A vehicle quantity determination method, device, apparatus and storage medium

Abstract

Embodiments of the present application disclose a vehicle quantity determination method and device, equipment and a storage medium, relating to the technical field of vehicle control, comprising: analyzing wireless signals broadcast by multiple signal sources in a preset road area in a preset period, determining signal identifiers and signal names of the corresponding signal sources, and determining signal strength sequences and passing times of each signal source in the preset period; using a device category classification model to classify each signal source based on the signal name, obtaining the device category of the corresponding signal source; using a motion classification model to classify the motion attribute of the signal source based on the signal identifier, signal name, device category, signal strength sequence and passing time of each signal source, obtaining the motion classification result of the corresponding signal source; determining the number of moving vehicles in the preset road area in the preset period based on the motion classification result of each signal source and reporting the number of moving vehicles to the traffic management system, improving the accuracy of the number of vehicles and reducing the cost.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a method, apparatus, device and storage medium for determining the number of vehicles. Background Technology

[0002] Currently, traffic management systems rely on two methods to determine the number of moving vehicles on a road: First, by connecting vehicles to the network and remotely uploading vehicle data, such as vehicles uploading their location and status information to a cloud platform via cellular networks, and then the traffic management system obtaining the vehicle data from the cloud platform to determine the number of moving vehicles on a specific road within a specific time period; Second, by using fixed facilities (such as inductive loop detectors or cameras) for perception and identification to determine the number of moving vehicles on a specific road within a specific time period.

[0003] However, some vehicles are not connected to the network or have an unstable connection, resulting in incomplete or delayed data uploads. This makes it impossible to accurately count the actual number of vehicles in motion, and the cost of deploying fixed facilities is high. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for determining the number of vehicles, thereby solving the problems of low accuracy and high cost in determining the number of vehicles in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for determining the number of vehicles, the method comprising:

[0006] Monitor wireless signals broadcast by multiple signal sources in a preset road area within a preset period;

[0007] The wireless signal of each signal source is analyzed to determine the signal identifier and signal name of the corresponding signal source, and the signal strength sequence and passage time of each signal source within a preset period are determined.

[0008] Using a device category classification model, the device category of each signal source is classified based on its signal name, thus obtaining the device category of the corresponding signal source;

[0009] Using a motion classification model, the motion attributes of each signal source are classified based on its signal identifier, signal name, device category, signal strength sequence, and transit time, thus obtaining the motion classification results for the corresponding signal source.

[0010] Based on the motion classification results of each signal source, determine the number of moving vehicles in the preset road area within the preset period, and report the number of moving vehicles in the preset road area within the preset period to the traffic management system.

[0011] In this embodiment, by parsing the wireless signals broadcast by multiple signal sources in a preset road area within a preset period, the signal identifier, signal name, signal strength sequence, and passage time of the corresponding signal source are obtained. Then, a device category classification model is used to determine the device category of the corresponding signal source based on the signal name of each signal source, i.e., vehicle and non-vehicle. A motion classification model is used to determine the motion classification result of the corresponding signal source based on the signal identifier, signal name, device category, signal strength sequence, and passage time of each signal source, i.e., moving vehicle and non-moving vehicle. Based on the classification performance of the device category classification model and the motion classification model, the motion classification result of each signal source can be accurately determined. Then, the number of signal sources whose motion classification result is moving vehicle is further counted, which improves the accuracy of determining the number of moving vehicles in the preset road area within a preset period. Moreover, the signal sources can broadcast wireless signals without being connected to the network, i.e., the number of moving vehicles can be counted without the vehicles being connected to the network. This solves the problem in the prior art that the actual number of moving vehicles cannot be accurately counted because some vehicles are not connected to the network or cannot be stably connected to the network. Thus, it provides the traffic management system with an accurate number of moving vehicles, which helps the traffic management department in its traffic management work. At the same time, it eliminates the need to install fixed facilities (such as inductive loop detectors or cameras), reducing costs.

[0012] Secondly, embodiments of this application provide a vehicle quantity determination device, the device comprising:

[0013] The monitoring module is used to monitor wireless signals broadcast by multiple signal sources in a preset road area within a preset period;

[0014] The first determining module is used to analyze the wireless signal of each signal source, determine the signal identifier and signal name of the corresponding signal source, and determine the signal strength sequence and passage time of each signal source within a preset period.

[0015] The first classification module is used to classify the device category of each signal source based on the signal name using a device category classification model, thereby obtaining the device category of the corresponding signal source.

[0016] The second classification module is used to classify the motion attributes of each signal source based on the signal identifier, signal name, device category, signal strength sequence and passage time using a motion classification model, and obtain the motion classification result of the corresponding signal source.

[0017] The second determining module is used to determine the number of moving vehicles in the preset road area within the preset period based on the motion classification results of each signal source, and to report the number of moving vehicles in the preset road area within the preset period to the traffic management system.

[0018] Thirdly, embodiments of this application provide an electronic device, which includes:

[0019] At least one processor; and a memory communicatively connected to the at least one processor;

[0020] The memory stores a computer program that can be executed by at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the vehicle quantity determination method of any embodiment of this application.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle quantity determination method as described in any embodiment of this application.

[0022] The descriptions of the second, third, and fourth aspects in this application can be referenced to the detailed description of the first aspect; and the beneficial effects described in the second, third, and fourth aspects can be referenced to the analysis of the beneficial effects in the first aspect, which will not be repeated here.

[0023] In this application, the name of the aforementioned vehicle quantity determining device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0024] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart illustrating a method for determining the number of vehicles provided in an embodiment of this application;

[0027] Figure 2 This is another flowchart illustrating the method for determining the number of vehicles provided in this application embodiment;

[0028] Figure 3 This is a schematic diagram of a vehicle quantity determination device provided in an embodiment of this application;

[0029] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0031] It should be noted that the terms "first," "second," "target," and "original," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in sequences other than those illustrated or described herein. Furthermore, the terms "comprising," "having," and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Figure 1 This is a flowchart illustrating a vehicle quantity determination method provided in this application embodiment. This embodiment can be applied to scenarios requiring the detection of the number of moving vehicles on a specific road within a specific time period. The vehicle quantity determination method provided in this embodiment can be executed by a vehicle quantity determination device provided in this application embodiment. This device can be implemented through software and / or hardware. In a specific embodiment, the vehicle quantity determination device can be integrated into an electronic device, which can be a roadside detection device or an on-board device in a stationary vehicle used by traffic management departments to detect the number of moving vehicles, such as a computer. The executing entity of this method can be an electronic device. See also... Figure 1 The method for determining the number of vehicles in this embodiment includes, but is not limited to, the following steps:

[0033] S110: Monitor wireless signals broadcast by multiple signal sources in a preset road area within a preset period.

[0034] The preset period is a pre-set duration of data used to represent the time range within which the number of moving vehicles in a preset road area is counted. The preset road area is a pre-set monitoring area, which is the physical space covering the road and its surrounding area centered on the location of the electronic device. Furthermore, the electronic device can listen to the wireless signals broadcast by all signal sources within the preset road area.

[0035] The signal source is a device capable of emitting wireless signals in a preset road area; for example, the signal source includes vehicle-mounted equipment, roadside infrastructure (such as intelligent traffic lights and charging piles), mobile terminals carried by pedestrians (such as smartphones, computers and Bluetooth speakers), and shared bicycles, etc., wherein the vehicle-mounted equipment includes vehicle-mounted WIFI modules and / or vehicle-mounted Bluetooth modules.

[0036] Wireless signals are information carriers that transmit through space via electromagnetic waves. They do not require physical cable connections and can be interpreted as data by wireless receiving devices. Optionally, wireless signals may include mid-range and / or short-range wireless signals. Mid-range wireless signals may include Bluetooth and Wi-Fi signals, while short-range wireless signals may include infrared and near-field communication signals.

[0037] Specifically, within a preset period, wireless signals emitted by multiple signal sources in a preset road area can be monitored at a preset sampling frequency. These signals include, for example, WIFI or Bluetooth signals emitted by vehicle-mounted equipment, Bluetooth or near-field communication signals emitted by mobile terminals, and WIFI, Bluetooth, or dedicated short-range communication signals emitted by roadside infrastructure.

[0038] S120. Analyze the wireless signal of each signal source, determine the signal identifier and signal name of the corresponding signal source, and determine the signal strength sequence and passage time of each signal source within a preset period.

[0039] The signal identifier is a specific identifier used to uniquely distinguish different signal sources; optionally, the signal identifier can be the physical address of the signal source. The signal name is the name of the signal source, which can be a user-defined name or the default name of the signal source at the factory. The default name includes the brand and model of the signal source; for example, the signal name can be the vehicle's Wi-Fi name, vehicle's Bluetooth name, or mobile phone's Bluetooth name, etc.

[0040] The signal strength sequence is an ordered combination of wireless signal strength values ​​from a specific signal source detected within a preset period, arranged chronologically. Each signal source corresponds to one signal strength sequence. The transit time is the duration from when the wireless signal from the signal source is detected to when it becomes undetectable within the preset period; that is, the duration from when the signal source enters the preset road area to when it leaves the preset road area.

[0041] Specifically, after detecting wireless signals from multiple signal sources, the detected wireless signals can be analyzed to extract the physical address field and the name field. The extracted physical address field is used as the signal identifier of the corresponding wireless signal, and the extracted name field is used as the signal name of the corresponding wireless signal. Since multiple wireless signals emitted by the same signal source have the same signal identifier and signal name, and multiple wireless signals emitted by different signal sources have different signal identifiers, multiple wireless signals can be classified based on the signal identifier to determine the signal source to which each wireless signal belongs. This allows us to determine the wireless signal corresponding to each signal source, as well as the signal identifier and signal name of each signal source. For example, for a WIFI signal, the Basic Service Set Identifier (BSSID) in the WIFI signal can be used as the signal identifier, and the Service Set Identifier (SSID) in the WIFI signal can be used as the signal name. In this embodiment, the BSSID is regarded as the physical address of the WIFI signal source. For a Bluetooth signal, the Bluetooth Device Address (BD_ADDR) in the Bluetooth signal can be used as the signal identifier. In this embodiment, BD_ADDR is regarded as the physical address of the Bluetooth signal source.

[0042] Then, for the current signal source among multiple signal sources, the signal strength of multiple wireless signals of the current signal source can be detected to obtain the signal strength of the corresponding wireless signal. The signal strengths of the multiple wireless signals of the current signal source are then combined in chronological order to obtain a signal strength sequence. That is, the signal strengths in the signal strength sequence are ordered in chronological order, which is the order in which the electronic device detects the wireless signals. Next, the time when the wireless signal of the current signal source is first detected within a preset period can be determined and recorded as the start time of the current signal source entering the preset road area. The time when the wireless signal of the current signal source is last detected within the preset period can be determined and recorded as the end time of the current signal source leaving the preset road area. Then, the difference between the end time and the start time is calculated and this difference is determined as the transit time of the current signal source within the preset period.

[0043] S130. Using the equipment category classification model, classify the equipment category of each signal source based on the signal name of each signal source to obtain the corresponding equipment category of the signal source.

[0044] The equipment category classification model is a pre-trained neural network model that captures the relationship between signal names and equipment categories. It is used to classify the equipment category of a signal source based on its signal name. The equipment category is the result of the equipment category classification model classifying the equipment category of the signal source, including vehicles and non-vehicles.

[0045] Specifically, after obtaining the signal name of each signal source, for the current signal source among multiple signal sources, the signal name of the current signal source can be input into the pre-trained device category classification model. At this time, the device category classification model uses the learned model parameters to analyze the signal name and outputs the device category corresponding to the signal name, that is, the device category corresponding to the current signal source, so that the device category of the signal source in the vehicle (i.e., vehicle-mounted equipment) is vehicle, and the device category of the signal source in the non-vehicle (such as roadside infrastructure and mobile terminals) is non-vehicle.

[0046] S140. Using a motion classification model, based on the signal identifier, signal name, device category, signal strength sequence, and transit time of each signal source, the motion attributes of the signal source are classified to obtain the motion classification result of the corresponding signal source.

[0047] The motion classification model is a pre-trained neural network model that captures the relationship between the attribute information and motion attributes of the signal source, and is used to classify the motion attributes of the signal source. The motion classification result is the classification result obtained by the motion classification model on the motion attributes of the signal source, including moving vehicles and non-moving vehicles.

[0048] Specifically, since users may customize the signal name of the signal source, the device category classification model may not be able to accurately distinguish the device category of the signal source based on the customized signal name, which may lead to misclassification of the device category classification model. Therefore, it is necessary to use a motion classification model to further distinguish the device category and motion attributes of the signal source based on the multi-dimensional information of the signal source. That is, after obtaining the device category of each signal source, for the current signal source among multiple signal sources, the signal identifier, signal name, device category, signal strength sequence and passage time of the current signal source can be input into the pre-trained motion classification model. At this time, the motion classification model uses the learned model parameters to analyze the signal identifier, signal name, device category, signal strength sequence and passage time, and outputs the motion classification result corresponding to the current signal source, so that the motion classification result of the signal source in the moving vehicle (i.e., the moving vehicle-mounted device) is the moving vehicle, and the motion classification result of the signal source in the stationary vehicle and the signal source in the non-vehicle (such as stationary roadside infrastructure, stationary mobile terminal and moving mobile terminal, etc.) is the non-moving vehicle.

[0049] S150. Based on the motion classification results of each signal source, determine the number of moving vehicles in the preset road area within the preset period, and report the number of moving vehicles in the preset road area within the preset period to the traffic management system.

[0050] Among them, the traffic management system is a complex system that comprehensively controls, coordinates, and optimizes elements such as people, vehicles, and roads in the transportation field, aiming to ensure traffic safety, improve traffic efficiency, and improve the traffic environment.

[0051] Specifically, after obtaining the motion classification result of each signal source, the number of signal sources whose motion classification result is a moving vehicle can be calculated, the number of moving vehicles in the preset road area within the preset period can be obtained, and the number of moving vehicles in the preset road area within the preset period can be reported to the traffic management system so that the traffic management system can accurately count the number of moving vehicles in the preset road area within the preset period.

[0052] The technical solution of this application embodiment analyzes the wireless signals broadcast by multiple signal sources in a preset road area within a preset period to obtain the signal identifier, signal name, signal strength sequence, and passage time of the corresponding signal source. Then, a device category classification model is used to determine the device category of the corresponding signal source based on the signal name of each signal source, i.e., vehicle and non-vehicle. A motion classification model is used to determine the motion classification result of the corresponding signal source based on the signal identifier, signal name, device category, signal strength sequence, and passage time of each signal source, i.e., moving vehicle and non-moving vehicle. Based on the classification performance of the device category classification model and the motion classification model, the motion classification result of each signal source can be accurately determined. Then, the number of signal sources whose motion classification result is moving vehicle is further counted, which improves the accuracy of determining the number of moving vehicles in the preset road area within a preset period. Moreover, the signal sources can broadcast wireless signals without being connected to the network, i.e., the number of moving vehicles can be counted without the vehicles being connected to the network. This solves the problem in the prior art that the actual number of moving vehicles cannot be accurately counted because some vehicles are not connected to the network or cannot be stably connected to the network. Thus, it provides the traffic management system with an accurate number of moving vehicles, which helps the traffic management department in its traffic management work. At the same time, it eliminates the need to install fixed facilities (such as inductive loop detectors or cameras), reducing costs.

[0053] The following further describes a method for determining the number of vehicles provided in an embodiment of this application. Figure 2 This is another flowchart illustrating the vehicle quantity determination method provided in this application embodiment, which is an optimization based on the above embodiments. See also... Figure 2 The method in this embodiment includes, but is not limited to, the following steps:

[0054] S210. Monitor wireless signals broadcast by multiple signal sources in a preset road area within a preset period.

[0055] S220. Analyze the wireless signal of each signal source, determine the signal identifier and signal name of the corresponding signal source, and determine the signal strength sequence and passage time of each signal source within a preset period.

[0056] S230. Using the equipment category classification model, classify the equipment category of each signal source based on the signal name of each signal source to obtain the corresponding equipment category of the signal source.

[0057] Optionally, the training process of the device category classification model is as follows: Signal names of wireless signals from multiple second sample signal sources (such as signal sources in vehicles and non-vehicles) can be collected to obtain second sample signal names from multiple second sample signal sources. These second sample signal names include the brand and model of the signal source. Based on the actual device category of each second sample signal source, a device category label is assigned to the corresponding second sample signal name, i.e., a vehicle label and a non-vehicle label. Then, a second training set is constructed based on the multiple second sample signal names and the device category label for each second sample signal name. The second sample signal names in the second training set are then input into the initial device category classification model. The initial device category classification model is trained using the corresponding device category labels to obtain the device category classification model. The initial device category classification model is a model framework that has not yet been trained and is used to learn the relationship between signal names and device categories, thereby achieving device category classification.

[0058] Specifically, the second sample signal name can be input into the initial device category classification model to obtain the device category training value, and the loss value between the device category training value and the corresponding device category label can be calculated. Then, the backpropagation algorithm is used to train and optimize the initial device category classification model to minimize the loss value, thus obtaining the device category classification model. That is, by using the backpropagation algorithm, the model parameters of the initial device category classification model are updated and adjusted according to the gradient information of the loss function to minimize the loss value, so that the device category classification model can gradually learn the relationship between the signal name and the device category.

[0059] In this embodiment, by collecting the signal names of multiple signal sources and labeling the signal names with device category tags based on the actual device categories of the signal sources, a training set for the device category classification model is constructed. The device category classification model is then trained based on the training set, enabling the device category classification model to accurately learn the relationship between signal names and device categories, thereby improving the classification accuracy of the device category classification model.

[0060] S240. For the current signal source among multiple signal sources, determine the relative distance sequence of the current signal source based on the signal strength sequence of the current signal source.

[0061] The relative distance sequence is an ordered combination of data obtained by combining the relative distances between a specific signal source and an electronic device within a preset period in chronological order.

[0062] Specifically, in one implementation, for the current signal source among multiple signal sources, a preset intensity distance relationship can be queried based on each signal intensity in the signal intensity sequence of the current signal source to obtain the relative distance between the current signal source and the electronic device at the corresponding time node. The preset intensity distance relationship includes the correspondence between signal intensity and relative distance. Then, according to the time sequence, the relative distance between the current signal source and the electronic device at each time node is combined to obtain a relative distance sequence.

[0063] Optionally, in another implementation, the relative distance sequence of the current signal source, including Sa1-Sa2, is determined based on the signal strength sequence of the current signal source:

[0064] Sa1. Analyze multiple wireless signals from the current signal source, determine the arrival time of the corresponding wireless signals, and combine the arrival times of multiple wireless signals in chronological order to obtain a signal arrival time sequence.

[0065] The signal arrival time is the time interval between the timestamp when the signal source emits the wireless signal and the timestamp when the electronic device receives the wireless signal. The signal arrival time sequence is an ordered data combination obtained by combining the signal arrival times of multiple wireless signals from a specific signal source within a preset period in chronological order.

[0066] Specifically, multiple wireless signals from the current signal source can be analyzed to obtain the transmission time of each wireless signal. The time when each wireless signal is detected is recorded as the reception time of each wireless signal. Then, the difference between the reception time and the corresponding transmission time of each wireless signal is calculated to obtain the arrival time of the corresponding wireless signal. That is, one wireless signal corresponds to one arrival time. Since the multiple wireless signals from the current signal source are detected by the electronic device in chronological order, that is, the electronic device detects one wireless signal from the current signal source at a certain time point, that is, each wireless signal corresponds to a time point. Therefore, the arrival times of the multiple wireless signals from the current signal source can be combined in chronological order to obtain the signal arrival time sequence of the current signal source.

[0067] Sa2. Determine the relative distance sequence of the current signal source based on the signal strength sequence and signal arrival time sequence of the current signal source.

[0068] Specifically, the relative distance between the current signal source and the electronic device at the same time point can be determined by jointly considering the signal strength and signal arrival time at the same time point, thereby obtaining a relative distance sequence.

[0069] Furthermore, the signal strength sequence and signal arrival time sequence can be synchronized in chronological order to obtain multiple matching pairs. At this point, the signal strength and arrival time of the same wireless signal are considered matching pairs, meaning the signal strength and arrival time at the same time node are considered matching pairs. In other words, a matching pair includes mutually matching signal strength and arrival times, and one matching pair corresponds to one time node. Next, based on the signal strength and arrival time at the same time node in each matching pair, a preset mapping relationship is queried to obtain the relative distance of the corresponding matching pair. That is, one matching pair corresponds to one relative distance, or one time node corresponds to one relative distance. The preset mapping relationship includes the correspondence between signal strength, signal arrival time, and relative distance. Then, the relative distances of multiple matching pairs are combined in chronological order to obtain a relative distance sequence. Compared to querying a relationship table based on single-dimensional data (i.e., signal strength), querying a preset mapping relationship using multi-dimensional data (i.e., signal strength and signal arrival time) at the same time node can comprehensively consider multi-dimensional information, improving the accuracy of relative distance determination. It also improves computational efficiency, reduces implementation complexity, and thus improves the accuracy and efficiency of determining the relative distance sequence, providing accurate input data for subsequent motion classification models.

[0070] In this embodiment, signal strength and signal arrival time can be comprehensively considered, which enriches the dimensional information when determining relative distance, avoids the accuracy problem caused by determining relative distance based solely on signal strength, and can improve computational efficiency and reduce implementation complexity. This improves the accuracy and efficiency of determining the relative distance sequence, providing accurate input data for subsequent motion classification models.

[0071] S250. Using a motion classification model, based on the signal identifier, signal name, equipment category, transit time, signal strength sequence, and relative distance sequence of the current signal source, classify the motion attributes of the current signal source to obtain the motion classification result of the current signal source.

[0072] Specifically, in one implementation, the signal identifier, signal name, equipment category, passage time, signal strength sequence, and relative distance sequence of the current signal source can be input into a motion classification model. The motion classification model can then combine multi-dimensional information to determine whether the current signal source is a moving vehicle or a non-moving vehicle. For example, the signal identifier includes equipment manufacturer information, thus allowing differentiation between vehicles and non-vehicles (such as roadside infrastructure or mobile terminals); the equipment category can differentiate between moving vehicles and moving non-vehicle equipment, such as slowly moving vehicles and mobile terminals carried by fast-walking pedestrians; the relative distance sequence of moving vehicles has a wider distribution, while the relative distance sequence of non-moving vehicles has a narrower distribution, thus allowing differentiation between moving vehicles and non-moving vehicles (such as stationary roadside infrastructure, stationary mobile terminals, or moving mobile terminals); then, by combining the differentiation results of each dimension, the motion classification result of the current signal source is determined. For example, if the equipment category is non-vehicle, but the differentiation results of other multiple dimensions indicate a moving vehicle, then the differentiation results of the other multiple dimensions shall prevail.

[0073] Alternatively, in another implementation, pattern matching can be performed on the signal strength sequence of the current signal source to determine the signal strength change trend of the current signal source; using a motion classification model, the motion attributes of the current signal source can be classified based on the signal identifier, signal name, device category, passage time, relative distance sequence and signal strength change trend of the current signal source to obtain the motion classification result of the current signal source.

[0074] Specifically, a preset template library can be obtained. That is, multiple signal strength change trend templates for signal sources can be pre-determined based on past experience data, known standard signal strength change patterns, or typical signal strength change patterns summarized from extensive testing of similar signal sources under similar environments. Then, a matching algorithm is selected based on the characteristics of wireless signals and the requirements for matching accuracy, such as Dynamic Time Warping (DTW) algorithm and Hidden Markov Model. Then, the selected matching algorithm is used to match the signal strength sequence of the current signal source with each template in the preset template library, and the signal strength change trend corresponding to the template with the highest matching degree is determined as the signal strength change trend of the current signal source. Next, the signal identifier, signal name, equipment type, passage time, relative distance sequence, and signal strength change trend of the current signal source are input into the motion classification model. At this time, the motion classification model can combine multi-dimensional information to determine whether the current signal source is a moving vehicle or a non-moving vehicle. For example, the signal strength change trend of a moving vehicle is faster and more stable, while the signal strength change trend of a non-moving vehicle is slower or more unstable. Thus, the distribution of signal strength change trends can be used to distinguish between moving vehicles and non-moving vehicles (such as stationary roadside infrastructure, stationary mobile terminals, or moving mobile terminals).

[0075] In this embodiment, the signal strength change trend is replaced with the signal strength sequence and input into the motion classification model. This captures the change characteristics of signal strength, which helps the motion classification model distinguish between moving and non-moving vehicles based on the signal strength change characteristics of the vehicle-mounted equipment. This improves the classification accuracy of the motion classification model and the accuracy of the motion classification results, providing an accurate data foundation for subsequently determining the number of moving vehicles.

[0076] Optionally, the training process for the motion classification model is as follows, including Sb1-Sb5:

[0077] Sb1. Collect the wireless signals broadcast by multiple sample signal sources in the road within a preset period, obtain the sample wireless signals of multiple sample signal sources, and analyze the sample wireless signals of each sample signal source to obtain the attribute information of the corresponding sample signal source.

[0078] The attribute information includes the sample signal identifier, sample signal name, sample signal intensity sequence, and sample transit time.

[0079] Sb2. Input the sample signal name of each sample signal source into the device category classification model to obtain the sample device category of the corresponding sample signal source.

[0080] Sb3. Process the sample signal intensity sequence of each sample signal source to obtain the sample relative distance sequence and sample signal intensity change trend of the corresponding sample signal source, and label the corresponding sample signal source with motion type based on the real motion attributes of each sample signal source.

[0081] Among them, the true motion attribute can include moving vehicles and non-moving vehicles.

[0082] Specifically, the data processing of the sample signal intensity sequence to obtain the sample relative distance sequence and the sample signal intensity change trend is the same as the processing steps of S240 and "performing pattern matching on the signal intensity sequence of the current signal source to determine the signal intensity change trend of the current signal source". Please refer to the above description and it will not be repeated here.

[0083] Sb4. Combine the sample signal identifier, sample signal name, sample device category, sample passage time, sample relative distance sequence, and sample signal intensity change trend of each sample signal source to obtain the corresponding sample data, and construct a training set based on multiple sample data and the motion type label of each sample data.

[0084] Sb5. Input the sample data from the training set into the initial motion classification model, use the corresponding motion type labels to guide the initial motion classification model, train the initial motion classification model, and obtain the motion classification model.

[0085] Specifically, sample data can be input into the initial motion classification model to obtain motion type training values, and the loss value between the motion type training values ​​and the corresponding motion type labels can be calculated. Then, the initial motion classification model can be trained and optimized using the backpropagation algorithm to minimize the loss value, thus obtaining the motion classification model. That is, by using the backpropagation algorithm, the model parameters of the initial motion classification model are updated and adjusted according to the gradient information of the loss function to minimize the loss value, so that the motion classification model can gradually learn the relationship between the attribute information of the signal source and the motion attributes.

[0086] In this embodiment, sample data is constructed by collecting attribute information of multiple signal sources on the road, and motion type labels are assigned to the sample data based on the actual motion attributes of the signal sources. This forms a training set for the motion classification model, which is then trained on the training set. This enables the motion classification model to accurately learn the relationship between the attribute information of the signal sources and the motion attributes, thereby improving the classification accuracy of the motion classification model.

[0087] S260. Based on the motion classification results of each signal source, determine the number of moving vehicles in the preset road area within the preset period, and report the number of moving vehicles in the preset road area within the preset period to the traffic management system.

[0088] The technical solution of this application embodiment can monitor wireless signals broadcast by multiple signal sources in a preset road area within a preset period. Next, it analyzes the wireless signal of each signal source to determine the signal identifier and signal name of the corresponding signal source, and determines the signal strength sequence and passage time of each signal source within the preset period. Then, using a device category classification model, it classifies the device category of each signal source based on its signal name to obtain the corresponding device category. Then, for the current signal source among multiple signal sources, it determines the relative distance sequence of the current signal source based on its signal strength sequence. Finally, using a motion classification model, it classifies the motion attributes of the current signal source based on its signal identifier, signal name, device category, passage time, signal strength sequence, and relative distance sequence to obtain the motion classification result of the current signal source. By adding a relative distance sequence, it can classify the relative distance sequence distribution characteristics of the vehicle-mounted device. The point-assisted motion classification model distinguishes between moving and non-moving vehicles and enriches the input data for the motion classification model. This allows the model to comprehensively consider multi-dimensional data to determine the motion classification result of a signal source, thereby improving the accuracy of the motion classification result and providing an accurate data foundation for subsequently determining the number of moving vehicles. Then, based on the motion classification result of each signal source, the number of moving vehicles in a preset road area within a preset period is determined and reported to the traffic management system. This method can count the number of moving vehicles without requiring vehicle networking, further improving the accuracy of motion vehicle counting and providing the traffic management system with accurate information, which is helpful for traffic management departments. Furthermore, it eliminates the need for fixed facilities (such as inductive loop detectors or cameras), reducing costs, facilitating deployment, and protecting user privacy by not requiring the acquisition of vehicle location information or other private data.

[0089] Figure 3 This is a schematic diagram of a vehicle quantity determination device provided in an embodiment of this application, referring to... Figure 3 The vehicle quantity determination device may include:

[0090] The monitoring module 310 is used to monitor wireless signals broadcast by multiple signal sources in a preset road area within a preset period;

[0091] The first determining module 320 is used to analyze the wireless signal of each signal source, determine the signal identifier and signal name of the corresponding signal source, and determine the signal strength sequence and passage time of each signal source within a preset period.

[0092] The first classification module 330 is used to classify the device category of each signal source based on the signal name of each signal source using the device category classification model, so as to obtain the device category of the corresponding signal source.

[0093] The second classification module 340 is used to classify the motion attributes of each signal source based on the signal identifier, signal name, device category, signal strength sequence and passage time using a motion classification model, and obtain the motion classification result of the corresponding signal source.

[0094] The second determining module 350 is used to determine the number of moving vehicles in a preset road area within a preset period based on the motion classification results of each signal source, and to report the number of moving vehicles in the preset road area within a preset period to the traffic management system.

[0095] In one embodiment, the second classification module 340 is specifically used for:

[0096] For the current signal source among multiple signal sources, determine the relative distance sequence of the current signal source based on the signal strength sequence of the current signal source;

[0097] Using a motion classification model, the motion attributes of the current signal source are classified based on the signal identifier, signal name, device category, transit time, signal strength sequence, and relative distance sequence, thus obtaining the motion classification result of the current signal source.

[0098] In one embodiment, the second classification module 340 uses a motion classification model to classify the motion attributes of the current signal source based on its signal identifier, signal name, device category, transit time, signal strength sequence, and relative distance sequence, obtaining the motion classification result of the current signal source, including:

[0099] Perform pattern matching on the signal strength sequence of the current signal source to determine the signal strength change trend of the current signal source;

[0100] Using a motion classification model, the motion attributes of the current signal source are classified based on the signal identifier, signal name, device category, passage time, relative distance sequence, and signal strength change trend, thus obtaining the motion classification result of the current signal source.

[0101] In one embodiment, the second classification module 340 determines the relative distance sequence of the current signal source based on the signal strength sequence of the current signal source, including:

[0102] The system analyzes multiple wireless signals from the current signal source to determine the arrival time of the corresponding wireless signals, and combines the arrival times of multiple wireless signals in chronological order to obtain a signal arrival time sequence.

[0103] The relative distance sequence of the current signal source is determined based on the signal strength sequence and signal arrival time sequence of the current signal source.

[0104] In one embodiment, the second classification module 340 determines the relative distance sequence of the current signal source based on the signal strength sequence and signal arrival time sequence of the current signal source, including:

[0105] Synchronize the signal strength sequence and the signal arrival time sequence in chronological order to obtain multiple matching pairs;

[0106] Based on the signal strength and signal arrival time at the same time point in each matching pair, a preset mapping relationship is queried to obtain the relative distance of the corresponding matching pair. The preset mapping relationship includes the correspondence between signal strength, signal arrival time and relative distance.

[0107] The relative distance sequence is obtained by combining the relative distances of multiple matching pairs in chronological order.

[0108] In one embodiment, the training process of the motion classification model in the second classification module 340 is as follows:

[0109] Collect wireless signals broadcast by multiple sample signal sources in the road within a preset period to obtain sample wireless signals of multiple sample signal sources, and parse the sample wireless signals of each sample signal source to obtain the attribute information of the corresponding sample signal source. The attribute information includes sample signal identifier, sample signal name, sample signal strength sequence and sample passage time.

[0110] Input the sample signal name of each sample signal source into the device category classification model to obtain the sample device category of the corresponding sample signal source;

[0111] Data processing is performed on the sample signal intensity sequence of each sample signal source to obtain the sample relative distance sequence and sample signal intensity change trend of the corresponding sample signal source, and motion type labels are marked for the corresponding sample signal source based on the real motion attributes of each sample signal source;

[0112] By combining the sample signal identifier, sample signal name, sample device category, sample passage time, sample relative distance sequence, and sample signal intensity change trend of each sample signal source, the corresponding sample data is obtained, and a training set is constructed based on multiple sample data and the motion type label of each sample data.

[0113] The sample data in the training set is input into the initial motion classification model. The initial motion classification model is then trained using the corresponding motion type labels to obtain the motion classification model.

[0114] In one embodiment, the wireless signal in the monitoring module 310 includes a mid-range wireless signal and / or a short-range wireless signal, and the signal identifier in the first determining module 320 is the physical address of the signal source.

[0115] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0116] The vehicle quantity determination device provided in this embodiment can be applied to the vehicle quantity determination method provided in any of the above embodiments, and has the corresponding functions and beneficial effects.

[0117] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 A block diagram is shown of an exemplary electronic device 11 suitable for implementing embodiments of the present application. Figure 4 The electronic device 11 shown is merely an example and should not impose any limitations on the functionality and scope of use of this embodiment.

[0118] like Figure 4 As shown, the electronic device 11 is represented in the form of a general-purpose computing electronic device. The components of the electronic device 11 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0119] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0120] Electronic device 11 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 11, including volatile and non-volatile media, removable and non-removable media.

[0121] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 11 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 4Not shown; usually referred to as a "hard drive"). Although Figure 4 As not shown, disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disc drives for reading and writing to removable non-volatile optical discs (e.g., CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0122] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this application.

[0123] Electronic device 11 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 11, and / or with any device that enables electronic device 11 to communicate with one or more other computing devices (e.g., network interface card and modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, electronic device 11 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20.

[0124] like Figure 4 As shown, network adapter 20 communicates with other modules of electronic device 11 via bus 18. It should be understood that, although... Figure 4 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 11, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] The processing unit 16 executes various functional applications and page displays by running programs stored in the system memory 28, such as implementing a vehicle quantity determination method provided in any embodiment of this application.

[0126] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements, for example, a method for determining the number of vehicles provided in any embodiment of this application.

[0127] The computer storage medium of this embodiment can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0128] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0129] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0130] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] Those skilled in the art will understand that the modules or steps described above in this application can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, which can then be stored in a storage device for execution by a computing device. Alternatively, they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0132] Furthermore, the acquisition, storage, use, and processing of data in this application's technical solution all comply with relevant laws and regulations.

[0133] Note that the above are merely preferred embodiments and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments. Many other equivalent embodiments may be included without departing from the inventive concept of this application, and the scope of this application is determined by the scope of the appended claims.

Claims

1. A method for determining the number of vehicles, characterized in that, The method includes: Monitor wireless signals broadcast by multiple signal sources in a preset road area within a preset period; The wireless signal of each signal source is analyzed to determine the signal identifier and signal name of the corresponding signal source, and the signal strength sequence and passage time of each signal source within the preset period are determined. Using a device category classification model, the device category of each signal source is classified based on the signal name of that signal source, thereby obtaining the device category of the corresponding signal source; Using a motion classification model, the motion attributes of each signal source are classified based on its signal identifier, signal name, device category, signal strength sequence, and transit time, to obtain the motion classification result for the corresponding signal source. Based on the motion classification results of each signal source, the number of moving vehicles in the preset road area within the preset period is determined, and the number of moving vehicles in the preset road area within the preset period is reported to the traffic management system.

2. The method for determining the number of vehicles according to claim 1, characterized in that, The motion classification model is used to classify the motion attributes of each signal source based on its signal identifier, signal name, device category, signal strength sequence, and transit time, thereby obtaining the motion classification result for the corresponding signal source, including: For the current signal source among multiple signal sources, determine the relative distance sequence of the current signal source based on the signal strength sequence of the current signal source; Using the motion classification model, the motion attributes of the current signal source are classified based on the signal identifier, signal name, device category, passage time, signal strength sequence, and relative distance sequence, to obtain the motion classification result of the current signal source.

3. The method for determining the number of vehicles according to claim 2, characterized in that, The motion classification model is used to classify the motion attributes of the current signal source based on the signal identifier, signal name, device category, passage time, signal strength sequence, and relative distance sequence, to obtain the motion classification result of the current signal source, including: Perform pattern matching on the signal strength sequence of the current signal source to determine the signal strength change trend of the current signal source; Using the motion classification model, the motion attributes of the current signal source are classified based on the signal identifier, signal name, device category, passage time, relative distance sequence, and signal intensity change trend, to obtain the motion classification result of the current signal source.

4. The method for determining the number of vehicles according to claim 2, characterized in that, Determining the relative distance sequence of the current signal source based on the signal strength sequence of the current signal source includes: The multiple wireless signals of the current signal source are analyzed to determine the arrival time of the corresponding wireless signals, and the arrival times of the multiple wireless signals are combined in chronological order to obtain a signal arrival time sequence. The relative distance sequence of the current signal source is determined based on the signal strength sequence and the signal arrival time sequence of the current signal source.

5. The method for determining the number of vehicles according to claim 4, characterized in that, Determining the relative distance sequence of the current signal source based on the signal strength sequence and the signal arrival time sequence of the current signal source includes: The signal strength sequence and the signal arrival time sequence are synchronized in chronological order to obtain multiple matching pairs; Based on the signal strength and signal arrival time at the same time point in each matching pair, a preset mapping relationship is queried to obtain the relative distance of the corresponding matching pair. The preset mapping relationship includes the correspondence between signal strength, signal arrival time and relative distance. The relative distance sequence is obtained by combining the relative distances of the multiple matching pairs in chronological order.

6. The method for determining the number of vehicles according to claim 1, characterized in that, The training process of the motion classification model is as follows: The wireless signals broadcast by multiple sample signal sources in the road within a preset period are collected to obtain sample wireless signals of multiple sample signal sources. The sample wireless signals of each sample signal source are then analyzed to obtain the attribute information of the corresponding sample signal source. The attribute information includes sample signal identifier, sample signal name, sample signal strength sequence and sample passage time. Input the sample signal name of each sample signal source into the device category classification model to obtain the sample device category of the corresponding sample signal source; Data processing is performed on the sample signal intensity sequence of each sample signal source to obtain the sample relative distance sequence and sample signal intensity change trend of the corresponding sample signal source, and motion type labels are marked for the corresponding sample signal source based on the real motion attributes of each sample signal source; By combining the sample signal identifier, sample signal name, sample device category, sample passage time, sample relative distance sequence, and sample signal intensity change trend of each sample signal source, the corresponding sample data is obtained, and a training set is constructed based on multiple sample data and the motion type label of each sample data. The sample data in the training set is input into the initial motion classification model, and the initial motion classification model is trained with the corresponding motion type label to obtain the motion classification model.

7. The method for determining the number of vehicles according to claim 1, characterized in that, The wireless signal includes medium-range wireless signals and / or short-range wireless signals, and the signal identifier is the physical address of the signal source.

8. A vehicle quantity determination device, characterized in that, The device includes: The monitoring module is used to monitor wireless signals broadcast by multiple signal sources in a preset road area within a preset period; The first determining module is used to analyze the wireless signal of each signal source, determine the signal identifier and signal name of the corresponding signal source, and determine the signal strength sequence and passage time of each signal source within the preset period; The first classification module is used to classify the device category of each signal source based on the signal name of each signal source using a device category classification model, so as to obtain the device category of the corresponding signal source. The second classification module is used to classify the motion attributes of each signal source based on the signal identifier, signal name, device category, signal strength sequence, and passage time using a motion classification model, and obtain the motion classification result of the corresponding signal source. The second determining module is used to determine the number of moving vehicles in the preset road area within the preset period based on the motion classification results of each signal source, and to report the number of moving vehicles in the preset road area within the preset period to the traffic management system.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the vehicle quantity determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the vehicle quantity determination method as described in any one of claims 1 to 7.

Images