>Ai(CrM a ti+rt'

[0102] Step b): discretization of the predetermined space into zones

[0103] In this step, the predetermined space is discretized into zones. These zones will be used in subsequent steps as origin and destination zones in the transport network. For example, the transport network may include the entire French transport network, and the zones of the predetermined space may be the different departments or the different regions; alternatively, the transport network can include the transport network of a certain area (a certain predetermined space), for example File de France (all transport combined), and areas can be identified as residential, commercial or industrial areas to determine the daily movements of users from their places of residence to their places of work (or vice versa).

[0104] Zones can also be discretized by exploiting spatial and temporal training data. Specifically, zones where the phone remained stationary or within a limited area (for example, a 200m radius) for a certain period of time (for example, half an hour or an hour) can be identified as origin and / or destination zones. Using CDR data for this identification is advantageous because this data allows for reaching a larger population and thus provides a broader spectrum for identifying zones within the predetermined space.

[0105] Determining the zones is particularly useful when grouping learning trajectories into clusters since it is then possible to group the learning trajectories according to the zones (in particular into origin and / or destination zones).

[0106] The zones also make it easier to create the model produced in step d).

[0107] To discretize the predetermined space, one can, for example, create regular zones, that is, divide the predetermined space into squares of predefined side length. Alternatively, one can use standard zones (a neighborhood, a city or town, a department, for example) or use IRIS zones, meaning "Grouped Islands for Statistical Information".

[0108] Step c): determination of learning trajectories for each route defined by an origin zone and a destination zone, and determination of the path and mode of transport for each learning trajectory

[0109] Step c) comprises two substeps c1) and c2) performed for each path, a path being defined by a starting zone and a destination zone, the path going from the starting zone to the destination zone (in other words, the path is oriented). The starting and destination zones are chosen from among the zones resulting from the discretization of the predetermined space.

[0110] Thus, for each route defined by an origin zone and a destination zone: cl) learning trajectories for the route are determined from the acquired spatial and temporal learning data, each learning trajectory corresponding to the sequence of antenna positions to which one of the phones connected and the times of these connections. Thus, for a route, several learning trajectories are identified linking the origin zone to the destination zone of the route in question. These different trajectories can be linked to different modes of transport or different possible routes for the same mode of transport. (c2) Then, for each determined learning trajectory, the path traveled on the transport network and the associated mode of transport are identified, the path being a succession of strands of the transport network at specific times. Indeed, depending, for example, on the average speed of transport, different modes of transport can be distinguished: for example, the speed of walking (approximately 5 km / h) is lower than that of a bicycle or scooter, which is itself lower than that of a bus or tram, which is itself lower than that of a car. A mode of transport can also be identified when a strand of the network directly identifies a strand of a specific mode of transport (for example, the metro). The method for identifying the mode of transport and the path traveled, as defined in the applicant's patent application FR 3130488 A1, can also be implemented for each learning trajectory.

[0111] Advantageously, a first adjustment coefficient can be assigned to the learning trajectories based on the users of the phones for which the spatial and temporal training data were acquired in step a). For example, the spatial and temporal training data can be classified according to the phone user. The different classifications could be: gender, age, social category of the user. Based on the distribution of users in these different classifications and by comparison with other known data, the spatial and temporal training data or the learning trajectories can be adjusted to correct errors that would be induced by the raw data.In other words, by applying an initial adjustment coefficient, we can mathematically correct the acquired statistical data to better represent the actual population.

[0112] According to an advantageous embodiment of the invention, in step c1), different predetermined learning trajectories can be grouped into clusters of learning trajectories. Clustering limits the number of iterations in step c2) and thus reduces computation time and the required computer memory. Indeed, by grouping the learning trajectories into clusters, step c2) only needs to be performed for one trajectory in each cluster.

[0113] Preferably, learning trajectories can be grouped 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 learning trajectories and a temporal distance that is a function of the difference in duration between the two learning trajectories, said spatial distance and temporal distance being determined from the spatial and temporal learning data, the groupings differentiating speeds and trajectories. The taking Taking into account spatial and temporal data makes it possible to form, in a single step, groupings that differentiate between journeys of different speeds and different paths. In other words, each grouping includes trajectories using similar paths at similar speeds, which makes it possible, in particular, to discriminate between a bicycle journey and 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 be fast in some places and very slow in others, while the bicycle will be much more consistent).

[0114] An agglomerative grouping method is a hierarchical grouping method that merges clusters in order of their degree of similarity until a predetermined number of groupings is reached, denoted here N^t^.

[0115] According to one embodiment, the spatiotemporal distance can be determined using the following formula:

[0116] dspatj&np — A-df with d^paîdei-np the spatiotemporal distance, dt the distance temporal, To a weighting scalar, which underlines the importance of travel time (the travel corresponding to a considered trajectory).

[0117] The hyperparameters to be set for the agglomerative grouping method can be the number of groups required Ne}us(fi(,o) and the weighting which allows giving more or less importance to travel time in the clustering. The choice of the parameter A can depend on the type of grouped information desired (clustering that is predominantly temporal, spatial, or spatiotemporal).

[0118] 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 NciustMgg = 1 to 40 clusters. The combination of A and Nciust.agg giving the best silhouette score can then be chosen.

[0119] For the embodiment in which the spatial and temporal training data are preprocessed, the spatial distance can be determined using the following formula:

[0120] ; y.\-±VN pj Hr v Wy v with the path i, A / le path j, d^t the spatial distance, N the number of points in the displacement, d!wversine a geodetic distance between two points, yj the coordinates of the k-th point of the displacement i, the coordinates of the k-th point of displacement j.

[0121] For the embodiment in which the spatial and temporal training data are preprocessed, the temporal distance can be determined by means of from the following formula:

[0122] x ( (ï v-? )2 with Xj the displacement i, the displacement j, the a^Xj, Xj) = .................... time distance, N the number of points of the displacement, the time of the last point of the displacement i, the time of the first point of the displacement i, "tj^ the time of the last point of the displacement], tji the time of the first point of the displacement].

[0123] According to an advantageous embodiment of the invention, transport graphs can be constructed for each mode of transport, each transport graph comprising nodes, road segments connecting the different nodes and the average speeds of travel on each road segment, each road segment of the transport graph representing the possible routes by the associated mode of transport, the superposition of the transport graphs forming the transport network, each strand of the transport network corresponding to at least one of said road segments of at least one of said transport graphs, then: (i) from the acquired spatial and temporal learning data, we can determine a succession of location-time pairs defined by locations corresponding to the positions of the antennas from the acquired spatial and temporal learning data and by the times corresponding to these locations and we can form at least one sub-route linking two successive location-time pairs, a succession of sub-routes determining a learning trajectory; ii) For each transport graph, we can determine the successive positions of the phone on successive identified nodes of the transport graph from the location-time pairs, the successive identified nodes being positioned as close as possible to each location; iii) Then for each transport graph and for each sub-route, we can determine, by shortest path optimizations, a predetermined number of possible paths allowing us to connect the different successive identified nodes by road segments, each possible path including the passage nodes connecting all the road segments of the possible path, and we can calculate the time of passage of each passage node from the average speeds associated with each road segment, each possible path being determined by the list of all pairs of passage nodes - times of passage of said possible path; (iv) a correlation index can be determined between each of the possible paths identified and the learning trajectory, the correlation index being representative of the spatial and / or temporal proximity of each successive identified node with the locations of the learning trajectory; and (v) We can determine the mode of transport of each learning trajectory, by determination of the mode of transport which optimizes the correlation index of the learning trajectory, the path taken corresponding to the possible path optimizing the correlation index.

[0124] These steps make it possible to reconstruct the user's path (from the user's phone) from spatial and temporal training data acquired at very low resolution, which makes this process transposable to other data that could be measured with higher spatial and / or temporal resolution.

[0125] Alternatively, the following mode of transport identification method can be applied: - The mode of transport for each trajectory (or each group of trajectories) is determined based on the speed of the trajectories (or possibly each group) and / or by interpolating a known mode of transport from at least one trajectory belonging to the group (i.e., if the mode of transport for at least one trajectory belonging to the group is known, then this mode of transport is applied to all the trajectories in the group) and / or based on the trajectory of the group; and - We can preferably assign to each trajectory of the group the mode of transport of the group.

[0126] This method has the advantage of easily determining the mode of transport for a large number of trajectories, with reduced computation time and limited computing resource requirements (memory and processor). Furthermore, due to grouping by trajectory and speed, the determination of the mode of transport 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 step of determining the mode of transport for each grouping may consist of: - Compare the speed of the trajectories of each group (which can be obtained by the distance of the trajectory and the average duration of the group's trajectories, or by measuring the speed simultaneously with the acquired spatial and temporal 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 for the group for which the mode of transport is known, for example by means of 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.

[0129] Furthermore, these steps can help identify the road infrastructure to be implemented and / or the transport networks (active mobility or public transport) to be developed. The process also makes it possible to track changes over time in users' transport choices within a given geographical area, depending, for example, on the implementation of road infrastructure or transport networks.

[0130] In this application, the term "succession" or "successive" indicates a succession in time (temporary). For example, two locations are successive if they are two locations that have been identified temporally one after the other.

[0131] Fig. 6 illustrates, schematically and without limitation, an example of a mode of transport identification step and path of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention.

[0132] Transport graphs G_MDP are constructed for each mode of transport, each transport graph comprising nodes, road segments connecting the different nodes, and the average travel speeds on each road segment. Each road segment in the G_MDP transport graph represents the possible routes for the associated mode of transport. The superposition of the transport graphs forms the transport network, and each strand of the transport network corresponds to at least one of the road segments of at least one of the transport graphs.

[0133] From each learning trajectory Traj and transport graphs G_MDP, we determine Det the successive identified nodes NIS of each transport graph G_MDP, as nodes of the transport graph considered to be closest to the positions of the antennas to which the phone connected on the path (we can also consider only some of these positions instead of all of them), while being connected to each other (in other words, there are portions of the road allowing us to connect the different successive identified nodes to each other).

[0134] From the successive identified nodes NIS, we perform an optimization of the shortest paths Opt for each sub-route of each transport graph in order to identify a predetermined number of possible paths CP for each mode of transport.

[0135] Then we evaluate the correlation Corr between each possible path CP of each mode of transport and the learning trajectory Traj, composed of the sub-routes and we determines a correlation index Ind. By optimizing the correlation (via the correlation index Ind), we can determine Det-MDP the output data Ch which includes the mode of transport and the path traveled on the transport network by the user for the relevant learning trajectory.

[0136] The steps described above can be implemented by computer means, for example a computer.

[0137] Preferably, a subgraph can be extracted from each transport graph, the subgraph being a portion of the transport graph limited to a predetermined width around each subroute determined in step i), and the subgraph can be used instead of the transport graph for each of steps ii) to v). As a result, the subgraph has a limited number of nodes and route segments, which facilitates the determination of the transport mode and, on the other hand, limits the possible paths determined in step iii). Thus, a great deal of information can be quickly obtained on the transport modes chosen by users based on their route, as well as on the evolution of this information over time. Consequently, it is easier to process the data, increasing the efficiency and speed of the method, and limiting the computer memory required for implementing the invention on a computer.

[0138] Step d): realization of a model of the number of uses of each mode of transport on said at least one strand of the transport network

[0139] Based on the paths and modes of transport determined in step c2) on the learning trajectories of the different routes between the origin and destination zones, a model of the number of uses (or the flow rate of users or uses, also called frequency, or a utilization rate) of each mode of transport is created on at least one segment of the relevant transport network. This model links the trajectories to a number of uses (or the flow rate of users or uses, also called frequency, or a utilization rate) of each mode of transport on the relevant segment of the transport network. In other words, the learning trajectories and the associated paths and modes of transport determined in step c2) are used to create the model of the number of uses of each mode of transport on the relevant segment of the transport network.The advantage of this model is its ability to determine, very quickly and with minimal computer memory and processing power requirements, the impact of travel rates on the transport network segments, based on new data (for example, new trajectories, i.e., trajectories different from the training trajectories). This new data can, for example, take into account planned modifications to the transport network (changes or additions of lanes, modifications to intersections, speed limits). It can also include data from other time periods or other contexts. The learning paths are completed in days. Thanks to the model, we can avoid applying steps b) and c) to new data, as these steps are lengthy and require significant memory and processing power. This allows us to test different configurations and quickly assess the impact in terms of user throughput or pollutant emissions (greenhouse gases, such as carbon dioxide, and / or particulate matter) on a strand of the transmission network. The new data corresponds to the data matrix used in the following steps.

[0140] For example, to create a model of the number of uses of each mode of transport on the relevant segment of the transport network, the following steps can be carried out: dl) For each journey, we identify a first number of learning trajectories linked to each mode of transport. Thus, for each journey from an origin zone to a destination zone, we count the number of learning trajectories for each mode of transport, this number defining the first number for each mode of transport;

[0141] The first number .f of learning trajectories of the route linking the origin zone A to the destination zone B by the mode of transport M can in particular be defined as follows:

[0142] / = W; • h -m

[0143] Where lexpr is the indicator which is 1 if exPr is true and 0 otherwise. In this case, le-m is equal to 1 if the mode of transport is mode of transport M and it is equal to 0 if it corresponds to another mode of transport different from mode of transport M.

[0144] corresponds to the number of learning trajectories of the mode of transport concerned, possibly corrected by a correction coefficient.

[0145] corresponding to the set of trajectories linking the origin zone A to the zone destination B.

[0146] d2) for each path, a second number of trajectories are identified learning paths are linked to each mode of transport and pass through the relevant segment of the transport network. Thus, for each journey from an origin zone to a destination zone, the number of learning paths for each mode of transport that pass through the relevant segment is counted; this number defines the second number for each mode of transport passing through the relevant segment.

[0147] The second number / BMb of learning paths of the route linking the origin zone A to the destination zone B via the mode of transport M and passing through strand b of the transport network can in particular be defined as follows: [DUS] f1 / ,^,

[0149] Where Uxpr is the indicator which is 1 if exPr is true and 0 otherwise. In this case, - 1£-=a / is equal to 1 if the mode of transport is mode of transport M and it is equal to 0 if it corresponds to another mode of transport different from the mode of transport M; - is equal to 1 if the considered strand bt belongs to the path Bj identified for the learning path (the path Bj comprising a sequence of strands from the transport network) and it is equal to 0 if the path Bj does not include the strand Bj.

[0150] wj corresponds to the number of learning trajectories of the mode of transport concerned, possibly corrected by a correction coefficient as explained previously.

[0151] Qajs corresponding to the set of trajectories linking the origin zone A to the destination zone B.

[0152] d3) then for each path, the proportion of trajectories is determined Learning curves related to each mode of transport and passing through the relevant segment of the transport network, this proportion being, for each mode of transport, the ratio between the second number and the first number; this proportion is particularly interesting because it changes little over time. Thus, we can use this proportion, which becomes an intrinsic characteristic of the distribution of the different modes of transport for each journey and the passage through the relevant segment.

[0153] For example, the proportion of learning trajectories of the route connecting the origin zone A to the destination zone B by mode of transport M and passing through strand bj of the transport network can be determined by:

[0154] ^a^m^ “ fABM

[0155] With f being the second number of learning paths of the route connecting the origin zone A to the destination zone B via the mode of transport M and passing through the strand bt of the transport network

[0156] And f ^BM the first number of learning paths of the route connecting the area from origin A to destination area B by mode of transport M.

[0157] d4) the model of the number of uses of each mode of transport is implemented on the relevant strand of the transport network from the following equation: f = VV / y ? with f the number of uses of the mode of JM,bt ^AéT^B^AéT^A^M^ AB.MJ Mb, predetermined transport M passing through said at least one strand bi of the transport network ^ABAfp, the proportion calculated in step d3) for each journey from the origin zone A to the destination zone B of the predetermined transport mode M passing through said at least one strand bi of the transport network ^bm 'C name of trips (from the data matrix) of the route from the origin zone A to the destination zone B for the predetermined mode of transport M. F being the space of the transport network considered which includes all origin zones and all destination zones.

[0158] Therefore, the number of uses f of the predetermined mode of transport M 7 M,bt passing through said at least one strand bi of the transport network is the sum over all journeys going from the different origin zones A to the different destination zones B, of the product of the proportion concerned and the number of trips of the data matrix of the journey leaving the origin zone A to the destination zone B for the predetermined mode of transport M.

[0159] Fig. 2 illustrates, schematically and without limitation, an example of an embodiment of the model of the number of uses of each mode of transport on the considered strand of the transport network of the method of determining the number of uses of different modes of transport on the considered strand of a transport network within a predetermined space according to the invention.

[0160] In this example, we construct Real the Mod model of the number of uses of each mode of transport on a strand of the transport network from the output data Ch, which include, for each learning path, the path traveled on the transport network (as a succession of strands on the transport network) and the associated mode of transport.

[0161] To do this, from the output data Ch, for each journey, INI is identified as a first number N1 and IN2 as a second number N2.

[0162] The first number NI corresponds, for each journey, to the number of learning trajectories linked to each mode of transport.

[0163] The second number N2 corresponds, for each journey, to the number of learning trajectories linked to each mode of transport and passing through the considered strand of the transport network.

[0164] From the first and second numbers for each journey, for each journey, we determine I_ratio the proportion ratio of learning trajectories linked to each mode of transport and passing through the considered strand of the transport network, this proportion ratio being, for each mode of transport and each journey, the ratio between the second number N2 and the first number NI.

[0165] We can then establish Eq the Mod model from the proportion ratio and new data (called data matrix in step e)).

[0166] Step e): Acquisition of a data matrix and application of the data matrix to the model of the number of uses for each mode of transport on the considered strand of the transport network.

[0167] During this step, a data matrix is ​​acquired. This data matrix can provide, for each journey from a starting zone to a destination zone, the number of trips made (over a predetermined period, for example). This can be the total number of trips made (all modes of transport combined) or the number of trips made for each type of transport mode. This data matrix can be obtained in various ways: for example, by using CDR or NSD data, by measuring vehicles on road segments, by surveys, etc. This data matrix can, in particular, be determined at a time distinct from the data used for the training trajectories or be derived from a projection that takes into account a change in the transport network.

[0168] The data matrix can, for example, be determined from second trajectories, which are new trajectories, distinct from the learning trajectories. These second trajectories may correspond to planned or implemented modifications to the transport network and / or to trajectories acquired at times and / or on days different from the learning trajectories.

[0169] The data matrix (which can be determined from the second trajectories for example) is then applied to the model of the number of uses (or the flow rate of users or uses, also called frequency, or a rate of uses) for each mode of transport on the considered strand of the transport network to determine the number of uses (or the flow rate of users or uses, also called frequency, or a rate of uses) of each mode of transport on this strand of the transport network from the data matrix (and / or possible second trajectories).

[0170] Advantageously, one can acquire second spatial and temporal connection data of phones to the mobile telephone network, the second spatial and temporal data comprising the positions of the antennas of the mobile telephone network to which each phone connected and the times at which these connections of each phone to the antennas took place.

[0171] The second spatial and temporal data can be NSD data and preferably they can be CDR data, as defined above.

[0172] From the second set of spatial and temporal data, we can then determine second trajectories, and from these second trajectories, we can construct a data matrix which defines, for each journey from an origin zone to a destination zone, the number of trips made for each type of transport mode (over a predetermined duration, for example). This is how we form the data matrix.

[0173] Preferably, a second adjustment coefficient can be applied to the second trajectories based on the users of the phones for which the second spatial and temporal data were acquired. For example, the second spatial and temporal data can be classified according to the phone user. The different classifications could be: sex, age, social category of the user. Based on the distribution of users in these different classes and by comparison with other known data, the second spatial and temporal data or the second trajectories can be adjusted to correct the errors that would be induced by the raw data. In other words, by applying a second adjustment coefficient, the acquired statistical data can be mathematically corrected to better represent the actual population.

[0174] Figure 4 illustrates, schematically and without limitation, a third embodiment of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention.

[0175] In this figure, the elements and references identical to [Fig.1] correspond to the same elements and references as [Fig.1] and are therefore not detailed again.

[0176] In this embodiment, to determine For2 the data matrix Mat, we acquire Acq2 of the second spatial and temporal data DSP2 from the connection data of Tel phones of the mobile telephone network Res.

[0177] These second spatial and temporal data DSP2 are used to determine Detl the second trajectories Traj2, from which the data matrix Mat is determined For2.

[0178] Before the Detl determination step of the second trajectories Traj2, a pre-processing step Pre2 and / or a filtering step Fil2 can be performed on the second spatial and temporal data DSP2. These pre-processing steps Pre2 and filtering steps Fil2 can be identical to the pre-processing and filtering steps (referred to respectively as Pre and Fil in [Fig.3]) applied to the spatial and temporal training data DSP.

[0179] Preferably, the second DSP2 spatial and temporal data are of the same type as the DSP training spatial and temporal data (for example, they are NSD data and preferably, they are CDR data).

[0180] The pre-treatment step Pre2 can be carried out before the filtering step Fil2 as illustrated in [Fig.4], or in the reverse order.

[0181] Of course, all the steps described can be carried out on several strands of the transport network, or even on all strands of the transport network.

[0182] Figure 5 illustrates, schematically and without limitation, a fourth mode of implementation of the method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space according to the invention.

[0183] In this figure, the elements and references identical to [Fig.1] correspond to the same elements and references as [Fig.1] and are therefore not detailed again.

[0184] In this embodiment, to determine the learning trajectories Traj, spatial and temporal training data DSP are acquired Acq from the connection data of phones Tel from the mobile telephone network Res.

[0185] These spatial and temporal training data DSP are used to determine For the intermediate learning trajectories Traj_int, which are the set of trajectories corresponding to the spatial and temporal training data DSP (one intermediate learning trajectory for each phone). Then, the intermediate learning trajectories Traj_int are grouped into clusters, which then form the learning trajectories Traj used in the MDT identification step of the mode of transport and the path traveled on the transport network. This limits the number of learning trajectories in which the mode of transport and the path are identified by MDT, and therefore also limits the number of learning trajectories for the Real construction step of the Mod model.

[0186] In this embodiment, to determine the data matrix Mat, Acq2 of the second spatial and temporal data DSP2 is acquired from the connection data of Tel phones of the mobile telephone network Res.

[0187] These second spatial and temporal data points DSP2 are used to determine Detlb the second intermediate trajectories Traj2_int, which are the set of trajectories corresponding to the second spatial and temporal data points DSP2 (one intermediate trajectory for each phone). Then, the second intermediate trajectories Traj2_int are grouped reg2 into clusters, which then form the second trajectories Traj2, used to determine For2 the data matrix Mat. The data matrix Mat is then used in the application step App of the Mod model. This limits the number of trajectories to which the Mod model is applied.

[0188] During the regi and reg2 grouping steps, the output trajectories (respectively the learning trajectories Traj and the second trajectories Traj2), which are each a cluster of trajectories, are assigned a number of trajectories corresponding to the number of intermediate trajectories grouped in the cluster concerned, so as to be able to count the number of similar trajectories of each cluster, and thus to determine the number of uses of each mode of transport of the concerned strand of the transport network.

[0189] Before the step of determining the second intermediate trajectories Traj2_int, a pre-processing and / or filtering step of the second spatial and temporal data DSP2 can be carried out. These pre-processing and filtering steps of the second spatial and temporal data DSP2 can be identical to the pre-processing and filtering steps of the second spatial and temporal data DSP2 (named Pre2 and Fil2 respectively in [Fig.4]) and can be identical to the pre-processing and filtering steps applied to the spatial and temporal training data (named Pre and Fil respectively in [Fig.3]).

[0190] Preferably, the second DSP2 spatial and temporal data are of the same type as the DSP training spatial and temporal data (for example, they are NSD data and preferably, they are CDR data).

[0191] The pre-processing step can be carried out before the filtering step as illustrated in [Fig.4], or in the reverse order.

[0192] Of course, all the steps described can be carried out on several strands of the transport network, or even on all strands of the transport network.

[0193] Of course, the different embodiments of figures 1, 3, 4 and 5 can be combined with each other (two by two, three by three or all together) without going out of the scope of the invention.

[0194] According to an advantageous embodiment of the invention, the second trajectories can be grouped into clusters of second trajectories. Grouping them into clusters limits the number of iterations and thus reduces computation time and the required computer memory. Indeed, by grouping the second trajectories into clusters, step e) only needs to be performed for one second trajectory in each cluster.

[0195] Preferably, the second trajectories can be grouped 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 second trajectories and a temporal distance that is a function of the difference in duration between the two second trajectories, said spatial distance and temporal distance being determined from the second spatial and temporal data, the groupings differentiating between speeds and trajectories. Taking into account spatial and temporal data makes it possible to form, in a single step, groupings differentiating between paths with different speeds and different routes.In other words, each grouping includes second trajectories taking similar paths at similar speeds, which makes it possible to discriminate between a bicycle journey and a car journey in congested traffic which would take the same amount of time, but which 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 slower). more regular).

[0196] When groupings have already been performed on the learning trajectories, it is also possible to use the learning trajectories resulting from these groupings, that is, to reuse the clusters of learning trajectories, for the second trajectories. Each of the second trajectories can be associated with the nearest cluster among the learning trajectories. Thus, a path and the mode of transport can be associated with each second trajectory.

[0197] According to one embodiment of the invention, the number of uses (or the throughput, rate, or frequency of uses or users) of each mode of transport passing through at least one strand of the transport network, preferably through at least one group of strands of the transport network, and even more preferably through all strands of the transport network, can be displayed on a map representing the transport network. This display allows for easy reading of the results. The display can take the form of a rating, a color code, or a thickness representing each strand on the map. This display can be implemented on board the vehicle: on the dashboard, on a portable, standalone device, such as a geolocation device (such as a GPS), a mobile phone (such as a smartphone), or a computer.It is also possible to display the number of uses (or the throughput, rate, or frequency of uses, or the number of users) of each mode of transport passing through at least one strand of the transport network on a website. Furthermore, the number of uses (or the throughput, rate, or frequency of uses, or the number of users) of each mode of transport passing through at least one strand of the transport network can be shared with public authorities (e.g., road managers) and public works companies. In this way, public authorities and public works companies can identify roads with high usage rates and the associated mode of transport, as well as the necessary improvements to the transport network to reduce congestion or limit polluting emissions (e.g., creating new lanes, modifying signage, etc.).

[0198] The invention relates to a method for determining pollutant emissions on at least one strand of a transmission network within a predetermined space. For this method, the process for determining the number of uses (or the rate, flow rate, or frequency of uses or users) of different modes of transport on at least one strand of a transmission network within a predetermined space, as described above, is implemented. For at least one strand of the transmission network, the pollutant emissions due to each mode of transport in each learning path and / or in the data matrix passing through the strand in question are determined. This method can, in particular, be used to modify transmission network infrastructure (adding tracks, constructing specific tracks for modes). private transport, bicycle or scooter for example), to modify the speed limits of some (at least one) strands of the transport network and / or to prohibit the circulation of certain vehicles on some (at least one) strands of the transport network, by assessing the impact of these modifications on the quantity of polluting emissions emitted on the strands of the transport network and consequently on air quality.

[0199] Advantageously, the pollutant emissions of each mode of transport can be determined by multiplying a pollutant emission value for each mode of transport on the relevant segment of the transmission network by the number of uses of each associated mode of transport on said relevant segment of the transmission network. Thus, a rapid assessment of pollutant emissions can be established based on the different modes of transport on the relevant segment.

[0200] Alternatively or additionally, when modes of transport are linked to vehicles, the quantity of polluting emissions emitted by each vehicle of each mode of transport on a strand can be determined by the method described in patent application FR3122011 Al.

[0201] Alternatively or additionally, the following method may be applied:

[0202] Furthermore, the invention relates to a method for determining the quantity of pollutants emitted by a plurality of routes. This method involves the following steps: - We apply a pollutant emission model that links speed and trajectory to a quantity of at least one emitted pollutant, thus obtaining a quantity of pollutant emissions per trajectory; and - We determine the quantity of at least one pollutant emitted by said plurality of trajectories.

[0203] The model of pollutant emissions can in particular be written in the form:

[0204] q = trai \ with <2 z a quantity of emissions of the trajectory considered, vw° a speed of the vehicles for the trajectory considered, / raj the trajectory considered, f a function corresponding to the model.

[0205] The function f can be obtained from a dynamic vehicle model, or by machine learning, or by any similar means.

[0206] Next, a quantity of pollutants can be determined for the set of trajectories using a formula of the type: 102071, pouUot pot^ro l

[0208] With the total quantity of pollutants emitted, Nc]ust^s the number of groupings (if groupings are used) or trajectories, the weighting of the grouping or trajectory 1, Qpoigro / the quantity of pollutants emitted for a trajectory or for group 1.

[0209] The weighting of the group œi is advantageously proportional to the number of trajectories within the group.

[0210] According to an advantageous embodiment of the invention, a vehicle fleet can be used to determine pollutant emissions, said vehicle fleet identifying a distribution of different types of vehicles and a pollutant emission value according to the different types of vehicles. The vehicle fleet can be the current fleet of vehicles using the transport network in question. It can also be defined based on historical data and / or prior knowledge of the vehicle fleet in the area under consideration (i.e., the transport network). Thus, the predefined fleet is a distribution, by number or percentage, of each predetermined vehicle circulating on the portion of the transport network.Within the vehicle fleet, the different vehicles are categorized. A vehicle category can include, in particular, a European emissions standard, engine displacement, type of powertrain (gasoline, diesel, electric, etc.), and aftertreatment technology. This breakdown of the vehicle fleet can be carried out for passenger cars, heavy goods vehicles, light commercial vehicles, motorcycles, etc. By taking the vehicle fleet into account, the determination of pollutant emissions is more representative of current or future conditions. Indeed, the vehicle fleet can be a projection into the future of the distribution of different vehicle categories, with the aim of testing different configurations to limit pollution (pollutant emissions) in certain areas.

[0211] Thus, the application of a pollutant emissions model can take into account the fleet of vehicles used for the transport network under consideration.

[0212] Preferably, the determined pollutant emissions can be displayed on a map representing the transport network. This display allows for easy interpretation of the results. The display can take the form of a rating, a color code, or a thickness representing each strand on the map. This display can be implemented on board the vehicle: on the dashboard, on a portable, stand-alone device such as a GPS tracking device, a mobile phone (such as a smartphone), or a computer. It is also possible to display the number of uses (or the flow rate, rate, or frequency of uses, or the number of users) of each mode of transport passing through at least one strand of the transport network on a website. Furthermore, the pollutant emissions from at least one strand of the transport network can be shared with public authorities (e.g., road authorities) and public works companies.Thus, public authorities and public works companies can determine which strands of the transport network have a high rate of polluting emissions, and what improvements need to be made to the network. transport to limit polluting emissions (for example, creation of new roads, modification of signage, etc.).

[0213] Furthermore, the invention relates to a method for managing the infrastructure of a transport network within a predetermined space. The following steps can be implemented for this method: a. The number of uses and / or pollutant emissions of each mode of transport are determined for at least one strand of the transmission network using the method for determining the number of uses of each mode of transport on at least one strand of the transmission network within the predetermined space or the method for determining pollutant emissions according to any of the variants or combinations of variants described above; and b. At least one transport network infrastructure is modified based on the number of uses of each mode of transport or polluting emissions, for example, an infrastructure for which the number of uses exceeds a predetermined threshold.

[0214] Thus, a transport network can be managed to limit or even avoid pollution peaks, traffic jams, and the risk of accidents.

[0215] According to one embodiment, the modification of the infrastructure can be chosen in particular from the addition of signage (speed limit, traffic light, yield, stop, etc.), the construction of a new lane, conversion of a strand to one direction, construction of a new road, etc. Examples

[0216] The method according to the invention has been tested by the following example.

[0217] CDR data were used as spatial and temporal training data and as second spatial and temporal data, at the scale of a large metropolis.

[0218] This data was used at two distinct times: - a first period known as "normal", between February 22, 2020, and March 1, 2020 and; - a second period known as the "COVID" period, between April 1st and 7th, 2020.

[0219] These two periods were deliberately chosen to have a period of circulation normal before the lockdown due to the Covid-19 pandemic and another period with very different circulation due to the confinement of the population during the Covid-19 pandemic.

[0220] During the normal period, 326,208,648 telephone records were acquired; during the COVID period, 128,406,026 records were acquired.

[0221] The records each correspond to spatial and temporal data of type CDR.

[0222] From this data, trajectories could be determined between origin areas and destination areas.

[0223] The normal period is used for determining learning trajectories and the learning model, and the COVID period is used for determining second trajectories.

[0224] Given the large amount of data, the spatial and temporal training data (normal period) and the second spatial and temporal data (Covid period) were grouped into clusters to limit computing resources and computation time.

[0225] Pollutant emissions were determined for a vehicle fleet comprising 18% heavy commercial vehicles, 6% heavy goods vehicles, 1% two-wheelers and 75% passenger vehicles. The proportions of engine types for each standard are specified in the tables below. Breakdown of passenger vehicle engine types by standard and percentage (%): Euro 1 Diesel 0.6, Euro 1 Petrol 0.3, Euro 2 Diesel 1.3, Euro 2 Petrol 0.8, Euro 3 Diesel 5.1, Euro 3 Petrol 2, Euro 4 Diesel 21.5, Euro 4 Petrol 6.5, Euro 5 Diesel 22, Euro 5 Petrol 9.2, Euro 0 Diesel 13.6, Euro 0 Petrol 16.1 Distribution of light commercial vehicle engines Standard Share (%)

[0226]

[0227]

[0228] Euro3 P 1.7 Euro4 P 2.8 Euro5 P 4.2 Euro3 M 10.1 Euro4 M 17.2 Euro5 M 25.6 Euro6 M 37.8 Distribution of heavy goods vehicle engines Standard Share (%) HGV 1 5.3 HGV 2 1 HGV 3 10 HGV 4 1.3 HGV 5 12.6 HGV 6 6.6 HGV 7 28.7 HGV 8 34.5 Figure 7 illustrates the comparison of pollutant emissions emitted on each strand of the transport network in the metropolis concerned for the normal period on the right and for the covid period on the left. On the map representing the transport network of this metropolis (which thus defines the predetermined area), the shades of gray represent the variations in pollutant emissions on each line: the darker the shade of gray, the higher the pollutant emissions (the poorer the air quality). Conversely, the lighter the shade of gray, the lower the pollutant emissions (the better the air quality). Thanks to the method of the invention, a highly significant difference in pollutant emissions can be observed on each strand of the transmission network, with pollutant emissions being much lower during the COVID period (left) than during the normal period (right). Furthermore, thanks to the model, it was not necessary to repeat steps b) to d), which require significant computer memory and processing power. The results for the COVID period were obtained from a matrix of data and the model obtained from the learning trajectories, very quickly.

Claims

1. Demands A method for determining the number of uses of different modes of transport on at least one strand of a transport network within a predetermined space, by means of telephones (Tel) and a mobile telephony network (Res) to which said telephones (Tel) can connect, and by means of at least one transport network (RT) comprising strands, characterized in that at least the following steps are carried out by computer means, such as a computer: a) spatial and temporal training data (STD) of telephone (Tel) connection information are acquired (Acq) to said mobile telephony network (Res), the spatial and temporal training data (STD) comprising the positions of the antennas of the mobile telephony network (Res) to which each telephone (Tel) has connected and the times at which these connections of each telephone (Tel) to the antennas took place,Preferably, the spatial and temporal training data (STD) being CDR or NSD data; b) the predetermined space is discretized into zones; (c) for each path defined by an origin zone (ZD) and a destination zone (ZA), each origin zone (ZD) and each destination zone being among said zones of the discretized predetermined space, (c) learning trajectories (Traj) of said path are determined from the acquired spatial and temporal learning data (DSP), each learning trajectory (Traj) corresponding to the succession of antenna positions to which one of said phones (Tel) has connected and the times of these connections; c2) we determine (MDT), for each determined learning trajectory (Traj), the path traveled on the transport network and the associated mode of transport, the path traveled being a succession of strands of the transport network (RT) at times of passage; d) from the paths and modes of transport determined in step c2), we realize (Real) a model (Mod) of the number of uses of each mode of transport on said at least one strand of the transport network linking the trajectories to a number of uses (Nb_mdt) of each mode of transport on said at least one strand of the transport network (RT); e) We acquire a data matrix (Mat) and apply said data matrix (Mat) to said model (Mod) of the number of uses for each mode of transport on said at least one strand of the transport network to determine the number of uses (Nb_mdt) of each mode of transport on said at least one strand of the transport network (RT) from said data matrix (Mat).

2. A method according to claim 1, wherein in step d), to realize (Real) the model (mod) of the number of uses (Nb_mdt) of each mode of transport on said at least one strand of the transport network, the following substeps are carried out: d1) for each journey, a first number (NI) of learning paths linked to each mode of transport is identified (IN1); d2) for each journey, a second number (N2) of learning paths linked to each mode of transport and passing through said at least one strand of the transport network (RT) is identified (IN2); d3) then for each journey, the proportion (ratio) of learning paths (Traj) linked to each mode of transport and passing through said at least one strand of the transport network (RT) is determined (I_ratio), this proportion (ratio) being, for each mode of transport, the ratio between the second number (N2) and the first number (NI);d4) we realize (Eq) the model (Mod) of the number of uses of each mode of transport on said at least one strand of the transport network from the following equation: f — V yf with / ' the number of uses J Mit AJ!MJ of the predetermined mode of transport M passing through said at least one strand bi of the transport network the proportion calculated in step d3) for each journey from the origin zone A to the destination zone B of the predetermined mode of transport M passing through said at least one strand bi of the transport network fM 'C number of trajectories of the journey from the origin zone A to the destination zone B for the predetermined mode of transport F being the space of the transport network (RT) considered.;

3. A method according to any one of the preceding claims, wherein pre-processing (Pre) and / or filtering (Fil) of the spatial and temporal training data (STD) is performed.

4. A method according to any one of the preceding claims, wherein a first correction coefficient is assigned to said learning trajectories (Traj) as a function of the telephone users (Tel) for which the spatial and temporal training data (SPD) were acquired in step a).

5. A method according to any one of the preceding claims, wherein second spatial and temporal data (STD2) of telephone (Tel) connection to said mobile telephony network (Res) are acquired, the second spatial and temporal data (STD) comprising the positions of the antennas of the mobile telephony network (Res) to which each telephone (Tel) connected and the times at which these connections of each telephone (Tel) to the antennas took place, and second trajectories (Traj2) are determined so as to form (For2) said data matrix (Mat) acquired from the second spatial and temporal data (STD2), and preferably a second rectification coefficient is assigned to said second trajectories (Traj2) as a function of the users of the telephones for which the second spatial and temporal data (STD2) were acquired.

6. A method according to claim 5, wherein the second trajectories are grouped (reg2) into clusters of second trajectories (Traj2), preferably by means of an agglomerative grouping method based on a spatio-temporal distance, said spatio-temporal distance being a weighted sum of a spatial distance between two second trajectories and a temporal distance as a function of the difference in duration between the two second trajectories, said spatial distance and temporal distance being determined from the second spatial and temporal data (DSP2), the groupings differentiating the speeds and the trajectories.

7. A method according to any one of the preceding claims, wherein in step cl), different learning trajectories (Traj_int) determined are grouped (régi) into clusters of learning trajectories (Traj).

8. A method according to claim 7, wherein the learning trajectories (Traj_int) are grouped by means of an agglomerative grouping method based on a spatio-temporal distance, said spatio-temporal distance being a weighted sum of a spatial distance between two learning trajectories (Traj_int) and a temporal distance that is a function of the difference in duration between the two learning trajectories (Traj_int), said spatial distance and temporal distance being determined from the spatial and temporal training data (SPD), the groupings differentiating the speeds and trajectories.

9. A method according to any one of the preceding claims, wherein, in steps c1) and c2), at least the following substeps are carried out: - transport graphs (G_MDP) are constructed for each mode of transport, each transport graph (G_MDP) comprising nodes, road segments connecting the different nodes and the average travel speeds on each road segment, each road segment of the transport graph (G_MDP) representing the possible routes by the associated mode of transport, the superposition of the transport graphs (G_MDP) forming the transport network (RT), each strand of the transport network (RT) corresponding to one of said road segments of at least one of said transport graphs (G_MDP), wherein at least the following steps are implemented: (i) from the acquired spatial and temporal learning data (SPD), a succession of location-time pairs is determined, defined by locations corresponding to said antenna positions from the acquired spatial and temporal learning data (SPD) and by the times corresponding to these locations, and at least one sub-route is formed linking two successive location-time pairs, a succession of sub-routes determining a learning trajectory (Traj); ii) For each transport graph (G_MDP), we determine (Det) the successive positions of the phone on successive identified nodes (NIS) of the transport graph (G_MDP) from the location-time pairs, the successive identified nodes (NIS) being positioned as close as possible to each location; iii) Then for each transport graph (G_MDP) and for each sub-route, we determine (Opt), by shortest path optimizations, a predetermined number of possible paths (CP) allowing us to connect the different successive identified nodes (NIS) by road segments, each possible path (CP) including the passage nodes connecting all the road segments of the possible path (CP), and we calculate the time of passage of each passage node from the average speeds associated with each road segment, each possible path (CP) being determined by the list of all pairs of passage nodes - passage times of said possible path (CP); iv) a correlation index (Ind) is determined (Corr) between each of the possible paths (CP) determined and the learning trajectory, the correlation index (Ind) being representative of the spatial proximity and / or temporal proximity of each successive identified node (NIS) with the locations of the learning trajectory (Traj); and v) we determine (Det_MDP) the mode of transport (MDP) of each learning trajectory, by determining the mode of transport which optimizes the correlation index (Ind) of the learning trajectory, and the path traveled corresponding to the possible path optimizing the correlation index.

10. A method according to claim 9, wherein a subgraph is extracted from each transport graph, the subgraph being a part of the transport graph (G_MDP) restricted to a predetermined width around each subroute determined in step i) and the subgraph is used instead of the transport graph (G_MDP) for each of steps ii) to v).

11. A method according to any one of the preceding claims, wherein the number of uses (Nb_mdt) of each mode of transport passing through at least one strand of the transport network (RT), preferably through at least one group of strands of the transport network (RT) and even more preferably through all strands of the transport network (RT), is displayed on a map representing the transport network (RT).

12. Method for determining pollutant emissions (Pol) on at least one strand of a transport network (RT) within a predetermined space, characterized in that the method according to one of the preceding claims is implemented and in that the pollutant emissions (Pol) due to each mode of transport of each learning path (Traj) and / or of the data matrix (Mat) passing through said strand are determined (Cale), for at least one strand of the transport network (RT).

13. A method according to claim 12, wherein the pollutant emissions (Pol) of each mode of transport are determined (Cale) by multiplying a pollutant emission value of each mode of transport on said at least one strand of the transport network (RT) and the number of uses (Nb_mdt) of each associated mode of transport on said at least one strand of the transport network (RT).

14. A method according to any one of claims 12 or 13, wherein the determined pollutant emissions (Pol) are displayed on a map representing the transport network (RT).

15. A method according to any one of claims 12 to 14, wherein a fleet of vehicles is used to determine (Calibrate) pollutant emissions (Pol), said fleet of vehicles identifying a distribution of different types of vehicles and a pollutant emission value depending on the different types of vehicles.

16. A method for managing the infrastructure of a transport network within a predetermined space, in which at least the following steps are implemented: 1) The number of uses and / or pollutant emissions of each mode of transport are determined for at least one strand of the transmission network by means of the method for determining the number of uses of each mode of transport on at least one strand of the transmission network within the predetermined space according to any one of claims 1 to 11 or the method for determining pollutant emissions according to any one of claims 12 to 15; and 2) At least one transport network infrastructure is modified according to the number of uses of each mode of transport or polluting emissions, preferably an infrastructure for which the number of uses is greater than a predetermined threshold.

Images