Crowd gathering prediction method, device and system

Abstract

The invention provides a crowd gathering prediction method, device and system, and relates to the field of communication. The method comprises the following steps: acquiring historical user data and user switching data of a plurality of sites; wherein the station is a base station or a base station cell, and the historical user data comprises the number of users of any station in a plurality of stations at any historical moment in a plurality of historical moments. The user switching data comprises the frequency of switching from one station to another station in the plurality of stations at any historical moment in the plurality of historical moments. And then, based on historical user data and user switching data, using a prediction model to predict whether abnormal increase of the number of users exists in a plurality of sites at a future moment, thereby inferring whether crowd aggregation occurs in an area covered by the sites. In this way, based on the relevance between the number of access users of the stations and crowd gathering, crowd gathering prediction of multi-base-station combination is achieved, and the accuracy of prediction of the crowd gathering condition is improved.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a method, device and system for predicting crowd gathering. Background Art

[0002] In the management of public places, it is usually necessary to predict the crowd gathering situation and formulate corresponding management measures according to the crowd gathering situation. The current crowd gathering prediction schemes include those based on non-visual technology. The scheme based on non-visual technology predicts the future number of user accesses to a designated access site (such as a base station, wireless access point, etc.) based on traffic data such as the number of user accesses to the designated access site, and uses the future number of user accesses to the designated access site to represent the crowd gathering situation within the coverage area of ​​the designated access site.

[0003] However, the above-mentioned solution based on non-visual technology can only predict the crowd gathering situation in the covered area based on the data of a single access site. The data of the access site is affected by the signal coverage range of the single access site, and there is a problem of low prediction accuracy. Summary of the invention

[0004] The present application provides a crowd gathering prediction method, device and system, which can solve the problem of low accuracy in predicting future crowd gathering conditions based on traffic data of a single access site.

[0005] In a first aspect, a crowd gathering prediction method is provided. The crowd gathering prediction method includes: first, a computing device obtains historical user data and user switching data of multiple sites. The site is a base station or a base station cell. Then, based on the historical user data and user switching data, the computing device uses a prediction model to predict whether there will be an abnormal increase in the number of users at multiple sites in the future, and the increase in the number of users at the first site among the multiple sites indicates that a crowd gathers in the coverage area of ​​the first site. The historical user data includes: the number of users at any one of the multiple sites at any historical moment in multiple historical moments. The user switching data includes: the frequency of switching from one site to another site among the multiple sites at any one of the multiple historical moments.

[0006] Based on the crowd gathering prediction method, the computing device introduces the user switching data between multiple base stations when predicting whether there will be abnormal crowd gathering at a site. In this way, considering the mutual influence between base stations or base station cells, the historical user data and user switching data of multiple sites with a larger coverage area are introduced, and based on the correlation between the abnormal growth of the number of users at the site and crowd gathering, the abnormal crowd gathering prediction of multiple base stations is realized, which improves the accuracy of the prediction of crowd gathering.

[0007] As a possible implementation, the computing device uses different models to predict the abnormal growth of different types of users of the site. The types of abnormal growth in the number of users may include sudden abnormal growth in the number of users and propagated abnormal growth in the number of users. For example, when the number of users of a site does not conform to the historical change pattern of the number of users of the site, it can be considered that the site has a sudden abnormal growth in the number of users. For another example, the abnormal change in the number of users of a site due to user switching between multiple sites can be considered as a propagated abnormal growth in the number of users.

[0008] Optionally, the prediction model includes a first prediction model and a second prediction model. The computing device inputs the historical user data and the user switching data into the first prediction model to obtain the reconstructed user data output by the first prediction model. Taking the first historical moment of the first site as an example, the corrected number of users of the first site at the first historical moment is the normal number of users of the first site at the first historical moment predicted by the first prediction model based on the number of users of the first site at multiple historical moments. The computing device calculates the difference between the reconstructed user data and the historical user data. Taking the first historical moment of the first site as an example, the greater the difference between the reconstructed user data and the historical user data corresponding to the first site at the first historical moment, the greater the possibility that the number of users of the first site at the first historical moment has abnormal growth. The computing device inputs the user switching data and the difference into the second prediction model, and determines whether there is abnormal growth in the number of users of multiple sites at future moments according to the user number status prediction result output by the second prediction model.

[0009] Based on the above implementation, the computing device uses the first prediction model to predict the reconstructed user data to calculate the difference between the reconstructed user data and the historical user data, and then uses the second prediction model to predict whether there will be abnormal growth in the number of users at multiple sites in the future based on the user switching data and the difference. Since the reconstructed user data is mainly predicted by the first prediction model according to the historical law of changes in the number of users at the site, the first prediction model can be regarded as predicting the sudden abnormal growth in the number of abnormal users. Since the second prediction model outputs the predicted results based on the user switching data and the difference, and integrates the impact of user switching between multiple sites and the changes in the number of users at each site on a single site, the second prediction model can be regarded as predicting the propagation of abnormal growth in the number of users. In this way, the computing device models the prediction tasks for sudden and propagation of abnormal growth in the number of users, respectively, which improves the prediction accuracy of crowd gathering caused by abnormal growth in the number of users of different types and the interpretability of the prediction results.

[0010] As a possible implementation manner, the first prediction model and the second prediction model are deep learning models based on graph neural network (GNN).

[0011] Optionally, the input of the first prediction model is first matrix data and graph structure data. The first matrix data is used to represent historical user data. The graph structure data is used to represent user switching data. The graph structure data includes multiple nodes and edges between multiple nodes. Multiple nodes are used to represent multiple sites, and the weight of the edge between two nodes is used to represent the frequency of switching between the two sites. In this way, since the graph structure data can more accurately and comprehensively characterize the user communication relationship between multiple sites, and the graph neural network is suitable for processing graph structure data, the first prediction model can perceive more user communication relationships between multiple sites, thereby improving the accuracy of the prediction, so that the prediction results can better reflect the actual situation.

[0012] Optionally, the input of the second prediction model is the second matrix data and the central graph of each site. The second matrix data is used to represent the difference. The multiple sites include a first site, and the central graph of the first site includes a central node, an associated node, and an edge for connecting the nodes. The central node is used to represent the first site, and the associated node is used to represent the site where user switching with the first site exists. The edge of the central graph is used to represent the frequency of switching between the two sites. In this way, the second prediction model can perceive the impact of user switching between multiple sites on a single site based on the central graph, thereby predicting the abnormal growth of the number of users of the site, and at the same time, it can obtain the dynamic trend of user switching between multiple sites, so as to more timely discover the abnormal growth of the number of users of potential transmission.

[0013] The central graph may be an ego-network graph.

[0014] As a possible implementation, the multiple sites include a first site, and the output of the second prediction model is a third matrix data. The third matrix data includes multiple vectors. The multiple vectors include a first vector, and the first vector is used to represent the user quantity state of the first site at a future time. When the first vector is greater than or equal to a first threshold, it indicates that the number of users of the first site increases abnormally at a future time, and it is determined that a crowd gathers in the coverage area of ​​the first site at a future time.

[0015] As a possible implementation method, the first prediction model is a deep learning model based on a long short-term memory (LSTM) network, and the second prediction model is a deep learning model based on a graph neural network.

[0016] Optionally, the historical user data includes the number of terminals accessed by any one of the multiple sites at any one of the multiple historical moments, and the computing device inputs the historical user data and the user switching data into the first prediction model, i.e., the deep learning model based on the long short-term memory network, to obtain the reconstructed user data output by the first prediction model. The reconstructed user data includes the number of terminals accessed by any one of the multiple sites at any one of the multiple historical moments. Taking the first historical moment of the first site as an example, the number of users accessed by the first site at the first historical moment after correction is the number of users accessed by the first site at the first historical moment predicted by the first prediction model according to the number of users accessed by the first site at multiple historical moments. The computing device calculates the difference between the reconstructed user data and the historical user data. Taking the first historical moment of the first site as an example, the greater the difference between the reconstructed user data and the historical user data corresponding to the first site at the first historical moment, the greater the possibility that the number of users at the first site has abnormal growth at the first historical moment. The computing device inputs the user switching data and the difference into the second prediction model, and determines whether the number of users at multiple sites has abnormal growth at future moments according to the user number state prediction result output by the second prediction model.

[0017] In a second aspect, a crowd gathering prediction device is provided, which includes various modules for executing the crowd gathering prediction method in the first aspect or any possible implementation of the first aspect. The crowd gathering prediction device in the present application may include a data processing module and a prediction module. The data processing module is used to obtain historical user data and user switching data of multiple sites. The site is a base station or a base station cell. The historical user data includes the number of users at any one of the multiple sites at any one of the multiple historical moments. The user switching data includes the frequency of switching from one site to another site in the multiple sites at any one of the multiple historical moments. The prediction module is used to predict whether there is an abnormal increase in the number of users at multiple sites in the future based on the historical user data and the user switching data using a prediction model.

[0018] As a possible implementation, the prediction model includes a first prediction model and a second prediction model. The prediction module is specifically used to: input historical user data and user switching data into the first prediction model to obtain reconstructed user data output by the first prediction model, the reconstructed user data including the corrected number of users at any one of the multiple sites at any one of the multiple historical moments; calculate the difference between the reconstructed user data and the historical user data; input the user switching data and the difference into the second prediction model, and determine whether there is an abnormal increase in the number of users at multiple sites at a future moment according to the user number status prediction result output by the second prediction model.

[0019] Optionally, the first prediction model and the second prediction model are deep learning models based on graph neural networks.

[0020] Optionally, the input of the first prediction model is first matrix data and graph structure data, the first matrix data is used to represent historical user data, the graph structure data is used to represent user switching data, the graph structure data includes multiple nodes and edges between the multiple nodes, the multiple nodes are used to represent multiple sites, and the edge between two nodes is used to represent the frequency of switching between the two sites.

[0021] Optionally, the input of the second prediction model is the second matrix data and the central graph of each site, the second matrix data is used to represent the difference, the multiple sites include the first site, the central graph of the first site includes a central node, associated nodes and edges for connecting the nodes, the central node is used to represent the first site, the associated nodes are used to represent the site where user switching occurs with the first site, and the edges of the central graph are used to represent the frequency of switching between the two sites.

[0022] As a possible implementation method, the multiple sites include a first site, the output of the second prediction model is third matrix data, the third matrix data includes multiple vectors, the multiple vectors include a first vector, the first vector is used to represent the user quantity status of the first site at a future moment, when the first vector is greater than or equal to a first threshold value, it indicates that there will be an abnormal increase in the number of users of the first site at a future moment, that is, it is determined that a crowd will gather in the coverage area of ​​the first site at a future moment.

[0023] As a possible implementation method, the first prediction model is a deep learning model based on a long short-term memory network, and the second prediction model is a deep learning model based on a graph neural network.

[0024] Optionally, the historical user data includes the number of terminals accessed at any one of the multiple sites at any one of the multiple historical moments, and the reconstructed user data includes the corrected number of terminals accessed at any one of the multiple sites at any one of the multiple historical moments.

[0025] In a third aspect, a computing device is provided, including a memory and a processor, the memory being used to store a set of computer instructions, and when the processor executes the set of computer instructions, it is used to execute the operating steps of the crowd gathering prediction method in the first aspect or any possible implementation of the first aspect.

[0026] In a fourth aspect, a crowd gathering prediction system is provided, the system comprising multiple terminals, multiple base stations and the computing device described in the third aspect, the multiple base stations are connected to the multiple terminals, the computing device is used to collect historical user data and user switching data of the multiple base stations, and execute the operating steps of the crowd gathering prediction method in the first aspect or any possible implementation method of the first aspect.

[0027] In addition, the technical effects of the second, third and fourth aspects can refer to the technical effects of the crowd gathering prediction method described in the first aspect and will not be repeated here.

[0028] In a fifth aspect, a readable storage medium is provided. The readable storage medium includes: a computer program or instructions; when the computer program or instructions are executed on a computer, the computer executes the crowd gathering prediction method described in any possible implementation of the first aspect.

[0029] In a sixth aspect, a computer program product is provided. The computer program product includes a computer program or instructions, and when the computer program or instructions are executed on a computer, the computer executes the crowd gathering prediction method described in any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic diagram of the architecture of a computer system provided for this application;

[0031] Figure 2 A flow chart of a crowd gathering prediction method provided in this application;

[0032] Figure 3 A schematic diagram of a process for predicting crowd gathering provided in this application;

[0033] Figure 4 A schematic diagram of a graph structure data provided for this application;

[0034] Figure 5 A schematic diagram of an egocentric network diagram provided for this application;

[0035] Figure 6 A schematic diagram of another crowd gathering prediction step provided in this application;

[0036] Figure 7 A schematic diagram of the structure of a crowd gathering prediction device provided in this application;

[0037] Figure 8 A schematic diagram of the structure of a computing device provided for this application;

[0038] Fig. 9 A schematic diagram of the structure of a crowd gathering prediction system provided in this application. DETAILED DESCRIPTION

[0039] The crowd gathering prediction method, device and system provided in the embodiments of the present application can be applied to scenarios where crowd gathering prediction and early warning are provided to telecommunications operators, planning departments, event organizers, etc. The following is a brief introduction to the technologies that may be involved in the present application.

[0040] (1) Neural Network

[0041] A neural network can be composed of neurons, and a neuron can be a s The output of this operation unit satisfies the following formula (1).

[0042]

[0043] Among them, h W,b is the output of the operation unit, x is the input of the operation unit, s = 1, 2, ... n, n is a natural number greater than 1, W s For x s , b is the bias of the operation unit. f is the activation function of the neuron, which is used to introduce nonlinear characteristics into the neural network to convert the input signal in the neuron into the output signal. The output signal of the activation function can be used as the input of the next layer, and the activation function can be a sigmoid function. A neural network is a network formed by connecting multiple single neurons mentioned above, that is, the output of one neuron can be the input of another neuron. The input of each neuron can be connected to the local receptive field of the previous layer to extract the features of the local receptive field. The local receptive field can be an area composed of several neurons. The weight represents the strength of the connection between different neurons. The weight determines the influence of the input on the output. A weight close to 0 means that changing the input does not change the output. A negative weight means that increasing the input reduces the output.

[0044] In some feasible embodiments, the input signal of the neural network can be a signal in various forms such as video signals, image signals, matrix data, graph structure data, etc. The input signal of the neural network also includes various other computer-processable engineering signals, which are not listed here one by one. If the neural network is used to perform deep learning on the prediction of crowd gathering at base stations, the accuracy of the neural network prediction of abnormal crowd gathering at base stations can be improved.

[0045] (2) Graph structure data

[0046] Graph structured data is data stored in a graph data structure, which can also be referred to as a graph. Graph structured data includes one or more nodes. A node can have zero, one or more adjacent nodes. The connection line between two nodes is called an edge. A node can also be called a vertex.

[0047] The types of graph structure data include undirected graphs, directed graphs, weighted graphs, etc. The edges of undirected graphs have no direction, that is, two connected nodes can reach each other. The edges of directed graphs have directions, that is, two connected nodes can only be connected from one node to another node according to the direction of the edge. Each edge in a weighted graph is attached with a weight value, which represents the distance or cost from one vertex to another.

[0048] Graph structured data can be represented in the form of an adjacency matrix or an incidence matrix.

[0049] (3) Graph Neural Networks

[0050] Graph neural network refers to the general term for algorithms that use neural networks to learn graph structured data, extract and discover features and patterns in graph structured data, and meet the needs of graph learning tasks such as clustering, classification, prediction, segmentation, and generation. Graph neural network is a framework that uses deep learning to directly learn graph structured data. By formulating certain strategies on the nodes and edges in the graph, the graph structured data is converted into a standardized and standard representation, and then input into a variety of different neural networks for training, achieving excellent results in tasks such as node classification, edge information propagation, and graph clustering.

[0051] The graph neural network mentioned in this application is not limited to specific types, such as graph convolutional network (GCN), graph auto-encoder (gAE), graph generative network (GGN), graph recurrent network (GRN), graph attention network (GAT), etc.

[0052] (4) Long Short-Term Memory Network

[0053] Long short-term memory network is a type of recurrent neural network (RNN), which can solve the short-term memory deficiency of recurrent neural network. When a sequence is long enough, it will be difficult for the recurrent neural network to transmit information from an earlier time step to a later time step. LSTM can learn long-term dependent information and remember the information of earlier time steps, so it can connect the context. Specifically, the long short-term memory network has three gates, namely the forget gate, the input gate (also called the update gate, candidate gate) and the output gate. These three gates are used to control which information should be forgotten and discarded, which information should be retained, or remain unchanged.

[0054] In the issue of public place safety management, how to accurately and timely predict possible crowd gathering is a key point. The current crowd gathering prediction schemes include those based on computer vision technology and those based on non-visual technology.

[0055] Solutions based on computer vision technology mainly rely on cameras deployed in various places. By analyzing the images captured by the cameras, real-time calculation and prediction of the number and density of people can be achieved. First, this method requires a large number of cameras to support it, which leads to high deployment and maintenance costs. Secondly, for large-scale and high-density crowd gathering places, relying solely on visual solutions to process large amounts of image data will result in high system complexity and difficulty in ensuring the timeliness of predictions, thus affecting the accuracy of predictions.

[0056] The solution based on non-visual technology mainly uses the number of user access points of access sites such as wireless access points (such as Wi-Fi access points) and base stations to process and analyze to estimate the number of people in a specific area. However, the current research on the estimation of the number of people for wireless access points such as Wi-Fi access points mainly focuses on how to accurately estimate the number of people in a specific area through signal processing, while there are relatively few studies on how to use this information to predict the risk of crowd gathering. At the same time, the research on the estimation of the number of people for base stations only predicts the abnormal crowd gathering of a single base station based on the data of the single base station, without considering the mutual influence between base stations. In actual situations, the signal coverage range of a single base station is small, and the number of user access may be affected by the base stations around it. Therefore, the solution based on non-visual technology only predicts based on data such as the number of access terminals of a single base station, and there is also a problem of prediction accuracy.

[0057] The present application provides a crowd gathering prediction method, and specifically relates to a crowd gathering prediction method of "introducing user switching data between base stations to perform abnormal crowd gathering prediction of a prediction model". First, a computing device obtains historical user data and user switching data of multiple sites. Then, based on the historical user data and user switching data of multiple sites, the computing device uses a prediction model to predict whether there will be an abnormal increase in the number of users at multiple sites in the future. The increase in the number of users at the first site among the multiple sites indicates that a crowd has gathered in the coverage area of ​​the first site. Among them, the site is a base station or a base station cell. The historical user data includes: the number of users at any site among the multiple sites at any historical moment in multiple historical moments. The user switching data includes: the frequency of switching from one site to another site among the multiple sites at any historical moment in multiple historical moments.

[0058] Based on the crowd gathering prediction method, the computing device introduces the user switching data between multiple base stations when predicting whether there will be abnormal crowd gathering at a site. In this way, considering the mutual influence between base stations or base station cells, the historical user data and user switching data of multiple sites with a larger coverage area are introduced, and based on the correlation between the abnormal growth of the number of users at the site and crowd gathering, the abnormal crowd gathering prediction of multiple base stations is realized, which improves the accuracy of the prediction of crowd gathering.

[0059] The implementation of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0060] Figure 1 This is a schematic diagram of the architecture of a computer system provided in this application. Figure 1 As shown, the computer system 100 includes an execution device 110 , a training device 120 , a database 130 , a terminal device 140 , a data storage system 150 and a data collection device 160 .

[0061] The execution device 110 may be a terminal, such as a computer, a mobile terminal, a tablet computer, a laptop computer, a virtual reality (VR) device, an augmented reality (AR) device, a mixed reality (MR) device, an extended reality (ER) device, a camera or a vehicle-mounted computer, or an edge device (e.g., a box carrying a chip with processing capabilities). In the present application, the execution device 110 may be a computing device connected to a base station, or a computing device deployed at a base station, such as a server or a cloud device.

[0062] The training device 120 may be a terminal, or other computing device that supports integer computing, such as a server or a cloud device.

[0063] As a possible embodiment, the execution device 110 and the training device 120 are deployed on different physical devices (such as a server or a server in a cluster), or the execution device 110 and the training device 120 are different physical devices. Exemplarily, the execution device 110 and the training device 120 are processors deployed on different physical devices. For example, the execution device 110 can be a graphics processing unit (GPU), a central processing unit, other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The training device 120 can be a graphics processing unit (GPU), a neural network processing unit (NPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0064] In another possible embodiment, the execution device 110 and the training device 120 are deployed on the same physical device, or the execution device 110 and the training device 120 are the same physical device.

[0065] The data acquisition device 160 is used to collect training data and store the training data in the database 120. The data acquisition device 160 can be the same or different devices as the execution device 110 and the training device 120. In the embodiment of the present application, the data acquisition device 160 can be a computing device or a network device of an access site such as a base station or a wireless access point.

[0066] The training device 120 is used to train the neural network using training data until the loss function in the neural network converges, and the neural network training is completed when the loss function value is less than a specific threshold, so that the neural network reaches a certain accuracy. For example, the training device 120 uses historical user data and user switching data as input training data and reconstructed user data as output to train the neural network. For another example, the training device 120 uses user switching data and difference as input training data and the prediction result of abnormal growth of the number of users of the site as output to train the neural network. In the training process, back propagation is performed according to the loss function, and the parameters of the neural network are updated with gradients until the loss function value is less than a specific threshold. Alternatively, all the training data in the database 130 are used for training, and the neural network training is completed, so that the trained neural network has target functions such as reconstructing user data and predicting abnormal growth of the number of users. Furthermore, the training device 120 configures the trained neural network 101 to the execution device 110. The execution device 110 is used to realize the function of predicting abnormal growth of the number of users according to the trained neural network 101.

[0067] The model obtained by training the neural network with reconstructed user data as output can be called a first prediction model, and the model obtained by training the neural network with the prediction result of abnormal number of users of the site as output can be called a second prediction model.

[0068] Optionally, the neural network 101 is used to predict the corrected number of users of the site's historical user data at multiple historical moments, or to predict whether the site will have an abnormal increase in the number of users in the future. The neural network 101 may be a network type suitable for processing historical user data, user switching data, and differences in the form of sequence data or graph data, for example, the neural network 101 is a convolutional neural network (CNN), a recurrent neural network, or a graph neural network.

[0069] In some embodiments, the execution device 110 and the training device 120 are the same computing device, and the computing device can configure the trained neural network 101 to itself and use the trained neural network 101 to achieve the above-mentioned target function.

[0070] In other embodiments, the training device 120 may configure the trained neural network 101 to multiple execution devices 110. Each execution device 110 uses the trained neural network 101 to implement the above target function.

[0071] In combination with the computer system 100, the crowd gathering prediction method provided in this embodiment can be applied to any scenario where the abnormal state of data traffic needs to be predicted, such as fixed network, mobile network and wireless access network. In fixed network scenarios such as large enterprise networks or school networks, the fixed network may also encounter a situation where the number of users suddenly increases, resulting in excessive network pressure. Therefore, the crowd gathering prediction method provided by this application can be used to predict crowd gathering and abnormal warning. In mobile network scenarios such as the fourth generation mobile communication technology (4G) network and the fifth generation mobile communication technology (4G) network, the crowd gathering prediction method provided by this application can be used to predict crowd gathering and abnormal warning based on the service data of the base station. In the scenario of wireless access networks such as Wi-Fi, crowd gathering prediction and abnormal warning can be performed based on the service data of Wi-Fi to assist the administrator in managing network resources for Wi-Fi. In the above-mentioned fixed network, mobile network and wireless access network scenarios, the training and prediction process of the neural network 101 will be adaptively adjusted according to the difference in input data and output data, which will not be repeated here.

[0072] In some embodiments, the crowd gathering prediction method can be applied to various public places in the city, such as commercial areas, schools, parks, stadiums, etc. For example, in large-scale music festivals or sports games, the computer system 100 can use the crowd gathering prediction method to predict and issue abnormal warnings of crowd gathering in advance, help managers effectively dispatch resources, ensure the normal operation of the network, and conduct crowd dispersal in advance to avoid possible safety risks.

[0073] In other embodiments, the computer system 100 can use the crowd gathering prediction method to assist network operators in optimizing the energy usage of base stations, improving network service quality, and reducing operating costs. For example, by using the crowd gathering prediction method to monitor and predict network traffic in real time, operators can dynamically adjust network resources according to demand and achieve more refined operation management.

[0074] It should be noted that, in actual applications, the training data maintained in the database 130 may not all come from the data acquisition device 160, but may also be received from other devices. In addition, the training device 120 may not train the neural network entirely based on the training data maintained by the database 130, but may also obtain training data from the cloud or other places to train the neural network. The above description should not be used as a limitation on the embodiments of the present application.

[0075] Furthermore, according to the functions performed by the execution device 110, the execution device 110 can be further divided into: Figure 1 In the illustrated architecture, as shown in the figure, the execution device 110 is configured with a computing module 111 , an I / O interface 112 and a pre-processing module 113 .

[0076] Taking the execution device 110 as a computing device connected to an access site such as a base station or a wireless access point as an example, the computing module 111 can be a GPU, CPU, other general-purpose processors, DSP, ASIC, FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. on a vehicle-mounted computer.

[0077] For example, the computing module 111 is used to run the neural network 101 to implement the function of the neural network 101 to reconstruct the historical user data to obtain the reconstructed user data corresponding to the historical user data.

[0078] For another example, the calculation module 111 is used to calculate the difference between the reconstructed user data and the historical user data, and use the difference as an abnormal coefficient representing a sudden abnormal increase in the number of users.

[0079] For example, the computing module 111 is also used to run the neural network 101 to implement the function of the neural network 101 to predict the abnormal growth of the number of users.

[0080] The I / O interface 112 is used to exchange data with external devices. The user can input data to the I / O interface 112 through the terminal device 140, for example, to instruct the execution device 110 to start the function of reconstructing historical user data and predicting the abnormal growth of the number of users to execute the crowd gathering prediction method. In addition, the input data can also come from the database 130.

[0081] The preprocessing module 113 is used to preprocess the input data received by the I / O interface 112. In the embodiment of the present application, the preprocessing module 113 can be used to generate training data, such as a training set, a validation set, and a test set, based on the input data received from the I / O interface 112. Optionally, the preprocessing module 113 can also perform preprocessing operations such as denoising on the input data, such as matrix data and graph structure data of the base station, to eliminate irrelevant information and restore useful real information.

[0082] When the execution device 110 preprocesses the input data, or when the computing module 111 of the execution device 110 performs calculations and other related processing, the execution device 110 can call the data, code, etc. in the data storage system 150 for corresponding processing, and can also store the data and instructions obtained from the corresponding processing in the data storage system 150.

[0083] Finally, the I / O interface 112 returns the processing result to the terminal device 140, thereby providing it to the user so that the user can view the processing result. In the embodiment of the present application, the processing result can be a prediction result of whether the number of users of the site will increase abnormally in the future.

[0084] The terminal device 140 can be used as a data collection terminal to collect the input data of the input I / O interface 112 and the processing results of the output I / O interface 112 as new sample data, and store them in the database 130. Of course, the sample data can also be collected without passing through the terminal device 140, but the I / O interface 112 can store the input data of the input I / O interface 112 and the processing results of the output I / O interface 112 as new sample data in the database 130.

[0085] Figure 1 This is only a schematic diagram of a system architecture provided by an embodiment of the present application. Figure 1 The positional relationship between the devices, components, modules, etc. shown in the figure does not constitute any limitation. Figure 1 In the embodiment, the data storage system 150 is an external memory relative to the execution device 110. In other cases, the data storage system 150 may also be placed in the execution device 110.

[0086] Next, the crowd gathering prediction method provided by this embodiment is described in detail with reference to the accompanying drawings.

[0087] In the mobile network scenario, the above Figure 1 The execution device 110 in the computer system 100 may be a computing device capable of acquiring the user quantity data of the base station. Therefore, the crowd gathering prediction method is described in detail below by taking the execution device 110 as an example. Figure 2 As shown, the crowd gathering prediction method may include the following steps 210 to 220.

[0088] Step 210: The execution device 110 obtains historical user data and user switching data of multiple sites.

[0089] As a possible example, the execution device 110 obtains historical user data of multiple sites at multiple historical moments, and user switching data, that is, user switching data of multiple sites switching from one site to another site at multiple historical moments.

[0090] As a possible implementation, the execution device 110 collects historical user data and user switching data of multiple sites from multiple sites, or reads historical user data and user switching data of multiple sites from the data collection device 160. The historical user data and user switching data in the data collection device 160 are collected and stored by the data collection device 160 from multiple sites.

[0091] Optionally, the site may be a base station or a base station cell.

[0092] Among them, historical user data can be used to describe the number of users at multiple sites at multiple historical moments. User switching data can be used to describe the frequency of each site switching from one site to another at each historical moment. For example, the site is a base station, and the number of times the terminal of base station A switches to base station B is 100 times within 5 hours, and the user switching data can be recorded as 20 times / hour. For another example, the site is a base station cell, and the number of times the terminal of base station cell A switches to base station cell B is 200 times within 4 hours, and the user switching data can be recorded as 50 times / hour. Base station cell A and base station cell B can be base station cells covered by the same or different base stations.

[0093] Step 220: The execution device 110 uses a prediction model to predict whether there will be an abnormal increase in the number of users at multiple sites in the future based on historical user data and user switching data. The increase in the number of users at a first site among the multiple sites indicates that a crowd is gathering in the coverage area of ​​the first site.

[0094] As a possible example, the prediction model includes a first prediction model and a second prediction model. The execution device 110 inputs the historical user data and the user switching data into the first prediction model to obtain the reconstructed user data output by the first prediction model. The reconstructed user data includes the corrected number of users at any one of the multiple sites at any one of the multiple historical moments. The execution device 110 calculates the difference between the reconstructed user data and the historical user data, and then uses the second prediction model to predict whether there is an abnormal increase in the number of users at multiple sites at a future moment based on the user switching data and the difference, that is, whether there is an abnormal crowd gathering at any one of the multiple sites at a future moment.

[0095] As a possible implementation, the execution device 110 uses the second prediction model to predict whether the number of users of multiple sites will increase abnormally at a future moment based on the user switching data and the difference, which may be to obtain the user quantity state prediction result output by the second prediction model, and then determine whether the number of users of multiple sites will increase abnormally at a future moment according to the user quantity state prediction result. Taking the first site among the multiple sites as an example, if the number of users of the first site increases abnormally at a future moment, it is determined that a crowd will gather in the coverage area of ​​the first site at a future moment.

[0096] Optionally, considering that graph structure data can more intuitively and accurately describe the user communication relationship of multiple sites, using a deep learning model to train and predict based on graph structure data can improve the accuracy of predicting abnormal crowd gatherings. Before inputting the historical user data and the user switching data, the execution device 110 preprocesses the historical user data and the user switching data to obtain matrix data or graph structure data, and uses the matrix data and the graph structure data as input data for the first prediction model and the second prediction model.

[0097] Based on the crowd gathering prediction method provided in the above steps 210 to 220, the execution device 110 introduces the user switching data between multiple base stations when predicting whether abnormal crowd gathering will occur at a site. In this way, considering the mutual influence between base stations or base station cells, the historical user data and user switching data of multiple sites with a larger coverage area are introduced, and based on the correlation between the abnormal growth of the number of users at the site and crowd gathering, the abnormal crowd gathering prediction of multiple base stations is realized, thereby improving the accuracy of the prediction of crowd gathering.

[0098] Please refer to the specific steps for determining the above crowd gathering situations Figure 3 Step 224 shown is not repeated here.

[0099] Combination of the above Figure 2 The overall process of the crowd gathering prediction method is explained below. Figure 3 Steps 221 to 224 are shown as examples, which illustrate the process of executing device 110 using the first prediction model and the second prediction model to predict abnormal crowd gathering.

[0100] Step 221: The execution device 110 pre-processes the historical user data and the user switching data.

[0101] As a possible implementation method, the execution device 110 preprocesses the historical user data and user switching data of multiple sites to obtain the historical user data of multiple sites in the form of first matrix data, the user switching data in the form of graph structure data, and the user switching data in the form of a central graph.

[0102] Optionally, the first matrix data is represented as a matrix D, and the element D[i][j] in the matrix D represents the number of users at the i-th site at the j-th moment.

[0103] Alternatively, for example Figure 4As shown, the graph structure data includes node A representing the first site, node B representing the second site, node C representing the third site, and node C representing the fourth site. The weight of the edge between node A and node B is 3, the weight of the edge between node A and node C is 5, the weight of the edge between node B and node C is 4, the weight of the edge between node C and node D is 3, and the weight of the edge between node A and node D is 6. The value of the weight of the edge between two nodes represents the frequency of user switching between sites.

[0104] Optionally, the central graph in the present application may be an egocentric network graph, which may also be regarded as a kind of graph structure data. Figure 5 As shown, taking the first site as an example, the center graph of the first site can be an egocentric network graph. The center node n of the egocentric network graph of the first site represents the first site, and the associated nodes 1-13 represent sites directly or indirectly connected to the first site. The edge between two nodes represents the communication connection between the sites corresponding to the two nodes, and the weight of the edge ( Figure 5 (not shown) indicates the frequency of user switching between sites corresponding to two nodes. t-1 , S t-2 , S t-3 The indicated ring range is used to indicate the closeness of the relationship between the site corresponding to the associated node and the first site. For example, S t-1 Indicates the site that interacts with the first site through zero network device jumps, S t-2 Indicates the site that interacts with the first site through one network device jump. S t-3 Indicates the site that interacts with the first site through two network device jumps.

[0105] For example, the weight of the edge represents the frequency of user switching between two sites at multiple historical moments in the form of a matrix. The single egocentric network graph corresponding to the first site can represent the frequency of user switching between the first site and other sites at multiple historical moments. In this way, the central graph of the first site input when the second prediction model predicts the first site can be a single egocentric network graph.

[0106] For another example, the weight of an edge represents the frequency of user switching between two sites at a specific historical moment in the form of a numerical value. A single egocentric network graph corresponding to the first site can only represent the frequency of user switching between the first site and other sites at a specific historical moment. In this way, the central graph of the first site input when the second prediction model predicts the first site can be multiple egocentric network graphs of the first site at multiple historical moments.

[0107] The above-mentioned egocentric network diagram can completely and accurately characterize the impact of traffic interactions between various sites on the number of users at each site. Using the egocentric network diagram as the input of the second prediction model can enable the second prediction model to dynamically perceive the abnormal growth in the number of communicable users, so as to more timely predict whether abnormal crowd gathering will occur at the site in the future, thereby improving the accuracy and timeliness of the prediction.

[0108] Since preprocessing the historical user data and user switching data is a conventional data format conversion, this application does not elaborate on the specific steps of the data format conversion.

[0109] Step 222: The execution device 110 inputs the pre-processed historical user data and user switching data of the multiple sites into the first prediction model to obtain reconstructed user data output by the first prediction model.

[0110] As a possible implementation manner, the execution device 110 inputs the historical user data in the form of first matrix data and the user switching data in the form of graph structure data into the first prediction model to obtain the reconstructed user data output by the first prediction model.

[0111] Optionally, the reconstructed user data is represented in the form of second matrix data. For example, the second matrix data includes a matrix R, and the element R[i][j] in the matrix R represents the corrected number of users at the i-th site at the j-th moment.

[0112] In a possible embodiment of the present application, the first prediction model may further output predicted user data, and the predicted user data is expressed in the form of a prediction matrix. For example, the prediction matrix data includes a matrix P, and the element P[i][j] in the matrix P represents the number of users at the i-th site at the j-th time.

[0113] Step 223: The execution device 110 calculates the difference between the reconstructed user data and the historical user data.

[0114] As a possible implementation manner, the execution device 110 calculates the difference between the reconstructed user data and the historical user data of each site based on a matrix algorithm.

[0115] Optionally, the difference between the reconstructed user data and the historical user data may be abnormal matrix data formed by the difference between the matrix R and the matrix D, expressed as a matrix S, where the element S[i][j] in the matrix S represents the difference between the corrected number of users and the number of users before correction at the i-th site at the j-th moment. The matrix S may also be called an abnormal coefficient.

[0116] Taking the first site as an example, the larger the anomaly coefficient of the first site at the first historical moment, the greater the possibility that the number of users of the first site has abnormally increased at the first historical moment. In this way, since the reconstructed user data is mainly predicted by the first prediction model based on the historical change pattern of the number of users of the site, the result predicted by the first prediction model can be regarded as a sudden abnormal increase in the number of users.

[0117] In a possible embodiment of the present application, when the historical user data is missing, the difference between the reconstructed user data and the predicted user data may be used to replace the difference between the reconstructed user data and the historical user data.

[0118] For example, when the number of users at the i-th site at the j-th moment is missing from the historical user data, the execution device 110 uses the number of users at the i-th site at the m-th moment in the predicted user data to replace the historical user data, and calculates the corrected number of users at the i-th site at the j-th moment in the reconstructed user data to obtain the element value in the abnormal coefficient. The m-th moment belongs to the same time period as the j-th moment, such as the m-th moment is 8 o'clock on Wednesday morning this week, and the j-th moment is 8 o'clock on Wednesday morning last week.

[0119] In a possible implementation of the present application, the abnormal coefficient may also be obtained by clustering or statistics performed by the execution device 110 based on historical user data, predicted user data and / or reconstructed user data, which will not be described in detail here.

[0120] Step 224: The execution device 110 inputs the user switching data and the difference into the second prediction model to obtain the user quantity status prediction result output by the second prediction model.

[0121] As a possible implementation manner, the execution device 110 inputs the user switching data in the form of a central graph and the difference in the form of abnormal matrix data into the second prediction model to obtain the user quantity status prediction result output by the second prediction model.

[0122] Optionally, the execution device 110 inputs the user switching data in the form of a central graph of the first site and the difference in the form of abnormal matrix data into the second prediction model, and obtains the second prediction model outputting the user quantity status prediction result of the first site. For example, the user quantity status prediction result is the third matrix data. Taking the first site as an example, the third matrix data is a vector, which is used to indicate whether there is an abnormal growth in the number of users of the first site at a future moment. If the vector output by the second prediction model is greater than or equal to the first threshold, it means that the first site will appear at a future moment in the future moment, that is, it represents that the coverage area of ​​the first site will have crowds gathering at a future moment. If the vector output by the second prediction model is less than the first threshold, it means that there will be no abnormal growth in the number of users at the first site at a future moment, that is, it represents that there will be no crowds gathering in the coverage area of ​​the first site at a future moment.

[0123] Optionally, the input of the second prediction model can also be the abnormal matrix data and the center map of multiple sites. The second prediction model performs pre-prediction according to the abnormal matrix data and the center map of each site in turn, and the vectors output for each site are combined into the third matrix data, and the third matrix data includes multiple vectors. V in the third matrix data i The vector corresponding to the i-th site is used to indicate whether the number of users of the i-th site will increase abnormally in the future.

[0124] In the present application, in order to cooperate with the types of input data of the above-mentioned first prediction model and the second prediction model to obtain better prediction accuracy, the execution device 110 adopts a graph neural network that has a better processing effect on graph structure data to implement the functions of the first prediction model and the second prediction model, that is, the first prediction model and the second prediction model are deep learning models based on graph neural networks.

[0125] Based on the selected deep learning model based on graph neural network, the difference between the training process of neural network based on graph neural network and the conventional model training process lies only in the adaptive changes of input, output and loss function, which will not be elaborated here.

[0126] After the execution device 110 obtains the third matrix data output by the second prediction model, it can also predict the abnormal growth of the number of users of multiple sites at a future moment according to the third matrix data.

[0127] Taking the first site as an example, the execution device 110 performs V in the third matrix data. 1 When it is greater than or equal to the first threshold, it is determined that the number of users of the first site will increase abnormally at a future time, and further, it is determined that a crowd will gather in the coverage area of ​​the first site at a future time.

[0128] In this way, the crowd gathering prediction method of the present application can effectively predict the crowd gathering situation at multiple sites, and issue early warnings in time when possible abnormal gathering situations are detected, thereby helping operators and managers take appropriate measures to avoid possible problems and risks.

[0129] Combination of the above Figure 2-Figure 5 Taking the first prediction model and the second prediction model as deep learning models based on graph neural networks as an example, the crowd gathering prediction method provided by the present application is described. The present application does not limit the model types of the first prediction model and the second prediction model. For example, the first prediction model and the second prediction model can also be models based on convolutional neural networks or recurrent neural networks, or one is a model based on convolutional neural networks and the other is a model based on recurrent neural networks.

[0130] Combine the following Figure 6, taking the first prediction model as a deep learning model based on long short-term memory network and the second prediction model as a deep learning model based on graph neural network as an example, the crowd gathering prediction method provided by the present application is described. Figure 6 As shown, the crowd gathering prediction method may include the following steps 221' to 224'.

[0131] Step 221 ′: Step 221 : The execution device 110 pre-processes the historical user data and the user switching data.

[0132] As a possible implementation method, the execution device 110 preprocesses the historical user data and user switching data of multiple sites to obtain the historical user data of multiple sites in the form of first matrix data, the user switching data in the form of graph structure data, and the user switching data in the form of a central graph.

[0133] The historical user data in the first matrix data form, the user switching data in the graph structure data form, and the user switching data in the central graph form of the above-mentioned multiple sites are the same as the data in step 221, except that the number of users described in the historical user data refers to the number of terminals accessed. For example, the historical user data includes the number of terminals accessed at any one of the multiple sites at any one of the multiple historical moments.

[0134] Optionally, the number of terminals accessed by the above-mentioned multiple sites at multiple historical moments is obtained by the execution device 110 collecting statistics on trajectory data of the terminals moving between the multiple sites or behavior data of the users.

[0135] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the relevant laws and regulations and do not violate public order and good morals. For example, in the technical solution of this application, the processing of user personal information is carried out with the authorization of the user, which is uniformly explained here and will not be repeated below.

[0136] Step 222': the execution device 110 inputs the pre-processed historical user data and user switching data of the plurality of sites into the first prediction model to obtain reconstructed user data output by the first prediction model.

[0137] As a possible implementation method, the specific implementation method of step 222' is different from the above-mentioned step 222 in that the first prediction model is a deep learning model based on a long short-term memory network, and the historical user data input into the first prediction model includes the number of terminals accessed to any site among multiple sites at any historical moment in multiple historical moments, and the reconstructed user data output by the first prediction model is obtained after correcting the number of terminals accessed to any site at any historical moment where there may be anomalies in the historical user data.

[0138] Step 223 ′: the execution device 110 calculates the difference between the reconstructed user data and the historical user data.

[0139] As a possible implementation, the specific implementation of step 223' differs from the above step 223 in that the difference is the difference between the number of terminals accessed by the site at any historical moment after correction and the number of terminals accessed by the site at the corresponding historical moment before correction.

[0140] Step 224 ′: the execution device 110 inputs the user switching data and the difference into the second prediction model to obtain the user quantity status prediction result output by the second prediction model.

[0141] As a possible implementation manner, for the specific implementation manner of step 224', please refer to the relevant description of the above step 224, which will not be repeated here.

[0142] Combination of the above Figure 2-Figure 6 The crowd gathering prediction method of the present application is described in detail. In conjunction with the above-mentioned crowd gathering prediction method, the present application also provides a crowd gathering prediction device. Figure 7 Schematic diagram of the structure of a possible crowd gathering prediction device provided in this embodiment. The crowd gathering prediction device can be used to implement the functions of the execution device 110 or the training device 120 in the above method embodiment, and thus also has the beneficial effects possessed by the above method embodiment. In this embodiment, the crowd gathering prediction device can be as follows Figure 2 The execution device 110, training device 120 or other device with computing function shown may also be a module (such as a chip) applied to a server.

[0143] like Figure 7 As shown, the crowd gathering prediction device 700 includes a data processing module 710 and a prediction module 720.

[0144] The crowd gathering prediction device 700 can be used to achieve the above Figure 2 and / or Figure 3 In the method embodiment shown in , the functions of the device 110 are executed, and the various modules included in the crowd gathering prediction device 700 are specifically used to implement the following functions.

[0145] The data processing module 710 is used to obtain historical user data and user switching data of multiple sites, where the historical user data includes the number of users of any site in the multiple sites at any historical moment in the multiple historical moments, and the user switching data includes the frequency of switching from one site to another site in the multiple sites at any historical moment in the multiple historical moments. The site may be a base station or a base station cell. For example, the data processing module 710 is used to perform the following steps: Figure 2Step 210 is shown.

[0146] The prediction module 720 is used to predict whether there will be abnormal growth in the number of users at multiple sites in the future based on historical user data and user switching data using a prediction model. Figure 2 Step 220 is shown.

[0147] As a possible implementation, the prediction model includes a first prediction model and a second prediction model. The prediction module 720 is specifically used to: input historical user data and user switching data into the first prediction model to obtain reconstructed user data output by the first prediction model, the reconstructed user data including the corrected number of users at any one of the multiple sites at any one of the multiple historical moments; calculate the difference between the reconstructed user data and the historical user data; input the user switching data and the difference into the second prediction model, and determine whether there is an abnormal increase in the number of users at multiple sites in the future according to the user number status prediction result output by the second prediction model.

[0148] Optionally, the first prediction model and the second prediction model are deep learning models based on graph neural networks.

[0149] Optionally, the input of the first prediction model is first matrix data and graph structure data, the first matrix data is used to represent historical user data, the graph structure data is used to represent user switching data, the graph structure data includes multiple nodes and edges between the multiple nodes, the multiple nodes are used to represent multiple sites, and the edge between two nodes is used to represent the frequency of switching between the two sites.

[0150] Optionally, the input of the second prediction model is the second matrix data and the central graph of each site, the second matrix data is used to represent the difference, the multiple sites include the first site, the central graph of the first site includes a central node, associated nodes and edges for connecting the nodes, the central node is used to represent the first site, the associated nodes are used to represent the site where user switching occurs with the first site, and the edges of the central graph are used to represent the frequency of switching between the two sites.

[0151] As a possible implementation method, the multiple sites include a first site, the output of the second prediction model is a third matrix data, the third matrix data includes multiple vectors, the multiple vectors include a first vector, the first vector is used to represent the user quantity status of the first site at a future moment, and when the first vector is greater than or equal to a first threshold, it indicates that the number of users of the first site will increase abnormally at a future moment.

[0152] As a possible implementation method, the first prediction model is a deep learning model based on a long short-term memory network, and the second prediction model is a deep learning model based on a graph neural network.

[0153] Optionally, the historical user data includes the number of terminals accessing any one of the multiple sites at any one of the multiple historical moments, and the reconstructed user data includes the corrected number of terminals accessing any one of the multiple sites at any one of the multiple historical moments.

[0154] It should be understood that the crowd gathering prediction device 700 of the embodiment of the present application may also include any module for implementing the functions of each step in the data processing method, and any module may be implemented by software or by hardware. Exemplarily, the implementation of the data processing module 710 is described below by taking the data processing module 710 as an example. Similarly, the implementation of the prediction module 720 may refer to the implementation of the data processing module 710.

[0155] As an example of a software functional unit, the data processing module 710 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above-mentioned computing instance may be one or more. For example, the data processing module 710 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code can be distributed in the same region (region) or in different regions. Furthermore, the multiple hosts / virtual machines / containers used to run the code can be distributed in the same availability zone (AZ) or in different AZs, each AZ including a data center or multiple data centers with similar geographical locations. Among them, usually a region can include multiple AZs.

[0156] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Usually, a VPC is set up in a region. For cross-region communication between two VPCs in the same region and between VPCs in different regions, a communication gateway needs to be set up in each VPC to achieve interconnection between VPCs through the communication gateway.

[0157] In this way, the crowd gathering prediction device 700 can be software, or it can be a service provided in the form of SaaS (software as a service). Users can subscribe to the service according to actual needs to obtain the functions of the crowd gathering prediction device 700 provided in this application.

[0158] As an example of a hardware functional unit, the data processing module 710 may include at least one computing device, such as a server, etc. Alternatively, the data processing module 710 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0159] The multiple computing devices included in the data processing module 710 can be distributed in the same region or in different regions. The multiple computing devices included in the data processing module 710 can be distributed in the same AZ or in different AZs. Similarly, the multiple computing devices included in the data processing module 710 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0160] It should be noted that, in other embodiments, the data processing module 710 can be used to execute any step in the crowd gathering prediction method, and the prediction module 720 can be used to execute any step in the crowd gathering prediction method. The steps that the data processing module 710 and the prediction module 720 are responsible for implementing can be specified as needed. The data processing module 710 and the prediction module 720 respectively implement different steps in the crowd gathering prediction method to realize all the functions of the crowd gathering prediction device 700.

[0161] For example, Figure 8 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. The computing device may be a terminal device, a network device, a robot, an onboard computer, etc., or may be a chip (system) or other components or assemblies that can be provided in a terminal device, a network device, a robot, or an onboard computer. For example, the computing device provided in an embodiment of the present application is Figure 1 An execution device 110 or a training device 120 in the computer system 100 is shown.

[0162] like Figure 8As shown, the computing device 800 may include a processor 801. Optionally, the computing device 800 may also include a memory 802 and / or a transceiver 803. The processor 801 is coupled with the memory 802 and the transceiver 803, such as being connected via a communication bus.

[0163] Combine the following Figure 8 The components of the computing device 800 are described in detail:

[0164] The processor 801 is the control center of the computing device 800, and may be a processor or a general term for multiple processing elements. For example, the processor 801 is one or more central processing units, or may be a dedicated integrated circuit, or may be configured to implement one or more integrated circuits of the embodiments of the present application, such as one or more microprocessors (digital signal processor, DSP), or one or more field programmable gate arrays.

[0165] Optionally, the processor 801 may execute various functions of the computing device 800 by running or executing software programs stored in the memory 802 and calling data stored in the memory 802, such as Figure 2 Steps 210 to 220 shown or functions implemented by modules such as the data processing module 710 and the prediction module 720 in the crowd gathering prediction device 700.

[0166] In a specific implementation, as an embodiment, the processor 801 may include one or more CPUs, such as Figure 8 CPU0 and CPU1 are shown in FIG.

[0167] In a specific implementation, as an embodiment, the computing device 800 may also include multiple processors, such as Figure 8 801 and processor 804 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0168] The memory 802 is used to store a software program for executing the solution of the present application, for example, to enable the processor 801 to execute the following Figure 2 The software program for the functions implemented by steps 210-220 or the data processing module 710, prediction module 720 and other modules in the crowd gathering prediction device 700 is controlled and executed by the processor 801. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0169] Optionally, the memory 802 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 802 may be integrated with the processor 801, or may exist independently and accessed through the interface circuit ( Figure 8 (not shown) is coupled to the processor 801, which is not specifically limited in the embodiment of the present application.

[0170] The transceiver 803 is used for communication with other devices. For example, the computing device 800 is a base station in a mobile network or a computing device connected to a base station, and the transceiver 803 can be used to communicate with another base station or another computing device.

[0171] Optionally, the transceiver 803 may include a receiver and a transmitter ( Figure 8 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0172] Optionally, the transceiver 803 may be integrated with the processor 801, or may exist independently and be connected to the processor 801 through the interface circuit ( Figure 8 (not shown) is coupled to the processor 801, which is not specifically limited in the embodiment of the present application.

[0173] It should be noted that Figure 8 The structure of the computing device 800 shown in the figure does not constitute a limitation on the device, and an actual device may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0174] In addition, the technical effects of the computing device 800 can refer to the technical effects of the crowd gathering prediction method described in the above method embodiment, and will not be repeated here.

[0175] Since the computing device 800 of the present application is used to process data from access sites such as base stations and wireless access points to implement the crowd gathering prediction method described in the above method embodiment, the present application also provides a crowd gathering prediction system 900.

[0176] like Fig. 9 As shown, the crowd gathering prediction system 900 includes multiple terminals 910, multiple base stations 920, and a computing device 800. The multiple terminals 910 are communicatively connected to the multiple base stations 920, and the computing device 800 is connected to the multiple base stations 920 or deployed in one or more base stations among the multiple base stations 920.

[0177] The multiple base stations 920 are used to collect user quantity data of the multiple terminals 910 and send the user quantity data to the computing device 800, so that the computing device 800 pre-processes the user quantity data to obtain historical user data and user switching data, etc., and executes the steps of the crowd gathering prediction method provided by the present application, such as Figure 2 Steps 210 to 220 shown or functions implemented by modules such as the data processing module 710 and the prediction module 720 in the crowd gathering prediction device 700.

[0178] It should be understood that the processor in the embodiments of the present application may be a central processing unit, and the processor may also be other general-purpose processors, digital signal processors, application-specific integrated circuits, field programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0179] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0180] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0181] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0182] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0183] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0184] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0186] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.

[0187] In the present application, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b and c can be single or multiple.

[0188] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0189] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A crowd gathering prediction method, characterized in that: include: Acquire historical user data and user switching data of multiple sites, wherein the historical user data includes the number of users of any site among the multiple sites at any historical moment of the multiple historical moments, and the user switching data includes the frequency of switching from one site to another site at any historical moment of the multiple historical moments, wherein the site is a base station or a base station cell; Based on the historical user data and the user switching data, a prediction model is used to predict whether there will be an abnormal increase in the number of users at multiple sites in the future. The increase in the number of users at a first site among the multiple sites indicates that a crowd is gathering in the coverage area of ​​the first site.

2. The method according to claim 1, characterized in that The prediction model includes a first prediction model and a second prediction model. The prediction model is used to predict whether there is an abnormal growth in the number of users of multiple sites at a future moment based on the historical user data and the user switching data, including: Inputting the historical user data and the user switching data into the first prediction model to obtain reconstructed user data output by the first prediction model, wherein the reconstructed user data includes a corrected number of users at any one of the multiple sites at any one of the multiple historical moments; Calculating a difference between the reconstructed user data and the historical user data; The user switching data and the difference are input into the second prediction model, and it is determined whether there will be an abnormal increase in the number of users at multiple sites in the future according to the user quantity status prediction result output by the second prediction model.

3. The method according to claim 2, characterized in that The first prediction model and the second prediction model are deep learning models based on graph neural networks.

4. The method according to claim 3, characterized in that The input of the first prediction model is first matrix data and graph structure data, the first matrix data is used to represent the historical user data, the graph structure data is used to represent the user switching data, the graph structure data includes multiple nodes and edges between the multiple nodes, the multiple nodes are used to represent the multiple sites, and the edge between two nodes is used to represent the frequency of switching between the two sites.

5. The method according to claim 3 or 4, characterized in that: The input of the second prediction model is second matrix data and a central graph of each site, the second matrix data is used to represent the difference, the multiple sites include a first site, the central graph of the first site includes a central node, associated nodes and edges for connecting nodes, the central node is used to represent the first site, the associated nodes are used to represent sites with user switching with the first site, and the edges of the central graph are used to represent the frequency of switching between the two sites.

6. The method according to any one of claims 2 to 5, characterized in that: The multiple sites include a first site, the output of the second prediction model is third matrix data, the third matrix data includes multiple vectors, the multiple vectors include a first vector, the first vector is used to represent the user quantity status of the first site at the future moment, when the first vector is greater than or equal to a first threshold value, it indicates that the number of users of the first site has an abnormal growth at the future moment.

7. The method according to claim 2, characterized in that The first prediction model is a deep learning model based on a long short-term memory network, and the second prediction model is a deep learning model based on a graph neural network.

8. The method according to claim 7, characterized in that The historical user data includes the number of terminals accessing any of the multiple sites at any historical moment in the multiple historical moments, and the reconstructed user data includes the revised number of terminals accessing any of the multiple sites at any historical moment in the multiple historical moments.

9. A crowd gathering prediction device, characterized in that: The invention comprises a module for executing the operation steps of the method described in any one of claims 1 to 8.

10. A computing device, characterized in that The computing device includes a memory and a processor, wherein the memory is used to store a set of computer instructions; when the processor executes the set of computer instructions, the operation steps of any one of the methods described in claims 1-8 are performed.

11. A crowd gathering prediction system, characterized in that: The system includes multiple terminals, multiple sites and the computing device described in claim 10, wherein the multiple sites are connected to the multiple terminals, and the computing device is used to collect historical user data and user switching data of the multiple sites and execute the operating steps of any method described in claims 1-8.

12. A readable storage medium, characterized in that: The readable storage medium includes a computer program or instructions. When the computer program or instructions are executed on a computer, the computer is caused to execute the operation steps of any one of the methods described in claims 1 to 8.

Images