Base station signaling data simulation method and device, equipment, storage medium and product

Abstract

The invention relates to a base station signaling data simulation method and device, equipment, a storage medium and a product, and the method comprises the steps: obtaining an initial user track set; each user track in the initial user track set has an authenticity label; performing data volume expansion based on the initial user track set, the user simulation data and the environment simulation data through a generator in the generative adversarial network to obtain a target user track set; simulating signaling data of the base stations based on each user track in the target user track set and the position information of each base station; according to the method, the accuracy and the credibility of the user track generated through simulation can be improved, so that the credibility and the accuracy of the generated base station signaling data are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communication technology, and in particular to a base station signaling data simulation method, apparatus, device, storage medium, and product. Background Art

[0002] In existing technologies, the generation of base station signaling data typically relies on actual user trajectory data and actual base station operation data, which is generated through communication between base stations and user devices in mobile communication networks. However, obtaining large-scale, authentic user trajectory data and base station signaling data is costly and time-consuming, especially since many data dimensions involve user privacy, making acquisition difficult. Furthermore, the user trajectory data generation methods used in existing technologies often rely on simple random walks or simulations based on historical data, lacking sufficient diversity and authenticity, resulting in low credibility and accuracy of the generated base station signaling data. Summary of the Invention

[0003] The present invention provides a method, apparatus, device, storage medium, and product for simulating base station signaling data, which can improve the accuracy and credibility of simulated user trajectories, thereby improving the credibility and accuracy of generated base station signaling data. The technical solution is as follows.

[0004] In one aspect, a base station signaling data simulation method is provided, the method comprising: Acquire an initial user trajectory set; each user trajectory in the initial user trajectory set has an authenticity label; Expanding the data volume based on the initial user trajectory set, user simulation data, and environment simulation data by generating an adversarial network to obtain a target user trajectory set; Based on the trajectory of each user in the target user trajectory set and the position information of each base station, signaling data of the base station is simulated.

[0005] On the other hand, a base station signaling data simulation device is provided, the device comprising: A trajectory acquisition module is used to acquire an initial user trajectory set; each user trajectory in the initial user trajectory set has an authenticity label; A trajectory expansion module is used to expand the data volume based on the initial user trajectory set, user simulation data and environment simulation data through a generative adversarial network to obtain a target user trajectory set; The simulation module is used to simulate the signaling data of the base station based on the trajectory of each user in the target user trajectory set and the position information of each base station.

[0006] In a possible implementation, the simulation module includes: An information acquisition submodule, configured to acquire location information of a first location, where the first location is any location in a target user trajectory; the target user trajectory is any one of the user trajectories; a base station determination submodule, configured to determine a neighboring base station of the first position by using a K-dimensional tree algorithm and location information of each base station, wherein the neighboring base station is a base station closest to the first position; The simulation submodule is configured to simulate and generate a signaling event between the user terminal at the first location and the neighboring base station.

[0007] In a possible implementation, the target area where each base station is located includes multiple sub-areas, and the apparatus further includes: An information acquisition module is used to obtain the center location information of each sub-area; The first establishing module is used to establish a top-level K-dimensional tree based on the center position information of each sub-region; The second establishing module is used to establish a regional K-dimensional tree corresponding to each sub-region based on the location information of the base stations covered by each sub-region.

[0008] In a possible implementation, the base station determines a submodule configured to: Determine the target sub-region to which the first position belongs by using a K-dimensional tree algorithm and the top-level K-dimensional tree; The neighboring base station of the first position is determined by using a K-dimensional tree algorithm and a regional K-dimensional tree corresponding to the target sub-region.

[0009] In a possible implementation, the trajectory expansion module includes: a trajectory synthesis submodule, configured to generate, by means of a generator of the generative adversarial network, respective synthetic user trajectories based on the user simulation data and the environment simulation data; A trajectory verification submodule, configured to determine, through the discriminator of the generative adversarial network, the probability that each to-be-verified user trajectory is a real user trajectory; the to-be-verified user trajectory is a real user trajectory or a synthetic user trajectory in the initial user trajectory set; A training submodule, configured to train the generator and the discriminator by optimizing an adversarial loss function until the function value of the optimized adversarial loss function converges, thereby obtaining a trained generator; The target user trajectory set is obtained by performing data expansion based on the user simulation data and the environment simulation data through a trained generator.

[0010] In a possible implementation, the user simulation data includes user attribute simulation data and social security information simulation data, and the environment simulation data includes weather condition simulation data and traffic condition simulation data.

[0011] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the above-mentioned base station signaling data simulation method.

[0012] On the other hand, a computer-readable storage medium is provided, in which at least one computer program is stored. The computer program is loaded and executed by a processor to implement the above-mentioned base station signaling data simulation method.

[0013] On the other hand, a computer program product is provided, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer is caused to execute to implement the base station signaling data simulation method provided in the above-mentioned various optional implementation methods.

[0014] The base station signaling data simulation method provided in the embodiments of the present application obtains an initial user trajectory set containing real user trajectories, and then uses a generative adversarial network to perform data expansion based on the initial user trajectory set, user simulation data, and environmental simulation data to obtain a target user trajectory set. Based on the individual user trajectories in the target user trajectory set and the location information of each base station, the base station signaling data is simulated. In the above method, the use of a generative adversarial network to fuse real user trajectories and multi-dimensional simulation data for data expansion improves the accuracy and credibility of the simulated user trajectories, reduces the privacy and cost thresholds for data acquisition, and provides more reliable data support for base station signaling data simulation, thereby improving the credibility and accuracy of the generated base station signaling data.

[0015] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] Figure 1 A flowchart of a base station signaling data simulation method provided by an exemplary embodiment of the present application is shown; Figure 2 A flowchart of a base station signaling data simulation method provided by another exemplary embodiment of the present application is shown; Figure 3 A structural block diagram of a base station signaling data simulation device provided by an exemplary embodiment of the present application is shown; Figure 4 A structural block diagram of a computer device according to an exemplary embodiment of the present application is shown; Figure 5 A structural block diagram of a computer device is shown in another exemplary embodiment of the present application. DETAILED DESCRIPTION

[0018] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numbers in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present application. Rather, they are merely examples of methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0019] In order to improve the credibility and accuracy of base station signaling data, the embodiment of the present application provides a base station signaling data simulation method. Figure 1 A flowchart of a base station signaling data simulation method provided by an exemplary embodiment of the present application is shown. The method can be executed by a computer device, which can be implemented as a server or a terminal, such as Figure 1 As shown, the method may include the following steps.

[0020] Step 110 , obtaining an initial user trajectory set; each user trajectory in the initial user trajectory set has an authenticity label.

[0021] The initial user trajectory set may include user trajectories with a small amount of data and authenticity labels, wherein the user trajectory records the user's position sequence in a continuous time and may include information such as timestamp, movement speed, and stay duration. The authenticity label may be a manually annotated label.

[0022] In a possible implementation, the user trajectories in the initial user trajectory set may be user trajectories obtained from real users.

[0023] In another possible implementation, the user trajectories in the initial user trajectory set can be randomly generated using a trajectory generation algorithm and manually screened for reasonable user trajectories. This trajectory generation algorithm can be a random walk algorithm, a path generation model based on random steps that generates a continuous position sequence by simulating irregular movement. In user trajectory generation, starting from the initial position, the direction (such as latitude and longitude offset) and step length (i.e., displacement distance) are randomly selected for each step. Randomness may be controlled by combining environmental constraints (such as road networks) or probability distributions (such as Gaussian distribution). The generation process can include a time dimension to simulate movement speed, and user stop behavior can be simulated using stop probabilities, ultimately outputting a trajectory that conforms to spatial continuity and realistic movement patterns.

[0024] For illustration, assume that the user's current location is The distance and direction of each move are random. The moving distance d is sampled from a normal distribution and is expressed as:

[0025] The movement direction 𝜃 is sampled from a uniform distribution and is expressed as:

[0026] The user's next location is calculated from the current location and the moving distance and direction, expressed as:

[0027]

[0028] By repeating the above process, each simulated user trajectory can be simulated, and the initial user trajectory set can be obtained through manual screening.

[0029] In step 120 , a generator in a generative adversarial network performs data expansion based on the initial user trajectory set, user simulation data, and environment simulation data to obtain a target user trajectory set.

[0030] A Generative Adversarial Network (GAN) is a model consisting of a generator and a discriminator. The generator is responsible for generating seemingly real data, while the discriminator distinguishes the generated data from real data. This setting allows the generator and discriminator to compete with each other during training, thereby improving the quality of the generated data.

[0031] The generator receives a random noise vector and transforms it into an output similar to real data through a complex network structure (such as a convolutional neural network). The goal of the generator is to deceive the discriminator as much as possible into thinking that the output is real.

[0032] The discriminator receives real data or data generated by the generator and outputs a probability value indicating the probability that the input data is real. The goal of the discriminator is to correctly distinguish between real and generated data.

[0033] In one possible implementation, the computer device may input only the initial user trajectory set into the generative adversarial network for data expansion. In another possible implementation, in order to further improve the authenticity of the expanded user trajectory, in addition to inputting the initial user trajectory set into the generative adversarial network, user simulation data and environment simulation data are also input into the generative adversarial network, so that the generative adversarial network outputs the expanded user trajectory to obtain the target user trajectory set. The user simulation data may include simulated user attribute information in multiple dimensions, such as user communication account, user income information, etc., and the environment simulation data may include simulated environmental attribute information of the user's environment in multiple dimensions, such as the transportation used by the user, weather conditions, etc.

[0034] The target user trajectory set may include each user trajectory in the initial user trajectory set and each user trajectory obtained after data expansion by the generative adversarial network. The data volume of the target user trajectory set is much larger than that of the initial user trajectory set.

[0035] Step 130 : Simulate base station signaling data based on the trajectory of each user in the target user trajectory set and the location information of each base station.

[0036] The computer device can obtain the location information of each base station from the operator's public base station database. This location information may include latitude and longitude information, and further, this location information may also include altitude information. Illustratively, the location information of each base station may be recorded in a base station information table. In other words, the base station information table includes the location information of each base station in the target area. Furthermore, the base station information table may also include other relevant parameters of each base station, such as signal coverage range, capacity, etc.

[0037] In one possible implementation, a computer device may associate the nearest base station based on the time and location on the user's trajectory to simulate a signaling event generated by the interaction between the base station and the terminal corresponding to the user; wherein the signaling data of the base station may refer to a log recording the interaction between the user and the base station, and the signaling data may include a user identifier, a base station identifier, a connection timestamp, and a signaling event type, and the signaling event type may include periodic registration, a switching event, and a service event, etc.

[0038] In a possible implementation, the computer device may output the simulated signaling data of the base station through a structured table or a log file.

[0039] In summary, the base station signaling data simulation method provided in the embodiment of the present application obtains an initial user trajectory set containing real user trajectories, and expands the data volume based on the initial user trajectory set, user simulation data, and environmental simulation data through a generative adversarial network to obtain a target user trajectory set. Based on the individual user trajectories in the target user trajectory set and the location information of each base station, the base station signaling data is simulated. In the above method, the data volume is expanded by using a generative adversarial network to fuse real user trajectories and multi-dimensional simulation data, which improves the accuracy and credibility of the simulated user trajectories, reduces the privacy and cost thresholds for data acquisition, and provides more reliable data support for base station signaling data simulation, thereby improving the credibility and accuracy of the generated base station signaling data.

[0040] In a possible implementation, in order to improve the efficiency of signaling data of the simulated base station, the computer device can determine the base station based on the K-dimensional tree algorithm. Based on this, Figure 2 A flowchart of a base station signaling data simulation method provided by another exemplary embodiment of the present application is shown. The method can be executed by a computer device, which can be implemented as a server or a terminal, such as Figure 2 As shown, the method may include the following steps.

[0041] Step 210: Acquire an initial user trajectory set; each user trajectory in the initial user trajectory set has an authenticity label.

[0042] Step 220 : Generate an adversarial network to perform data expansion based on the initial user trajectory set, user simulation data, and environment simulation data to obtain a target user trajectory set.

[0043] In the embodiment of the present application, user simulation data includes user attribute simulation data, social security information simulation data, and environmental simulation data includes weather condition simulation data and traffic condition simulation data. Illustratively, user attribute simulation data can be data such as mobile phone number, age, gender, and place of residence, and the computer device can randomly assign various types of user data simulation data to users in a normal distribution manner; considering privacy issues, social security information simulation data can simulate social security data in a gear division manner. For example, the computer device can use a random distribution method to assign no social security, low social security gear, medium social security gear, and high social security gear to users. It should be noted that the types of the above-mentioned user attribute simulation data and the gear division of the social security information simulation data can be determined based on actual needs, and this application does not impose any restrictions on this.

[0044] Environmental simulation data can simulate changes in the real environment, increasing the diversity and authenticity of user trajectory data. Traffic simulation data can be fitted based on the type of transportation and congestion data in the target area. For example, transportation types can include bus, subway, car, walking, etc. Combined with the congestion data in the target area, speed fitting is performed at the target time level, such as hourly speed aggregation or minute-by-minute speed fitting.

[0045] The target area is the area where the base station for signaling data simulation is located. The weather condition simulation data can be randomly generated based on the climate change laws corresponding to the target area. The number of rainy days in target area A each year is approximately 70 to 90 days, mainly concentrated in June-August. In one possible implementation method, the weather condition simulation data can be randomly generated according to weather classification, such as sunny days, rainy days, cloudy days, etc. In another possible implementation method, it can be classified into two categories according to good weather and bad weather, such as sunny and cloudy days as good weather, rainy and snowy days as bad weather, etc. This application does not limit the generation method of weather condition simulation data. When generated by binary classification, the division of good and bad weather can be set based on actual needs, and this application does not limit this.

[0046] In an embodiment of the present application, a computer device can generate corresponding user attribute simulation data and social security information simulation data for each user. Schematically, Table 1 shows the user attribute simulation data and social security information simulation data corresponding to a certain user provided by an exemplary embodiment of the present application.

[0047] Table 1

[0048] In one possible implementation, the computer device may perform data expansion based on the user simulation data. This process may be implemented by generating individual synthetic user trajectories based on a noise vector using a generator of a generative adversarial network. In this case, the adversarial loss function of the adversarial neural network GAN is expressed as:

[0049] Among them, G is the generator, D is the discriminator, x is the real user trajectory, and z is the noise vector.

[0050] In another possible implementation, the computer device can introduce user simulation data and environment simulation data during the data expansion process to generate more detailed and realistic user trajectory data. In this case, the adversarial loss function of the adversarial neural network cGAN can be expressed as:

[0051] Where y represents user simulation data and environment simulation data.

[0052] Taking data expansion based on the initial user trajectory set, user simulation data, and environment simulation data as an example, the data expansion process can be implemented as follows: Generate synthetic user trajectories based on user simulation data and environment simulation data through the generator of the generative adversarial network; The probability that each to-be-verified user trajectory is a real user trajectory is determined by the discriminator of the generative adversarial network; the to-be-verified user trajectory is a user trajectory in the initial user trajectory set or a synthetic user trajectory; The generator and discriminator are trained by optimizing the adversarial loss function until the function value of the optimized adversarial loss function converges to obtain a trained generator; The trained generator is used to expand the data volume based on user simulation data and environment simulation data to obtain the target user trajectory set.

[0053] To further improve the data quality of the synthetic user trajectories produced by the trained generator, the computer device can use self-supervised learning or multiple discriminators to train the generative adversarial network. In the self-supervised learning mode, the generator is pre-trained through auxiliary tasks (such as trajectory segment prediction, speed consistency verification, or geographical rationality verification) to enable it to initially grasp the spatiotemporal patterns of real trajectories, and then further optimize the details through adversarial training. When adopting a multiple discriminator architecture, multiple discriminators focusing on different dimensions (such as spatial distribution discriminators, mobility mode discriminators, and temporal continuity discriminators) can be deployed to respectively evaluate the geographical rationality, behavioral logic, and temporal coherence of the user trajectory to be verified. Through multi-angle adversarial losses, the generator can synthesize more comprehensive and realistic trajectories.

[0054] Schematically, the synthetic user trajectory simulated by the generator can be that user 1 is a fixed working user, whose user trajectory can be going to work at 7 am and arriving home at 8 pm; user 2 is a mobile user, whose user trajectory is randomly moving starting at 10 am and arriving home at 9 pm.

[0055] In another possible implementation, in order to further verify the rationality of the synthetic user trajectory simulated by the generator, a multi-dimensional cross-verification mechanism can be used to evaluate the quality of the synthetic user trajectory output by the generator. Schematically, the computer device can sample the synthetic user trajectory output by the generator and verify it from multiple dimensions such as the rationality of the spatiotemporal distribution and the rationality of the motion characteristics. For example, it checks whether the control distribution of the mobile trajectory conforms to the real geographical constraints, verifies whether the time distribution conforms to the real law, whether the speed distribution conforms to the expected normal distribution, whether the steering angle obeys the von Mises distribution, etc. It should be noted that the above verification process is manual verification, or it can also be human-machine collaborative verification, or it can also be automatically verified by the computer device based on preset verification rules. This application does not limit this. When the verification result indicates that the proportion of samples that pass the verification is greater than or equal to the proportion threshold, the synthetic user trajectory simulated by the generator is added to the target user trajectory set; when the verification result indicates that the proportion of samples that pass the verification is less than the proportion threshold, retraining is performed.

[0056] After obtaining the target user trajectory set, the signaling data of the base station is simulated based on the position information of each user trajectory and each base station in the target user trajectory set. The following is an example of simulating the signaling data of the base station based on any position in any user trajectory of each user trajectory.

[0057] Step 230 : Acquire location information of a first location, where the first location is any location in a target user trajectory; the target user trajectory is any one of the user trajectories.

[0058] Step 240: Determine a neighboring base station of the first location using a K-dimensional tree algorithm and location information of each base station. The neighboring base station is a base station closest to the first location.

[0059] In one possible implementation, a computer device can construct a KD-tree structure based on the location information of each base station. The tree structure can alternately divide spatial regions according to k-dimensional space. Taking the location information of the base station as longitude and latitude information as an example, schematically, when dividing the spatial region, a splitting axis is selected, such as alternating division according to longitude and latitude, dividing nodes according to the median, the left subtree stores points less than the median, and the right subtree stores points greater than or equal to the median. The subtree is recursively processed until the leaf node contains a single node or less than a threshold number of nodes; when determining the neighboring base station of the first position, the computer device can use the nearest neighbor search algorithm of the KD-tree to recursively compare the spatial distance between the first position and each node splitting hyperplane starting from the root node until it reaches the leaf node. When the search is completed, it backtracks and checks each possible candidate node, and determines the base station corresponding to the candidate node with the smallest distance from the first position as the neighboring base station of the first position.

[0060] Taking the base station location information as latitude and longitude information as an example, the calculation formula of spatial distance can be expressed as:

[0061] in, and Represent the latitude and longitude coordinates of the first position and the latitude and longitude coordinates of the base station respectively.

[0062] In another possible implementation, the target area where each base station is located includes multiple sub-areas. The computer device may construct a multi-level KD-tree structure to further improve the efficiency of determining neighboring base stations. The process of constructing the multi-level KD-tree structure may be implemented as follows: Get the center location information of each sub-area; Establish a top-level K-dimensional tree based on the center location information of each sub-region; A regional K-dimensional tree corresponding to each sub-region is established based on the location information of the base stations covered by each sub-region.

[0063] Among them, when dividing the target area, it can be divided in a uniform grid manner, for example, the target area can be divided into several sub-areas of similar size; or, it can be divided according to geographical constraints, such as according to the boundaries of natural obstacles or administrative boundaries, etc. This application does not limit the division method of the target area and the number of sub-areas.

[0064] The center position of each sub-region may be a position corresponding to a geometric center determined based on the geometric shape of the region outline of the sub-region.

[0065] When constructing a top-level K-dimensional tree, the computer device can obtain the central position information of each sub-region, divide the nodes by the median, recursively calculate the nodes corresponding to the central position information of each sub-region, and construct a top-level K-dimensional tree; when constructing a regional K-dimensional tree, the computer device can construct a K-dimensional tree with the location information of each base station covered by the same sub-region as the processing object, that is, divide the nodes by the median, recursively calculate the nodes corresponding to the location information of each base station in the sub-region, and obtain the regional K-dimensional tree of the sub-region.

[0066] When constructing a multi-level KD-tree structure, the process of determining neighboring base stations can be implemented as follows: Determine the target sub-region to which the first position belongs by using the K-dimensional tree algorithm and the top-level K-dimensional tree; Each neighboring base station of the first position is determined by using a K-dimensional tree algorithm and a regional K-dimensional tree corresponding to the target sub-region.

[0067] That is, the computer device can roughly determine the sub-area of ​​the first position through the top-level K-dimensional tree, and then search for neighboring base stations of the first position through the regional K-dimensional tree, thereby improving the search efficiency of neighboring base stations and achieving rapid positioning.

[0068] Furthermore, when determining the neighboring base stations of a user's location, the computer device may also comprehensively consider factors such as the signal coverage range and load conditions of each base station to improve the authenticity of the signaling data simulation. For example, among the top n candidate locations with the smallest distance to the user's location, the base station with the smallest load and whose signal coverage the user falls within may be determined as the neighboring base station of the user's location. It should be noted that, based on different actual needs, more factors may be introduced when determining neighboring base stations, and this application does not limit this.

[0069] Step 250: simulate and generate a signaling event between a user terminal at a first location and a neighboring base station.

[0070] In principle, when simulating signaling events, the computer device can dynamically generate a complete signaling sequence including a timestamp according to the 3GPP protocol stack specification. That is, after the terminal initiates a random access preamble, the neighboring base station triggers a switching decision through a measurement report, and the network side sends an RRC (Radio Resource Control) reconfiguration instruction to complete the base station switching. The device synchronously records characteristic parameters such as signaling type, bearer identifier, and delay, and simulates real channel fluctuations by adding Gaussian noise, and finally outputs a collection of signaling events that conform to the protocol timing and contain spatial location tags.

[0071] For each user location on the trajectory of the target user trajectory set, the neighboring base stations of each location can be determined using the above method, and signaling events between each location and the corresponding neighboring base stations are simulated. For the same user trajectory, the interaction between the user terminal of the user and each base station is determined based on the sequence of each time point on the user trajectory, such as signaling events such as accessing a base station and switching base stations.

[0072] In summary, the base station signaling data simulation method provided in the embodiment of the present application obtains an initial user trajectory set containing real user trajectories, and expands the data volume based on the initial user trajectory set, user simulation data, and environmental simulation data through a generative adversarial network to obtain a target user trajectory set. Based on the individual user trajectories in the target user trajectory set and the location information of each base station, the base station signaling data is simulated. In the above method, the data volume is expanded by using a generative adversarial network to fuse real user trajectories and multi-dimensional simulation data, which improves the accuracy and credibility of the simulated user trajectories, reduces the privacy and cost thresholds for data acquisition, and provides more reliable data support for base station signaling data simulation, thereby improving the credibility and accuracy of the generated base station signaling data.

[0073] In addition, when determining the neighboring base stations corresponding to each user position in the user trajectory, searching through the KD-tree algorithm can improve the base station search efficiency and achieve rapid positioning.

[0074] Figure 3 A block diagram of a base station signaling data simulation device provided by an exemplary embodiment of the present application is shown. The device can perform the following steps: Figure 1 or Figure 2 All or part of the steps of the embodiment shown, such as Figure 3 As shown, the device may include the following modules.

[0075] The trajectory acquisition module 310 is used to acquire an initial user trajectory set; each user trajectory in the initial user trajectory set has an authenticity label; A trajectory expansion module 320 is configured to expand the data volume based on the initial user trajectory set, user simulation data, and environment simulation data through a generative adversarial network to obtain a target user trajectory set; The simulation module 330 is configured to simulate signaling data of a base station based on the trajectory of each user in the target user trajectory set and the location information of each base station.

[0076] In a possible implementation, the simulation module 330 includes: An information acquisition submodule, configured to acquire location information of a first location, where the first location is any location in a target user trajectory; the target user trajectory is any one of the user trajectories; a base station determination submodule, configured to determine a neighboring base station of the first position by using a K-dimensional tree algorithm and location information of each base station, wherein the neighboring base station is a base station closest to the first position; The simulation submodule is configured to simulate and generate a signaling event between the user terminal at the first location and the neighboring base station.

[0077] In a possible implementation, the target area where each base station is located includes multiple sub-areas, and the apparatus further includes: An information acquisition module is used to obtain the center location information of each sub-area; The first establishing module is used to establish a top-level K-dimensional tree based on the center position information of each sub-region; The second establishing module is used to establish a regional K-dimensional tree corresponding to each sub-region based on the location information of the base stations covered by each sub-region.

[0078] In a possible implementation, the base station determines a submodule configured to: Determine the target sub-region to which the first position belongs by using a K-dimensional tree algorithm and the top-level K-dimensional tree; The neighboring base station of the first position is determined by using a K-dimensional tree algorithm and a regional K-dimensional tree corresponding to the target sub-region.

[0079] In a possible implementation, the trajectory extension module 320 includes: a trajectory synthesis submodule, configured to generate, by means of a generator of the generative adversarial network, respective synthetic user trajectories based on the user simulation data and the environment simulation data; A trajectory verification submodule, configured to determine, through the discriminator of the generative adversarial network, the probability that each to-be-verified user trajectory is a real user trajectory; the to-be-verified user trajectory is a real user trajectory or a synthetic user trajectory in the initial user trajectory set; A training submodule, configured to train the generator and the discriminator by optimizing an adversarial loss function until the function value of the optimized adversarial loss function converges, thereby obtaining a trained generator; The target user trajectory set is obtained by performing data expansion based on the user simulation data and the environment simulation data through a trained generator.

[0080] In a possible implementation, the user simulation data includes user attribute simulation data and social security information simulation data, and the environment simulation data includes weather condition simulation data and traffic condition simulation data.

[0081] In summary, the base station signaling data simulation device provided in the embodiment of the present application obtains an initial user trajectory set containing real user trajectories, and expands the data volume based on the initial user trajectory set, user simulation data, and environmental simulation data through a generative adversarial network to obtain a target user trajectory set. Based on the individual user trajectories in the target user trajectory set and the location information of each base station, the base station signaling data is simulated. The above-mentioned device can use a generative adversarial network to fuse real user trajectories and multi-dimensional simulation data to expand the data volume, thereby improving the accuracy and credibility of the simulated user trajectories, lowering the privacy and cost thresholds for data acquisition, and providing more reliable data support for base station signaling data simulation, thereby improving the credibility and accuracy of the generated base station signaling data.

[0082] Figure 4 A block diagram of a computer device 400 is shown in accordance with an exemplary embodiment of the present application. This computer device can be implemented as the server in the aforementioned solution of the present application. The computer device 400 includes a central processing unit (CPU) 401, a system memory 404 including a random access memory (RAM) 402 and a read-only memory (ROM) 403, and a system bus 405 connecting the system memory 404 and the CPU 401. The computer device 400 also includes a mass storage device 406 for storing an operating system 409, application programs 410, and other program modules 411. The system memory 404 and mass storage device 406 may be collectively referred to as memory.

[0083] According to various embodiments of the present application, the computer device 400 may also be connected to a remote computer on a network such as the Internet for operation. That is, the computer device 400 may be connected to the network 408 via the network interface unit 407 connected to the system bus 405. Alternatively, the network interface unit 407 may be used to connect to other types of networks or remote computer systems (not shown).

[0084] The memory also includes at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is stored in the memory. The central processing unit 401 implements all or part of the steps in the base station signaling data simulation method shown in the above-mentioned embodiments by executing the at least one instruction, at least one program, code set or instruction set.

[0085] Figure 5The following is a block diagram of a computer device 500 according to another exemplary embodiment of the present application. The computer device 500 can be implemented as the terminal described above. For example, the computer device can be an Android terminal device. Typically, the computer device 500 includes a processor 501 and a memory 502. The memory 502 may include one or more computer-readable storage media configured to store at least one instruction, which is executed by the processor 501 to implement all or part of the steps in the base station signaling data simulation method described in the method embodiment of the present application.

[0086] In some embodiments, the computer device 500 may further optionally include: a peripheral device interface 503 and at least one peripheral device. The processor 501, the memory 502 and the peripheral device interface 503 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 503 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 504, a display screen 505, a camera assembly 506, an audio circuit 507 and a power supply 508. In some embodiments, the computer device 500 also includes one or more sensors 509. The one or more sensors 509 include but are not limited to: an acceleration sensor 510, a gyroscope sensor 511, a pressure sensor 512, an optical sensor 513 and a proximity sensor 514. Those skilled in the art will appreciate that Figure 5 The structure shown in the figure does not constitute a limitation on the computer device 500, and the computer device 500 may include more or fewer components than shown in the figure, or combine some components, or adopt a different component arrangement.

[0087] In an exemplary embodiment, a computer-readable storage medium is further provided. The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to implement all or part of the steps in the above-mentioned base station signaling data simulation method. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, or an optical data storage device.

[0088] In an exemplary embodiment, a computer program product is further provided, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, which, when executed by a computer, enable the computer to execute the above-mentioned Figure 1 or Figure 2All or part of the steps of any embodiment shown in any embodiment.

[0089] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely as exemplary, and the true scope and spirit of the present application are indicated by the claims.

[0090] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A base station signaling data simulation method, characterized in that: The method comprises: Acquire an initial user trajectory set; each user trajectory in the initial user trajectory set has an authenticity label; Expanding the data volume based on the initial user trajectory set, user simulation data, and environment simulation data by generating an adversarial network to obtain a target user trajectory set; Based on the trajectory of each user in the target user trajectory set and the position information of each base station, signaling data of the base station is simulated.

2. The method according to claim 1, characterized in that The simulating base station signaling data based on each user trajectory in the target user trajectory set and the location information of each base station includes: Acquire location information of a first location, where the first location is any location in a target user trajectory; the target user trajectory is any one of the user trajectories; Determine a neighboring base station of the first location using a K-dimensional tree algorithm and location information of each base station, where the neighboring base station is a base station closest to the first location; A signaling event between the user terminal at the first location and a neighboring base station is simulated and generated.

3. The method according to claim 2, characterized in that The target area where each base station is located includes multiple sub-areas. The method further includes: Get the center location information of each sub-area; Establish a top-level K-dimensional tree based on the center location information of each sub-region; A regional K-dimensional tree corresponding to each sub-region is established based on the location information of the base stations covered by each sub-region.

4. The method according to claim 3, characterized in that The determining the neighboring base stations of the first position by using a K-dimensional tree algorithm and the location information of each base station includes: Determine the target sub-region to which the first position belongs by using a K-dimensional tree algorithm and the top-level K-dimensional tree; The neighboring base station of the first position is determined by using a K-dimensional tree algorithm and a regional K-dimensional tree corresponding to the target sub-region.

5. The method according to claim 1, wherein The generating an adversarial network performs data expansion based on the initial user trajectory set, the user simulation data, and the environment simulation data to obtain a target user trajectory set, including: generating, by a generator of the generative adversarial network, respective synthetic user trajectories based on the user simulation data and the environment simulation data; Determining the probability that each to-be-verified user trajectory is a real user trajectory through the discriminator of the generative adversarial network; the to-be-verified user trajectory is a real user trajectory or a synthetic user trajectory in the initial user trajectory set; The generator and the discriminator are trained by optimizing the adversarial loss function until the function value of the optimized adversarial loss function converges, thereby obtaining a trained generator; The target user trajectory set is obtained by performing data expansion based on the user simulation data and the environment simulation data through a trained generator.

6. The method according to claim 5, characterized in that The user simulation data includes user attribute simulation data and social security information simulation data, and the environment simulation data includes weather condition simulation data and traffic condition simulation data.

7. A base station signaling data simulation device, characterized in that: The device comprises: A trajectory acquisition module is used to acquire an initial user trajectory set; each user trajectory in the initial user trajectory set has an authenticity label; A trajectory expansion module is used to expand the data volume based on the initial user trajectory set, user simulation data and environment simulation data through a generative adversarial network to obtain a target user trajectory set; The simulation module is used to simulate the signaling data of the base station based on the trajectory of each user in the target user trajectory set and the position information of each base station.

8. A computer device, characterized in that: The computer device includes a processor and a memory, the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the base station signaling data simulation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that At least one computer program is stored in the computer-readable storage medium, and the computer program is loaded and executed by the processor to implement the base station signaling data simulation method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer is caused to execute to implement the base station signaling data simulation method as described in any one of claims 1 to 6.

Images