Traffic condition prediction method, classification model training method, and medium

Abstract

The present application discloses a traffic condition prediction method, a classification model training method, and a computer readable storage medium. The method comprises: acquiring cell load data of a target cell within a target time period and user terminal switching data, wherein the target cell is a cell where a signal covers a target road section; constructing a target feature vector on the basis of the cell load data and the user terminal switching data; and inputting the target feature vector into a preset classification model for identification to obtain a congestion level of the target road section within the target time period, wherein the preset classification model is obtained by training by using the feature vector constructed on the basis of the load data of the cell and the user terminal switching data as model input data and using label data constructed on the basis of an actual congestion level of the road section covered by the cell as a model training label.

Description

Traffic condition prediction method, classification model training method and medium

[0001] Related applications

[0002] This application claims priority to Chinese patent application No. 202310770982.1 filed on June 27, 2023, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of communication technology, and in particular to a traffic condition prediction method, a classification model training method, and a computer-readable storage medium. Background Art

[0004] Currently, common traffic condition perception technologies include cameras, microwave radar, and GPS. These technologies enable accurate, real-time, and comprehensive monitoring and analysis of traffic conditions. However, these technologies also have numerous drawbacks, such as reliance on the number and location of cameras and susceptibility to weather conditions. In particular, due to cost constraints, the limited number of cameras deployed in a transportation network cannot fully monitor and perceive road conditions. This is especially true for cameras on highways.

[0005] Summary of the Invention

[0006] In a first aspect, the present application provides a traffic condition prediction method, the method comprising: obtaining cell load data and user terminal switching data of a target cell in a target time period, wherein the target cell is a cell whose signal covers a target road section; constructing a target feature vector based on the cell load data and the user terminal switching data; inputting the target feature vector into a preset classification model for identification to obtain the congestion level of the target road section in the target time period, wherein the preset classification model is trained using a feature vector constructed using the cell load data and user terminal switching data as model input data and label data constructed using the actual congestion level of the road section covered by the cell as model training labels.

[0007] In the second aspect, the present application also provides a classification model training method, which includes: obtaining a sample data set, wherein the sample data set includes multiple sample data, each sample data includes cell load data and user terminal switching data of a cell in a time period, and the actual congestion level of the road section covered by the cell signal; constructing feature vectors according to the cell load data and user terminal switching data in each of the sample data, and constructing label data according to the actual congestion level in each of the sample data; using the feature vector corresponding to each sample data as model input data, and using the label data corresponding to each sample data as model training label, to train the classification model to be trained, and obtain a target classification model for predicting road congestion level.

[0008] In a third aspect, the present application further proposes a computer-readable storage medium, on which a traffic condition prediction program is stored. When the traffic condition prediction program is executed by a processor, the steps of the traffic condition prediction method as described above are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] FIG1 is a flow chart of a first embodiment of a traffic condition prediction method of the present application;

[0010] FIG2 is a flow chart of a second embodiment of the traffic condition prediction method of the present application;

[0011] FIG3 is a schematic diagram of a training and storage system architecture for a classification model according to an embodiment of a classification model training method of the present application;

[0012] FIG4 is a schematic diagram of the structure of a classification model involved in an embodiment of a classification model training method of the present application;

[0013] FIG5 is a schematic diagram of the structure of a traffic condition prediction device involved in an embodiment of the present application;

[0014] FIG6 is a schematic diagram of the structure of a training device for a classification model involved in an embodiment of the present application;

[0015] FIG7 is a schematic diagram of a computer-readable storage medium involved in an embodiment of the present application;

[0016] FIG8 is a schematic diagram of another computer-readable storage medium involved in an embodiment of the present application.

[0017] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] The specific embodiments described herein are merely used to explain the present application and are not intended to limit the present application.

[0019] Based on the above structure, various embodiments of the traffic condition prediction method are proposed.

[0020] Refer to Figure 1, which is a flow chart of the first embodiment of the traffic condition prediction method of the present application. The embodiment of the present application provides an embodiment of the traffic condition prediction method. Although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here. In this embodiment, there is no restriction on the execution subject of the traffic condition prediction method. For example, it can be a network element device, a personal computer, a server, a smart phone and other devices. For the convenience of description, the following description of each embodiment is based on the prediction device as the execution subject. In this embodiment, the traffic condition prediction method includes:

[0021] Step S10: Acquire cell load data and user terminal handover data of a target cell in a target time period, wherein the target cell is a cell whose signal covers a target road section.

[0022] The road section for which traffic conditions need to be predicted is referred to as a target road section for distinction. The traffic condition prediction method of this embodiment is applicable to any road section for which traffic conditions need to be predicted. The following description takes a target road section as an example. There are many ways to determine the target road section, which are not limited in this embodiment. For example, it can be manually pre-selected and configured in the prediction device, or it can be obtained by dividing each road according to road network data by the prediction device. In a feasible implementation, the road sections divided by the highway can be used as target road sections, and the road condition prediction of the target road section can be performed to specifically solve the problem that it is difficult for cameras on the highway to achieve comprehensive monitoring and perception of road conditions.

[0023] A cell refers to a communication cell, such as a cellular cell. The application environment of this embodiment can be, but is not limited to, an LTE / NR network environment, that is, a cell can refer to a cell in an LTE / NR network environment. A cell whose signal covers the target road section is used as a target cell. The signal of the target cell can cover a part or all of the target road section, that is, it is not necessary for the cell whose signal covers the entire area of ​​the target road section to be used as the target cell. In a specific embodiment, if the signals of two or more cells cover the target road section, each cell can be used as a target cell, or the cell with the largest area of ​​signal coverage of the target road section can be used as the target cell. There are many ways to determine the target cell, which are not limited in this embodiment. For example, it can be manually determined in advance based on the signal coverage of each cell and the selected target road section and configured in the prediction device, or it can be determined by the prediction device based on the signal coverage of each cell in the configured cell information and the selected target road section. For example, in one feasible implementation, the prediction device may obtain cell information including the signal coverage of each cell. The prediction device uses the cell whose signal coverage covers the target road section as the target cell corresponding to the target road section.

[0024] If it is desired to predict the congestion situation of a target road segment during a specific time period, this time period is referred to as a target time period for purposes of distinction. The traffic condition prediction method of this embodiment is applicable to predicting the congestion situation of a target road segment during any time period. The following description uses a target time period as an example. There are many ways to determine the target time period, which are not limited in this embodiment. For example, the target time period can be manually pre-selected and configured in the prediction device, or it can be determined by dividing the target time period according to a time period division rule set by the prediction device.

[0025] The prediction device may obtain cell load data and user equipment (UE) handover data of the target cell within a target period.

[0026] Among them, the cell load data is data that can reflect the load level of the target cell during the target time period. However, in this embodiment, there is no restriction on which data items the cell load data specifically includes. In a specific implementation method, the data that the prediction device needs to obtain that can reflect the load level of the target cell during the target time period can be set as needed. The more congested the target road section, the more users will use the communication services provided by the target cell within the target road section, and the higher the load level of the target cell will be. Conversely, the smoother the target road section, the fewer users will use the communication services provided by the target cell within the target road section, and the lower the load level of the target cell will be. Therefore, the cell load data of the target cell is correlated with the congestion of the target road section.

[0027] For example, in a feasible implementation, the cell load data may include at least one of the following data: the average number of connected users of the cell radio resource control (RRC), the number of activated users, the uplink medium access control (MAC) layer traffic, the downlink medium access control layer traffic, and the physical resource block (PRB) utilization.

[0028] User terminal handover data is data that can reflect the number of users entering or leaving the target cell during a target period. However, in this embodiment, the specific data items included in the user terminal handover data are not limited. In specific implementations, the data reflecting the number of users entering or leaving the target cell during the target period that the prediction device needs to obtain can be set as needed. The more congested the target road section, the more users will use the communication services provided by the target cell within the target road section, and the slower the users' movement speed will be. Therefore, the longer the users will stay within the signal coverage of the target cell, and the fewer users will enter or leave the target cell during the target period. Conversely, the more unobstructed the target road section, the fewer users will use the communication services provided by the target cell within the target road section, and the faster the users' movement speed will be. Therefore, the shorter the users will stay within the signal coverage of the target cell, and the more users will enter or leave the target cell during the target period. Therefore, the user terminal handover data of the target cell is correlated with the congestion of the target road section.

[0029] For example, in a feasible implementation, the user terminal handover data may include at least one of the following data: the number of times the user terminal successfully enters the target cell, the number of times the user terminal successfully exits the target cell, the number of times the user terminal requests to enter the target cell, and the number of times the user terminal requests to exit the target cell.

[0030] In this embodiment, the method by which the prediction device obtains the cell load data and user terminal handover data is not limited and can be set as needed. For example, in one feasible implementation, the data can be obtained from a network element module, a network management module, or a data service module.

[0031] Step S20: constructing a target feature vector according to the cell load data and the user terminal handover data.

[0032] After obtaining the cell load data and user terminal handover data of the target cell within the target time period, the prediction device can use the cell load data and user terminal handover data to construct a feature vector (hereinafter referred to as the target feature vector for distinction). In a specific embodiment, there are many ways to construct the target feature vector, which are not limited in this embodiment and can be set as needed. For example, in one feasible embodiment, step S20 includes:

[0033] Step S201 : Preprocess each item of the cell load data and the user terminal handover data to obtain a characteristic quantity corresponding to each item of the data.

[0034] The cell load data includes at least one item of data, and the user terminal handover data includes at least one item of data. The prediction device preprocesses each item of data in the cell load data and the user terminal handover data to obtain a feature value corresponding to each item of data. The method of data preprocessing is not limited in this embodiment. For example, in one feasible embodiment, the preprocessing may include normalization.

[0035] Step S202: combining the feature quantities corresponding to each item of data to obtain a target feature vector.

[0036] The prediction device combines the feature quantities corresponding to each data item to obtain a target feature vector. For example, when M items of data are included, the target feature vector can be expressed as X = [x1, x2, ..., x M ], where xi, i∈{1,…M} represents the feature quantity corresponding to each data item.

[0037] Step S30, inputting the target feature vector into a preset classification model for identification to obtain the congestion level of the target road section within the target time period, wherein the preset classification model is trained using the feature vector constructed with the cell's load data and user terminal switching data as model input data, and label data constructed with the actual congestion level of the road section covered by the cell as model training labels.

[0038] The preset classification model can be pre-trained and configured in the prediction device. In this embodiment, the model structure and training method of the preset classification model are not limited. For example, the model structure can adopt the model structure of a commonly used classification model, such as a logistic regression model, a decision tree model, an SVM support vector machine model, etc. The training method of the preset classification model is also not limited. For example, a supervised training method can be used. By using feature vectors constructed from cell load data and user terminal handover data related to the congestion situation of the road section as model input data, and label data constructed from the actual congestion level of the road section covered by the cell as model training labels, the preset classification model can learn the mapping relationship between the feature vectors constructed from the cell load data and user terminal handover data and the actual congestion level of the road section. This mapping relationship learned by the preset classification model can then be used to accurately identify the congestion level of the target road section within the target time period based on the input target feature vector. Multiple congestion levels (hereinafter referred to as preset congestion levels) can be pre-set to represent different degrees of congestion on the road section. The number of preset congestion levels can be set as needed and is not limited here. For example, two preset congestion levels may be set, namely, congested traffic and smooth traffic, and the actual congestion level of the road section is one of the preset congestion levels.

[0039] Since the load data of a cell can reflect the number of users in the cell, and further reflect the number of users on the road section covered by the cell signal, and the user terminal switching data of the cell can reflect the situation of users switching in and out of the cells, and further reflect the flow speed of users on the road section covered by the cell signal, in the embodiment of the present application, the congestion level of the road section is predicted by combining wireless communication network data such as the cell load data and user terminal switching data with a machine learning model, which can achieve accurate and real-time monitoring and perception of the road conditions. Moreover, there is no need to set up cameras on the road section, and it can be achieved by using cells deployed in the mobile communication network, thereby achieving accurate and real-time monitoring and perception of the road conditions even on sections without cameras.

[0040] Based on the above first embodiment, a second embodiment of the traffic condition prediction method of the present application is proposed. Referring to FIG. 2 , in this embodiment, after step S30, the method further includes:

[0041] Step S40: In response to the congestion level being greater than a preset level, adjusting the signal coverage of the neighboring cells of the target cell, wherein the adjusted signal coverage of the neighboring cells includes part or all of the target road section.

[0042] After identifying the congestion level of the target road section within the target time period, the prediction device can compare the congestion level with a preset level. The preset level is a level set in advance as needed, so that when the congestion level is greater than the preset level, it can indicate that the target road section is relatively congested, and the number of users in the target road section has exceeded the number of users that the target cell can handle. In response to the congestion level being greater than the preset level, the prediction device can adjust the signal coverage range of the adjacent cells of the target cell so that the adjusted signal coverage range of the adjacent cells includes part or all of the area of ​​the target road section. There are many ways to adjust the signal coverage range of adjacent cells, which are not limited in this embodiment. For example, in one feasible implementation, the signal coverage weight of the adjacent cells can be adjusted toward the target cell to adjust the signal coverage range of the adjacent cells to include part or all of the area of ​​the target road section.

[0043] In this embodiment, when the target road section in the target cell is relatively congested and the number of users in the target road section has exceeded the number of users that the target cell can load, the signal coverage range of the adjacent cells of the target cell is adjusted to include part or all of the area of ​​the target road section, so that the adjacent cells of the target cell can share the load of the target cell, thereby achieving "network follows business", adaptively balancing the business load between cells, and improving the user experience in congested cells.

[0044] Based on the first and / or second embodiments described above, a third embodiment of the traffic condition prediction method of the present application is proposed. In this embodiment, the preset classification model includes an input layer, at least one hidden layer, and an output layer. Step S30 includes:

[0045] Step S301: input the target feature vector into the hidden layer through the input layer.

[0046] In this embodiment, a feasible model structure of a preset classification model is proposed, including an input layer, at least one hidden layer and an output layer. Among them, the input layer is the first layer of the neural network, which is used to receive the input signal (value) and pass it to the next layer, that is, the hidden layer in this embodiment, but does not perform any operation on the input signal (value). The neurons (nodes) of the hidden layer convert the input data in different ways, and a hidden layer is a vertically stacked set of neurons. The output layer is the last layer of the neural network, which receives the input from the last hidden layer and outputs a value within a reasonable range.

[0047] After constructing the target feature vector, the prediction device inputs the target feature vector into the hidden layer through the input layer.

[0048] Step S302: After the input vector is processed by the hidden layer, the processed vector is input to the output layer.

[0049] After the target feature vector is input into the hidden layer, the prediction device processes the input vector through the hidden layer. The specific processing method may vary depending on the combination of neurons in the hidden layer, and this is not limited in this embodiment. After the input vector is processed by the hidden layer, a vector is also obtained, and the prediction device inputs the processed vector into the output layer.

[0050] Step S303 : obtaining the congestion level of the target road section within the target time period by identifying the input vector through the output layer.

[0051] The prediction device identifies the vector input to the output layer through the output layer, and can obtain the congestion level of the target road section during the target time period.

[0052] In one feasible implementation, during the training of the preset classification model, the model parameters of each layer in the preset classification model need to be updated and optimized so that the preset classification model can accurately predict the congestion level of the road section covered by the cell based on the input feature vector (feature vector constructed based on the cell load data and user terminal switching data).

[0053] In one feasible implementation, step S302 includes:

[0054] Step S3021: After performing linear processing on the input vector using the weight matrix of the neurons in the hidden layer, activation processing is performed on the linearly processed vector using the activation function in the hidden layer.

[0055] In this embodiment, a feasible method for the hidden layer to process the input vector is proposed. When there are multiple hidden layers, the prediction device inputs the target feature vector into the first hidden layer through the input layer. After the first hidden layer processes the vector, the processed vector is input into the second hidden layer. After the second hidden layer processes the vector, the processed vector is input into the third hidden layer, and so on. Each hidden layer processes the input vector in the same way, except that the number of neurons and weight values ​​of each hidden layer are different. Taking a single hidden layer as an example, the prediction device can perform linear processing on the input vector using the weight matrix of the neurons in the hidden layer, then activate the linearly processed vector using the activation function in the hidden layer, and then input the activated vector into the next layer.

[0056] The activation function can be set as needed. In this embodiment, there is no limitation. For example, sigmoid, tanh, Relu, etc. can be used.

[0057] Step S3022: input the vector obtained by the activation process of the last hidden layer into the output layer.

[0058] The prediction device inputs the vector obtained by the activation processing of the last hidden layer into the output layer.

[0059] When there is only one hidden layer in the preset classification model, the target feature vector is input into the hidden layer through the input layer, and then the input vector is processed by the hidden layer, and the processed vector is input into the output layer.

[0060] In one feasible implementation, step S303 includes:

[0061] Step S3031 : performing linear processing on the input vector using the weight matrix of the neurons in the output layer to obtain output values ​​corresponding to respective preset congestion levels.

[0062] This embodiment proposes a feasible congestion level identification method, using an output layer to identify the input vector. The output layer includes neurons and a normalization function, with the number of neurons configured to match the number of preset congestion levels, so that the output value corresponds to each preset congestion level. The prediction device can linearly process the input vector using the weight matrix of the neurons in the output layer to obtain the output value corresponding to each preset congestion level.

[0063] Step S3032: Normalize the output values ​​corresponding to the respective preset congestion levels using the normalization function in the output layer to obtain the probability that the target road section belongs to each preset congestion level within the target time period.

[0064] The prediction device normalizes the output values ​​corresponding to each preset congestion level using a normalization function in the output layer to obtain the probability that the target road segment falls within each preset congestion level during the target time period. The normalization function can be configured as needed, and the present embodiment is not limited to the specific normalization function used. For example, a softmax function can be used.

[0065] y1, y2, ...y C The values ​​output by the C neuron nodes in the output layer represent the probability that the target road section will fall into one of the C preset congestion levels during the target time period. Because the output layer vector Y does not necessarily satisfy the mathematical properties of a probability distribution—that is, the sum of its dimensions does not necessarily equal 1—a normalization operation is performed to convert Y into a probability distribution vector.

[0066] Step S3033: determining the congestion level of the target road section within the target time period from various preset congestion levels according to the probabilities.

[0067] The prediction device determines the congestion level for the target road segment during the target time period from among the preset congestion levels based on the probabilities of the preset congestion levels. This embodiment is not limited to the method of determining the congestion level based on probability. For example, in one feasible embodiment, the preset congestion level with the highest probability may be used as the congestion level for the target road segment during the target time period.

[0068] Based on the above-mentioned first, second and / or third embodiments, a fourth embodiment of the training method of the classification model of the present application is proposed. In this embodiment, there is no restriction on the execution subject of the training method of the classification model. For example, it can be a personal computer, a server, a smart phone and other devices. For the convenience of description, the following embodiments are explained with the training device as the execution subject. The training device and the prediction device can be the same device or different devices. They can be set as needed and are not limited in this embodiment; when the prediction device and the training device are different devices, after the target classification model is trained in the training device, the target classification model can be deployed to the prediction device. Referring to Figure 3, in this embodiment, the training method of the classification model includes:

[0069] Step A10: Obtain a sample data set, wherein the sample data set includes multiple sample data, each sample data includes cell load data and user terminal switching data of a cell in a time period, and the actual congestion level of the road section covered by the cell signal.

[0070] In this embodiment, a feasible training method for a target classification model is proposed. This embodiment does not limit the method by which the training device obtains the sample data set. For example, in one feasible implementation, the user can upload the sample data set to the training device.

[0071] The sample data set includes multiple pieces of sample data. Each piece of sample data includes cell load data and user terminal handover data for a cell within a time period, as well as the actual congestion level of the road section covered by the cell's signal. The duration of the time period can be set as needed, representing the time granularity for dividing the sample data. For example, if the granularity is minutes, then for a cell, the cell load data, user terminal handover data, and actual congestion level for a one-minute period can be obtained to form a single piece of sample data. Multiple pieces of sample data can be obtained for the cell, and multiple pieces of sample data can also be obtained for different cells. The sample data for each cell are combined to form a sample data set.

[0072] The actual congestion level of the road section covered by the cell signal may be manually marked or obtained through other means, which is not limited in this embodiment.

[0073] Step A20: constructing feature vectors according to the cell load data and user terminal handover data in each piece of sample data, and constructing label data according to the actual congestion level in each piece of sample data.

[0074] For each piece of sample data in the sample data set, the training device can construct a feature vector (also referred to as a "cell congestion feature vector") based on the cell load data and user terminal switching data in the sample data, and construct label data (also referred to as a "congestion level label") based on the actual congestion level in the sample data. For example, in one feasible implementation, constructing label data based on the actual congestion level can be: pre-setting labels corresponding to each preset congestion level, for example, using C integers from 0 to (C-1) to represent each preset congestion level, respectively, the number of C is determined by the number of preset congestion levels, and using the label corresponding to the actual congestion level as the label data corresponding to the sample data; without loss of generality, when two preset congestion levels are set, namely, traffic flow is smooth and traffic is congested, 0 can be used as the label for traffic flow is smooth, and 1 can be used as the label for traffic congestion. For example, in one feasible implementation, the label data can be constructed using a one-hot encoding method; the number of preset congestion levels is C, and the label data is represented by a vector of length C, where each element in the vector corresponds to each preset congestion level, the element corresponding to the actual congestion level is set to 1, and the elements corresponding to other preset congestion levels are set to 0, indicating that the probability that the congestion level of the road section covered by the cell signal is the actual congestion level is 1, and the probability of it being other preset congestion levels is 0.

[0075] The specific implementation method of the training device constructing the feature vector based on the cell load data and user terminal switching data in the sample data can refer to the specific implementation method of the prediction device constructing the target feature vector based on the cell load data and user terminal switching data of the target cell in the above embodiment, which will not be repeated here.

[0076] In step A30 , the feature vector corresponding to each piece of sample data is used as model input data, and the label data corresponding to each piece of sample data is used as model training label to train the classification model to obtain a target classification model for predicting road congestion levels.

[0077] A classification model to be trained can be pre-configured in the training device. The model structure of the classification model can be customized and is not limited here. The model parameters in the classification model can be initialized based on experience or randomly, and the training process is the process of optimizing the model parameters. The training device can use the feature vector corresponding to each sample as the model input data and the label data corresponding to each sample data as the model training label to train the classification model to obtain a target classification model for predicting road congestion levels.

[0078] In one feasible embodiment, as shown in FIG4 , the model structure of the classification model can be set to include an input layer, at least one hidden layer and an output layer, the input layer includes M nodes, M is the size of the feature vector, and the input layer is used to input the feature vector into the hidden layer. In one feasible embodiment, the number of hidden layers can be 1, and the number of neurons in the hidden layer is K. The number of neurons in the output layer is C, and the probability values ​​of C categories are output. The weight matrix of the neurons in the hidden layer can be expressed as W1, with a dimension of (K, M), and the weight matrix of the neurons in the output layer can be expressed as W2, with a dimension of (C, K). The input feature vector is expressed as X=[x1, x2,…, x M ], the mathematical formula of the classification model is as follows: Y=W2*W1*X+b

[0079] Where b is the bias vector. The physical meaning of the W1 and W2 matrices is that they represent the weighted influence of different eigenvectors in the road congestion classification. W1, W2, and b are the model parameters that need to be optimized during training.

[0080] In one feasible implementation, cross entropy can be used as the loss function of the model:

[0081] N represents the total number of samples input during training; C represents the number of preset congestion levels, that is, the number of model classifications; y ij is a one-dimensional one-hot encoding vector, indicating whether the i-th sample belongs to the j-th category; p ijRepresents the predicted probability of the classification model that the i-th sample belongs to the j-th category. On the training sample set, by using the gradient descent algorithm to optimize the model parameters of the loss function L, the model parameters with the best congestion level classification effect for the road section can be obtained. The optimizer (Optimizer) determines the convergence mode of the gradient descent of the model loss function. In one feasible implementation, the optimizer can use Adadelta, which is an adaptive learning rate method. During the training process, the number of samples in each training batch (BatchSize) can be set as needed, for example, it can be set to 10. The number of training rounds can be set as needed, for example, it can be set to 100 times.

[0082] In one possible implementation, to evaluate the effectiveness of the model application, the sample dataset can be divided into a training set and a test set, with the training set divided into a ratio of K and the test set divided into a ratio of (1-K). Multiple iterations of training are performed on the training set, and then the model's effectiveness is evaluated on the test set. Ultimately, the optimal model that minimizes the loss function is obtained through training, and the trained model is saved for use in subsequent modules.

[0083] In one feasible implementation, step A10 includes:

[0084] Step A101: Collect cell load data and user terminal handover data of at least one cell in each hour period from a network management module, a network element module or a data service module, wherein each hour period is obtained by dividing a preset time period according to a preset time granularity.

[0085] In this embodiment, a feasible method for obtaining a sample data set is proposed. The network element module is a functional module deployed in the network element device, which stores the communication data in the network element device; the network management module refers to the network management module, which manages multiple network element devices and stores the communication data in multiple network element devices; the data service module is deployed in an external server, provides data calculation and analysis services for the cell, and stores the communication data in the cell. Therefore, in this embodiment, the training device can collect the cell load data and user terminal switching data of at least one cell in each hourly period from the network management module, the network element module or the data service model. Each hourly period is obtained by dividing the time period of the preset duration according to the preset time granularity. The preset time granularity is the time granularity set in advance according to the needs, for example, it can be set to minute granularity. The preset duration can be set as needed, for example, it can be set to one month. Then, the training device can obtain the cell load data and user terminal switching data of at least one cell every minute in one month.

[0086] In one possible implementation method, the training device can collect cell load data and user terminal switching data of the cell within a preset time period. The collected data can carry timestamp information, including but not limited to timestamp information with year / month / day / hour / minute granularity, and then divide the collected data into cell load data and user terminal switching data within each hour period according to the preset time granularity according to the timestamp information.

[0087] Step A102: collecting the actual congestion level of the road section covered by the cell signal in each hour period.

[0088] The training device can also collect the actual congestion level of the road section covered by the cell signal in each hour period. The collection method is not limited in this embodiment, for example, it can be obtained through manual marking.

[0089] Step A103: obtaining one piece of sample data based on the cell load data, user terminal handover data and actual congestion level of the same cell collected in the same hour period, and obtaining the sample data set based on multiple pieces of sample data.

[0090] The training equipment combines the cell load data, user terminal switching data and actual congestion level of the same cell collected in the same hour period into a sample data. Then, based on the acquired data, multiple sample data can be combined to form a sample data set.

[0091] In one feasible implementation, step A102 includes:

[0092] Step A1021: collecting surveillance videos from surveillance cameras installed on the road section covered by the cell signal within each of the hourly periods.

[0093] This embodiment proposes a feasible method for training equipment to collect actual congestion levels on road sections covered by cell signals. When collecting sample data, a road section covered by surveillance cameras can be selected. Cell load data and user terminal handover data for cells covering that road section are collected, as well as surveillance video from the surveillance cameras installed on that road section during various hourly periods.

[0094] Step A1022: performing image analysis on the surveillance video of each hour period to obtain the actual congestion level of the road section covered by the cell signal in each hour period.

[0095] The training device can perform image analysis on surveillance videos for each hourly period and, based on the image analysis results, determine the actual congestion level of the road section within each hourly period. The image analysis method is not limited in this embodiment; for example, an image classification algorithm can be used to classify the images and determine the actual congestion level.

[0096] In addition, an embodiment of the present application also proposes a traffic condition prediction device, which includes: a first acquisition module, used to obtain cell load data and user terminal switching data of a target cell in a target time period, wherein the target cell is a cell whose signal covers a target road section; a first construction module, used to construct a target feature vector based on the cell load data and the user terminal switching data; an identification module, used to input the target feature vector into a preset classification model for identification, and obtain the congestion level of the target road section in the target time period, wherein the preset classification model is trained using a feature vector constructed using the cell load data and user terminal switching data as model input data, and label data constructed using the actual congestion level of the road section covered by the cell as model training labels.

[0097] In a feasible embodiment, the traffic condition prediction device also includes: an adjustment module, which is used to adjust the signal coverage range of the adjacent cells of the target cell in response to the congestion level being greater than a preset level, wherein the adjusted signal coverage range of the adjacent cells includes part or all of the area of ​​the target road section.

[0098] In a feasible implementation manner, the cell load data includes at least one of the following data: the average number of connected users of the cell radio resource control, the number of activated users, the uplink medium access control layer traffic, the downlink medium access control layer traffic, and the physical resource block utilization rate.

[0099] In a feasible implementation manner, the user terminal handover data includes at least one of the following data: the number of times the user terminal successfully enters the target cell, the number of times the user terminal successfully exits the target cell, the number of times the user terminal requests to enter the target cell, and the number of times the user terminal requests to exit the target cell.

[0100] In one feasible implementation, the first construction module is further used to: pre-process each item of the cell load data and the user terminal switching data to obtain a feature quantity corresponding to each item of data; and combine the feature quantities corresponding to each item of data to obtain a target feature vector.

[0101] In a feasible embodiment, the preset classification model includes an input layer, at least one hidden layer and an output layer, and the recognition module is further used to: input the target feature vector into the hidden layer through the input layer; after processing the input vector through the hidden layer, input the processed vector into the output layer; and obtain the congestion level of the target road section during the target time period by identifying the input vector through the output layer.

[0102] In one feasible embodiment, the recognition module is also used to: perform linear processing on the input vector through the weight matrix of the neurons in the hidden layer, and then activate the linearly processed vector through the activation function in the hidden layer; and input the vector obtained after the activation processing of the last hidden layer into the output layer.

[0103] In one feasible embodiment, the identification module is further used to: perform linear processing on the input vector through the weight matrix of the neurons in the output layer to obtain output values ​​corresponding to each preset congestion level; normalize the output values ​​corresponding to each preset congestion level through the normalization function in the output layer to obtain the probability that the target road section belongs to each preset congestion level within the target time period; determine the congestion level of the target road section within the target time period from each preset congestion level according to each of the probabilities.

[0104] In addition, an embodiment of the present application also proposes a training device for a classification model, and the training device for the classification model includes: a second acquisition module, used to obtain a sample data set, wherein the sample data set includes multiple sample data, each sample data includes cell load data and user terminal switching data of a cell within a time period, and the actual congestion level of the road section covered by the cell signal; a second construction module, used to construct feature vectors according to the cell load data and user terminal switching data in each piece of the sample data, and to construct label data according to the actual congestion level in each piece of the sample data; a training module, used to use the feature vector corresponding to each piece of sample data as model input data, and use the label data corresponding to each piece of sample data as model training label, to train the classification model to be trained, and obtain a target classification model for predicting road congestion level.

[0105] In a feasible embodiment, the second acquisition module is further used to: collect cell load data and user terminal switching data of at least one cell in each hour period from the network management module, the network element module or the data service module, wherein each hour period is obtained by dividing a time period of a preset length according to a preset time granularity; collect the actual congestion level of the road section covered by the cell signal in each of the hour periods; obtain one piece of sample data based on the cell load data, user terminal switching data and actual congestion level of the same cell collected in the same hour period, and obtain the sample data set based on multiple pieces of sample data.

[0106] In one feasible implementation manner, the second acquisition module is further used to: collect surveillance videos from surveillance cameras installed on the road sections covered by the cell signals within each of the hourly periods; perform image analysis on the surveillance videos of each of the hourly periods to obtain the actual congestion level of the road sections covered by the cell signals within each of the hourly periods.

[0107] An embodiment of the present application also provides a traffic condition prediction device, comprising: a memory, a processor, and a traffic condition prediction program stored in the memory and executable on the processor. When the traffic condition prediction program is executed by the processor, the steps of the traffic condition prediction method described in each of the above embodiments are implemented. In a specific embodiment, as shown in FIG5 , the traffic condition prediction device may further include a network interface, a user interface, and a communication bus. The communication bus is used to enable connection and communication between these components. The user interface may include a display screen and an input unit such as a keyboard. The user interface may also include a standard wired interface and a wireless interface. The network interface may include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory may be a high-speed RAM memory or a non-volatile memory, such as a disk storage device. The memory may also be a storage device independent of the aforementioned processor. The memory, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a traffic condition prediction program. The operating system is a program that manages and controls the hardware and software resources of the device and supports the operation of the traffic condition prediction program and other software or programs. Those skilled in the art will understand that the device structure shown in FIG5 does not constitute a limitation on the traffic condition prediction device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0108] An embodiment of the present application also provides a classification model training device, the classification model training device comprising: a memory, a processor, and a classification model training program stored in the memory and executable on the processor. When the classification model training program is executed by the processor, the steps of the classification model training method described in each of the above embodiments are implemented. In a specific embodiment, the classification model training device may be a line card device in a network element device. In a specific embodiment, as shown in FIG6 , the classification model training device may further include a network interface, a user interface, and a communication bus. The communication bus is used to implement connection and communication between these components. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface may also include a standard wired interface and a wireless interface. The network interface may include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory may be a high-speed RAM memory or a non-volatile memory, such as a disk memory. The memory may also be a storage device independent of the aforementioned processor. The memory, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a classification model training program. The operating system is a program that manages and controls the hardware and software resources of the device, supporting the classification model training program and the operation of other software or programs. Those skilled in the art will appreciate that the device structure shown in FIG6 does not limit the classification model training device, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0109] Referring to Figure 7 , embodiments of the present application further provide a computer-readable storage medium storing a traffic condition prediction program. When executed by a processor, the traffic condition prediction program implements the steps of the traffic condition prediction method described in the above embodiments. As shown in Figure 7 , in a specific embodiment, a memory serving as a computer-readable storage medium can be connected to the processor via a communication bus.

[0110] Referring to Figure 8 , an embodiment of the present application further provides a computer-readable storage medium, on which a classification model training program is stored. When the classification model training program is executed by a processor, the steps of the classification model training method described in the above embodiments are implemented. As shown in Figure 8 , in a specific embodiment, a memory as a computer-readable storage medium can be connected to the processor for communication via a communication bus.

[0111] The various embodiments of the traffic condition prediction device, prediction equipment, classification model training device, training equipment and computer-readable storage medium of the present application can refer to the various embodiments of the traffic condition prediction method and classification model training method of the present application, and will not be repeated here.

[0112] As used herein, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0113] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0115] The above are merely optional embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for predicting traffic conditions, wherein: The method comprises: Acquire cell load data and user terminal switching data of a target cell in a target period, wherein the target cell is a cell whose signal covers a target road section; Constructing a target feature vector according to the cell load data and the user terminal switching data; The target feature vector is input into a preset classification model for identification to obtain the congestion level of the target road section within the target time period, wherein the preset classification model is trained using a feature vector constructed using cell load data and user terminal switching data as model input data and label data constructed using actual congestion levels of the road section covered by the cell as model training labels.

2. The traffic condition prediction method according to claim 1, wherein: After the step of inputting the target feature vector into a preset classification model for identification to obtain the congestion level of the target road section within the target time period, the method further includes: In response to the congestion level being greater than a preset level, the signal coverage of a cell adjacent to the target cell is adjusted, wherein the adjusted signal coverage of the adjacent cell includes a portion or all of the target road section.

3. The traffic condition prediction method according to claim 1, wherein: The cell load data includes at least one of the following data: the average number of connected users, the number of activated users, the uplink medium access control layer flow, the downlink medium access control layer flow, and the utilization rate of physical resource blocks in the cell radio resource control.

4. The traffic condition prediction method according to claim 1, wherein: The user terminal switching data includes at least one of the following data: the number of times the user terminal successfully switches into the target cell, the number of times the user terminal successfully switches out of the target cell, the number of times the user terminal requests to switch into the target cell, and the number of times the user terminal requests to switch out of the target cell.

5. The traffic condition prediction method according to claim 3, wherein: The step of constructing a target feature vector according to the cell load data and the user terminal switching data comprises: Preprocessing each item of the cell load data and the user terminal switching data to obtain a characteristic quantity corresponding to each item of the data; The feature quantities corresponding to each data item are combined to obtain the target feature vector.

6. The traffic condition prediction method according to any one of claims 1 to 5, wherein: The preset classification model includes an input layer, at least one hidden layer and an output layer. The step of inputting the target feature vector into the preset classification model for identification to obtain the congestion level of the target road section in the target time period includes: Inputting the target feature vector into the hidden layer through the input layer; After the input vector is processed by the hidden layer, the processed vector is input into the output layer; The output layer identifies the input vector to obtain the congestion of the target road section within the target time period. grade.

7. The traffic condition prediction method according to claim 6, wherein: After the input vector is processed by the hidden layer, the step of inputting the processed vector into the output layer comprises: After performing linear processing on the input vector through the weight matrix of the neurons in the hidden layer, performing activation processing on the linearly processed vector through the activation function in the hidden layer; The vector obtained by the activation process of the last hidden layer is input into the output layer.

8. The traffic condition prediction method according to claim 6, wherein: The step of obtaining the congestion level of the target road section within the target time period by identifying the input vector through the output layer includes: The input vector is linearly processed by the weight matrix of the neurons in the output layer to obtain output values ​​corresponding to each preset congestion level; Normalizing the output values ​​corresponding to the preset congestion levels by the normalization function in the output layer to obtain the probability that the target road section belongs to each preset congestion level in the target time period; The congestion level of the target road section within the target time period is determined from various preset congestion levels according to the probabilities.

9. A method for training a classification model, wherein: The training method of the classification model includes: Acquire a sample data set, wherein the sample data set includes a plurality of sample data, each sample data including cell load data and user terminal switching data of a cell in a time period, and an actual congestion level of a road section covered by the cell signal; Constructing feature vectors according to the cell load data and user terminal switching data in each of the sample data, and constructing label data according to the actual congestion level in each of the sample data; The feature vector corresponding to each piece of sample data is used as model input data, and the label data corresponding to each piece of sample data is used as model training label, and the classification model to be trained is trained to obtain a target classification model for predicting the road congestion level.

10. A computer-readable storage medium, wherein: The computer-readable storage medium stores a traffic condition prediction program, and when the traffic condition prediction program is executed by a processor, the traffic condition prediction method according to any one of claims 1 to 7 is implemented.

Images