Method and system for generating traffic volume data

Abstract

A method for generating traffic data indicative of traffic volume and / or traffic density within a navigable network in an area covered by an electronic map is provided, the electronic map comprising a plurality of segments representing navigable elements of the navigable network. The method generally comprises obtaining data indicative of a count of devices associated with vehicles traversing the navigable elements represented by the segments with respect to a given time, wherein the count of devices is based on location data and associated timing data related to movement of a plurality of devices associated with vehicles along the navigable elements represented by the segments; and using the determined count data and a scaling factor to obtain data indicative of an estimated traffic volume of the segments with respect to the given time, wherein the scaling factor is time dependent.

Description

Technical Field

[0001] This invention relates to a method and system for generating data indicating traffic volume within a navigable network. The navigable network is located in an area covered by an electronic map, which includes multiple segments representing navigable elements of the navigable network. Background Technology

[0002] Traffic volume (also known as traffic flow) is a measure of the number of vehicles passing through a navigable element, such as a given cross-section of a road, within a specified time period.

[0003] Traffic volume is a crucial parameter for determining the average speed of travel (or conversely, the travel time) associated with road elements in a road network. When planning routes through a road network, the average speed (or travel time) associated with different road elements can be considered. For example, each road element in a navigable network can be represented by a road segment on an electronic map. The average speed (or travel time) data associated with the road segment can then be used, for example, with an appropriate cost function, to plan the fastest route through the navigable network. Similarly, average speed data can be used to determine the precise arrival time of a route. The more accurate the traffic volume data available for road elements in the road network, the more accurate the determination of the fastest route and / or the estimated arrival time.

[0004] Besides being important in navigation environments, traffic volume is generally a crucial quantity used to characterize the state of traffic within a road network. Therefore, understanding this type of traffic data can be highly beneficial for traffic management and control purposes. For example, traffic volume, along with traffic speed, is a key parameter in many traffic management and control applications. Generally, traffic volume data can be used in a variety of applications to provide a more complete operational measure. For instance, traffic volume data can provide insights into real-time flow through the network, which can be useful for monitoring significant events or incidents occurring within the network, including monitoring the impact of pedestrian information on the route (which is typically not equipped with a traffic monitoring system). As another example, traffic volume data can be used to determine traffic demand patterns, such as for calibrating and validating traffic light signal patterns. Traffic volume data can also be used to estimate road capacity, for example, in traffic planning models. As yet another example, combining traffic volume data with data reporting delays (or costs) caused by traffic congestion allows for the estimation of transportation costs.

[0005] Traditionally, traffic volume is measured by directly counting the number of vehicles at a specific location within a road network using manual or automatic counting methods. Automatic counting can be performed by employing various sensors at the desired locations within the road network. For example, video or radar sensors are known for automatically counting vehicles passing through a given cross-section of a road; however, the most widely used techniques for automatic counting rely on inductive sensing (e.g., inductive loop sensors embedded in the road network). These types of sensors can be expensive to install and maintain, and their availability varies widely depending on location. Therefore, such direct counting methods provide accurate data but cannot be easily scaled to provide broader road network coverage.

[0006] Figure 9 The map displays map areas including road segments. Highways are shown in dark gray. The map also indicates the location of sensor loops on highways (dark dots 500 on highways). Road segments that are not highways typically do not have sensor loops. These segments are shown in light gray or using a single gray line. This indicates that only a small portion of the road segments are equipped with traffic flow detectors.

[0007] Map data used by navigation applications is specifically designed for route guidance algorithms and typically uses location data from positioning systems such as GPS or GNSS. For example, a road can be described as a line, i.e., a vector (e.g., the road's start, end, and direction; a road is composed of hundreds of such segments, each uniquely defined by the start / end direction parameters). A map is a set of such road vectors, data associated with each vector (speed limits, direction of travel, etc.), additional points of interest (POIs), additional road names, and additional geographic features such as park boundaries, river boundaries, etc., all defined in vectors. All map features (e.g., road vectors, POIs, etc.) are typically defined in a coordinate system corresponding to or related to the positioning system, such as GPS, so that a location determined by the positioning system can be located on the relevant roads shown on the map and used to plan the optimal route to a destination.

[0008] Within a given road network, a number of vehicles are associated with devices containing location detection components (such as GPS devices). These devices transmit location data indicating their position, and thus, location data of the vehicle relative to time. This data may be referred to as "detector data," or more specifically, "vehicle detector data." Another term commonly used for this data is "floating vehicle data." Each device (or vehicle) may be referred to as a "detector."

[0009] Therefore, detector data transmitted by a device associated with a vehicle provides indication of the vehicle's movement through the network. In some embodiments, the device associated with the vehicle transmitting the detector data may be a device running a navigation application. This device may be referred to as a "navigation device." For example, such a navigation device may comprise a dedicated navigation device or any mobile device (e.g., a mobile phone, tablet computer, or wearable device, such as a watch) that executes a suitable navigation application thereon, or it may be implemented using an integrated in-vehicle navigation system. However, the detector data may comprise location data obtained from any device associated with the vehicle and having location determination capabilities. For example, the device may include components for accessing and receiving information from a WiFi access point or cellular communication network, such as a GSM device, and using this information to determine its location. However, typically, the device includes a Global Navigation Satellite System (GNSS) receiver, such as a GPS receiver, for receiving satellite signals indicating the receiver's location at a specific point in time and preferably receiving updated location information at regular intervals. Such devices may include navigation devices, mobile telecommunications devices with positioning capabilities, wearable devices with positioning capabilities, location sensors, etc. For example, a navigation application may cause a device running the application to periodically sample at least its current location. This location data sample may be referred to as a "detector" data sample. The detector data sample contains at least the device's location and may include data indicating the time associated with that location.

[0010] Optionally, the detector data sample may include other data. For example, the detector data sample may include latitude coordinates, longitude coordinates, and time values, and optionally additional information such as one or more of the following: azimuth, speed of travel, altitude, etc. The device is arranged to transmit the detector sample data to a server. Such location data samples, i.e., detector data samples, may be collected by the server from multiple devices traversing navigable elements of a navigable network in a geographic area. Navigable elements may be represented by segments of an electronic map. The device may be associated with a vehicle traversing an element of the network. The detector data sample obtained from a given device indicates the path traveled by that particular device.

[0011] Techniques for determining traffic volume using detector data have been proposed. Such techniques are advantageous because traffic volume data for any segment of interest is available without the cost and lack of flexibility associated with traditional techniques using fixed sensor infrastructure. However, detector data is typically collected from only a portion of the total vehicle fleet. Penetration level can be defined as the proportion of vehicles from which detector data is collected. Penetration level can also be referred to as penetration rate, sample fraction, (device) extent, or (relative) percentage (level). For consistency, the term "penetration level" will be used here. Currently, the percentage of vehicles whose data is collected (i.e., the "penetration level") is only about 10%, and even lower in some areas. Low penetration and potentially uneven sampling rates mean that traffic volume is generally not (and cannot) be determined directly from detector data.

[0012] Electronic maps comprise multiple segments of navigable elements (e.g., road elements) representing navigable networks (e.g., road networks). Traffic volume in a segment of the electronic map can be estimated using the count of elements traversed by a vehicle-associated device at time t (as indicated by detector data (i.e., the count of detectors traversing the segment at the relevant time)) and a scaling factor.

[0013] therefore:

[0014] Y(s,t)=kX(s,t)

[0015] (Equation 1)

[0016] in:

[0017] Y(s,t) is the traffic volume of (directed) road segment s at time t;

[0018] X(s,t) is, at time t, a count (i.e., detector count) of navigable elements (represented by the segment of the electronic map) traversed by the device at the obtained location data related to the movement of the device associated with the vehicle; and

[0019] k is the proportionality coefficient.

[0020] The proportionality coefficient indicates the permeability level, and in this example, it is the reciprocal of the permeability level.

[0021] To simplify the notation, time t can be expressed in units of time, such as time interval Δt. For example, in one such system, hours are used as Δt, and time t is a time indicator in hours (t has an accuracy of 1 hour).

[0022] Therefore, the scaling factor k is used to project the detector counts associated with a given time period (e.g., a clustering time interval) onto the traffic volume of that segment at that given time. It will be seen that the factor k (and the corresponding penetration level θ) is crucial for the ability to accurately perform this projection.

[0023] For ease of reference, properties such as traffic volume, measured traffic volume, or crossing counts, whether measured or based on detector data, may be referenced herein relative to navigable segments, such as road segments on an electronic map representing navigable elements, such as road elements of a navigable network (e.g., a road network associated with it). Unless explicitly stated otherwise, it will be understood that such properties, such as traffic volume or counts, indicate corresponding properties in the real world of the navigable elements represented by the segments.

[0024] Traffic flow detectors, such as sensing loops, can be used to directly measure the count of vehicles along a navigable element. The total traffic volume measured at time t for a given navigable segment s is represented as Y(s,t). The total traffic volume Y(s,t) of the segment can be obtained corresponding to the measured count of vehicles passing along the road element represented by the segment at a relevant time (e.g., within a relevant aggregation time interval). This sensed or measured traffic volume can be used to estimate a scaling factor k, which allows the traffic volume to be projected from the detector counts of the segment at the relevant time. In other words, the measured counts of vehicles serve as ground reality, from which the scaling factor k can be directly estimated by comparing the measured counts with sample detector counts X(s,t) about the same time t. As mentioned above, for the sake of simplicity in notation, time t can be expressed in time units of Δt, for example, using hours as Δt, where time t is an hourly time indicator (t has an accuracy of 1 hour).

[0025] A common technique is to use traffic flow detectors to determine a constant proportionality coefficient indicating the infiltration level, such as a coefficient k that is the reciprocal of the infiltration level. Although the common approach is to use a constant coefficient k, the applicant has recognized that this can introduce errors because the infiltration level varies at different times of day and / or between different road sections.

[0026] To illustrate this point, two sets of induction loops were used to perform the experiment. The first set of induction loops yielded a coefficient k = 5.68 (θ = 17.6%). Using this result to analyze the second set of induction loops, a mean relative prediction error (MRE) of 12.9% was obtained. Figure 10 The figures shown are for the estimated actual traffic flow kX(s,t) and the measured traffic flow Y(s,t) of the second set of induction loops, based on the observed error.

[0027] The figure illustrates the error distribution determined using the second set of observed detector data and induction loop data. The error distribution suggests a need for a better method to estimate the coefficients used to obtain total traffic volume from the detector data.

[0028] WO2019 / 158438A1, published on August 22, 2019, under the name of TomTom Traffic BV and entitled "Methods and Systems for Generating Traffic Volume or Traffic Density Data", describes a technique for estimating traffic volume on a road segment using the average speed of detectors detected on the segment and segment parameters.

[0029] Another method for estimating traffic volume using detector data is described in US 2015 / 0120174 A1, published on April 30, 2015, under the name of HERE Global BV and entitled "Traffic Volume Estimation". However, various drawbacks can still be seen in the method described in US 2015 / 0120174 A1.

[0030] Therefore, the applicant has recognized that there is still a need for improved methods and systems for providing traffic volume data about navigable networks based on detector data. Summary of the Invention

[0031] According to a first aspect of the invention, a method is provided for generating traffic data indicating traffic volume within a navigable network in an area covered by an electronic map, the electronic map comprising a plurality of segments representing navigable elements of the navigable network, the method comprising, for one or more segments of the electronic map:

[0032] Obtain data indicating a count of devices associated with a vehicle traversing the navigable element represented by the segment at a given time, wherein the count of devices is based on position data and associated timing data related to the movement of multiple devices associated with the vehicle along the navigable element represented by the segment; and

[0033] The determined count data and scaling factor are used to obtain data indicating the estimated traffic volume of the segment with respect to the given time, wherein the scaling factor is a time-dependent scaling factor, and the method includes using the scaling factor with respect to the given time in obtaining the estimated traffic volume of the segment.

[0034] Therefore, according to the present invention, a count of devices associated with a vehicle traversing a navigable element represented by a segment of the electronic map at a given time is obtained. The count is based on location data and associated timing data (i.e., vehicle detector data) related to the movement of multiple devices associated with the vehicle along the navigable element represented by the segment; that is, it is obtained using the location data and associated timing data. The count data, together with a scaling factor, is used to obtain an estimated traffic volume for the segment with respect to the given time. The estimated traffic volume indicates the estimated traffic volume for the navigable element represented by the segment with respect to the given time.

[0035] The method may be performed relative to one or more segments, which may be referred to as segments of interest. Any of the steps described herein with respect to determining traffic volume and / or proportionality coefficients for the (segment of interest) interest may be performed relative to one or more additional segments of interest.

[0036] According to the present invention, the scaling factor is a time-dependent scaling factor. A scaling factor with respect to (i.e., applicable to) a given time is used to obtain the estimated traffic volume. Therefore, the scaling factor (value) will vary depending on the time considered, rather than using a scaling factor that is constant with respect to time, so that the same scaling factor (value) can be used regardless of the time associated with the required estimated traffic volume.

[0037] The proportionality coefficient is preferably estimated, i.e., calculated, rather than measured. However, as described below, the process of estimating the estimated proportionality coefficient may involve using measured data.

[0038] A scaling factor is used to estimate traffic volume for a segment. Traffic volume is a measure of the number of vehicles passing through a given cross-section of a road within a specific time period. Therefore, in an embodiment, to estimate traffic volume for a segment, the number of detector counts (i.e., the “sample size”) at a given time (e.g., within a given time interval) is determined, and an appropriate scaling factor is used to scale the determined sample size to estimate the total traffic volume for that segment. The scaling factor indicates penetration rate, for example, and is inversely proportional to it.

[0039] The given time (the count data and the proportionality coefficient, and therefore the estimated traffic volume, are related to the given time) is preferably a time interval. The time interval can be a cyclical time interval, such as a given time interval for a given day of the week. In a preferred embodiment, the given time is a time interval for a given day of the week.

[0040] The count of devices associated with a vehicle traversing the navigable element represented by the segment at the given time can be a count of such devices associated with a vehicle traversing the navigable element at the given time, for example, within a given time interval.

[0041] To use vehicle location (i.e., detector) data to determine the count of devices or perform other operations, location data must be aggregated over a time interval. In embodiments where the given time is a time interval, the time interval may be a time interval used to aggregate location data, for example, to obtain a count of devices traversing a navigable element. The time interval may be an aggregation time interval for aggregating the location data while obtaining the count of devices. It will be understood that obtaining a count of devices traversing a navigable element represented by a segment will generally involve aggregating location data, i.e., detector data, related to the movement of devices associated with vehicles along the element within a time window or "aggregation interval." When obtaining a count with respect to an aggregation interval, any devices that traverse the element within that aggregation interval will be counted. In cases where the aggregation time interval is a cyclical interval (e.g., an interval between days of the week), detector data related to traversing the element within the same time interval on a different day of the week may be counted over a time interval such as between 3 p.m. and 4 p.m. on Tuesday.

[0042] The time interval can be of any desired size. Typically, traffic volume is reported per hour of vehicles (or even per hour per lane for multi-lane roads). In some embodiments, the interval is a 1-hour interval. However, the size of the aggregation time interval can often be chosen as desired, for example, depending on the application. For example, for dynamic traffic phenomena such as traffic congestion, where it may be desirable to report traffic volume over relatively short intervals, the sample size may be aggregated over periods ranging from about 1 minute to up to about 1 hour. In other cases, such as for traffic light signal calibration or traffic planning, it may be desirable to report traffic volume over longer intervals.

[0043] The time interval can be one of a set of predefined time intervals. The time interval is preferably a regular time interval. For example, the time interval can be one of a set of predefined time intervals obtained by dividing each day of the week into predetermined time units. If a larger or smaller granularity is desired, the time unit can be a 1-hour unit, or a smaller unit (e.g., 10 minutes), or a larger unit (e.g., 20 minutes). Each time interval can be identified by a time index.

[0044] A given time (count data and a scaling factor, and therefore estimated traffic volume, are associated with the given time) can be obtained based on an indicated time of interest. The method may include receiving data indicating a segment of interest requiring estimated traffic volume data and data indicating a time of interest, and using the data indicating the time of interest to identify the given time. The method may include using data indicating a segment of interest requiring estimated traffic volume data and data indicating the time of interest to obtain data indicating a count of devices associated with vehicles traversing a navigable element represented by the segment with respect to the given time. In a preferred embodiment where the given time is a time interval, the data indicating the time of interest can be used to identify the time interval with which the count data is obtained. The time interval may be a time interval covering the time of interest.

[0045] The proportionality coefficient is time-dependent because its applicable value varies depending on the time being considered, such as the estimated traffic volume of the required segment.

[0046] The method may further include obtaining a scale factor (value) with respect to the given time to obtain an estimated traffic volume for the segment. The method may include selecting the scale factor from a set of scale factors, each scale factor relating to a different time, such as different time intervals. In other embodiments, the method includes determining, i.e., deriving, the scale factor with respect to the given time. Regardless of whether the method extends to the step of determining the scale factor, the scale factor is preferably an estimated scale factor.

[0047] While it is envisioned that scale factors could be exported and stored for later use, making obtaining scale factors simply a matter of finding a suitable value applicable to the time of interest, the present invention enables scale factors to be easily exported, for example, using a database of detector data associated with segments of an electronic map and measured vehicle count data. Therefore, advantageously, scale factors can be estimated as needed, for example, in response to a request for estimated traffic volume. This allows the latest detector and measured count data to be taken into account. In some embodiments, scale factors are determined (i.e., exported) on an ad hoc basis.

[0048] Regardless of whether the method involves deriving scaling factors, the scaling factors used are applicable to a given time when estimated traffic volume is required. Preferably, the given time is a given time interval and is one of a set of predefined time intervals (e.g., obtained by dividing each day of the week into predetermined time units). Where the scaling factors form part of a set of scaling factors, the set of scaling factors may be a set of predefined scaling factors. The set of scaling factors may include scaling factors with respect to each predefined time interval. It will be understood that, for ease of processing, the given time associated with the scaling factors is preferably the same as the given time interval for which the estimated traffic volume data (and count data associated with it) is required. However, this is not necessarily the case, provided that the scaling factors used are with respect to time intervals associated with the given time, such as a given time interval that includes or is included within the given time interval for counts (and therefore traffic volume).

[0049] Methods may include using received data indicating the time of interest (which may involve deriving coefficients or selecting coefficients from a set of predefined coefficients) in obtaining the scaling factors to be used.

[0050] In a preferred embodiment of any aspect of the invention, a count of devices associated with vehicles traversing the segment is determined with respect to a plurality of different given times (e.g., time intervals), and an estimated traffic volume of the segment with respect to each of the plurality of different given times is obtained using determined count data and corresponding scaling factors, wherein a different corresponding scaling factor is used for each different given time.

[0051] The step of obtaining data indicating the count of devices based on location (i.e., detector) data obtained from devices associated with vehicles can simply involve looking up applicable counts of devices for relevant segments and times. Therefore, in some embodiments, the method includes obtaining count data from a database of counts of devices traversing navigable elements of a navigable network represented by segments of an electronic map at different times (e.g., time intervals). The time intervals may correspond to the time intervals used in the method of the present invention, or appropriate count data may be derived from count data in the database for other time intervals (e.g., by summing count data within smaller time intervals). In other embodiments, the method extends to the step of determining the count data.

[0052] In some embodiments, the method includes obtaining location data and associated timing data relating to the movement of a plurality of devices associated with a vehicle along a navigable element represented by a segment, and using the location data and associated timing data to determine a count of devices associated with a vehicle that traverses the segment with respect to a given time. This can be performed using appropriate filtering of the location data relative to time. The count of devices can be obtained using only the location data and associated timing data relating to the movement of devices associated with a vehicle along a navigable element, i.e., using only detector data, without using other forms of data, such as data obtained from sensors associated with the navigable element represented by the segment.

[0053] The proportionality coefficient indicates the permeability level of a section. For example, the proportionality coefficient can be inversely proportional to the permeability level.

[0054] Therefore, the present invention recognizes that the most appropriate value of the scaling factor for a segment will depend on the time period considered. In other words, in order to more accurately estimate traffic volume based on the number of vehicles crossing the segment using detector data, it is necessary to consider the time period considered. For a given segment, the scaling factor that most accurately projects detector counts to the estimated traffic volume may differ, for example, between parts of a day and / or days of a week.

[0055] According to the present invention, time-dependent scaling factors can be obtained in any suitable manner. The method may include obtaining a scaling factor for a given time from a database of scaling factors for different times. In other embodiments, the method extends to the step of determining scaling factors (or, in embodiments, a group of scaling factors for different times).

[0056] The scaling factor can be one of a set of scaling factors that have values ​​that are obtained or available at different times and form continuous values ​​with respect to time, or it can be one of a set of discrete scaling factors for each of the different times (or time intervals). For example, a set of discrete scaling factors for each of the different time intervals can be provided. The scaling factor can be obtained using a time-dependent function. The function can be arranged to provide scaling factors for different times, which form continuous values ​​with respect to time or a set of discrete values ​​with respect to time.

[0057] Various techniques can be used to estimate time-dependent scaling factors. These techniques can be used to provide a set of such scaling factors for different times.

[0058] Scale factors can be determined (i.e., derived) using data indicating the counts of vehicles traversing one or more navigable elements represented by a segment of an electronic map at a given time (e.g., detected by at least one traffic detector associated with the element) and the counts of devices associated with each of these navigable elements at the given time (e.g., determined using location data and associated timing data related to the movement of multiple devices associated with the vehicles along the navigable element). Therefore, scale factors for segments with both types of data can be derived based on the relationship between the counts of vehicles traversing the element represented by the segment at a given time (e.g., a clustering time interval), as determined using at least one traffic detector and as determined based on detector data. The scale factor for the segment of interest can be based on this data associated with the segment itself and / or with one or more reference segments. For simplicity, the time can correspond to the same time or time interval used when determining the counts based on detector data used to obtain estimated traffic volume, but other time intervals can be used, provided that the resulting scale factor is related to the given time when the estimated traffic volume is needed, e.g., included in or encompassing that time interval. Therefore, in a simple embodiment, the scaling factor can be a measured scaling factor obtained using the detectors of the segment and measured count data (both forms of data are available for a given time for the segment). This contrasts with prior art arrangements that use a constant scaling factor regardless of the time period considered. However, in a preferred embodiment, the scaling factor is estimated using detectors and measured count data associated with other segments.

[0059] Various possibilities are conceivable, in which a scaling factor for a segment of interest is derived for different times based on a comparison of traffic counts based on at least some segments of detector data and traffic detector data (for said at least some segments, both types of data are available for different times). Such segments may include the segment of interest and / or a set of one or more reference segments. This invention makes it possible to obtain a scaling factor for a segment of interest where traffic detector data is unavailable, and therefore, the segments used to determine said scaling factor may include a set of one or more reference segments instead of the segment of interest. The scaling factor is then an estimated scaling factor. Some form of aggregation between different (reference) segments is conceivable to obtain a total scaling factor value for each time considered.

[0060] In some preferred embodiments, the scaling factor of the (segment of interest) is an estimated scaling factor, estimated using data indicating the similarity of each of a detector profile and one or more reference detector profiles associated with the (segment of interest), each reference detector profile being associated with a corresponding reference segment. As used herein, a detector profile or reference detector profile with respect to a segment or reference segment refers to a profile indicating the change over time of the count of devices associated with a vehicle traversing a navigable element represented by the segment or reference segment, as determined based on location data and associated timing data related to the movement of multiple devices associated with a vehicle along a navigable element represented by the segment or reference segment.

[0061] Scale coefficients can be estimated using data indicating the similarity between the detector profile of the segment and each of a plurality of reference detector profiles, each reference detector profile being associated with different reference segments. The scale coefficients can be estimated using a set of similarity parameters indicating the similarity between the detector profile of the segment and the reference detector profiles. The method may include the step of determining such a set of similarity parameters. The set of similarity parameters may include similarity parameters indicating the similarity between the detector profile of the segment and the reference detector profiles with respect to each of the reference detector profiles. The similarity parameters may be expressed using a predefined similarity scale, which may be continuous or include discrete levels.

[0062] The method may include using a kernel function to determine data, such as a similarity parameter, indicating the similarity between a detector profile and a reference detector profile. The kernel function may be a non-negative kernel function. The function may accept two vector arguments and output a single real number within a predefined range. The predefined range may correspond to a desired predefined similarity range, such as 0 to 1. The kernel function maps the similarity between the two detector profiles to a real-valued function result. The kernel function may be a radial basis function. The number may be considered as a similarity parameter. Therefore, in this embodiment, the similarity profile is obtained using a kernel function.

[0063] Preferably, each reference segment is a segment representing a navigable element associated with at least one traffic detector. Thus, in these embodiments, each reference segment is a segment of traffic detector data available to it (e.g., a server used to perform the methods described herein). This data enables the determination of a measured count of vehicles traversing the segment at a given time (i.e., within a given time interval). The traffic detector can be any device or system capable of detecting the presence of vehicles on the navigable element represented by the segment.

[0064] It will be understood that, where measured traffic data for a segment is available, the accurate value of the scaling factor for a given time can be determined by comparing the measured count of vehicles traversing the segment at a given time with the count determined by detector data using the segment at a given time.

[0065] In an embodiment, the scaling factor is estimated based on a set of one or more reference scaling factors, each reference scaling factor being a scaling factor determined with respect to a corresponding entity in the one or more reference segments, with respect to a given time, and based on data obtained from at least one traffic detector associated with the corresponding entity.

[0066] A reference scaling factor can be determined using location data and associated timing data related to the movement of multiple devices associated with vehicles along a navigable element represented by a reference segment, a count of devices associated with a vehicle that crosses the navigable element represented by the reference segment at a given time, and a measured count of vehicles that cross the reference segment at a given time, as determined based on data measured by at least one traffic detector associated with the reference segment. The reference scaling factor can be determined by dividing the measured count of vehicles by the count of vehicles determined using location data related to the movement of multiple devices (i.e., using vehicle detector data).

[0067] The given time associated with the data used to estimate the scaling factor is preferably a time interval, such as a clustering time interval. The given time preferably corresponds to a given time about which a count of devices traversing a navigable element represented by a segment requiring estimated traffic volume is obtained, and the count is used to obtain data indicating the estimated traffic volume of the segment about the given time. However, this is not necessarily the case, provided that the given time used to estimate the scaling factor results in a scaling factor applicable to the given time requiring estimated traffic volume, for example, at least approximately corresponding to that given time (e.g., a time interval), or overlapping with or contained therein.

[0068] Preferably, similarity data as described in any of the above techniques, together with reference scaling factor data, are used to derive the scaling factor of the segment.

[0069] It can be assumed that the scaling factor of the segment of interest is more likely to be similar to the reference scaling factors associated with those reference segments whose reference detector profiles are more similar to the detector profile associated with the segment of interest. In embodiments, similarity data is used to determine the contribution of each reference scaling factor to the estimated scaling factor determined for the segment of interest. In other words, similarity data can be used to weight the contribution of each reference scaling factor. An executable method is provided such that reference scaling factors associated with reference segments whose reference detector profiles are more similar to the detector profile associated with the segment of interest contribute a greater to the estimated scaling factor compared to reference scaling factors associated with reference segments whose reference detector profiles are less similar to the detector profile associated with the segment of interest. The greater the similarity between the reference detector profile associated with the reference segment and the detector profile associated with the segment of interest, the greater the contribution of the reference scaling factor to the estimated scaling factor of the segment of interest.

[0070] However, regardless of whether the method for determining the scaling factor involves considering the similarity between the detector profile of a segment and one or more reference detector profiles, generally, the scaling factor of a segment can be based on a set of one or more (and preferably more) reference scaling factors, each of which is a scaling factor determined using data obtained from at least one traffic detector associated with a reference segment, with respect to a set of one or more reference segments, and with respect to a given time. Therefore, in such embodiments, the reference segment (or each reference segment) represents a segment of a navigable element associated with at least one traffic detector. The set of one or more reference segments preferably corresponds to a group of reference segments, which is obtained for the group of reference segments in embodiments where detector profile similarity data is obtained. Each reference scaling factor can provide a contribution to the estimated scaling factor.

[0071] In any embodiment using a reference scaling factor, the reference scaling factor can be determined using location data and associated timing data related to the movement of multiple devices associated with a vehicle along a navigable element represented by a reference segment, a count of devices associated with a vehicle that crosses the navigable element represented by the reference segment at a given time, and a measured count of vehicles that cross the reference segment at a given time, as determined by data measured by at least one traffic detector associated with the reference segment. The reference scaling factor can be determined by dividing the measured count of vehicles by the vehicle count determined using location data related to the movement of multiple devices (i.e., using vehicle detector data).

[0072] Preferably, the scaling factor (of the segment of interest) is based on a set of multiple such reference scaling factors, and may be based on their sum.

[0073] It has been found that some reference segments may be more important than others in the accurate scaling factor of the derived segment. This may be the case in embodiments using similarity data, regardless of the similarity between the reference segments and the segments requiring scaling factors. Preferably, in any embodiment using reference scaling factors, the scaling factor of the (segment of interest) is based on a weighted sum of multiple reference scaling factors.

[0074] One or more sets of weighted values ​​can be derived, containing weighted values ​​for each member of the reference segment group. Each weighted value indicates the weight assigned to the reference scale factor associated with the reference segment when determining the scale factor for the segment. The set of weighted values ​​can be defined by a vector. This set of one or more sets of weighted values ​​can be used to obtain the scale factor for the segment. Multiple sets of weighted values ​​can be obtained regarding different factors influencing the contribution of the reference scale factor to the overall estimated scale factor for the segment. The overall contribution of the reference scale factor can be based on weighted values ​​for different factors, such as similarity to the segment in question, and / or the results of implementing a linear regression training model.

[0075] The contribution of a given reference scaling factor to the estimated scaling factor of the (interested) segment can be based, at least in part, on the similarity between the reference detector profile associated with the reference segment and the detector profile associated with the segment of interest.

[0076] Alternatively or additionally, the relative importance of different reference segments (i.e., the associated reference scale coefficients) in determining the scale coefficients of a segment can be explored, for example, by comparing the results obtained using an algorithm that implements methods for estimating scale coefficients (e.g., based on similarity data and reference segment data) with the scale coefficients associated with that segment based on measured data (i.e., traffic sensor data), where both measured data and detector data are available for said segment. This can capture factors that influence the relative importance of reference segments in determining the estimated scale coefficients of segments of interest that may not contribute to detector profile similarity.

[0077] In this embodiment, a linear regression model is used, at least in part, to determine the contribution of each reference scaling factor to the estimated scaling factor of the segment of interest. The linear regression model can be used to obtain, for example, a set of weighted values ​​for obtaining a weighted sum of multiple reference scaling factors. For one (or each) reference segment, the model can use data indicating, for example, a measured count of vehicles traversing the navigable element represented by the reference segment at a given time, determined based on data measured by at least one traffic detector associated with the navigable element represented by the reference segment. This data can be used as basic fact data.

[0078] The step of using a linear regression training model to determine the contribution of each reference scaling factor to the estimated scaling factor of the segment of interest may involve determining one or more estimated reference scaling factors for a given time for one or more reference segments, and for each such reference segment, comparing the estimated reference scaling factor of the measured reference segment with the reference scaling factor of the segment obtained using data measured by at least one traffic detector associated with the reference segment, and determining whether any adjustment is needed to the contribution (e.g., a set of weights). The method may include adjusting the contribution of the reference scaling factor to the estimated reference scaling factor (e.g., adjusting a set of weights for the reference scaling factor) to result in a closer match to the estimated reference scaling factor of the measured reference scaling factor. The steps of comparing the estimated reference scaling factor with the measured reference scaling factor and determining whether any adjustment is needed, and if so, performing that adjustment, may be performed iteratively. The method may include using a linear regression training model in this manner to obtain a set of weights.

[0079] The method according to any of the embodiments described herein can be repeated to obtain the estimated traffic volume of the segment with respect to one or more other given times. For each such other given time, an applicable proportional coefficient can be obtained (e.g., estimated) with respect to said other given time, for example based on the same other given time.

[0080] The present invention extends to the step of estimating the scaling factor of the segment with respect to the given time, and to the method of deriving a function that can be used to estimate the scaling factor of the segment with respect to the given time.

[0081] According to a further aspect of the present invention, a method is provided for generating traffic data indicating traffic volume within a navigable network in an area covered by an electronic map, the electronic map comprising a plurality of segments representing navigable elements of the navigable network, the method comprising:

[0082] Receive data indicating the segment of interest and the time of interest. The segment of interest is the segment that requires estimated traffic volume data.

[0083] For each of a set of multiple segments of the electronic map, data indicating the count of devices associated with a vehicle traversing the navigable element represented by the segment with respect to a given time selected based on the time of interest, wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices associated with the vehicle along the navigable element represented by the segment;

[0084] Identify reference subsets of the segments of the electronic map, wherein each segment of the reference subset is associated with at least one traffic detector;

[0085] For each of the reference subsets of the segments of the electronic map, data indicating a measured count of vehicles traversing the navigable element represented by the segment at a given time is obtained based on data obtained from the at least one traffic detector associated with the segment.

[0086] A reference scaling factor is obtained for each of the reference subsets of the segments, each reference scaling factor being a scaling factor determined based on data measured by the at least one traffic detector associated with the segment, a measured count of vehicles crossing the segment at the given time, and a scaling factor determined with respect to the given time based on location data and associated timing data related to the movement of the plurality of devices along the segment, and a count of devices associated with vehicles crossing the segment at the given time;

[0087] Based on the obtained or each reference scaling factor, determine the estimated scaling factor for the segment of interest for the given time; and

[0088] In obtaining the estimated traffic volume of the segment, an estimated scaling factor with respect to the given time is used, along with location data and associated timing data related to the movement of multiple devices along the navigable element represented by the segment of interest relative to time, and data on the count of devices associated with vehicles traversing the navigable element represented by the segment of interest with respect to the given time.

[0089] In this further aspect, the invention may include any or all of the features described with respect to other aspects and embodiments of the invention.

[0090] The method may include any of the features described above in the various steps concerning the estimation of traffic volume data and / or proportional coefficients.

[0091] The time of interest is the time when estimated traffic volume is applied.

[0092] The given time for applying the counting data based on detector data can be the given time interval as described above.

[0093] The method may include: for each of the plurality of segments of an electronic map, obtaining location data and associated timing data relating to the movement of a plurality of devices associated with vehicles along a navigable element represented by the segment; and for each of the plurality of segments, using the location data and associated timing data to determine a count of devices associated with a vehicle traversing the segment at a given time selected based on a time of interest. The count of devices may be obtained using only the location data and associated timing data relating to the movement of devices associated with vehicles along a navigable element, i.e., using only detector data without using other forms of data.

[0094] In other embodiments, the required count data based on detector data can be obtained from a database of such count data about different times (e.g., time intervals).

[0095] Crossing counts of elements represented by segments of a segment reference subset, obtained based on traffic detector data, can be entirely based on data obtained from at least one traffic detector associated with said element. The step of obtaining crossing counts based on segment-measured data may involve obtaining the counts from a database of such counts (e.g., a database containing such measured count data from different times), or can be extended to a step of determining the counts based on data from at least one traffic detector.

[0096] The reference subset of the group of segments preferably includes multiple segments and may include all segments of the group of segments under consideration that are associated with at least one traffic detector.

[0097] A reference scaling factor can be obtained by dividing the measured count of vehicles by the count determined using detector data.

[0098] Each reference scaling factor can provide a contribution to the estimated scaling factor.

[0099] The method may further include: for each segment in the reference segment group, obtaining a reference detector profile, the reference detector profile indicating, for example, the change in the count of devices associated with vehicles traversing the navigable elements represented by the segment relative to time, as determined based on location data and associated timing data related to the movement of devices associated with vehicles along the navigable elements represented by the segment;

[0100] And for the segment of interest, a detector profile is obtained, the detector profile indicating positional data and associated timing data related to the movement of devices associated with vehicles along the navigable element represented by the segment, and the change in the count of devices associated with vehicles traversing the navigable element represented by the segment relative to time.

[0101] The estimated scaling factor for a given time segment of interest further depends on the similarity of each of the detector profile associated with the segment of interest and one or more of the reference detector profiles.

[0102] Therefore, the method may include using data indicating the similarity between the detector profile associated with the segment of interest and each of the obtained one or more (and preferably each) reference detector profiles (i.e., with respect to one or more or each of the set of reference segments having a reference detector profile) to determine an estimated scaling factor for the segment of interest at a given time.

[0103] The detector profile and reference profile are each based on detector data. The method can be extended to determine a reference detector profile and detector profile for a segment of interest based on acquired position data and associated timing data related to the movement of multiple devices associated with a vehicle along a navigable element represented by a segment. This profile can be obtained using existing counting data from different times (e.g., from a database), or this counting data can be obtained using detector data.

[0104] The method may include comparing a detector profile of a segment of interest with each of a plurality of reference detector profiles (e.g., with each reference profile under consideration), and determining similarity parameters that indicate the similarity between the detector profile of the segment of interest and the reference detector profiles. Therefore, the method may include obtaining a set of similarity parameters that indicate the similarity between the detector profile of the segment of interest and each of the said reference detector profiles. The set of similarity parameters may be used to estimate a scaling factor for the segment of interest.

[0105] Similarity data can be used together with reference scaling factor data to derive the estimated scaling factor for the segment of interest, for example, to determine the contribution of each reference scaling factor to the estimated scaling factor determined for the segment of interest.

[0106] The method may include determining the estimated scale factor of the segment of interest based on each obtained reference scale factor and the similarity between the detector profile associated with the segment of interest and each of the reference profiles.

[0107] The estimated scale factor of the segment of interest can be based on a weighted sum of reference scale factors. In an embodiment, a linear regression training model is used at least in part to determine the contribution of each reference scale factor to the estimated scale factor of the segment of interest. A linear regression training model can be used to obtain a set of weighted values ​​for obtaining a weighted sum of multiple reference scale factors. For each reference segment, the linear regression training model can use data indicating, for example, a measured count of vehicles crossing the navigable element represented by the reference segment at a given time, determined based on data from at least one traffic detector associated with the navigable element represented by the reference segment. This data can be used as basic fact data.

[0108] The step of determining the contribution of each reference scaling factor to the estimated scaling factor of the segment of interest can be performed in any of the ways described above.

[0109] The contribution of the reference scaling factor to the overall estimated scaling factor of the segment of interest can be based, at least in part, on the similarity between the reference detector profile associated with the reference segment and the detector profile associated with the segment of interest. The segment of interest whose estimated scaling factor is determined can be a segment representing a navigable element unassociated with any traffic detector. Therefore, the segment of interest may not form a subset of the reference segment.

[0110] According to a further aspect of the invention, a method is provided for estimating traffic volume over a given time for a given segment of an electronic map representing a navigable network in an area, the electronic map comprising a plurality of segments representing navigable elements of the navigable network in the area, wherein the navigable network in the area includes navigable segments associated with at least one traffic detector and navigable segments not associated with any traffic detector, and wherein the given segment is a segment representing at least a portion of the navigable segments of the navigable network in the area that are not associated with any traffic detector, wherein the electronic map further comprises a plurality of reference segments, each reference segment representing at least a portion of the navigable segments of the navigable network in the area that are associated with at least one traffic detector. The method comprises: a segment, wherein each reference segment is associated with data indicating a corresponding reference scale factor for a given time, the reference scale factor being based on a measured count of vehicles traversing at least a portion of the segment represented by the reference segment at the given time and a count of devices associated with vehicles traversing at least a portion of the segment represented by the reference segment at the given time, the measured count of vehicles being based on data measured by at least one traffic detector associated with the segment, and the count of devices associated with vehicles being based on location data and associated timing data related to the movement of multiple devices along at least a portion of the segment represented by the reference segment; the method includes:

[0111] Traffic volume for a given segment at a given time is estimated using data indicating the count of devices associated with vehicles traversing at least a portion of the navigable network represented by the given segment at the given time, and an estimated scale factor of the given segment at the given time, wherein the estimated scale factor of the segment is based on a reference scale factor associated with each of one or more reference segments of the electronic map associated with the given segment, and wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices along at least a portion of the navigable segment represented by the given segment relative to time; and

[0112] Generate data indicating the estimated traffic volume for the given time period.

[0113] In this further aspect, the invention may include any or all of the features described with respect to other aspects and embodiments of the invention.

[0114] The method may include any of the features described in the steps above relating to the estimation of traffic volume data and / or proportionality coefficients.

[0115] The given time is the time when the estimated traffic volume is applied.

[0116] As in earlier aspects and embodiments, the given time can be any suitable time, such as the current time or a future time. Alternatively, the given time can be a past time. The given time can be obtained based on a time of interest indicated. The time of interest can be determined in any of the ways described with respect to earlier aspects and embodiments of the invention. Similarly, a given segment can be determined in any of the ways mentioned above and can be referred to as the segment of interest. As previously described, data indicating the segment of interest and / or the time of interest can be received from any suitable source.

[0117] The given time for applying detector-based counting data can be a given time interval as described above. The given time can also be a cyclical time interval. For example, the given time could be a time interval for a given day of the week.

[0118] The method can be performed relative to one or more given segments of the electronic map. The described steps are then performed with respect to each given segment under consideration.

[0119] As mentioned in earlier aspects and embodiments of the invention, the navigable network in the area under consideration includes navigable segments associated with at least one traffic detector and navigable segments not associated with any traffic detector. A navigable segment may include at least a portion of one or more navigable elements of the navigable network. In some embodiments, a navigable segment corresponds to a corresponding navigable element of the navigable network.

[0120] A navigable segment associated with at least one traffic detector allows a measured count of vehicles traversing the segment at a given time to be available for that segment. Conversely, this measured count data cannot be used for navigable segments not associated with any traffic detector. Traffic detectors can be defined as previously described.

[0121] A given segment is a segment representing at least a portion of a navigable segment of a navigable network within the area that is not associated with any traffic detector. Therefore, a given segment is a segment to which measurement count data is unavailable. A given segment may represent a navigable element to which measurement count data is unavailable (i.e., it is not associated with any traffic detector). The given segment, or each given segment, may be considered a "non-reference" segment.

[0122] A navigable segment includes at least a portion of one or more navigable elements of a navigable network.

[0123] Reference segments may be as previously defined. Each reference segment represents at least a portion of a navigable segment to which measured count data is available. Each reference segment may represent a navigable element to which measured count data is available (i.e., it is associated with at least one traffic detector). A reference segment may represent at least a portion of one or more navigable elements forming a navigable network of segments to which measured count data is available. When measured count data is available for a navigable segment, the navigable segment may be considered associated with a traffic detector, regardless of where the traffic detector(s) are located. Therefore, a particular portion of a segment represented by a reference segment may not itself include a traffic detector, provided that measured count data applicable to the portion of the segment represented by the reference segment is available, for example, based on data obtained from one or more traffic detectors arranged in any suitable location to determine the count of vehicles traveling along said segment.

[0124] In these further aspects or embodiments of the invention, and indeed, according to any of the aspects or embodiments described herein, it will be understood that a given segment may be a segment representing at least a portion of a navigable segment of a navigable network in an area, to which data indicating an absolute count of vehicles traversing at least a portion of the navigable segment is unavailable. Conversely, the aforementioned or each reference segment is a segment representing at least a portion of a navigable segment of a navigable network in an area, to which data indicating an absolute count of vehicles traversing at least a portion of the navigable segment is available. Thus, more broadly, “non-reference” and “reference” segments may be segments to which absolute count data is available and unavailable. This absolute count data may be data obtained from traffic detectors associated with segments as described herein.

[0125] Each reference segment is associated with data representing a corresponding reference scale factor for a given time. The reference scale factor is based on a measured count of vehicles traversing at least a portion of the segment represented by the reference segment at a given time, and a count of devices associated with vehicles traversing at least a portion of the segment represented by the reference segment at a given time. The measured count of vehicles is based on data measured by at least one traffic detector associated with the segment, and the count of devices associated with vehicles is based on location data and associated timing data related to the movement of multiple devices along at least a portion of the segment. As mentioned above, at least one traffic detector may be associated with the segment in any way to provide it with measured count data applicable to a portion of the segment represented by the reference segment (and may not necessarily be located within that portion of the segment represented by the reference segment).

[0126] Therefore, the reference proportionality coefficient is based on measured count data (i.e., measured by at least one traffic detector) applicable to a given time segment and counts based on vehicle detector data for that segment at the given time. The reference proportionality coefficient can be based on the ratio of the measured counts to the detector data counts for that segment at a given time. The reference proportionality coefficient can be obtained by dividing the measured vehicle counts by the counts determined using the detector data.

[0127] A reference segment can be associated with data indicating a reference scale factor for a given time in any suitable manner. Each reference segment can be associated with data indicating a time-dependent reference scale factor profile from which a reference scale factor for a given time can be obtained. The reference scale factor profile indicates the change of the reference scale factor of the reference segment relative to time. The reference scale factor for a given time can then be obtained from the scale factor profile. The reference scale factor profile can be at least partially based on a detector profile of the reference segment. The detector profile indicates, for example, the change of the count of devices associated with a vehicle traversing at least a portion of the navigable segment represented by the given reference segment relative to time, determined based on position data and associated timing data related to the movement of multiple devices associated with a vehicle along at least a portion of the navigable segment represented by the given reference segment. The reference scale factor profile can be based on this detector profile and a profile indicating the change of the measured count of vehicles traversing at least a portion of the segment represented by the reference segment relative to time.

[0128] The reference scale factor can be based on real-time data and / or historical data. For example, historical detector data in the form of detector profiles can be used to obtain the reference scale factor, regardless of whether the given time is in the past, present, or future. The detector profiles indicate the counts of the devices used in obtaining the reference scale factor. The measured count data used can also be based on real-time data and / or historical data. Therefore, the detector data and measured count data used to provide the reference scale factor can be based on real-time data, historical data, or any combination thereof, provided that the resulting factor can be considered applicable to the current time. Advantageously, when the given time is the current time, the reference scale factor is based at least in part on real-time data, such as real-time measured counts and / or real-time detector data. This provides a more accurate factor. Real-time data is data that can be considered to reflect the current state in the navigable network. Alternatively, historical data may or may not be used.

[0129] Traffic volume for a given segment is estimated using a device associated with vehicles traversing at least a portion of a navigable network represented by a given segment at a given time (i.e., vehicle detector data for the segment at a given time) and an estimated scale factor for the given segment at a given time, the estimated scale factor being based on one or more of reference scale factors.

[0130] Detector data based on a reference segment and counts of measured data can be based on real-time data and / or historical data. For example, historical detector data in the form of detector profiles can be used regardless of whether a given time is in the past, present, or future. When the given time is the current time, real-time data can be used in addition to or as a substitute for historical data. Detector profiles indicate the change in the count of devices associated with a vehicle traversing at least a portion of a navigable segment represented by a given reference segment relative to time, determined based on location data and associated timing data related to the movement of multiple devices associated with the vehicle along at least a portion of the navigable segment represented by the reference segment.

[0131] Reference scale coefficients associated with one, more than one, or all reference segments can be used to determine traffic volume for a given segment. Therefore, the estimated scale coefficients can be based on a subset of a set of multiple reference scale coefficients associated with one of the multiple reference segments; the subset may be a single reference scale coefficient or may include multiple reference scale coefficients.

[0132] The method may further include the step of determining a subset of one or more reference segments of an electronic map associated with a given segment, wherein the estimated scale factor is based on a reference scale factor associated with each of the set of one or more reference segments. The navigable network will contain various segments of reference segments that may generate the electronic map. In determining the estimated scale factor of a given segment, some of these reference segments may be more relevant than others. Therefore, in these embodiments, when determining the estimated scale factor of a given segment, only the reference scale factors associated with reference segments that can be considered associated with the given segment are considered. The subset of reference segments associated with a given segment may be a single reference segment or multiple reference segments that form a subset of the total number of reference segments representing segments of the navigable network in the area associated with the traffic detector in the electronic map. Therefore, a given segment may be associated with a single reference segment or multiple reference segments.

[0133] A subset of one or more reference segments may be associated with data indicating a given segment in an electronic map. Therefore, the association between a reference segment and the segment of interest may be known. In other embodiments, the method can be extended to identify a subset of one or more reference segments.

[0134] Regardless of whether the method extends to the step of identifying a subset of one or more reference segments associated with a given segment, the subset of one or more reference segments can be selected in any suitable manner.

[0135] A subset of one or more reference segments may be determined based on a comparison of a detector profile associated with a given segment and reference detector profiles associated with some of the reference segments. The detector profile indicates, for example, a change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the given segment, relative to time, based on location data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the reference segment. The reference detector profile indicates, for example, a change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the reference segment, relative to time, based on location data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the reference segment. Therefore, the detector profile and the reference detector profile are time-dependent detector profiles, such as weekly detector profiles.

[0136] A subset of one or more reference segments may include (or correspond to) one or more reference segments having a reference detector profile determined to be most similar to the detector profile of a given segment. Similarity can be evaluated in any suitable manner. For example, a single most similar reference segment may be identified. Alternatively, a corresponding similarity value may be assigned to each reference detector profile, and the reference detector profiles may be sorted in order of similarity. A predefined number of most similar detector profiles may then be selected, or all reference detector profiles with similarity higher than a predetermined threshold may be included in the set of one or more reference segments.

[0137] Alternatively or additionally, the selection of a subset of one or more reference segments may be based at least in part on the proximity of the reference segments to a given segment. This proximity may be temporal and / or spatial proximity. For example, a subset of reference segments may include or correspond to a predefined number of reference segments that are closest in terms of travel time or distance. Alternatively, a subset of reference segments may include or correspond to segments within a predetermined travel time or distance of a given segment. Distance and / or travel time may be measured based on straight paths between segments or along a road network.

[0138] Alternatively or additionally, the selection of a subset of one or more reference segments may be based at least in part on the similarity of the reference segments to one or more of the properties of the given segment. For example, said properties may include functional road classification. Any relevant properties may be considered. Each reference segment may be assigned a similarity value indicating its similarity to the given segment. For example, a subset of reference segments may include or correspond to a subset of reference segments considered most similar to the given segment (e.g., a predefined number of segments, or segments with similarity above a given threshold, etc.).

[0139] Any one or more of the above measures can be used to attempt to obtain a subset of reference segments for determining the estimated proportionality coefficients that are expected to be associated with a given segment. When using multiple factors, any suitable technique can be used to obtain a subset of reference segments that simultaneously satisfy all the criteria considered. Weights of different criteria can be used.

[0140] The estimated scaling factor of a given segment can be determined using one or more reference scaling factors on which it is based, or any of the methods discussed above.

[0141] An estimated scale factor for a given segment can be estimated using data indicating the similarity of detector profiles associated with the given segment and each of one or more reference detector profiles, each reference detector profile associated with a corresponding one of one or more reference segments, the reference scale factor of which is used to determine the estimated scale factor. The detector profiles can indicate, for example, the change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the given segment, relative to time, based on location data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the given segment, and the reference detector profiles can indicate, for example, the change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the reference segment, relative to time, based on location data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the reference segment.

[0142] When considering multiple reference scaling factors, the contribution of a given reference scaling factor to the estimated scaling factor of a given segment can be based at least in part on the similarity between the reference detector profile associated with the reference segment to which the reference scaling factor is associated and the detector profile associated with the given segment.

[0143] Alternatively or additionally, the contribution of each reference scaling factor to the estimated scaling factor may be based at least in part on the proximity of the reference segment associated with the reference scaling factor and the given segment. Proximity may be temporal or spatial proximity, and may be any of the types discussed above relative to a subset of the determined reference segments. Greater weight may be assigned to the reference scaling factors associated with reference segments that are closer to the given segment. The contribution of the reference scaling factor associated with the given reference segment to the estimated scaling factor of the given segment may approximate the average value of the reference scaling factors considered as the distance between the given reference segment and the given segment increases. This distance may be temporal or spatial.

[0144] The estimated scaling factor can be based on a weighted sum of multiple reference scaling factors.

[0145] A linear regression model can be used to obtain data indicating a set of weighted values ​​used to obtain a weighted sum of multiple reference scale coefficients. The linear regression model can use data indicating, for example, measured counts of vehicles traversing at least a portion of the navigable segment at a given time, based on data from at least one traffic detector associated with the navigable segment represented by the reference segment.

[0146] Therefore, according to these further aspects of the invention, the reference scaling factor associated with each reference segment can be based on the ratio of the measured count for a given time based on traffic detector data to the count for a given time based on location and associated timing data.

[0147] Each reference segment can be associated with data indicating a time-dependent reference scale profile, wherein the reference scale profile indicates the change of the reference scale of the reference segment relative to time.

[0148] The reference scale profile may be at least partially based on the detector profile, which indicates the change in the count of devices associated with a vehicle traversing at least a portion of the navigable segment represented by the reference segment, as determined by location data and associated timing data related to the movement of multiple devices associated with the vehicle along at least a portion of the navigable segment represented by the given reference segment.

[0149] The given time can be the current time, and the reference scaling factor can be based at least in part on real-time data.

[0150] The method may further include determining a subset of one or more reference segments associated with a given segment, wherein the estimated scaling factor is based on a reference scaling factor associated with each of the subsets of one or more reference segments.

[0151] A subset of one or more reference segments may be determined at least in part based on a comparison of a detector profile associated with a given segment and reference detector profiles associated with some of the reference segments, wherein the detector profile may indicate, for example, a change in the count of devices associated with a vehicle traversing at least a portion of the navigable segment represented by the given segment, based on location data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the reference segment, and wherein the reference detector profile indicates, for example, a change in the count of devices associated with a vehicle traversing at least a portion of the navigable segment represented by the reference segment, based on location data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the reference segment, based on time.

[0152] A subset of one or more reference segments may include one or more reference segments having a reference detector profile that is determined to be most similar to the detector profile of a given segment.

[0153] The selection of a subset of one or more reference segments may be based at least in part on the proximity of the reference segments to the given segments.

[0154] The selection of a subset of one or more reference segments may be based at least in part on the similarity of the reference segments to the properties of a given segment, such as said properties including Functional Road Class (FRC).

[0155] An estimated scale factor for a given segment can be estimated using data indicating the similarity of detector profiles associated with the given segment and each of one or more reference detector profiles in a set of one or more reference segments, each reference detector profile being associated with a corresponding one in one or more reference segments, the reference scale factor of the corresponding one being used to determine the estimated scale factor, wherein the detector profile indicates, for example, a change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the given segment, relative to time, as determined by position data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the segment, and wherein the reference detector profile indicates, for example, a change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the reference segment, relative to time, as determined by position data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the reference segment.

[0156] The estimated scale factor for a given segment may be based on multiple reference scale factors, and the contribution of a given reference scale factor to the estimated scale factor for a given segment is at least in part based on the similarity between the reference detector profile associated with the reference segment associated with the reference scale factor and the detector profile associated with the given segment.

[0157] The estimated scale factor for a given segment may be based on multiple reference scale factors, and the contribution of each reference scale factor to the estimated scale factor is at least in part based on the proximity of the reference segment associated with the reference scale factor and the given segment; optionally, a larger weight is assigned to the reference scale factor associated with the reference segment that is closer to the given segment.

[0158] The estimated scaling factor can be based on a weighted sum of multiple reference scaling factors.

[0159] A linear regression model can be used to obtain a set of weighted values ​​that indicate the weighted sum of multiple reference scaling factors.

[0160] The linear regression training model can use data such as measured counts of vehicles traversing at least a portion of the navigable segment at a given time, determined based on data from at least one traffic detector associated with a navigable segment represented by a reference segment.

[0161] The method may further include: receiving data for a given segment indicating the need for traffic volume data and data indicating the time of interest, and using the data indicating the time of interest to identify the given time.

[0162] The given time can be the current time or a future time.

[0163] The given time can be a time interval, or optionally a cyclical time interval, such as a time interval for a given day of the week.

[0164] The method may further include: associating data indicating estimated traffic volume with data indicating a given segment related to the estimated traffic volume; and optionally transmitting to a user the obtained estimated traffic volume indicating the given segment and / or displaying the obtained estimated traffic volume indicating the given segment.

[0165] The method may further include storing estimated traffic volume and / or traffic density for subsequent display, and / or including displaying the estimated traffic volume and / or traffic density to a user.

[0166] The method according to any aspect or embodiment of the invention can be repeated for one or more additional segments of interest and / or one or more additional times of interest. Thus, the method may include using an estimated scaling factor determined relative to different given times selected based on additional times of interest to determine the estimated traffic volume for the (same) segment of interest at at least one additional time of interest. The method can be extended to estimate the scaling factor with respect to different given times. The applicant also recognizes that, in order to obtain a more accurate estimate of the traffic volume of a segment, the scaling factor (value) should vary depending on the location of the (segment of interest). Preferably, the scaling factor (used or estimated according to any aspect or embodiment of the invention) is location-dependent, and the scaling factor (value) used is applicable to the location of the segment under consideration. The value of the scaling factor may be specific to the segment under consideration, or in other embodiments, the same scaling factor may be applicable to more than one segment, such as segments within a given geographic area. The scaling factor is again preferably an estimated scaling factor.

[0167] It is believed that such aspects are inherently advantageous, regardless of whether the proportional coefficient is time-dependent.

[0168] In a further aspect of the invention, a method is provided for generating traffic data indicating traffic volume within a navigable network in an area covered by an electronic map, the electronic map comprising a plurality of segments representing navigable elements of the navigable network, the method comprising, for one or more segments of the electronic map:

[0169] Obtain data indicating a count of devices associated with a vehicle traversing the navigable element represented by the segment at a given time, wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices associated with the vehicle along the navigable element represented by the segment; and

[0170] Using the determined count data and a scaling factor to obtain data indicating the estimated traffic volume of the segment with respect to the given time, wherein the scaling factor is a location-dependent scaling factor, and the method includes using a scaling factor with respect to the location associated with the segment when obtaining the estimated traffic volume of the segment.

[0171] This invention may include any or all of the features described in relation to earlier aspects of the invention, and vice versa, provided that they do not contradict each other.

[0172] The estimated traffic volume is relative to a given time, which is preferably a time interval, as described in an earlier embodiment.

[0173] Preferably, the scaling factor of the segment is an estimated scaling factor.

[0174] Preferably, the scaling factor is additionally time-dependent. Therefore, the scaling factor can be relative to a given time, as in the earlier described embodiments. It will be understood that, in embodiments, at least the above-described time-dependent embodiments will also provide estimated scaling factors for position-dependent (i.e., segment-dependent) scaling factors.

[0175] A set of reference scaling factors can be used to perform the method for estimating location-dependent scaling factors in a manner similar to the time-dependent embodiments described above, regardless of whether they are additionally time-dependent. However, for these further embodiments, the reference scaling factors need not be related to a given time for determining the count data associated with the estimated traffic volume. In other words, the reference scaling factors do not need to be time-dependent.

[0176] In an embodiment, the scaling factor is based on a set of one or more reference scaling factors, each reference scaling factor being a scaling factor determined with respect to one of a set of one or more reference segments, wherein each reference segment is a segment representing a navigable element associated with at least one traffic detector, and the reference scaling factor of the reference segment is obtained using data obtained from at least one traffic detector associated with said reference segment.

[0177] Each reference scaling factor can be determined using location data and associated timing data related to the movement of multiple devices associated with vehicles along a navigable element represented by a reference segment, counts of devices associated with vehicles crossing the navigable element represented by the reference segment, and measured counts of vehicles crossing the reference segment, such as those determined based on data measured by a set of one or more traffic detectors associated with the reference segment. The corresponding detectors and measured counts can be relative to any reference time (i.e., time interval), which preferably corresponds to a given time. However, it will be understood that for non-time-dependent embodiments, the reference time can be a time different from the given time. For example, the same reference time can be obtained to determine the reference scaling factor, which is used to determine the estimated scaling factor for segments of interest with respect to different given times.

[0178] Location-dependent embodiments may or may not involve the similarity between the detector profile of the considered (interested) segment and the reference detector profile associated with each of one or more, preferably several, reference segments associated with at least one traffic detector. Embodiments considering similarity may be performed as described above, for example, using a kernel function to evaluate similarity. In this case, the set of reference segments considered for the similarity evaluation may or may not correspond to the reference segments considered for the location.

[0179] In an earlier embodiment, the location-dependent scaling factor could be estimated based on contributions from multiple reference scaling factors. For example, the estimated scaling factor could be based on a weighted sum of multiple reference scaling factors.

[0180] The contribution of each reference scale factor to the overall estimated scale factor of the (interested) segment can be based on the distance between the location associated with the reference segment to which the reference scale factor is associated and the location of the segment under consideration. A larger weight can be assigned to the reference scale factor associated with the location of the reference segment closer to the location of the segment under consideration. The contribution of the reference scale factor associated with a given reference segment in a given electronic map area to the estimated scale factor of said segment can approximate the value corresponding to the average of the reference scale factors associated with the reference segments in the given electronic map area as the distance between the location associated with the given reference segment and the location of the (interested) segment increases. This can be achieved using a decay function. The decay function can decay to the average reference scale factor contribution value of the area. In these embodiments, when evaluating distances, any suitable reference distance can be used, such as Euclidean distances measured between reference points (e.g., the start, mid, and end points of a road segment), route distances (e.g., shortest or fastest distances), or distances depending on road class.

[0181] The contribution of each reference scaling factor to the overall estimated scaling factor of the (interested) segment can be alternatively or additionally based on the similarity between the reference detector profile associated with the reference segment and the detector profile of the (interested) segment.

[0182] The contribution of each reference scaling factor to the overall estimated scaling factor (of the segment of interest) may alternatively or additionally be based at least in part on the results of performing a linear regression training model. In any of these embodiments, the scaling factors may be time-dependent. For example, this can be implemented using appropriate time-dependent data from a linear regression training model as described above.

[0183] The model can use indicators such as measured counts of vehicles crossing the navigable element represented by the reference segment at a given time, based on data measured by at least one traffic detector associated with the navigable element represented by the reference segment.

[0184] The method according to any aspect or embodiment of the invention can be repeated for one or more additional segments of interest and / or one or more additional times of interest. Therefore, the method may include determining the estimated traffic volume for the (same) segment of interest at at least one additional time of interest using a scaling factor determined relative to different given times selected based on the additional times of interest. The method can be extended to estimating the scaling factor with respect to different given times.

[0185] According to the present invention, in any aspect or embodiment thereof, one or more segments of an electronic map (for which data is obtained of the count of devices associated with a vehicle traversing a navigable element represented by the segment at a given time) may be a set of multiple segments in a given map area of ​​the electronic map, wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices associated with the vehicle along the navigable element represented by the segment.

[0186] The segment whose scaling factor is determined in any aspect or embodiment of the invention is preferably a segment for which measured traffic data obtained by measuring traffic traversing the element represented by the segment is unavailable, for example, unavailable to a server performing the methods described herein. The segment may be a segment representing a navigable element not associated with any traffic detector. Therefore, such a segment does not form part of a set of reference segments associated with a traffic detector.

[0187] In this document, references to traffic detectors associated with elements represented by segments (or, for ease of reference, to traffic detectors associated with segments) refer to traffic detectors that form part of a fixed infrastructure constituting a navigable network, such as inductive loops, traffic cameras, infrared, radar, photoelectric sensors, or any type of sensor. Such traffic detectors that form part of a fixed infrastructure differ from data from floating vehicles or detectors, where the vehicles themselves traversing the network of navigable elements act as sensors.

[0188] The step of obtaining an estimated traffic volume for a segment using determined detector count data and a scaling factor, according to any aspect or embodiment of the invention, may include multiplying the count by the scaling factor. This is based on Equation 1 above.

[0189] The present invention extends to systems for performing steps of methods according to any aspect of the invention.

[0190] According to a further aspect of the invention, a system is provided for generating traffic data indicating traffic volume within a navigable network in an area covered by an electronic map, the electronic map comprising a plurality of segments representing navigable elements of the navigable network, the system comprising a group of one or more processors for performing a method comprising the steps of: for one or more segments of the electronic map:

[0191] Obtain data indicating the count of devices associated with a vehicle traversing the navigable element represented by the segment at a given time, wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices associated with the vehicle along the navigable element represented by the segment;

[0192] and using the determined count data and scaling factor to obtain data indicating the estimated traffic volume for the given time period;

[0193] The scaling factor is a time-dependent scaling factor, and the method includes using the scaling factor with respect to the given time when obtaining the estimated traffic volume of the segment.

[0194] This invention may include any or all of the features described with respect to other aspects of the invention, and vice versa, provided that they do not contradict each other. Therefore, even if not expressly stated herein, the system of the invention may include components or a group of one or more processors or circuit systems for carrying out any of the steps of the methods or inventions described herein.

[0195] According to a further aspect of the invention, a system is provided for generating traffic data indicating traffic volume within a navigable network in an area covered by an electronic map, the electronic map comprising a plurality of segments representing navigable elements of the navigable network, the system comprising a group of one or more processors for performing a method comprising:

[0196] Receive data indicating the segment of interest and data indicating the time of interest, wherein the segment of interest is a segment that requires estimated traffic volume data;

[0197] For each of a set of multiple segments of the electronic map, data indicating the count of devices associated with a vehicle traversing the navigable element represented by the segment about a given time selected based on the time of interest is obtained, wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices associated with the vehicle along the navigable element represented by the segment;

[0198] Identify reference subsets of the segments of the electronic map, wherein each segment of the reference subset is associated with at least one traffic detector;

[0199] For each of the reference subsets of the segments of the electronic map, data indicating a measured count of vehicles traversing the navigable element represented by the segment at a given time is obtained based on data obtained from the at least one traffic detector associated with the segment.

[0200] A reference scaling factor is obtained for each of the reference subsets of the segments, each reference scaling factor being a scaling factor determined with respect to a given time based on data measured by the at least one traffic detector associated with the segment, a measured count of vehicles crossing the segment at the given time, and a scaling factor determined with respect to a given time based on location data and associated timing data related to the movement of the plurality of devices along the segment, and a count of devices associated with vehicles crossing the segment at the given time.

[0201] The estimated scaling factor for the segment of interest for the given time is determined based on the obtained or each reference scaling factor.

[0202] In obtaining the estimated traffic volume of the segment, the estimated scaling factor with respect to the given time and the data based on location data and associated timing data related to the movement of multiple devices along the navigable element represented by the segment of interest relative to time, and the data of the count of devices associated with vehicles crossing the navigable element represented by the segment of interest with respect to the given time are used.

[0203] This invention may include any or all of the features described with respect to other aspects of the invention, and vice versa, provided that they do not contradict each other. Therefore, even if not expressly stated herein, the system of the invention may include components or a group of one or more processors or circuit systems for carrying out any of the steps of the methods or inventions described herein.

[0204] According to a further aspect of the invention, a system is provided for estimating traffic volume over a given time for a given segment of an electronic map representing a navigable network in an area, the electronic map comprising a plurality of segments representing navigable elements of the navigable network in the area, wherein the navigable network in the area includes navigable segments associated with at least one traffic detector and navigable segments not associated with any traffic detector, and wherein the given segment is a segment representing at least a portion of the navigable segments of the navigable network in the area that is not associated with any traffic detector, wherein the electronic map further comprises a plurality of reference segments, each reference segment being a segment representing at least a portion of the navigable segments of the navigable network in the area that is associated with a traffic detector, and wherein each A reference segment is associated with data indicating a corresponding reference scale factor for the given time, the scale factor being based on a measured count of vehicles traversing at least a portion of the segment represented by the reference segment at the given time and a count of devices associated with the vehicles traversing at least a portion of the segment represented by the reference segment at the given time. The measured count of vehicles is based on data measured by at least one traffic detector associated with the segment, and the count of devices associated with vehicles is based on location data and associated timing data related to the movement of multiple devices along at least a portion of the segment represented by the reference segment. The system includes a group of one or more processors for performing a method comprising the following steps:

[0205] Traffic volume for a given segment at a given time is estimated using data indicating the count of devices associated with vehicles traversing at least a portion of the navigable network represented by the given segment at the given time, and an estimated scale factor for the given segment at the given time, wherein the estimated scale factor for the segment is based on a reference scale factor associated with each of one or more reference segments of the electronic map associated with the given segment, and wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices along at least a portion of the navigable segment represented by the given segment relative to time; and

[0206] Generate data indicating the estimated traffic volume for the given time period.

[0207] This invention may include any or all of the features described with respect to other aspects of the invention, and vice versa, provided that they do not contradict each other. Therefore, even if not expressly stated herein, the system of the invention may include components or a group of one or more processors or circuit systems for carrying out any of the steps of the methods or inventions described herein.

[0208] According to a further aspect of the invention, it is provided;

[0209] A system for generating traffic data indicating traffic volume within a navigable network in an area covered by an electronic map, the electronic map comprising multiple segments representing navigable elements of the navigable network, the system comprising a group of one or more processors for performing a method comprising, for one or more segments of the electronic map:

[0210] Obtain data indicating the count of devices associated with a vehicle traversing the navigable element represented by the segment at a given time, wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices associated with the vehicle along the navigable element represented by the segment;

[0211] And using the determined count data and scaling factor to obtain data indicating the estimated traffic volume for the given time period,

[0212] The scaling factor is a location-dependent scaling factor, and the method includes using a scaling factor with respect to the location associated with the segment when obtaining the estimated traffic volume of the segment.

[0213] This invention may include any or all of the features described with respect to other aspects of the invention, and vice versa, provided that they do not contradict each other. Therefore, even if not expressly stated herein, the system of the invention may include components or a group of one or more processors or circuit systems for carrying out any of the steps of the methods or inventions described herein.

[0214] In a preferred embodiment, the system of any of these further aspects of the invention includes one or more servers. The method can be performed by a server operating on a suitable source of measured traffic data and vehicle detector data, for example, by filtering to obtain data at the applicable time. However, it is conceivable that the arrangement and steps can be implemented by a distributed system that may include one or more servers and / or one or more computing devices of any type, such as navigation devices.

[0215] The various functions described herein can be implemented in any desired and suitable manner. For example, the invention can generally be implemented in hardware or software as desired. Thus, for example, unless otherwise indicated, the various functional elements, stages, units, and “components” of the technology described herein may include suitable processors or processors, controllers or controllers, functional units, circuit systems, processing logic, microprocessor arrangements, etc., operable to perform various functions, such as suitable dedicated hardware elements (processing circuit systems) and / or programmable hardware elements (processing circuit systems) that can be programmed to operate in a desired manner.

[0216] The components (processing circuitry system) used to implement any of the steps of the method may include one or more processors configured (e.g., programmed) to do so. A given step may be implemented using the same or different set of processors as any other step. Any given step may be implemented using a combination of several sets of processors. The system may further include data storage components, such as computer memory, for storing, for example, traffic volume and / or traffic density data. The system may further include display components, such as computer monitor, for displaying, for example, traffic volume and / or traffic density data.

[0217] The method described in this article is a computer-implemented method.

[0218] In a preferred embodiment, the method of the present invention is implemented by a server. Therefore, in an embodiment, the system of the present invention includes a server comprising components (processing circuitry) for carrying out the various steps described herein, and the method steps described herein are implemented by the server.

[0219] A navigable network may include a road network, wherein each navigable element represents a road or a portion of a road. For example, a navigable element may represent a road between two adjacent intersections of a road network, or a navigable element may represent a portion of a road between two adjacent intersections of a road network. However, it will be understood that a navigable network is not limited to a road network and may include networks such as sidewalks, bike paths, rivers, etc. It should be noted that the term "segment" as used herein takes its usual meaning in the art. A segment of an electronic map is a navigable link connecting two points or nodes. While embodiments of the invention are described with particular reference to road segments, it should be recognized that the invention is also applicable to other navigable segments, such as segments of paths, rivers, canals, bike paths, towpaths, railway lines, etc. Therefore, any reference to "road segment" may be replaced by a reference to "navigable segment" or any particular type or types of such segments.

[0220] The network is represented by electronic map data. In embodiments where a server is used to implement the method, the electronic map data may be stored by the server or otherwise accessible to the server. The simplest form of an electronic map (or sometimes called a mathematical map) is actually a database containing data representing nodes (most commonly road intersections) and lines between those nodes representing roads between those intersections. In more detailed digital maps, lines can be divided into segments defined by start and end nodes. These nodes can be "real" because they represent road intersections where at least three lines or segments intersect, or they can be "artificial" because they are provided as anchor points for segments not defined by real nodes at one or both ends, particularly providing shape information for specific sections of the road, or as identifying elements along the road where a certain characteristic of the road changes, such as a speed limit. In fact, in all modern digital maps, nodes and segments are further defined by various attributes, which are represented by data in the database. For example, each node will typically have geographic coordinates to define its real-world location, such as latitude and longitude. Nodes will also typically have associated manipulation data indicating whether it is possible to move from one road to another at an intersection; and segments will also have associated attributes such as maximum allowed speed, lane size, number of lanes, and whether there is a dividing line in the middle.

[0221] In various aspects and embodiments, the present invention includes the steps of obtaining and / or using location data and associated timing data related to the movement of multiple devices along navigable elements of a navigable network, such as represented by electronic map data. The location data can provide data indicating the movement of multiple devices along navigable elements relative to time. The location data used according to the invention is location data related to the movement of multiple devices along said or each navigable element. The method may include obtaining location data and associated timing data related to the movement of multiple devices in the navigable network, and filtering the location data to obtain location data and associated timing data related to the movement of multiple devices along said or each given navigable element. The step of obtaining location data related to the movement of devices along said or each navigable element may be performed with reference to electronic map data indicating the navigable network. The method may involve the step of matching location data related to the movement of devices in a geographical area containing the navigable network with at least said or each navigable element as considered according to the invention.

[0222] In some arrangements, the step of obtaining location data may include accessing the data, i.e., the data having been previously received and stored. However, preferably, the method may include receiving location data from the device. In embodiments where the step of obtaining the data involves receiving the data from the device, it is envisioned that the method may further include storing the received location data before proceeding to other steps of the invention, and optionally filtering the data. The step of receiving location data need not be performed at the same time or place as other steps or steps of the method.

[0223] The location data used according to the invention is collected from one or more, preferably multiple, devices and is associated with the movement of said devices relative to time. Therefore, said device is a mobile device. It will be understood that at least some of the location data is associated with time data (e.g., timestamps). However, for the purposes of the invention, it is not necessary to associate all location data with time data, provided that it can be used to provide information related to the movement of the device along a navigable segment according to the invention. However, in a preferred embodiment, all location data is associated with time data (e.g., timestamps). It will be understood that timing data may be associated with a "trace" containing a set of location data "fixes" obtained by the device, rather than directly with each individual location data fix. For example, each location data "fix" may be associated with an offset relative to the time associated with the trace.

[0224] Location data and associated timing data are related to the movement of the device and can be used to provide a location "trace" of the path taken by the device. As mentioned above, the data may be received from (a number of) devices or may be stored prior to the data. For the purposes of this invention, the device may be any mobile device capable of providing location data and sufficient associated timing data. The device may be any device with location determination capabilities. For example, the device may include components for accessing and receiving information from a WiFi access point or cellular communication network, such as a GSM device, and using this information to determine its location. However, in a preferred embodiment, the device includes a Global Navigation Satellite System (GNSS) receiver, such as a GPS receiver, for receiving satellite signals indicating the receiver's location at a specific point in time, and preferably receiving updated location information at regular intervals. Such devices may include navigation devices, mobile telecommunications devices with positioning capabilities, location sensors, etc.

[0225] The device is associated with a vehicle. In these embodiments, the location of the device will correspond to the location of the vehicle. References to location data obtained from a device associated with a vehicle may be replaced by references to location data obtained from the vehicle, and references to the movement of one or more devices may be replaced by references to the movement of the vehicle, and vice versa, unless explicitly stated otherwise. The device may be integrated with the vehicle or may be a separate device associated with the vehicle, such as a portable navigation device. Of course, location data may be obtained from a combination of different devices or a single type of device.

[0226] Location data obtained from multiple devices is generally referred to as “detector data.” Data obtained from devices associated with vehicles may be referred to as vehicle detector data (or sometimes as floating car data). Therefore, the reference to “detector data” in this document should be understood as being interchangeable with the term “location data,” and for the sake of brevity, location data may be referred to as detector data in this document.

[0227] The sample size, along with a selected average penetration rate, can be used to estimate either traffic volume or traffic density (or both) in a segment (or preferably multiple segments) within a region. Both traffic volume and traffic density are important parameters for characterizing the state of traffic in a network and can be used in a variety of traffic planning and control applications.

[0228] This invention allows for traffic volume estimation for any segment within a network, with a suitable scaling factor for said segment obtained according to the method described herein. That is, given sufficient detector data, it is possible to reliably estimate the scaling factor, and thus the traffic volume over a relatively wide area of ​​the network, at a lower cost than conventional methods typically can. For example, and preferably, the scaling factor and thus the traffic volume can be determined for multiple (or all) segments within a region, making it possible to provide a picture of the traffic volume across the entire region. Therefore, the method described herein can be repeated for one or more additional segments representing navigable elements of a navigable network. For example, the method can be performed at least for each of a subset of segments for which traffic detector data is unavailable (i.e., a subset of segments not associated with at least one traffic detector).

[0229] The method includes the step of obtaining estimated traffic volume data for an indicated segment over a given time interval. The method may include generating estimated traffic volume data for output. The method may include associating the estimated traffic volume data with data indicating the segment. Thus, traffic volume data may be associated with electronic map data. In a preferred embodiment, the invention includes transmitting and / or storing and / or displaying traffic volume data to a user. That is, traffic volume data may be provided to the user as output. Where the method described herein is performed by a server, the method may include the server transmitting the estimated traffic volume data of the indicated segment to a device associated with a user and / or a vehicle, such as a navigation device. As described above, a navigation device refers to a device running a navigation application.

[0230] It will be understood that the methods according to the invention can be implemented at least in part using software. Therefore, it will be seen that, when viewed from a further perspective and in further embodiments, the invention extends to computer program products comprising computer-readable instructions adapted to perform any or all of the methods described herein when executed on a suitable data processing component. The invention also extends to computer software carriers including this software. This software carrier may be a physical (or non-transitory) storage medium or may be a signal, such as an electronic signal transmitted via wires, an optical signal, or a radio signal, for example, to a satellite.

[0231] Any reference to comparing one item with another may involve comparing any item with another, and in any way said.

[0232] It should be noted that the phrase "associated with" regarding one or more segments or elements should not be interpreted as requiring any specific restrictions on the location of data storage. The phrase only requires that the features be identifiable as related to the element. Therefore, association could be achieved, for example, by referencing a side file that might be located on a remote server.

[0233] Unless explicitly stated otherwise, it will be understood that any aspect of the invention may include any or all of the features described with respect to other aspects or embodiments of the invention, provided that they are not mutually exclusive. Specifically, while various embodiments of operations that may be performed in the method and by the system or device have been described, it will be understood that any one or more or all of these operations may be performed in the method and by the system or device in any combination as appropriate.

[0234] The advantages of these embodiments are set forth below, and further details and features of each of these embodiments are defined elsewhere in the appended dependent claims and the following detailed description. Attached Figure Description

[0235] Embodiments of the invention will now be described by way of example only with reference to the accompanying drawings, in which:

[0236] Figure 1 This is a schematic diagram of an instance of the Global Positioning System (GPS) that can be used by navigation devices;

[0237] Figure 2 This is a schematic diagram of a communication system used for communication between a navigation device and a server;

[0238] Figure 3 yes Figure 2 A schematic diagram of the electronic components of a navigation device or any other suitable navigation device;

[0239] Figure 4 This is a schematic diagram of the layout for installing and / or docking navigation devices;

[0240] Figure 5 It is by Figure 3 A schematic representation of the stacked architecture used in the navigation device;

[0241] Figure 6 Explain the various forms that navigation devices can take;

[0242] Figure 7 Explain the various devices that can be associated with vehicles;

[0243] Figure 8 This describes another exemplary navigation system;

[0244] Figure 9 Indicate the number of road segments with traffic flow detectors in a given map area;

[0245] Figure 10 This explains the observed error between estimated traffic flow and measured traffic flow using a constant proportionality coefficient.

[0246] Figure 11 Explain the observed error when using a time-dependent but location-independent scaling factor;

[0247] Figure 12 An exemplary detector outline illustrating the weekly pattern of detector data is shown;

[0248] Figure 13 Demonstrate the similarity between the detector profile (which may be associated with the segment of interest) and four (reference) detector profiles;

[0249] Figure 14 This is a functional diagram illustrating a system for implementing the generation of a set of scaling factors according to the embodiments described herein;

[0250] Figure 15This is an explanation of what to use. Figure 14 A flowchart of a method for obtaining time-dependent scaling factors using a system;

[0251] Figure 16 Explain the observed error when using the scaling factors obtained according to some preferred embodiments of the present invention;

[0252] Figure 17 This section describes examples of attenuation functions that can be used to obtain position-dependent scaling factors; and

[0253] Figure 18 The map area displays the location-dependent scaling factor values. Detailed Implementation

[0254] Now refer to Figures 1 to 5 The following describes a system that can be used to facilitate understanding of the context of the invention. Embodiments will now be described with particular reference to portable navigation devices (PNDs). However, it should be remembered that the teachings of the invention are not limited to PNDs, but are generally applicable to devices capable of transmitting detector data samples to a server, including, but not limited to, any type of processing device configured to execute navigation software in a portable manner to provide route planning and navigation functionality. References below... Figure 6 and 7 To describe some such exemplary devices. Therefore, it is concluded that, in the context of this application, a navigation device is intended to include (but is not limited to) any type of route planning and navigation device, regardless of whether that device is embodied as a PND, and includes devices integrated into a vehicle such as a car, or portable computing resources such as portable personal computers (PCs), mobile phones, or personal digital assistants (PDAs) that actually perform route planning and navigation software. The invention is also applicable to devices capable of transmitting detector data samples, which may not necessarily be configured to perform navigation software, but rather to transmit detector data samples and be arranged to implement other functionalities described herein.

[0255] Furthermore, embodiments of the invention are described with reference to road segments. It should be understood that the invention is also applicable to other navigable segments, such as paths, rivers, canals, bicycle paths, towpaths, railway lines, etc. For ease of reference, these are generally referred to as road segments.

[0256] As will become apparent below, this can also occur when performing route planning, even if the user is not seeking instructions on how to navigate from one point to another, but simply wants to be provided with a view of a given location. In such cases, the “destination” location chosen by the user does not need to have a corresponding starting point from which the user wishes to begin navigation, and therefore, references to the “destination” location or, in effect, to the “destination” view herein should not be interpreted as implying that route generation is essential, travel to the “destination” must occur, or that the existence of the destination actually requires specifying a corresponding starting point.

[0257] Taking into account the above additional conditions, Figure 1 The Global Positioning System (GPS) is used for a variety of purposes. Generally, GPS is a satellite radio-based navigation system capable of determining the continuous position, speed, time, and in some cases, direction information for an unlimited number of users. Formerly known as NAVSTAR, GPS incorporates multiple satellites orbiting the Earth in extremely precise orbits. Based on these precise orbits, GPS satellites can relay their positions as GPS data to any number of receiving units. However, it will be understood that other global positioning systems, such as GLOSNAS, the European Galileo system, COMPASS, or IRNSS (Indian Regional Navigation Satellite System), can also be used.

[0258] The GPS system is implemented when a device specifically equipped to receive GPS data begins scanning radio frequencies to search for GPS satellite signals. Upon receiving radio signals from a GPS satellite, the device determines the precise position of that satellite using one of several different conventional methods. In most cases, the device continues scanning signals until it has acquired signals from at least three different satellites (note that the position is usually not determined by just two signals but can be determined using other triangulation techniques). Performing geometric triangulation, the receiver uses three known positions to determine its own two-dimensional position relative to the satellites. This can be done in a known manner. Additionally, acquiring a fourth satellite signal allows the receiving device to calculate its three-dimensional position using the same geometric calculations in a known manner. Position and velocity data can be continuously and instantly updated by an unlimited number of users.

[0259] like Figure 1As shown, the GPS system 100 includes multiple satellites 102 orbiting the Earth 104. A GPS receiver 106 receives GPS data from several of the satellites 102 as spread-spectrum GPS satellite data signals 108. The spread-spectrum data signals 108 are transmitted continuously from each satellite 102, and each transmitted spread-spectrum data signal 108 includes a data stream containing information identifying the specific satellite 102 from which the data stream originates. The GPS receiver 106 typically requires spread-spectrum data signals 108 from at least three satellites 102 to be able to calculate two-dimensional position. Reception of a fourth spread-spectrum data signal enables the GPS receiver 106 to calculate three-dimensional position using known techniques.

[0260] Turn Figure 2 The navigation device 200 (e.g., a PND), including or coupled to the GPS receiver device 106, can, as needed, establish a data session with network hardware of a "mobile" or telecommunications network via a mobile device (not shown) (e.g., a mobile phone, PDA, and / or any device with mobile phone technology) to establish a digital connection, such as a digital connection via known Bluetooth technology. The mobile device can then establish a network connection with the server 150 (e.g., via the Internet) through its network service provider. Thus, a "mobile" network connection can be established between the navigation device 200 (which is often mobile, as it travels independently and / or in a vehicle) and the server 150 to provide an "instant" or at least very "up-to-date" information gateway.

[0261] For example, establishing a network connection between a mobile device (via a service provider) and another device (e.g., server 150) using the Internet can be done in known ways. In this regard, any number of suitable data communication protocols can be used, such as the TCP / IP layered protocol. Furthermore, the mobile device can utilize any number of communication standards, such as CDMA2000, GSM, IEEE 802.11a / b / c / g / n, etc.

[0262] Therefore, it can be seen that an Internet connection can be used, which can be achieved, for example, via a data connection, via a mobile phone or mobile phone technology within the navigation device 200.

[0263] Although not shown, the navigation device 200 may of course incorporate its own mobile phone technology (e.g., including an antenna, or optionally using an internal antenna of the navigation device 200). The mobile phone technology within the navigation device 200 may include internal components and / or may include an insertable card (e.g., a Subscriber Identity Module (SIM) card), for example equipped with the necessary mobile phone technology and / or antenna. Therefore, the mobile phone technology within the navigation device 200 can similarly establish a network connection between the navigation device 200 and the server 150 via, for example, the Internet in a manner similar to that of any mobile device.

[0264] For phone settings, the Bluetooth-enabled navigation device can be used to work correctly with mobile phone models, manufacturers, etc., whose spectrum is constantly changing. For example, model / manufacturer-specific settings can be stored on the navigation device 200. The data stored for this information can be updated.

[0265] exist Figure 2 In this design, navigation device 200 is depicted communicating with server 150 via a general communication channel 152, which can be implemented in any of several different arrangements. Communication channel 152 typically represents the propagation medium or path connecting navigation device 200 and server 150. When a connection is established between server 150 and navigation device 200 via communication channel 152 (note that this connection can be a data connection via a mobile device, a direct connection via the Internet via a personal computer, etc.), server 150 and navigation device 200 can communicate.

[0266] Communication channel 152 is not limited to a specific communication technology. Furthermore, communication channel 152 is not limited to a single communication technology; that is, channel 152 may contain several communication links using multiple technologies. For example, communication channel 152 may be adapted to provide paths for electrical, optical, and / or electromagnetic communications, etc. Therefore, communication channel 152 includes (but is not limited to) one or a combination of the following: circuits, electrical conductors (e.g., wires and coaxial cables), fiber optic cables, converters, radio frequency (RF) waves, the atmosphere, free space, etc. In addition, communication channel 152 may include intermediate devices, such as routers, repeaters, buffers, transmitters, and receivers.

[0267] In one illustrative arrangement, communication channel 152 includes telephone and computer networks. Furthermore, communication channel 152 may be adapted for wireless communication, such as infrared communication, radio frequency communication, such as microwave frequency communication, etc. Additionally, communication channel 152 may be adapted for satellite communication.

[0268] The communication signals transmitted through communication channel 152 include (but are not limited to) signals that a given communication technology may require or desire. For example, the signals may be adapted for cellular communication technologies such as Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Code Division Multiple Access (CDMA), Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), etc. Both digital and analog signals may be transmitted through communication channel 152. These signals may be modulated, encrypted, and / or compressed, as the communication technology may desire.

[0269] In addition to other components that may not be specified, server 150 also includes processor 154, which is operatively connected to memory 156 and further operatively connected via wired or wireless connection 158 to mass storage device 160. Mass storage device 160 contains storage for navigation data and map information and may again be a separate device from server 150 or may be incorporated into server 150. Processor 154 is further operatively connected to transmitter 162 and receiver 164 to transmit information to and receive information from navigation device 200 via communication channel 152. The transmitted and received signals may include data, communications, and / or other propagated signals. Transmitter 162 and receiver 164 may be selected or designed according to the communication requirements and communication technologies used in the communication design of navigation system 200. Furthermore, it should be noted that the functions of transmitter 162 and receiver 164 may be combined into a single transceiver.

[0270] As mentioned above, the navigation device 200 can be arranged to communicate with the server 150 via communication channel 152, using transmitter 166 and receiver 168 to transmit and receive signals and / or data via communication channel 152. It should be noted that these devices can be further used to communicate with devices other than the server 150. Furthermore, transmitter 166 and receiver 168 are selected or designed according to the communication requirements and technologies used in the communication design of the navigation device 200, and the functions of transmitter 166 and receiver 168 are as described above. Figure 2 It is assembled into a single transceiver as described. Of course, the navigation device 200 includes other hardware and / or functional components, which will be described in further detail below.

[0271] The software stored in server memory 156 provides instructions for processor 154 and allows server 150 to provide services to navigation device 200. One service provided by server 150 involves processing requests from navigation device 200 and transferring navigation data from mass data storage device 160 to navigation device 200. Another service that may be provided by server 150 involves processing navigation data using various algorithms desired for application and sending the results of these calculations to navigation device 200.

[0272] Server 150 constitutes a remote data source that can be accessed by navigation device 200 via a wireless channel. Server 150 may include a network server located on a local area network (LAN), wide area network (WAN), virtual private network (VPN), etc.

[0273] Server 150 may include a personal computer, such as a desktop or laptop computer, and communication channel 152 may be a cable connecting the personal computer and navigation device 200. Alternatively, the personal computer may be connected between navigation device 200 and server 150 to establish an Internet connection between server 150 and navigation device 200.

[0274] Information from server 150 can be provided to navigation device 200 via information download. This information may be updated from time to time or automatically when a user connects navigation device 200 to server 150, and / or may be more dynamic as a more constant or frequent connection is established between server 150 and navigation device 200, for example, via a wireless mobile connection device and TCP / IP connection. For many dynamic calculations, processor 154 in server 150 can be used to handle most of the processing needs; however, the processor of navigation device 200 ( Figure 2 (Not shown in the text) It can also handle a lot of processing and computation, and usually does not depend on a connection to server 150.

[0275] refer to Figure 3 It should be noted that the block diagram of navigation device 200 does not include all components of the navigation device, but only represents a number of example components. Navigation device 200 is located within a housing (not shown). Navigation device 200 includes a processing circuitry system, which includes, for example, the processor 202 mentioned above, coupled to input device 204 and a display device, such as display screen 206. Although input device 204 is referred to herein in the singular, those skilled in the art will understand that input device 204 means any number of input devices, including keyboard devices, voice input devices, touch panels, and / or any other known input devices for inputting information. Similarly, display screen 206 may include any type of display screen, such as a liquid crystal display (LCD).

[0276] In one arrangement, one aspect of the input device 204, the touch panel, and the display screen 206 is integrated to provide an integrated input and display device (including a touch panel or touch screen input 250). Figure 4 The processor 202 enables both information input (via direct input, menu selection, etc.) and information display via the touch panel screen, allowing users to select one of multiple display options or activate one of multiple virtual or "soft" buttons by touching only a portion of the display screen 206. In this respect, the processor 202 supports a graphical user interface (GUI) combined with touchscreen operation.

[0277] In navigation device 200, processor 202 is operably connected to input device 204 via connection 210 and is capable of receiving input information from input device 204, and is operably connected to at least one of display screen 206 and output device 208 via corresponding output connection 212 to output information to said at least one. Navigation device 200 may include output device 208, such as an audible output device (e.g., a speaker). Since output device 208 can generate audible information for the user of navigation device 200, it should also be understood that input device 204 may also include a microphone and software for receiving input voice commands. Furthermore, navigation device 200 may also include any additional input device 204 and / or any additional output device, for example, an audio input / output device.

[0278] Processor 202 is operatively connected to memory 214 via connection 216 and is further adapted to receive / send information from / to input / output (I / O) port 218 via connection 220, wherein I / O port 218 may be connected to an external I / O device 222 of navigation device 200. External I / O device 222 may include (but is not limited to) an external listening device, for example, headphones. The connection to I / O device 222 may further be a wired or wireless connection to any other external device (e.g., a car stereo unit) for hands-free operation and / or for, for example, voice-activated operation, for connection to a handset or headphones, and / or for, for example, connection to a mobile phone, wherein the mobile phone connection may be used to establish a data connection between navigation device 200 and, for example, the Internet or any other network, and / or, for example, to a server via the Internet or some other network.

[0279] The navigation device 200's memory 214 includes a portion of non-volatile memory (e.g., for storing program code) and a portion of volatile memory (e.g., for storing data while the program code is being executed). The navigation device also includes a port 228 that communicates with the processor 202 via connection 230 to allow the addition of a removable memory card (typically referred to as a card) to the device 200. In the described embodiment, the port is arranged to allow the addition of an SD (Secure Digital) card. In other embodiments, the port may allow connection to other formats of memory (e.g., Compact Flash (CF) cards, memory sticks, xD memory cards, USB (Universal Serial Bus) flash drives, MMC (Multimedia Cards), smart media cards, micro drives, etc.).

[0280] Figure 3 Further explanation is provided regarding the operational connection between the processor 202 and the antenna / receiver 224 via connection 226, wherein the antenna / receiver 224 may be, for example, a GPS antenna / receiver and thus will serve as... Figure 1The function of the GPS receiver 106. It should be understood that, for illustrative purposes, the antenna and receiver specified by component symbol 224 are combined schematically, but the antenna and receiver may be separately positioned components, and the antenna may be, for example, a GPS patch antenna or a helical antenna.

[0281] Of course, those skilled in the art will understand. Figure 3 The electronic components shown are powered in a conventional manner by one or more power sources (not shown). Such power sources may include internal batteries and / or inputs for low-voltage DC supply or any other suitable arrangement. As will be understood by one of ordinary skill in the art, this can be considered... Figure 3 The different configurations of the components shown in the example. Figure 3 The components shown can communicate with each other via wired and / or wireless connections. Therefore, the navigation device 200 described herein can be a portable or handheld navigation device 200.

[0282] in addition, Figure 3 The portable or handheld navigation device 200 can be connected or "docked" to a vehicle, such as a bicycle, motorcycle, car, or boat, in a known manner. This navigation device 200 can then be removed from the docking position for portable or handheld navigation use. In practice, in other embodiments, the device 200 may be arranged in a handheld configuration to allow the user to navigate.

[0283] refer to Figure 4 The navigation device 200 may include an integrated input and display device 206 and Figure 2 Other components (including, but not limited to, internal GPS receiver 224, processor 202, power supply (not shown), memory system 214, etc.) are also present.

[0284] The navigation device 200 may be located on an arm 252, which itself may be secured to a vehicle dashboard, window, etc., using a suction cup 254. This arm 252 is an example of a docking station to which the navigation device 200 may be docked. For example, the navigation device 200 may be docked to the arm 252 by snapping the navigation device 200 onto it or otherwise connected to the arm 252 of the docking station. The navigation device 200 may then rotate on the arm 252. For example, to release the connection between the navigation device 200 and the docking station, a button (not shown) on the navigation device 200 may be pressed. Other equally suitable arrangements for coupling and decoupling the navigation device 200 from the docking station are well known to those skilled in the art.

[0285] Of course, the navigation device does not need to be provided by a PND type device as described below. As described below, when running a navigation client, a wide range of general-purpose computing devices can provide the functionality described in the reference navigation device 200 and can communicate with the server in the same manner.

[0286] Turn Figure 5 The processor 202 and memory 214 cooperate to support a BIOS (Basic Input / Output System) 282, which serves as an interface between the functional hardware components 280 of the navigation device 200 and the software executed by the device. The processor 202 then loads an operating system 284 from memory 214, which provides an environment in which application software 286 (implementing some or all of the described route planning and navigation functionalities) can run. The application software 286 provides an operating environment including a graphical user interface (GUI) that supports the core functions of the navigation device, such as map viewing, route planning, navigation functions, and any other functions associated with the navigation device. In this regard, a portion of the application software 286 includes a view generation module 288.

[0287] In the described embodiment, the processor 202 of the navigation device is programmed to receive GPS data received by antenna 224, and when triggered according to the method described herein, stores that GPS data, along with a timestamp of when the GPS data was received, in memory 214 to establish a record of the navigation device's location. Each data record thus stored can be considered a GPS location; that is, it is a location of the navigation device and includes latitude, longitude, and a timestamp. This data is referred to herein as a detector data sample.

[0288] Furthermore, processor 202 is configured to upload each detector data sample (i.e., GPS data and timestamps) to server 150. Navigation device 200 may have a permanent or at least normally existing communication channel 152 connecting it to server 150.

[0289] In the described embodiment, detector data samples provide one or more tracks, each track representing the movement of that navigation device 200 within an applicable period (e.g., while traversing a given path). Server 150 is configured to receive and store records of received detector data samples and these samples as the movement of the device within a mass data storage device 160 for processing. Thus, over time, the mass data storage device 160 accumulates multiple records of the movement of the navigation device 200 with uploaded detector data samples. The server can reconstruct the detector data samples forming the tracks, for example, by associating common elements (e.g., device identifier values ​​or data associated with a specific period) with the entire track (rather than with each of the detector data samples constituting the track). After moving the common elements to the track level, individual detector data samples within the track may contain at least a position value and a time offset (e.g., time since the start of the period or sequence number) within the track and its associated period.

[0290] As discussed above, the large-capacity data storage device 160 also contains map data. This map data provides information about the location of road segments, points of interest, and other such information typically found on maps.

[0291] As mentioned above, the term "navigation device" as used herein should be understood to encompass any form of device that runs a suitable navigation client, and is not limited to devices using, for example... Figure 4 The specific purpose PND type device described herein. The navigation client is a software application running on a computer device. Navigation devices can be implemented using a wide range of computing devices. Figure 6 Some such exemplary devices are shown in the image.

[0292] Figure 6 All the devices in this document include a navigation screen to assist the user in navigating to their desired destination. These devices include personal navigation devices (PNDs), which are general-purpose computing devices in the form of single-purpose computing devices (top left), mobile phones (top right), laptops (bottom left), and in-vehicle integrated computing devices (bottom right). Of course, these devices are just some examples of a wide range of general-purpose computing devices that can be used to run navigation clients. For example, tablet computers or wearable devices, such as watches, can be used.

[0293] Vehicles can have multiple computing devices and multiple displays to support the driver, such as Figure 7 As shown in the image. Figure 7 The interior of the vehicle is shown, featuring a steering wheel 300, a first display area 320 behind the steering wheel, a head-up display 330 projected onto the windshield, a central display 340, and multiple controls (buttons, touchscreens) 350. Furthermore, the vehicle can support the integration of mobile devices into the vehicle's computer environment.

[0294] exist Figure 8 The diagram illustrates a functional representation of another exemplary navigation system 400. This system includes a navigation client 402, which can be provided by a software application running on any suitable computing device, as shown in the reference... Figure 6 and 7 As illustrated, system 400 also includes a map server 404, a traffic information server 406, and an in-vehicle control system 408. These components are described in more detail below. It will be understood that the navigation system will include multiple navigation clients 402 that communicate with the map server 404 and the traffic information server 406.

[0295] Navigation client 402

[0296] The navigation client is provided by a navigation application running on a computing device. Navigation client 402 provides user input and output devices 410, 412, as are common to most computing devices. The navigation client also provides a map data controller 414, which acquires map data and stores the map data in the non-volatile memory of the computing device, on which the navigation application providing the client runs. In addition to conventional computing device components such as a processing unit, memory, display, long-term storage (flash memory), and networking interface, the navigation device on which the navigation application runs also includes a position sensor 416. Figure 8 Such more conventional components are not shown in the document. Figure 8 Explain those components that are more relevant to supporting navigation functionality.

[0297] The navigation client 400 operates using an electronic map of the geographic area. The map information may be stored locally on the device (e.g., in non-volatile solid-state memory) or retrieved from a navigation server. The navigation client uses the electronic map to generate a map view of the geographic area of ​​interest on the display of the computing device. Typically, the geographic area is centered on the current location of the computing device executing the navigation client software application.

[0298] The current location is determined using a position sensor 416, which may employ any wide range of position sensing technologies, such as satellite positioning (GPS, GNSS, ...), WiFi (wireless triangulation), mobile phone tracking, Bluetooth beacons, image analysis (examples of image analysis are described in the applicant's PCT / EP2016 / 068593, PCT / EP2016 / 068594, PCT / EP2016 / 068595 and PCT / IB2016 / 001198, the entire contents of which are incorporated herein by reference), map matching, dead reckoning, and any of other position sensing technologies. In the presence of position sensing errors, map matching may be used to adjust (some) measured positions to best match road segments on a map.

[0299] The navigation client 402 assists the user in navigating from their current location to their destination. The destination can be entered using the destination selection module 418. The route selection module 420 of the navigation client calculates the route to the selected destination. In addition to the electronic map, the route selection module 420 also obtains current traffic information to determine the estimated travel time or estimated arrival time. The current traffic information describes the current state of the road network in the geographic area of ​​the electronic map. This includes current average speed, current traffic density, current road closures, etc. The route selection module 420 can present a preferred route and alternative routes that allow the end user to select the preferred route.

[0300] The navigation client's guidance module 422 uses a selected preferred route to guide the end user to a selected destination. It can use a display to show a map and a portion of the route to the destination. Guidance can also take the form of additional graphical indicators on the display. Most navigation clients also support audio guidance with turn-by-turn instructions.

[0301] The active navigation client generates location detectors and provides them to a traffic information server, which uses these detectors to calculate and update traffic information. The navigation client 402 includes a location detector generator 426 and a detector interface 428 for implementing these functions.

[0302] The navigation client 402 also includes an HTTPS client for communicating with the map server 404 and the traffic information server 424.

[0303] Map server 404

[0304] A map server (404) is an infrastructure used to store, manage, and create the vast amounts of information used to create electronic maps and for navigation. Map servers can be provided by cloud server systems.

[0305] Map server 404 includes a map compiler 430 that receives map data from a suitable map production unit 432. Map production unit 432 receives map source data from map data source 434 and converts this data into a suitable format for inclusion in an electronic map. For example, map compiler 430 can categorize map data into corresponding layers and tiles of the electronic map. Map server 404 further includes a map data service 436 and a map metadata service 436. The combination of map data service 436 and map metadata service 436 can be collectively referred to as a "cloud service". HTTPS client 424 can retrieve map metadata from map metadata service 436, and then, as needed, can use the metadata to retrieve map data from map data service 438.

[0306] Typical navigation server management and a wide range of countries (approximately 200 countries) 10 7 Up to 10 8 The map information is linked to a road network spanning kilometers. This map information needs to be of high quality, therefore the server infrastructure processes updates to the map information at an average rate of approximately 1000 updates per second. Additionally, the map information needs to be distributed to navigation clients via a global infrastructure. Besides cloud computing systems, distribution also requires a complex content distribution network to generate the map information to be distributed. The navigation server also aggregates, processes, and distributes real-time traffic information.

[0307] Traffic Information Server 406

[0308] Traffic information server 406 includes traffic information compiler 440 that compiles traffic information using data obtained from detector data source 442. Detector data source 442 receives data from detector data service 446, which is configured to receive detector data from navigation clients. Traffic information compiler 440 provides traffic information to traffic information service 444, which communicates with HTTPS client 424 to provide the traffic information to the HTTPS client.

[0309] Traffic information server 406 provides road and traffic information to navigation client 402.

[0310] Map information typically contains static traffic information based on historical data. For more dynamic traffic information, such as traffic density, parking availability, accidents, road closures, updated road signs, and points of interest, the traffic information server receives location detector data from navigation clients. The traffic information compiler uses current location detector data obtained from multiple navigation clients to generate current traffic information.

[0311] Location detector data

[0312] During normal operation, the navigation client 402 periodically sends location detector data to the traffic information server 406. The location detector data includes information about the navigation client's recent or current location. The location detector data can be combined into a set of detector data elements, commonly referred to as a track. The traffic information server 406 uses the track or detector data to estimate current traffic information. This information includes parameters of the road segment, such as the current average speed and current traffic density. The traffic information server 406 processes the location detector data to provide real-time traffic information to the navigation client 402, thereby enabling better route generation and improved estimated travel time to the destination.

[0313] The term "location detector" (or "detector") refers to a data sample that contains at least location information indicating the location of a navigation client (i.e., the device implementing the client). Typically, the location data will include longitude and latitude values ​​(both with a typical accuracy of approximately 10 meters). The detector data sample may contain other data, such as time values. The time values ​​provide the time associated with the location data and can be received from the positioning system to correspond to the time when the location data was generated, or to the transmission time of the detector data sample. The detector data sample may also contain a device identifier value (uniquely associated with the end-user device and the user).

[0314] The term trace describes a set of location detectors associated with the same device, user, and common period. Trace data can be reconstructed at the server, for example, by associating common elements related to the detector data (such as device identifier values ​​or time periods) with the trace (rather than with each individual detector that makes up the trace). After moving the common elements to the trace level, the individual detectors in the trace contain at least a location value and a time offset within the period (e.g., time since the start of the period or sequence number).

[0315] At least in a preferred embodiment, the present invention relates to a method for generating data indicating traffic volume within a navigable network. The accurate generation of this traffic data is crucial for many traffic management and control applications. Therefore, the present invention provides an improved method for generating this traffic data. Specifically, the present invention provides a method for generating this traffic data from detector data. Preferred embodiments will now be described with respect to traffic volume estimation. Such techniques can be performed by a server with access to vehicle detectors and measured traffic count data, as described below. For example, the server may be a reference... Figure 8 The traffic server operating in the system described.

[0316] Traffic volume (also known as traffic flow) is defined as the number ΔN of vehicles passing through a cross-section at location x within a time interval Δt. That is, traffic volume Y is typically given by the following formula:

[0317]

[0318] The time interval Δt is typically set or selected based on the desired application and, for example, the required time resolution (and accuracy). For instance, in the context of dynamic traffic phenomena such as traffic congestion, a typical aggregation time interval Δt may appropriately range from about 1 minute to 1 hour. However, for other applications, such as traffic light calibration, traffic planning, etc., much larger time intervals, such as days, weeks, or even months, may need to be considered.

[0319] Traffic volume cannot typically be measured directly from detector data because only a small fraction of the total traffic on the road network is reported in the data. That is, detector data only represents a specific sample of the total traffic within the road network. Although the percentage of detectors is generally increasing, currently, coverage (or “penetration level”) is typically only around 10% (e.g., in Germany or the Netherlands), and even less in some areas.

[0320] Embodiments of the present invention therefore provide an improved method, in which probe data from samples of floating vehicles can be used to estimate traffic volume. The basic idea underlying this concept is that, given a suitable scaling factor, which may indicate the penetration level in inverse proportion, the observed probe count in a segment during a given time interval can be predicted or extrapolated to give the total traffic volume of said segment during that time interval.

[0321] The present invention relates to an improved technique for estimating this scaling factor. The scaling factor is time-dependent and / or position-dependent. As described with reference to the above Figure 9 illustrated, current technologies rely on a scaling factor that is constant across all segments of the map and for all times under consideration. However, as Figure 10 shown, this may lead to considerable errors.

[0322] Some embodiments of the present invention will now be described with reference to a method implemented by a traffic information server.

[0323] The traffic information server uses vehicle probe data obtained from traffic detectors associated with road elements represented by segments of an electronic map and measured traffic data to provide an improved estimate of the scaling factor for a segment in a given time interval. For simplicity, this measured traffic data will be referred to as "loop detector data", but it will be understood that measured traffic data (instead of probe data) can be obtained from any other type of traffic detector associated with a road element (i.e., forming part of fixed road infrastructure), such as a camera.

[0324] The traffic information server receives vehicle probe data for a set S of road segments s in a map area A. The set of road segments S comprises a first subset L={s i |0≤i<N}, which comprises N road segments s i of map area A. Each road segment s i in this first set is associated with a traffic flow detector.

[0325] The remaining road segments in this map area form a second subset M of R road segments s r that are not associated with a traffic flow detector, M={s r |0≤i<R}. Therefore, L={s i |0≤i<N} and M={s r |0≤r<R} and S=L∪M, where |S|=N+R.

[0326] The traffic information server receives from road segment s i the measured traffic flow data Y(s i ,t). The traffic information server further receives from the road segment s iA navigation device associated with a vehicle traveling upstream receives probe data X(s i ,t). The navigation device may be any device that runs a navigation application as discussed above.

[0327] Since the two traffic flow data sources are time-dependent and position (road segment)-dependent, the traffic information server determines a scaling factor k(s i ,t), which is also a function of time t and position s i . The scaling factor indicates the penetration level;

[0328]

[0329] k(s i ,t) correlates the received measured traffic flow data obtained from traffic detectors associated with the segments with the received probe data obtained from navigation devices.

[0330] However, the traffic information server does not receive measured traffic flow data for the second set of road segments s r . Instead, the traffic information server only receives probe data X(s r from navigation devices associated with vehicles traveling on road segment s r ,t).

[0331] In equation 4, time t represents time with Δt as a fixed time unit. This means that a high-resolution time T (e.g., counting the number of microseconds since a reference time) can be converted to t, where t = trunc(T / Δt). Accordingly, t counts the number of time intervals Δt since the reference time. Using 1 hour as Δt, time t is an hourly time indicator with an accuracy of 1 hour. Since traffic patterns at the same time and the same day of the week are very similar, a common simplification is to replace time with a discrete time index t k that covers 24x7 hours in a week. The time index t k counts Z time intervals Δt in a week. The formula t k = t mod Z uses modular arithmetic to map the time t to a time index t k with a range of 0,…,Z-1 (0≤k<Z). If Δt is 10 minutes, then the value of Z is 24*7*(60 / 10) = 1008. For Δt of 1 hour (60 minutes), Z is equal to 168 (24*7).

[0332] There is a need for a method for determining k(s r ,t r ) k for road segment s that has no measured traffic information.

[0333] In a simplified embodiment, by comparing traffic count data based on detector data with measured inductive loop data, the time-dependent value of the scaling factor determined for the segment associated with the inductive loop can be used to infer the time-dependent scaling factor value for determining traffic volume in segments without measured traffic information. This provides some improvement in the accuracy of determining traffic volume in such segments compared to using a constant scaling factor across all segments.

[0334] In the experiment using two sets of induction loops, k(t) is calculated from the first set of induction loops. k ) coefficients. These k(t) k The coefficients are discrete-time dependent but location-independent, meaning they are used for all road segments. Next, the detector data from these induction loops and k(t) are used... k The coefficient is used to compare the measured traffic data of the second set of induction loops with the traffic estimates. Compared to the average relative prediction error (MRE) of 12.9% with the constant coefficient k, the discrete-time dependent coefficient k(t) is used. k The MRE level was reduced to 10.5%.

[0335] Figure 11 Show the constant coefficient k and discrete-time dependent coefficient k(t) of the same set of induction loops k The median relative error of the coefficient is thus increased. Therefore, increasing the granularity of the coefficient improves the accuracy of traffic estimation. Ideally, further refinement of the granularity would involve considering the location of road segments to estimate their traffic flow. Therefore, the expected estimate of the scaling factor depends on location, such as the location of the segment under consideration. Some techniques for implementing this are described below.

[0336] The traffic information server is for road segment s i Receive measured traffic data Y(s) from traffic detectors i ,t k And receive detector data X(s) from navigation devices associated with vehicles. i ,t k ).

[0337] The traffic information service will process the received and measured traffic data Y(s) according to Equation 4 above. i ,t k ) and received detector data X(s) i ,t k Divide by ) to obtain k(s) i ,t k Road segment s will be available later. i k(s) i ,t k The coefficient is used in cases where measured traffic data Y(s) is lacking. i ,t k) to estimate the traffic flow of road section s i , t k ) from the probe data X(s i in the case of.

[0338] The traffic information server receives probe data X(s r ) only from navigation devices associated with vehicles traveling towards road section s r , t k ). The object of the present invention is to determine k(s r , t k ) for such road sections s r that are not associated with any traffic flow detector but for which the traffic information server receives probe data X(s r , t k ).

[0339] The traffic information server uses the probe data X(s r , t k ) and X(s i , t k ) to generate a traffic pattern profile P(s), referred to herein as a "probe profile". The probe profile describes how the probe count, that is, the count of vehicles based on probe data, varies with respect to the time within a week. This profile is obtained by aggregating probe data associated with weekly cyclic time intervals, for example 1-hour intervals. Therefore, the probe profile describes the weekly pattern of the probe data, as Figure 12 shown in.

[0340] Figure 12 shows the number of probes for a road section varying with time index t k , said time index t k counts the number of time intervals for each day of a day and each day of a week. The profile shows the number of probes X(s r , t k ) where 0≤k<Z, where Z is the number of time intervals in a week. Since the traffic information server receives probe data for all road sections s r and s i , it can generate the probe profile P(s) for all these road sections.

[0341] P(s)=X(s,t k mod Z ), wherein s∈{s r |r=0…N}∪{s i |i=1…M}

[0342] (Equation 5)

[0343] Equation 5 shows that there are Z elements in the probe profile. For the map area, there are N+M road segments, and the traffic information server receives probe data thereof. The number of probe counts for each element of the probe profile is an average value over each different week considered when constructing the profile.

[0344] The traffic information server uses the probe profile of road segments to determine a parameter indicating profile similarity. The similarity value is for the road segment s of interest r and all road segments {s with traffic detectors i |i=1…M} that are associated. Road segments provided with traffic detectors may be referred to as "reference road segments". In other words, the probe profile of a road segment not associated with any traffic flow detector is matched with each probe profile (reference probe profile) of a road segment s i with a traffic detector. Said matching in turn drives the estimation of k(s r , t k ).

[0345] Finding the similarity between probe profiles P(s1) and P(s2) is implemented using a non-negative kernel function K(a,b) (not to be confused with the coefficient k(s,t) function), said non-negative kernel function K(a,b) accepts two vector arguments and outputs a single real number within the range (0…1] or 0<K(a,b)≤1. The kernel function produces a result of 1 if and only if a=b (identical vectors), otherwise it returns a value within the range (0…1]. The kernel function K(P(s1),P(s2)) maps the similarity between two probe profiles P(s1) and P(s2) to a real-valued function result. The profile P(s j ) is a vector with dimension Z: Z: P(s j ) = [X(s j , t0), X(s j , t1), …, X(s j , t Z ).

[0346] As an example, the kernel function may be a radial basis function, that is, Specifically, the kernel function is a radial basis function kernel: wherein

[0347] in Figure 13 the similarity between profiles and the method by which the similarity parameter can be determined are shown.

[0348] Figure 13This section shows the similarity between the leftmost detector profile (which may be associated with the segment of interest) and the four (reference) detector profiles on the right. The leftmost detector profile shows a significant peak near the end of the day (indicating evening traffic congestion). Similarity parameters are used to obtain similarity indices between the detector profile associated with the segment of interest and each reference profile. These similarity parameters are within a range of 0.3 to 0.9, from a maximum range of 0 to 1. In other words, the parameters are normalized.

[0349] Road segment s r The detector profile similarity between the detector profile and the reference detector profile from group L (representing the road segment associated with the traffic flow detector) is used to estimate the road segment s. r The coefficient k(s) r ,t k ).

[0350]

[0351] Equation 6 demonstrates the use of the similarity measure K(P(s)) i ),P(s r and weighting coefficient α i k(s) i ,t k The weighted contribution of the coefficient (see Equation 3).

[0352] The weighting factor is based on the ground-based real-time data Y(s) i ,t k That is, road segment s i The linear regression model was obtained by training the measured traffic data. Advantageously (although by way of illustration rather than limitation), the L2 penalized ridge regression model is used for the regression function Q(α):

[0353]

[0354]

[0355] In Equation 7, the constant C is associated with the regularization term found through cross-validation. The regression model uses the standard quadratic loss function l(x,y)=||xy|| 2 .

[0356] The above describes how a traffic information server receives data X(s,t) from its detectors. k A set of traffic volume estimates Y(s,t) is generated for road segments s in the map region. k An example of α). Equation 4 describes the received detector data X(s,t) of road segment s. k Traffic volume estimation Y(s,t) k ;α) through coefficient k(s,t)k (Connect them)

[0357] Equations 4 and 6 yield the following coefficient equations.

[0358]

[0359] Equations 8 and 6 use Y(s,t) k ;α)=k(s,t k ;α)X(s,t k This means that the process for determining α can also be linked to the coefficient k(s,t). k ;α) to formulate.

[0360] Figure 14 This is a functional diagram illustrating a system for implementing the generation of a set of scaling factors according to the embodiments described herein.

[0361] Now refer to Figure 15 A preferred embodiment of a method for obtaining time-dependent scaling factors using this system is described below.

[0362] Figure 14 The system displays the detector data and traffic detector data received by the traffic information server.

[0363] In step 1, the traffic information server selects a group of road segments s in map area A, and the traffic information server receives detector data for the road segments. Figure 14 (600 in the map). These road segments can be segments within the area of ​​interest of a given map. In step 3, the server identifies a subset L of road segments from group S where traffic detector data is also available, and a subset M of road segments where only detector data is available (similar to the earlier description above). The detector data and traffic detector data of the segments in subset L are... Figure 14 These are labeled 610 and 620. Related detector and traffic detector data can be stored in the corresponding database.

[0364] In step 5, the traffic information server determines detector profiles describing detector data for each road segment in group S (using detector profile builder module 630) and each road segment in group L (using detector profile builder module 640) at a one-week time interval. In step 7, the traffic server compares the detector profiles of the road segments from S with the detector profiles of all road segments in group L (using profile similarity comparison module 650) and stores the results in the similarity parameter module (660) – step 9.

[0365] In step 11, the traffic volume estimation module 670 of the traffic information server uses the similarity parameters of road segments in L and has α (with a value α)i The N-dimensional vector of S is used to obtain traffic volume estimates for road segments in L. Regression analysis module 680 compares the traffic volume estimates with observed traffic volume data for all road segments in L and updates the weighted vector α (where the weights are stored in weighting module 690). When an optimal match is found, the final weighted vector from module 690 and similarity parameters from module 660 are used to generate a set of coefficients k for each road segment in S, where the coefficients k describe the value that converts the received detector counts into the estimated traffic volume for each time interval in the detector profile.

[0366] This method can be performed on any segment of interest from S, but it is particularly useful when obtaining estimated traffic volumes for any segment for which traffic detector data is not available (i.e., the portion forming subset M). Traffic detector data from subset L is used to validate the accuracy of the estimation function in the linear regression module. Based on Equation 8 above, it can be seen that the estimated scale factor of the segment of interest (for which traffic detector data is not available) in the interest time interval forming subset M will be based on the similarity of the detector profile of the segment of interest to the reference detector profile associated with each of the multiple reference segments (for which traffic detector data is available) corresponding to the segment of subset L. The estimated scale factor is also based on the reference scale factor of each of the reference segments, based on the count of crossings of the segment according to detector data and measured traffic count data, i.e., the measured count divided by the detector count in a given interest time interval (Equation 4). The weights assigned to each of these reference scale factors are determined using a linear regression model trained with measured traffic detector data associated with the segments in subset L.

[0367] refer to Figure 16 The experiment in which the group of road segments L is divided into two subsets of map regions (the first subset is used to generate traffic volume estimates and the second subset is used to verify the accuracy of the estimation function) has the following characteristics: Figure 16 The accuracy shown in the figure.

[0368] The figure shows the distribution of previous results (baselines 1 and 2) and the estimation method using detector contour matching and weighted vector estimation (neighborhood). The quantity estimation has a median relative prediction error (MRE) of 5.78% (compared to the corresponding baseline 1). Figure 1 ) and baseline 2 ( Figure 11 (Compared to 12.9% and 10.5% of MRE).

[0369] As mentioned above, in order to further improve accuracy, it is expected that the scaling factor is also position-dependent, that is, it depends on the position of the segment.

[0370] This method can be performed as follows. As mentioned above, the following terminology should be used;

[0371] ·S is a set of road segments s in map area A

[0372] ·L={s i |0≤i<N} is a set of road segments s in map area A for which traffic information is available i . Each road segment s i is associated with a traffic flow detector

[0373] ·M={s r |0≤i<R} is a set of road segments s in map area A that are not associated with any traffic flow detector r .

[0374] ·k(s,t k ) is an estimated coefficient depending on the position of s and the time index t k .

[0375] In this further embodiment, the difference is that the estimated proportional coefficient (function) uses the reference proportional coefficient (obtained by using measured traffic detector data of reference segments for which relevant data is available) in different ways.

[0376]

[0377] In the above equation, the kernel function of equation (8) is replaced by an attenuation function, which represents the contribution of the reference (measured) proportional coefficient that decreases as the distance between the reference road segment and the road segment whose estimated coefficient is to be determined decreases. The weighting value α i adjusts the estimated coefficient to the average coefficient of map area A.

[0378] Therefore, instead of considering the similarity between the detector profile of the segment and the reference segment and using a linear regression training model to refine the weighting of the reference proportional coefficient calculated for segments with traffic detector data, in these embodiments, the proportional coefficient of the segment of interest is based on the reference proportional coefficients of reference segments, wherein the reference segments are segments with measured traffic data available, and weights are assigned to different reference proportional coefficients depending on the distance between the reference segment and the segment of interest.

[0379] This method extends the difference between the measured reference proportional coefficient and the average coefficient within several nearby road segments.

[0380] The distance function can be based on any suitable distance metric, such as Euclidean distance measured between (start / end / mid) points of road segments, (shortest, fastest) routing distance between these points, or distance depending on road grade. The distance function can be any function that attenuates to the contribution value of the average coefficient.

[0381] In this example, the obtained scaling factor of the segment of interest is additionally time-dependent, where the reference scaling factor and therefore the scaling factor of the segment of interest are relative to a given time interval. However, it is conceivable that the obtained scaling factor could alternatively be only position-dependent.

[0382] This embodiment can be combined with earlier embodiments, for example, to take into account the similarity between detector profiles of other segments, or to use a linear regression model based on measured (reference) scale factor data.

[0383] More specifically, Equation 9 introduces the decay function D(s) i ,s r ), used to calculate the reference (measured) scaling factor k(s) based on measured data and a normalized value α. i ,t k Estimate the proportionality coefficient k(s) r ,t k (α). The attenuation function is designed to extend the reference scale coefficient to a specific map area (e.g., a location within a specific range). At longer distances, the attenuation function result should closely approximate the average value of the reference scale coefficient (based on measured data).

[0384] exist Figure 17 The example shown is a decay function.

[0385] The diagram shows two reference segments. i and s i+1 The figure shows the reference scale coefficients and the map locations associated with these reference segments. For clarity, the map locations are presented as one-dimensional maps, for example, based on the distance between two reference segments. The figure also shows the coefficients k(s,t) for these map locations. k ) and in all reference segments s i The average coefficient k within av (or time dependence coefficient k) av (t k For the two reference locations, the figure also shows the calculation of road segment s in Equation 8. r The coefficient k(s) r ,t k The instance decay function of α). In the figure, road segment s r In s i and s i+1 Nearby, therefore, reference coefficients from these reference segments are propagated to segment s using a decay function. r .

[0386] The attenuation function in Equation 8 is combined with the reference scaling coefficients to obtain the estimated scaling coefficients for the road segment. For locations far from the reference road segment, the contribution of all reference scaling coefficients should be close to the average value k of the reference scaling coefficients. av .

[0387] The propagation model described in Equation 8 contains a vector of scaling values ​​for the propagation. For example, scaling can adjust the propagation to ensure that all road segments s in map region A are included. r The average value on the above is close to that of all reference road segments s i The average scaling factor. The decay function in the graph is merely an example. For example, other forms of decay functions can be used, such as exponential decay, stepwise decay, hyperbolic decay, or inverse distance weighted functions. The decay should preferably occur over a relatively short range.

[0388] exist Figure 18 The two-dimensional results of the covered map area are displayed in the middle.

[0389] refer to Figure 18 Such embodiments are shown in more detail. Figure 18 The map displays a region containing road segments (light gray) and traffic volume detectors (black dots). The map also shows the k(s) function for the map region. It displays the measured k values ​​for the distributed reference road segments (i.e., the road segments associated with the traffic volume detectors). The map presents the k(s) function as a "heatmap" overlay of the map region. In practice, the k(s) scaling factor is determined based on the location associated with each road segment in the map region. For example, the location could be the start, end, or center point of the road segment. Then, the k(s) value at that location on the road segment is associated with the entire road segment.

[0390] Figure 18 The heatmap description is derived from the estimated coefficients k(s), which are determined using a decay function. The k(s) coefficients can also be obtained using a detector profile similarity method. In both methods, the estimated coefficients can also depend on time or the time index t. k Thus, the estimated coefficients k(s,t) and k(s,t) are obtained respectively. k Methods for determining estimated coefficients that vary with (map) location typically involve determining a weighted value α used to scale the contribution of the estimated coefficients.

[0391] According to the present invention, in various embodiments, electronic map data comprising reference segments (segments available from measurement count data) and "non-reference" segments unavailable from measurement count data can be provided. Each "reference segment" (i.e., a segment available from measurement count data) is associated with data indicating a reference scale factor for a given time of interest. Each reference segment may be associated with a reference scale factor profile representing the change of the reference scale factor with respect to time, from which the scale factor for a given time can be obtained.

[0392] The reference ratio can be based on the ratio of measured traffic counts to detector counts over a period of time or several periods.

[0393] The reference scale factor for a reference segment can be based at least in part on real-time data. For example, this might be particularly useful when an estimated scale factor for a non-reference segment is needed for the current time. Alternatively or additionally, the reference scale factor (or scale factor profile) can be based on historical data, such as historical detector profiles. This might be useful when the time of interest requiring the estimated scale factor is past or future, but also applicable to the current time.

[0394] Each non-reference segment may be associated with one or more reference segments. These reference segments are a subset of reference segments in the area under consideration by the electronic map, which have been determined to be relevant to obtaining traffic volume data for a given non-reference segment. In other embodiments where no association exists in the map data, the method can be extended to determine several associated reference segments for a given segment.

[0395] A subset of reference segments associated with a given non-reference segment can be determined as desired. For example, associated reference segments can be determined by comparing the temporally dependent (e.g., weekly) detector profiles of the segment with the corresponding detector profiles of the reference segments. The subset of reference segments can be selected based on the similarity between their detector profiles and the detector profiles of the non-reference segments. For example, the most similar reference segments can be selected, or a similarity value can be assigned to each reference segment, where those reference segments with similarity values ​​higher than a predetermined value or a predefined number of most similar reference segments are selected, etc.

[0396] The selection of reference segments included in the subset can be, alternatively or additionally, based on the proximity of the reference segments to the non-reference segments for which traffic volume data is required. Proximity can be spatial or temporal, such as straight-line distance in terms of travel time or spatial distance, or distance through the navigable network between reference and non-reference segments. For example, only a few reference segments within a predetermined distance or travel time can be considered, or only a predefined number of nearest reference segments can be used.

[0397] Alternatively or otherwise, selection may be based on the similarity of the properties of the reference and non-reference segments (e.g., considering functional road class).

[0398] Any of these techniques can be used alone or in any combination and can enable the identification of one or more reference segments associated with the non-reference segment of interest. This helps to obtain a more accurate estimated scale factor for the non-reference segment associated with the segment.

[0399] This step of identifying a subset of reference segments, which may be a single reference segment or multiple reference segments, can be performed prior to the previously described step of determining the estimated scale coefficients based on multiple reference scale coefficients. Therefore, the determination of the estimated scale coefficients may be based on multiple reference scale coefficients and may involve weighted contributions from multiple reference scale coefficients, such as based on the similarity of the detector profile and / or the proximity of associated reference segments to non-reference segments and / or any other criteria, as described above.

[0400] In a broader sense, it will be understood that the present invention can use reference scale factors associated with one or more reference segments in which absolute vehicle count data does exist to determine traffic volume in segments where such absolute vehicle count data does not exist (at least at a given time of interest).

[0401] Those skilled in the art will understand that the apparatus provided to perform the methods described herein may include hardware, software, firmware, or any combination of two or more of these.

[0402] Those skilled in the art will understand that while the term GPS data is used to refer to positioning data derived from the GPS Global Positioning System, other positioning data can be processed in a similar manner to the methods described herein. Therefore, the term GPS data can be replaced by the phrase positioning data.

[0403] All features disclosed in this specification and / or all steps of any method or process so disclosed may be combined in any combination, except for at least some mutually exclusive combinations of such features and / or steps.

[0404] Each feature disclosed in this specification may be replaced by an alternative feature for the same, equivalent, or similar purpose, unless otherwise expressly stated. Therefore, unless otherwise expressly stated, each disclosed feature is merely one instance of a general series of equivalent or similar features.

[0405] This invention is not limited to the details of any of the foregoing embodiments. The invention extends to any novel version or combination of features disclosed in this specification, or any novel version or combination of steps of any method or process so disclosed. The claims should not be construed as covering only the foregoing embodiments, but also as covering any embodiments falling within the scope of the claims.

Claims

1. A method for estimating traffic volume over a given time for a given segment of an electronic map representing a navigable network in an area, the electronic map comprising a plurality of segments representing navigable elements of the navigable network in the area, wherein the navigable network in the area includes navigable segments associated with at least one traffic detector and navigable segments not associated with any traffic detector, and wherein the given segment is a segment representing at least a portion of the navigable segments of the navigable network in the area that is not associated with any traffic detector, wherein the electronic map further comprises a plurality of reference segments, each reference segment being a segment representing at least a portion of the navigable segments of the navigable network in the area that is associated with a traffic detector, and Each reference segment is associated with data indicating a corresponding reference scale factor for the given time, the reference scale factor being based on a measured count of vehicles traversing at least a portion of the segment represented by the reference segment at the given time and a count of devices associated with the vehicles traversing at least a portion of the segment represented by the reference segment at the given time, the measured count of vehicles being based on data measured by at least one traffic detector associated with the segment, and the count of devices associated with vehicles being based on position data and associated timing data related to the movement of multiple devices along at least a portion of the segment represented by the reference segment, the method comprising: Traffic volume for a given segment at a given time is estimated using data indicating the count of devices associated with vehicles traversing at least a portion of the navigable network represented by the given segment at the given time, and an estimated scaling factor for the given segment at the given time, wherein the estimated scaling factor for the segment is based on a reference scaling factor associated with each of one or more reference segments of the electronic map associated with the given segment, and wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices along at least a portion of the navigable segment represented by the given segment relative to time, wherein the estimated scaling factor is a time-dependent scaling factor. and Generate data indicating the estimated traffic volume for the given time period.

2. The method of claim 1, wherein the reference scaling factor associated with each reference segment for the given time is based on the ratio of the measured count for the given time based on the traffic detector data to the count of the device for the given time based on the location and associated timing data.

3. The method of claim 1 or 2, wherein each reference segment is associated with data indicating a time-dependent reference scale factor profile, wherein the reference scale factor profile indicates the change of the reference scale factor of the reference segment relative to time.

4. The method of claim 3, wherein the reference scaling factor profile is at least partially based on a detector profile indicating, for example, the change in the count of devices associated with a vehicle traversing the at least portion of the navigable segment represented by the reference segment, as determined by location data and associated timing data related to the movement of multiple devices associated with the vehicle along the at least portion of the navigable segment represented by the reference segment, relative to time.

5. The method according to claim 1 or 2, wherein the given time is the current time, and the reference scaling factor is at least partially based on real-time data.

6. The method of claim 1 or 2, wherein for each segment that is not a reference segment, the electronic map further includes data indicating the subset of one or more reference segments associated with said segment.

7. The method of claim 1 or 2, further comprising determining a subset of one or more of the reference segments associated with the given segment.

8. The method of claim 7, further comprising storing the determined subset indicating one or more reference segments together with data of the associated segments in the electronic map.

9. The method of claim 7, wherein the subset of one or more reference segments is determined at least in part based on a comparison of a detector profile associated with the given segment and reference detector profiles associated with some of the reference segments, wherein the detector profiles indicate, for example, changes in the count of devices associated with vehicles traversing the at least portion of the navigable segment represented by the given segment, as determined based on location data and associated timing data related to the movement of multiple devices associated with vehicles along the at least portion of the navigable segment represented by the segment, and wherein the reference detector profiles indicate, for example, changes in the count of devices associated with vehicles traversing the at least portion of the navigable segment represented by the reference segment, as determined based on location data and associated timing data related to the movement of multiple devices associated with vehicles along the at least portion of the navigable segment represented by the reference segment, as determined based on the reference detector profiles.

10. The method of claim 9, wherein the subset of one or more reference segments includes one or more reference segments having a reference detector profile determined to be most similar to the detector profile of the given segment.

11. The method of claim 7, wherein the subset of one or more reference segments is determined at least in part based on the proximity of the reference segments to the given segments.

12. The method of claim 7, wherein the subset of one or more reference segments is determined at least in part based on the similarity of the properties of the reference segments to the given segments.

13. The method of claim 12, wherein the property includes Functional Road Class (FRC).

14. The method of claim 1 or 2, wherein the estimated scale factor of the given segment is estimated using data indicating the similarity between a detector profile associated with the given segment and each of one or more reference detector profiles in a set of one or more reference segments, each reference detector profile being associated with a corresponding one of the one or more reference segments, the reference scale factor of the corresponding one being used to determine the estimated scale factor, wherein the detector profile indicates, as determined based on location data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the segment, a change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the given segment relative to time, and wherein the reference detector profile indicates, as determined based on location data and associated timing data related to the movement of multiple devices associated with vehicles along at least a portion of the navigable segment represented by the reference segment, a change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the reference segment, a change in the count of devices associated with vehicles traversing at least a portion of the navigable segment represented by the reference segment.

15. The method of claim 14, wherein the estimated scaling factor of the given segment is based on a plurality of the reference scaling factors, and the contribution of the given reference scaling factor to the estimated scaling factor of the given segment is based at least in part on the similarity between the reference detector profile associated with the reference segment associated with the reference scaling factor and the detector profile associated with the given segment.

16. The method of claim 1 or 2, wherein the estimated scaling factor of the given segment is based on a plurality of the reference scaling factors, and the contribution of each reference scaling factor to the estimated scaling factor is at least in part based on the proximity of the reference segment and the given segment associated with the reference scaling factor.

17. The method of claim 16, wherein a larger weight is assigned to a reference scaling factor associated with a reference segment that is closer to the given segment.

18. The method of claim 1 or 2, wherein the estimated scaling factor is a weighted sum of a plurality of reference scaling factors.

19. The method of claim 18, wherein a linear regression model is used to obtain data indicating a set of weighted values ​​for obtaining the weighted sum of the plurality of reference scaling coefficients.

20. The method of claim 19, wherein the linear regression training model uses data indicating, as determined by data measured by the at least one traffic detector associated with the navigable segment represented by the reference segment, a measured count of vehicles traversing the at least portion of the navigable segment at the given time.

21. The method of claim 1 or 2, further comprising receiving data indicating a given segment requiring traffic volume data and data indicating a time of interest, and using the data indicating the time of interest to identify the given time.

22. The method according to claim 1 or 2, wherein the given time is the current time or a future time.

23. The method according to claim 1 or 2, wherein the given time is a time interval.

24. The method of claim 23, wherein the given time is a cyclic time interval.

25. The method of claim 24, wherein the cyclic time interval is a time interval for a given day in a week.

26. The method of claim 1 or 2, further comprising associating data indicating the estimated traffic volume with data indicating the given segment associated with the estimated traffic volume.

27. The method of claim 26, further comprising transmitting to a user data indicating the obtained estimated traffic volume for the given segment and / or displaying data indicating the obtained estimated traffic volume for the given segment.

28. The method according to claim 1 or 2, further comprising storing the estimated traffic volume and / or traffic density for subsequent display, and / or including displaying the estimated traffic volume and / or traffic density to a user.

29. A system for estimating traffic volume over a given time for a given segment of an electronic map representing a navigable network in an area, the electronic map comprising a plurality of segments representing navigable elements of the navigable network in the area, wherein the navigable network in the area includes navigable segments associated with at least one traffic detector and navigable segments not associated with any traffic detector, and wherein the given segment is a segment representing at least a portion of the navigable segments of the navigable network in the area that is not associated with any traffic detector, wherein the electronic map further comprises a plurality of reference segments, each reference segment being a segment representing at least a portion of the navigable segments of the navigable network in the area that is associated with a traffic detector, and wherein each reference segment is associated with a traffic detector. The system is associated with data representing a corresponding reference scale factor for a given time, the reference scale factor being based on measured counts of vehicles traversing at least a portion of the segment represented by the reference segment at the given time and counts of devices associated with the vehicles traversing at least a portion of the segment represented by the reference segment at the given time. The measured counts of vehicles are based on data measured by at least one traffic detector associated with the segment, and the counts of devices associated with vehicles are based on location data and associated timing data related to the movement of multiple devices along at least a portion of the segment represented by the reference segment. The system includes a group of one or more processors configured to: Traffic volume for a given segment at a given time is estimated using data indicating the count of devices associated with vehicles traversing at least a portion of the navigable network represented by the given segment at the given time, and an estimated scaling factor for the given segment at the given time, wherein the estimated scaling factor for the segment is based on a reference scaling factor associated with each of one or more reference segments of the electronic map associated with the given segment, and wherein the count of devices is based on location data and associated timing data related to the movement of multiple devices along at least a portion of the navigable segment represented by the given segment relative to time, wherein the estimated scaling factor is a time-dependent scaling factor; and Generate data indicating the estimated traffic volume for the given time period.

30. A computer program product comprising instructions that, when read by a computing device, cause the computing device to operate according to the method of any one of claims 1 to 28.

31. The computer program product of claim 30, wherein the computer program product is stored on a non-transitory computer-readable medium.

Images