A method and device for identifying a home area, an electronic device, and a storage medium

Abstract

This application discloses a method, apparatus, electronic device, and storage medium for identifying a home region, belonging to the field of communication technology, to improve the accuracy of user route determination in boundary roaming states. The method includes: determining the signal coverage ratio of two adjacent target regions corresponding to a first base station; and, based on the signal coverage ratio, determining which of the two adjacent target regions a target user within the signal coverage area of ​​the first base station belongs to.

Description

Technical Field

[0001] This application belongs to the field of communication technology, and specifically relates to a method, device, electronic device and storage medium for identifying a home region. Background Technology

[0002] With the development of communication technology, especially the advent of 5G, base stations, as the core equipment of mobile communication networks, are used to realize the wireless signal transmission between wired communication networks and wireless terminals, and their construction is becoming increasingly common.

[0003] However, when a base station is built near the boundary between two administrative regions, the base station signal may cover both adjacent regions simultaneously, resulting in boundary roaming. In this case, using the base station location to collect user travel information may lead to errors in the determination of user travel data. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for identifying a home region, which can improve the accuracy of user travel determination during boundary roaming.

[0005] In a first aspect, embodiments of this application provide a method for identifying a home region, comprising: determining the signal coverage ratio of two adjacent target regions corresponding to a first base station; and determining, based on the signal coverage ratio, one of the two adjacent target regions to which a target user within the signal coverage area of ​​the first base station belongs.

[0006] Secondly, embodiments of this application provide a home area identification device, including: a first determining module, configured to determine the signal coverage ratio of two adjacent target areas corresponding to a first base station; and a second determining module, configured to determine, based on the signal coverage ratio, one of the two adjacent target areas to which a target user within the signal coverage area of ​​the first base station belongs.

[0007] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the home region identification method as described in the first aspect.

[0008] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the home region identification method as described in the first aspect.

[0009] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the home region identification method as described in the first aspect.

[0010] In this embodiment of the application, by determining the signal coverage ratio of two adjacent target areas corresponding to the first base station, and determining one of the two adjacent target areas to which the target user belongs within the signal coverage range of the first base station based on the signal coverage ratio, the accuracy of user trip determination can be improved in boundary roaming state. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating a method for identifying a home region provided in an embodiment of this application;

[0012] Figure 2 This is a flowchart illustrating another method for identifying a home region provided in an embodiment of this application;

[0013] Figure 3 This is a schematic diagram of the structure of a home area identification device provided in an embodiment of this application;

[0014] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0017] The following description, in conjunction with the accompanying drawings, details a method, apparatus, electronic device, and storage medium for identifying a home region provided in this application, through specific embodiments and application scenarios.

[0018] Figure 1 This application illustrates an embodiment of a method for identifying a home region, which can be executed by an electronic device. The electronic device may include a server and / or a terminal device. In other words, the method can be executed by software or hardware installed on the electronic device, and includes the following steps:

[0019] S101: Determine the signal coverage ratio of the two adjacent target areas corresponding to the first base station.

[0020] In one implementation, the target area may include an administrative region.

[0021] Currently, identifying administrative region affiliation is a key technology for big data travel cards. The signaling and communication status of user terminals determines the areas visited or traversed. With the development of telecommunications networks from 2G to 5G, the number of telecommunications base stations has increased exponentially, reaching 100% coverage in densely populated cities. Typically, there is signal overlap between base stations. When a user terminal is powered on or making calls, using the internet, or sending text messages through the telecommunications network, the terminal establishes a communication channel with the base station and exchanges information. At this time, the base station transmits data in the form of signaling and call detail records (CDRs). Therefore, the administrative region where the user is located can be inferred from the location of the base station, and then displayed as travel card information using big data statistical methods.

[0022] However, as telecommunications technology gradually enters the 5G era, compared to 4G, it has the characteristics of low latency, high speed, and wide and deep coverage. In order to meet the needs of the development of communication technology, more base stations need to be built. If a base station is built near the boundary of an administrative region, a boundary roaming situation will occur. Boundary roaming refers to the phenomenon that the base stations in the two places at the junction of administrative regions A and B have overlapping signal coverage. When a mobile phone user belonging to region A is using his mobile phone, he may enter the mobile communication network through the access network of region B because the signal of the base station in region B is too strong.

[0023] The big data travel card is based on the location of base stations to collect user travel information. In the case of border roaming, a mobile phone user in location A is considered to have visited or passed through location B because he / she used a base station in location B, when in fact the user is in location A. This leads to errors in the determination of user travel data. When an epidemic occurs in location B, the user's travel code changes color, and according to national control requirements, isolation policies need to be implemented, which will have an unnecessary impact on the user's life and work.

[0024] This step considers the situation of border roaming, where the signal of a base station simultaneously covers two adjacent administrative regions with different coverage areas, and determines the signal coverage ratio of the two adjacent administrative regions corresponding to the first base station based on this.

[0025] S102: Based on the signal coverage ratio, determine which of the two adjacent target areas the target user belongs to within the signal coverage area of ​​the first base station.

[0026] In one implementation, determining which of the two adjacent target areas to which the target user belongs within the signal coverage range of the first base station belongs, based on the signal coverage ratio, includes: determining the one of the two adjacent target areas with the larger signal coverage ratio as the area to which the target user belongs.

[0027] This application provides a method for identifying a home region. By determining the signal coverage ratio of two adjacent target regions corresponding to a first base station, and based on the signal coverage ratio, determining which of the two adjacent target regions a target user belongs to within the signal coverage area of ​​the first base station, the method can improve the accuracy of user travel determination in boundary roaming states. The target region includes administrative regions.

[0028] Figure 2 This application illustrates an embodiment of a method for identifying a home region, which can be executed by an electronic device. The electronic device may include a server and / or a terminal device. In other words, the method can be executed by software or hardware installed on the electronic device, and includes the following steps:

[0029] S201: Determine the signal coverage area of ​​the first base station.

[0030] Typically, the coverage radius of a 2G base station is 5 to 10 kilometers, that of a 3G base station is 2 to 5 kilometers, that of a 4G base station is 1 to 3 kilometers, and that of a 5G base station is 100 to 300 meters. To obtain a more precise signal coverage range, this step can be calculated based on the base station equipment power and the propagation medium.

[0031] In one implementation, the signal coverage area of ​​the first base station includes the area of ​​a circle centered on the coverage radius of the first base station.

[0032] S202: Determine the boundary lines of the two adjacent target areas.

[0033] In one implementation, step S202 includes: determining multiple location information of multiple sampling points on the boundary line; and determining the boundary line of the two adjacent target regions based on the multiple location information of the multiple sampling points and a linear regression algorithm.

[0034] For example, the latitude and longitude coordinates of multiple sampling points on the boundary line can be obtained by using the Global Positioning System (GPS) positioning method. For example, each sampling point is 50 meters long, and approximately 200 sampling points can be selected. The sampling interval and the number of sampling points can be set according to the situation, and this application does not impose any restrictions on them.

[0035] Generally, two administrative regions are divided by irregular boundary lines, meaning the boundary line is not a regular straight line but a discontinuous, differentiable broken line. This application can use linear regression from machine learning to predict the boundary lines, learning the irregular administrative boundary curves as a linear model, and calculating the distance between points and the line using the least squares method, minimizing the squared error of the distance from all boundary coordinates to the line, i.e., minimizing the sum of the Euclidean distances of all samples to the line. It should also be understood that because linear regression is used to approximate the true boundary line, the more sampling points selected and the smaller the sampling interval, the more accurate the result.

[0036] Linear model methods attempt to learn a function that makes predictions through a linear combination of attributes, i.e.: f(x) = w1x1 + w2x2 + ... + w d x d +b, simplified using vector representation, becomes: f(x) = w T x+b, where w T =(w1,w2,…,w d ) T Determine w T After obtaining the values ​​of b, we can obtain a linear model of the administrative boundary, and the loss function of this linear model can be:

[0037] The sampled dataset consists of longitude and latitude, where longitude is represented by x and latitude by y, where y (i) Given that w and b are vector matrices with only one-dimensional features in a linear model, the unknown variables w and b are obtained using the linear regression algorithm, where w represents the slope of the line and b represents the intercept. The linear function can then be expressed as y = wx + b.

[0038] S203: Determine the signal coverage ratio of the two adjacent target areas based on the signal coverage range and the boundary line.

[0039] In one implementation, step S203 includes: determining the areas of the two coverage regions obtained by dividing the signal coverage range by the boundary line based on the definite integral formula; and determining the signal coverage ratio according to the areas of the two coverage regions.

[0040] In one implementation, the determining the areas of the two coverage regions obtained by dividing the signal coverage range by the boundary line based on the definite integral formula includes: determining the areas of the two coverage regions obtained by dividing the signal coverage range by the boundary line according to the following formula:

[0041]

[0042] where y c = wx + b1 represents the slope-intercept equation of the boundary line, (x - a) 2 + (y l - b2) 2 = r 2 represents the equation of the circle corresponding to the signal coverage range, r represents the coverage radius of the first base station, and x1, x2 (x1 < x2) are the abscissas of the two intersection points of the boundary line and the circle corresponding to the signal coverage range respectively.

[0043] This step transforms the problem of the signal coverage ratios of two administrative regions into the problem of the ratio of the two coverage areas obtained by dividing the circle centered at the longitude and latitude position of the base station by the boundary line of two adjacent regions. Thus, the signal coverage ratio of the two adjacent regions can be calculated as p = (πr 2 - S) / S.

[0044] S204: Determine one of the two adjacent target regions according to the signal coverage ratio and the communication data of the target user.

[0045] Wherein, the communication data of the target user comes from the complaint work order data of the target user.

[0046] In one implementation, step S204 includes: inputting the signal coverage ratio and the communication data of the target user into an error backpropagation BP neural network model, and outputting one of the two adjacent target regions. Among them, the BP neural network model is trained with the signal coverage ratios corresponding to multiple base stations and the communication data of multiple users as feature data, and the multiple users do not include the target user.

[0047] Back Propagation (BP) neural networks continuously adjust network weights and thresholds through training on samples. They use gradient descent to make the error function decrease along the negative gradient direction, constantly approaching the desired output. They have high nonlinearity and strong generalization ability. This algorithm is a multi-layer feedforward neural network trained by back propagating the error.

[0048] The backpropagation (BP) algorithm suffers from problems such as being prone to getting trapped in local minima, slow convergence speed, and low learning efficiency. This application can optimize the BP neural network using the momentum method. Momentum, as the name suggests, introduces a parameter similar to inertia during the weight parameter update process, so that the weight update will not immediately change direction in the next time interval, but will continue to run along the running direction of the previous time interval for a period of time. The weight update formula is as follows:

[0049]

[0050] w t =w t-1 -v t ,

[0051] Where γ is the momentum factor, usually set to 0.9, and η is the learning rate. V represents the gradient of the loss function with respect to the weights w. t This represents the update rate of the weights at time t, and the initial value of this value is 0.

[0052] As shown in the formula above, during the training of a BP neural network, the actual update value of each parameter does not depend on the current gradient, but on the weighted average of the gradients over a recent period. Generally speaking, in the early stages of iteration, the gradient directions are relatively consistent, and the momentum method will accelerate the process, allowing the system to reach the optimum more quickly. In the later stages of iteration, the gradient directions become inconsistent, causing the system to oscillate around the convergence value. In this case, the momentum method will slow down the process and increase stability.

[0053] It should be noted that the BP neural network of this application can also use other optimization methods, such as the adaptive gradient (AdaGrad) algorithm that adaptively adjusts the learning rate, the root mean square propagation (RMSprop) algorithm, etc., and this application does not impose any restrictions on them.

[0054] Furthermore, the BP neural network model described in this application can consist of an input layer, an output layer, and a hidden layer network. The model's prediction result includes one of the two adjacent target regions, so the output layer includes two neurons, and can be located in the interval [a,b] (a,b∈N). +To ensure the network has sufficient approximation and generalization capabilities, an ideal number of hidden layer nodes is selected within the range [b, c] (where b = 0.618*(ca) + a). To further guarantee high-precision approximation, the golden section method is used to extend the interval [b, c] (where b = 0.618*(ca) + a). Finding the optimal solution within [b, c] yields a number of hidden layer nodes with even stronger approximation capabilities. Based on practical applications, the following approach is adopted... Calculate the number of hidden layer nodes, where m represents the number of hidden layer nodes, n is the number of input layer nodes (e.g., 10), l is the number of output layer nodes, and a is a constant between [1, 10]. Here, the number of hidden layer nodes can be designed to be 6.

[0055] Regarding the design of the error function, in order to learn an optimized model, the training gradient descent is continuously maintained during backpropagation. The mean squared error function is chosen as the error function for backpropagation, expressed as:

[0056]

[0057] Where T i Q represents the expected output value of the output layer. i This represents the actual output value of the network layer.

[0058] To prevent the gradient vanishing problem in the hidden layers and to normalize the network output to the range [-1, 1], this paper uses the sigmoid tangent function tanH as the activation function for the hidden layers, expressed as:

[0059]

[0060] The output layer needs dimensionality reduction through differentiation, and it must be suitable for forward propagation characteristics while ensuring effective data compression. Therefore, the linearly differentiable sigmoid function is chosen as the activation function for the output layer, expressed as:

[0061]

[0062] In one implementation, this application collects travel history location complaint data to form a certain scale of categorized complaint work orders. It also collects call logs of complaint numbers where the big data travel card has discrimination errors due to border roaming, and stores these logs in a MySQL database. The logs contain 33-dimensional data features. Based on feature engineering steps and principles, the correlation between feature items and classification items is measured. Principal component analysis is used to extract core data features with significant physical or statistical meaning. The feature data in the call logs related to border roaming includes four dimensions: signal administrative affiliation, transmission rate per second, duration percentage within 4 hours, and connection percentage within 4 hours. The "4-hour" feature is determined according to the big data travel card judgment rules, where a user's call log showing communication activity for a continuous 4-hour period indicates actual visit to that area.

[0063] To ensure the model's generalization ability and adaptability, and to prevent underfitting and overfitting during training, the sample data N is obtained according to the sample size formula:

[0064]

[0065] Where N is the number of samples, α is the number of standard normal distributions corresponding to a 95% confidence level, ε represents the acceptable error range, and σ represents the standard deviation of the samples.

[0066] This application trains the BP neural network model by taking the signal coverage ratios of multiple base stations and the communication data of multiple users in the above four dimensions as inputs to obtain a prediction model, which can predict the target area to which the target user belongs, thereby improving the accuracy of user trip determination.

[0067] Taking the border between a certain city in a certain province 1 and a certain city 2 as an example, a certain GPS positioning method was used to collect the latitude and longitude coordinate data of the administrative boundary line between the two places, as shown in Table 1 below.

[0068] Table 1. Data set of administrative boundary coordinate systems collected using a certain GPS positioning method.

[0069] Sampling points Longitude x Latitude y 1 121.554826 31.701483 2 121.554861 31.701533 3 121.554896 31.701583 4 121.554931 31.701633 5 121.554966 31.701683 … … …

[0070] This application can calculate, based on the capacity formula, to sample N data points with these characteristics from the database for this type of problem, and use 80% of these samples as model training data and the other 20% as model testing data. The training and testing data are stored as text according to the output classification, as shown in Table 2 below:

[0071] Table 2 Classification Feature Dataset

[0072]

[0073] This application uses MATLAB tools to perform linear regression learning. After training, the values ​​of w and b are obtained, thus obtaining the boundary linear function y = wx + b. The area of ​​intersection of the two functions is obtained by using the definite integral formula, thereby obtaining the signal coverage ratio p of the boundary base station in locations A and B. The signal coverage ratio is an important element in the feature data set. After obtaining this value, the improved BP algorithm is used to predict the user's administrative region affiliation.

[0074] This application uses MATLAB as the training tool. Based on the roaming location and base station location information in the call detail records, the user's final administrative region is determined. The model training results are divided into two categories. The output layer consists of two neurons, represented by 1 and 2 respectively. The feature data consists of four input layer neurons. The training text data is normalized and set in the interval [-1,1]. The target parameter matrix of the training result set is constructed. The above functions tanH and Sigmoid are used as activation functions respectively. The number of network training epochs is set to g, and the value of g can be 5% of the number of samples N. The learning rate η can be set to 0.01.

[0075] It should be noted that the parameter settings in this application can also be other suitable values, and better values ​​can be obtained after multiple training sessions. This application does not impose specific restrictions.

[0076] This application also proposes an optimal training dataset for the BP neural network, using 70% of the samples as the training dataset, 15% as the validation dataset, and the remaining 15% as the test dataset. The training, validation, and test sets are compared based on a linear regression expression. By randomly sampling 20% ​​of the test set data (N), the expected target classification results are iteratively validated against the actual target classification results. The validation model achieves a recognition rate of 98%. Furthermore, experimental results and analysis show that the minimum target error is reached after 184 learning iterations. The optimized BP neural network avoids getting trapped in local minima during the learning process, and the gradient decreases smoothly in a curve-like pattern. The best validation performance is achieved at the 178th iteration, with a maximum learning rate η of 10.4322.

[0077] This application provides a method for identifying a home area, which involves determining the signal coverage range of a first base station; determining the boundary lines of two adjacent target areas; determining the signal coverage ratio of the two adjacent target areas based on the signal coverage range and the boundary lines; and determining one of the two adjacent target areas based on the signal coverage ratio and the communication data of a target user. The communication data of the target user originates from the target user's complaint work order data. This method can improve the accuracy of user travel determination in boundary roaming situations. The target area includes administrative regions.

[0078] This application provides a method for identifying a home region. The method involves: determining the signal coverage area of ​​a first base station; determining multiple location information of multiple sampling points on the boundary line; determining the boundary line of two adjacent target regions based on the multiple location information of the multiple sampling points using a linear regression algorithm; determining the area of ​​two coverage regions divided by the boundary line based on a definite integral formula; determining the signal coverage ratio based on the area of ​​the two coverage regions; and inputting the signal coverage ratio and the communication data of the target user into a backpropagation BP neural network model to output one of the two adjacent target regions. The BP neural network model is trained using multiple signal coverage ratios corresponding to multiple base stations and communication data of multiple users as feature data. The multiple users do not include the target user. This method can improve the accuracy of user travel determination in boundary roaming states. The target region includes administrative regions. Furthermore, the optimized BP neural network can improve the efficiency of user travel determination.

[0079] It should be noted that the home region identification method provided in this application embodiment can be executed by a home region identification device or a control module within that home region identification device for executing the home region identification method. This application embodiment uses the home region identification device executing the home region identification method as an example to illustrate the home region identification device provided in this application embodiment.

[0080] Figure 3 This diagram illustrates the structure of a home region identification device according to an embodiment of this application. Figure 3 As shown, the identification device 300 for the home area includes: a first determining module 310, used to determine the signal coverage ratio of two adjacent target areas corresponding to the first base station; and a second determining module 320, used to determine, based on the signal coverage ratio, one of the two adjacent target areas to which the target user within the signal coverage range of the first base station belongs.

[0081] In one implementation, the first determining module 310 is configured to: determine the signal coverage range of the first base station; determine the boundary line of the two adjacent target areas; and determine the signal coverage ratio of the two adjacent target areas based on the signal coverage range and the boundary line.

[0082] In one implementation, the first determining module 310 is used to: determine multiple location information of multiple sampling points on the boundary line; and determine the boundary line of the two adjacent target regions based on the multiple location information of the multiple sampling points and a linear regression algorithm.

[0083] In one implementation, the first determination module 310 is configured to: determine the areas of the two coverage regions obtained by dividing the signal coverage range by the boundary line based on the definite integral formula; and determine the signal coverage ratio according to the areas of the two coverage regions.

[0084] In one implementation, the first determination module 310 is configured to: determine the areas of the two coverage regions obtained by dividing the signal coverage range by the boundary line according to the following formula:

[0085]

[0086] where y c = wx + b1 represents the slope-intercept equation of the boundary line, (x - a) 2 + (y l - b2) 2 = r 2 represents the equation of the circle corresponding to the signal coverage range, r represents the coverage radius of the first base station, and x1, x2 (x1 < x2) are the abscissas of the two intersection points of the boundary line and the circle corresponding to the signal coverage range respectively.

[0087] In one implementation, the second determination module 320 is configured to: determine one of the two adjacent target regions according to the signal coverage ratio and the communication data of the target user, where the communication data of the target user comes from the complaint work order data of the target user.

[0088] In one implementation, the second determination module 320 is configured to: input the signal coverage ratio and the communication data of the target user into an error backpropagation (BP) neural network model, and output one of the two adjacent target regions, where the BP neural network model is trained by using, as feature data, the signal coverage ratios corresponding to multiple base stations and the communication data of multiple users, and the multiple users do not include the target user.

[0089] The identification device for the home region in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0090] The region identification device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0091] The region identification device provided in this application embodiment can achieve... Figures 1 to 3 The various processes implemented in the method embodiments are not described in detail here to avoid repetition.

[0092] Optional, such as Figure 4 As shown, this application embodiment also provides an electronic device 400, including a processor 401, a memory 402, and a program or instructions stored in the memory 402 and executable on the processor 401. When the program or instructions are executed by the processor 401, they perform the following: determining the signal coverage ratio of two adjacent target areas corresponding to a first base station; and determining, based on the signal coverage ratio, one of the two adjacent target areas to which the target user belongs within the signal coverage range of the first base station.

[0093] In one implementation, when the above program or instructions are executed by the processor 401, the following are achieved: determining the signal coverage range of the first base station; determining the boundary lines of the two adjacent target areas; and determining the signal coverage ratio of the two adjacent target areas based on the signal coverage range and the boundary lines.

[0094] In one implementation, when the above program or instructions are executed by the processor 401, the following is achieved: determining multiple position information of multiple sampling points on the boundary line; and determining the boundary line of the two adjacent target regions based on the multiple position information of the multiple sampling points and a linear regression algorithm.

[0095] In one implementation, when the above program or instruction is executed by the processor 401, it realizes: based on the definite integral formula, determining the areas of the two coverage regions obtained by dividing the signal coverage range by the boundary line; and determining the signal coverage ratio according to the areas of the two coverage regions.

[0096] In one implementation, when the above program or instruction is executed by the processor 401, it realizes: determining the areas of the two coverage regions obtained by dividing the signal coverage range by the boundary line according to the following formula:

[0097]

[0098] where y c = wx + b1 represents the slope-intercept form equation of the boundary line, and (x - a) 2 + (y l - b2) 2 = r 2 represents the equation of the circle corresponding to the signal coverage range, r represents the coverage radius of the first base station, and x1, x2 (x1 < x2) are respectively the abscissas of the two intersection points of the boundary line and the circle corresponding to the signal coverage range.

[0099] In one implementation, when the above program or instruction is executed by the processor 401, it realizes: determining one of the two adjacent target regions according to the signal coverage ratio and the communication data of the target user, where the communication data of the target user comes from the complaint work order data of the target user.

[0100] In one implementation, when the above program or instruction is executed by the processor 401, it realizes: inputting the signal coverage ratio and the communication data of the target user into an error backpropagation BP neural network model, and outputting one of the two adjacent target regions, where the BP neural network model is trained with the signal coverage ratios corresponding to multiple base stations and the communication data of multiple users as feature data, and the multiple users do not include the target user.

[0101] For the specific execution steps, reference can be made to the respective steps of the embodiment of the identification method of the attribution area above, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0102] It should be noted that the electronic device in the embodiments of the present application includes: a server, a terminal device or other devices other than the terminal device.

[0103] The above electronic device structure does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or arrange them differently. For example, an input unit may include a Graphics Processing Unit (GPU) and a microphone, and a display unit may use a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar display panels. User input units include at least one of a touch panel and other input devices. A touch panel is also called a touchscreen. Other input devices may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be elaborated further here.

[0104] Memory can be used to store software programs and various data. Memory can primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0105] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0106] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described method for identifying the home region and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0107] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0108] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described method embodiment for identifying the home region, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0109] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0110] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0112] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for identifying a region of origin, characterized in that, The method includes: Determine the signal coverage ratio of the two adjacent target areas corresponding to the first base station; Based on the signal coverage ratio, determine which of the two adjacent target areas the target user belongs to within the signal coverage area of ​​the first base station; The step of determining, based on the signal coverage ratio, which of the two adjacent target areas to which the target user belongs within the signal coverage range of the first base station comprises: Based on the signal coverage ratio and the target user's communication data, one of the two adjacent target areas is determined, wherein the target user's communication data comes from the target user's complaint ticket data; The step of determining which of the two adjacent target areas the target user belongs to based on the signal coverage ratio and the target user's communication data includes: The signal coverage ratio and the communication data of the target user are input into a backpropagation BP neural network model to output one of the two adjacent target regions. The BP neural network model is trained by using multiple signal coverage ratios corresponding to multiple base stations and communication data of multiple users as feature data. The multiple users do not include the target user.

2. The method according to claim 1, characterized in that, Determining the signal coverage ratio of two adjacent target areas corresponding to the first base station includes: Determine the signal coverage area of ​​the first base station; Determine the boundary lines of the two adjacent target regions; The signal coverage ratio of the two adjacent target areas is determined based on the signal coverage range and the boundary line.

3. The method according to claim 2, characterized in that, Determining the boundary lines of the two adjacent target regions includes: Determine the location information of multiple sampling points on the boundary line; Based on the location information of the multiple sampling points, the boundary line of the two adjacent target regions is determined using a linear regression algorithm.

4. The method according to claim 2, characterized in that, Determining the signal coverage ratio of the two adjacent target areas based on the signal coverage range and the boundary line includes: Based on the definite integral formula, the areas of the two coverage regions obtained by dividing the signal coverage area by the boundary line are determined; The signal coverage ratio is determined based on the area of ​​the two coverage areas.

5. The method according to claim 4, characterized in that, The determination of the areas of the two coverage regions obtained by dividing the signal coverage area by the boundary line based on the definite integral formula includes: The areas of the two coverage regions obtained by dividing the signal coverage area by the boundary line are determined according to the following formula: ， in, The slope-intercept equation of the boundary line is given. The equation representing the circle corresponding to the signal coverage area. This indicates the coverage radius of the first base station. , These are the x-coordinates of the two intersection points of the boundary line and the circle corresponding to the signal coverage area. .

6. A device for identifying a region of ownership, characterized in that, The device includes: The first determining module is used to determine the signal coverage ratio of two adjacent target areas corresponding to the first base station; The second determining module is used to determine, based on the signal coverage ratio, one of the two adjacent target areas to which the target user belongs within the signal coverage area of ​​the first base station; In the second determining module, determining one of the two adjacent target areas to which the target user belongs within the signal coverage area of ​​the first base station, based on the signal coverage ratio, includes: Based on the signal coverage ratio and the target user's communication data, one of the two adjacent target areas is determined, wherein the target user's communication data comes from the target user's complaint ticket data; The step of determining which of the two adjacent target areas the target user belongs to based on the signal coverage ratio and the target user's communication data includes: The signal coverage ratio and the communication data of the target user are input into a backpropagation BP neural network model to output one of the two adjacent target regions. The BP neural network model is trained by using multiple signal coverage ratios corresponding to multiple base stations and communication data of multiple users as feature data. The multiple users do not include the target user.

7. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for identifying the home region as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, include: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the home region identification method as described in any one of claims 1 to 5.

Images