Call and traffic hotspot area acquisition method, system, device and medium

Abstract

The present application relates to the field of communication technology, and more particularly to a call and traffic hotspot area acquisition method, system, device and medium, the method comprising: in a collection period, a base station acquires signaling data of in-network users and radio frequency signals within the coverage range, analyzes the call behavior and traffic session behavior of in-network users and out-of-network users, and generates a behavior record table for the users respectively; after filtering the noise in the behavior record table, a grid division is performed on a specified area, the behavior records are embedded into the corresponding grid according to the positioning of the call behavior and traffic session behavior, and a behavior distribution matrix is output; the behavior distribution matrix is analyzed by using a density clustering algorithm, and a hotspot area distribution map is output, realizing the synchronous acquisition and analysis of the call and traffic behavior of in-network and out-of-network users in a rural scenario, breaking through the limitation that the traditional base station can only process in-network data, and providing data support for precise marketing and network configuration optimization of operators.

Description

Technical Field

[0001] This invention relates to the field of communication technology, specifically to a method, system, device, and medium for obtaining call and data traffic hotspot areas. Background Technology

[0002] Rural communication scenarios have unique characteristics that are significantly different from those in cities: Geographically, this is characterized by scattered village settlements and vast field operation areas, with base station deployment exhibiting features such as large coverage radius of a single base station, long distance between base stations, and mostly single-base station coverage. In terms of user behavior, rural users mainly make short, greeting-style calls in their daily lives, and their data traffic needs are concentrated in intermittent scenarios such as checking agricultural input apps and watching short videos. At the same time, user density and business demand fluctuate greatly during market hours and busy / slack farming seasons.

[0003] From the perspective of operators' business needs, conducting targeted marketing in rural markets, optimizing network resources, and deploying village-level service outlets urgently requires access to rural user behavior data as a support for decision-making. On the one hand, this data is crucial for identifying the hot spots and time periods for calls and data usage among users on the network, enabling the development of targeted village-specific packages and optimization of base station sector coverage. On the other hand, the high proportion of users on different networks in rural areas means that a lack of behavioral data on these users can lead to biased network optimization decisions and hinder efficient allocation of network resources.

[0004] Furthermore, base stations can only demodulate signaling and service data of users on their own network, and cannot extract call and traffic behavior information of users on other networks; moreover, existing solutions mostly focus on call hotspot analysis, ignoring the trend of rapid growth in traffic demand from rural users, and the lack of dual hotspot data leads to a lack of comprehensive support for rural marketing decisions. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method for extracting call and data traffic behavior information of users on the same network and users on other networks, and to identify data traffic sessions and call hotspot areas.

[0006] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: A method for obtaining call and data hotspot areas includes: Step 1: During the collection period, use the base station in conjunction with the core network to obtain the signaling data of the user identifier, call behavior and traffic session behavior of the network users in the designated area, calculate the location corresponding to the call behavior and traffic session behavior, and generate the behavior record table of the network users based on the user identifier, call behavior and traffic session behavior and the corresponding signaling data. During the collection period, all base stations in the designated area collect radio frequency signals within their respective coverage areas, identify call behavior and traffic session behavior and obtain corresponding radio frequency signal characteristics, calculate the location of the corresponding call behavior and traffic session behavior based on the radio frequency signal characteristics, and generate a behavior record table of the users on different networks based on the call behavior and traffic session behavior and the corresponding radio frequency signal characteristics of the users on different networks. Step 2: Filter noise from the behavior log tables of users on this network and users on other networks; Step 3: Divide the specified area into grids. Based on the location of each behavior record in the behavior record tables of users in this network and users in other networks, embed the behavior record into the grid where the corresponding location falls, and output the behavior distribution matrix. Step 4: Use density clustering algorithm to perform cluster analysis on call behavior and traffic session behavior in the behavior distribution matrix, identify hotspot areas of call behavior and traffic session behavior within the collection period, and output a hotspot area distribution map.

[0007] Based on the above technical solution, the present invention can be further improved as follows.

[0008] Furthermore, it also includes step 5, which includes: Multiple time periods can be preset, and each preset time period includes at least two data collection cycles; Based on the hotspot areas determined by all collection cycles in each preset time period, the relationship between the number of users in the hotspot areas and time is statistically analyzed. Based on this relationship, the hotspot areas corresponding to the peak number of users are extracted and used as the hotspot areas for that preset time period.

[0009] The beneficial effect of adopting the above-mentioned further solution is: to extract the differences in peak call / data traffic times in each hotspot area.

[0010] Furthermore, step 4 also includes: calculating the proportion of users from the local network and users from other networks in the call behavior hotspot areas and traffic session behavior hotspot areas.

[0011] Furthermore, designated areas are divided according to scenarios, including fields, villages, towns, and markets; in the density clustering algorithm of step 4, the hotspot thresholds in the field and village scenarios are lower than those in the town and market scenarios.

[0012] The beneficial effects of adopting the above-mentioned further solutions are: adapting to the population density in different rural scenarios and improving the accuracy of hotspot area delineation.

[0013] Furthermore, designated areas are divided according to scenarios. In step 1, the data collection period for fields and villages by the base station is longer than that for towns and markets.

[0014] The beneficial effects of adopting the above-mentioned further scheme are: the differentiated collection cycle is adapted to the signal density characteristics of different rural areas, the statistical accuracy is improved in densely populated towns and markets, and the base station computing power consumption is reduced in sparsely populated fields and villages, thus achieving a balance between accuracy and resources.

[0015] Furthermore, in step 4, a hotspot distribution map with overlaid geographic identifiers is output.

[0016] The advantage of adopting the above-mentioned further solutions is that it makes it easier for marketers to quickly identify the geographical locations of hotspot areas based on the hotspot distribution map.

[0017] Furthermore, it also includes: the proportion of users from the local network and users from other networks in the hot areas of call behavior and traffic session behavior.

[0018] Furthermore, in step 1, the signaling data for the call behavior and data traffic session behavior of users on this network include start time, AOA, and signal reception strength, respectively. If a user's communication behavior or traffic session behavior is simultaneously accessed by at least two base stations, the TDOA and AOA fusion technology is used to calculate and locate the user's communication behavior or traffic session behavior. If the communication behavior or traffic session behavior of a user on this network is connected to a single base station, the communication behavior or traffic session behavior of the user on this network is calculated and located using AOA and signal received strength fusion technology.

[0019] Furthermore, the radio frequency signal characteristics of inter-network users' call behavior and data traffic session behavior include AOA and signal reception strength. AOA and signal reception strength fusion technology is used to locate the communication behavior or data traffic session behavior of inter-network users.

[0020] Furthermore, when using AOA and signal reception strength fusion technology to locate communication behavior or traffic session behavior, terrain correction parameters are introduced to correct the location results based on the terrain features of the specified area.

[0021] The beneficial effects of adopting the above-mentioned further solutions are: solving the problem of excessive errors in traditional single-base station positioning in hilly and mountainous terrain, and improving the positioning accuracy of single base stations.

[0022] Furthermore, the signaling data for users' call behavior includes the call start time and the access base station identifier; the signaling data for traffic session behavior includes the traffic transmission start time and end time, data transmission rate, and the access base station identifier. The step 2 of filtering noise in the call behavior record table of users of this network includes: determining whether the call duration and signal strength fluctuation value of the call behavior both fall within the preset threshold range; if not, it is determined to be noise and the call behavior is filtered out. The step 2 of filtering noise in the traffic session behavior of users on this network includes: determining whether the transmission rate, continuous transmission duration, and data packet interaction frequency of the traffic session behavior all fall within the preset threshold range; if not, it is determined to be noise and the traffic session behavior is filtered out.

[0023] Furthermore, the radio frequency signal characteristics of call behavior of users on different networks include signal duration, fluctuation range, and the time of radio frequency signal appearance and disappearance; the radio frequency signal characteristics of traffic session behavior include signal transmission duration, data packet exchange frequency, and the time of radio frequency signal appearance and disappearance. The step 2 of filtering noise from call behavior in the behavior record table of users on other networks includes: determining whether the duration of the radio frequency signal, the signal strength fluctuation value, and the signal spectrum stability all fall within the preset threshold range; if not, it is determined to be noise and the call behavior is filtered out. The step 2 of filtering noise in the traffic session behavior of users on other networks includes: determining whether the continuous transmission duration of the radio frequency signal, the data packet interaction frequency, and the signal strength all fall within the preset threshold range; if not, it is determined to be noise and the traffic session behavior is filtered out.

[0024] Furthermore, the noise filtering of call behavior in the behavior record table of users on different networks in step 2 includes: Typical rural noise was sampled and modeled to establish a noise model; The collected behavioral records of users from other networks are input into the noise model. The matching degree between the behavioral record and the noise model is calculated. If the matching degree is greater than or equal to the preset matching degree threshold, the behavioral record is marked as a suspicious behavioral record. The designated area is divided into core area and non-core area according to the geographic information system. The regional attributes of the core area include villages, markets and roads; the regional attributes of the non-core area include field operation areas, mountains and forests and rivers. If the location corresponding to a suspicious behavior record falls into a non-core area, the suspicious behavior record is determined to be noise and filtered out. If the location corresponding to a suspicious behavior record falls within the core area, compare the radio frequency model characteristics in the suspicious behavior record with a preset threshold range. If the radio frequency model characteristics in the suspicious behavior record fall within the preset threshold range, the suspicious behavior record is retained; otherwise, the suspicious behavior record is filtered out.

[0025] The beneficial effect of adopting the above-mentioned further solution is that, for suspicious behavior records of users on other networks, the location of the suspicious behavior records can be identified by combining the geographic information system, thereby improving the accuracy of the filtering effect.

[0026] Furthermore, it also includes: sampling and modeling typical rural noises, and establishing noise models; In step 1, the collected call and data session records of users from other networks are input into the noise model, and the matching degree between the behavior record and the noise model is calculated. If the matching degree is greater than or equal to the preset threshold, the preset threshold range is adjusted to improve the filtering effect of the behavior records of users from other networks in step 2.

[0027] The beneficial effects of adopting the above-mentioned further solution are: using a noise model to achieve dynamic adjustment of the preset threshold range, dynamically adapting to noise changes in rural areas at different times, and solving the problem of poor filtering effect of traditional fixed thresholds in special scenarios such as busy farming seasons and market days.

[0028] Furthermore, if the duration of a user's behavior record from another network intersects with the preset peak hours for crowds, the maximum value of the preset threshold range corresponding to the signal strength will be reduced.

[0029] The beneficial effect of adopting the above-mentioned further solutions is to reduce the impact of dense crowds on signal strength, thereby preventing the corresponding call or data session behavior from being mistakenly filtered.

[0030] Furthermore, step 2 also includes: performing secondary verification on the behavior records of the filtered users from other networks, including: Construct an effective signal model. Input each behavior record from the filtered behavior record table of users from other networks into the effective signal model and output a matching value. If the matching value is greater than or equal to the preset effective threshold, the behavior record is retained. If the matching value is less than the preset effective threshold, the behavior record is filtered.

[0031] The beneficial effect of adopting the above-mentioned further solution is that the secondary verification ensures that noise can be effectively filtered.

[0032] Furthermore, in step 3, dividing the specified area into grids includes: The designated areas are divided according to scenes, which include fields, villages, towns, and markets; When dividing a specified area into grids, the grid density of the areas corresponding to fields and villages is less than that of the areas corresponding to towns and markets.

[0033] The beneficial effects of adopting the above-mentioned further solutions are: ensuring the statistical granularity of village areas while accurately capturing the dense user distribution in market areas.

[0034] Furthermore, the radio frequency signal characteristics of traffic session behavior and call behavior of users from other networks collected in step 1 also include frequency bands and standards. In step 1, the operators corresponding to the frequency bands and standards are analyzed. The behavior records in the behavior record table of users from other networks also include operators. Step 4 generates a hotspot area distribution map and counts the number of users from different operators in the hotspot areas.

[0035] Furthermore, if the frequency bands of traffic session behavior and call behavior of users on different networks correspond to two different operators, the signal frame structure of the corresponding radio frequency signals is analyzed to determine the operator.

[0036] The advantages of adopting the above-mentioned further solution are: during analysis, the signal frequency band and modulation method are extracted first, and the operator affiliation is determined by matching the mapping table. This quickly and accurately distinguishes between different network operators, providing data support for statistics on the proportion of users on different networks and targeted penetration marketing. If the frequency bands of traffic session behavior or call behavior of users on different networks correspond to two operators, the signal frame structure of the corresponding radio frequency signals is analyzed to determine the operator, resolving the problem of operator affiliation ambiguity caused by frequency band overlap.

[0037] Furthermore, after embedding the behavior record into the grid where the corresponding location falls in step 3, the processor is configured to: for users of the same network, deduplicate the call behavior and traffic behavior generated simultaneously by the same user of the same network in the grid; for users of different networks, based on the call behavior and traffic session behavior generated simultaneously in the grid, use signal trajectory matching degree to determine whether the call behavior and traffic session behavior generated simultaneously belong to the same user of different networks, and if so, deduplicate the call behavior and traffic behavior generated simultaneously.

[0038] The advantage of adopting the above-mentioned further solution is that it avoids the impact of simultaneous user call behavior and data traffic session behavior on the accuracy of statistical results.

[0039] Furthermore, the user identifiers of users on this website are anonymous.

[0040] The beneficial effects of adopting the above-mentioned further solutions are: to achieve anonymization processing from the source of data collection, to avoid the storage of user privacy information on the ground, and to eliminate the possibility of reverse deduction of personal information.

[0041] The technical solution of the present invention to solve the above-mentioned technical problems is as follows.

[0042] A call and data traffic hotspot area acquisition system includes at least one base station deployed in a designated area, the base station being connected to a processor; The base station is configured to acquire signaling data of user identifiers, call behavior, and traffic session behavior of users in a designated area by combining the core network during the acquisition period; and to acquire radio frequency signals within the coverage area during the acquisition period, identify call behavior and traffic session behavior, and acquire corresponding radio frequency signal characteristics. The processor is configured to calculate the location corresponding to call behavior and traffic session behavior using the signaling data of the network user, and generate a behavior record table of the network user based on the user identifier, call behavior and traffic session behavior and the corresponding signaling data of the network user; The processor is also configured to calculate the location of the corresponding call behavior and data traffic session behavior using the radio frequency signal characteristics of the user on the other network, and generate a behavior record table of the user on the other network based on the call behavior and data traffic session behavior and the corresponding radio frequency signal characteristics. The processor is also configured to filter noise from the behavior record tables of users on the local network and users on other networks, divide the specified area into grids, embed the behavior record into the grid where the corresponding location falls according to the location of each behavior record in the behavior record tables of users on the local network and users on other networks, and output a behavior distribution matrix. The processor is also configured to use a density clustering algorithm to perform cluster analysis on call behavior and traffic session behavior in the behavior distribution matrix, identify hotspot areas of call behavior and traffic session behavior within the collection period, and output a hotspot area distribution map.

[0043] Furthermore, the processor is also configured to: preset multiple time periods, each preset time period including at least two collection cycles; based on the hotspot areas determined by all collection cycles in each preset time period, statistically analyze the relationship between the number of users in the hotspot areas and time; and according to this relationship, extract the hotspot areas corresponding to the peak number of users and use them as the hotspot areas of the preset time period.

[0044] Furthermore, the processor is also configured to calculate the proportion of local network users and external network users in the call behavior hotspot areas and traffic session behavior hotspot areas in the hotspot area distribution map.

[0045] Furthermore, the designated area is divided into scenarios, including fields, villages, towns, and markets. The hotspot threshold of the density clustering algorithm in the field and village scenarios is lower than that in the town and market scenarios.

[0046] Furthermore, the designated area is divided according to scenarios, and the base station collects data on scenarios in fields and villages for a longer period than it collects data on scenarios in towns and markets.

[0047] Furthermore, the processor outputs a hotspot distribution map overlaid with geographic identifiers.

[0048] Furthermore, the signaling data for the call behavior and data traffic session behavior of users on this network include start time, AOA, and signal reception strength, respectively. The processor uses the signaling data of users on this network to calculate the location corresponding to the call behavior and data traffic session behavior, including: If a user's communication behavior or traffic session behavior is simultaneously accessed by at least two base stations, the TDOA and AOA fusion technology is used to calculate and locate the user's communication behavior or traffic session behavior. If the communication behavior or traffic session behavior of a user on this network is connected to a single base station, the communication behavior or traffic session behavior of the user on this network is calculated and located using AOA and signal received strength fusion technology.

[0049] Furthermore, the radio frequency signal characteristics of the call behavior and data traffic session behavior of users on different networks include AOA and signal reception strength. The processor uses the radio frequency signal characteristics of users on different networks to calculate the localization corresponding to the call behavior and data traffic session behavior, including: The communication behavior or traffic session behavior of users on different networks is located by using AOA and signal reception strength fusion technology.

[0050] Furthermore, when the processor uses AOA and signal reception strength fusion technology to locate communication behavior or traffic session behavior, it introduces terrain correction parameters to correct the positioning results based on the terrain features of the specified area.

[0051] Furthermore, the signaling data for users' call behavior includes the call start time and access base station identifier; the signaling data for traffic session behavior includes the traffic transmission start time and end time, data transmission rate, and access base station identifier. The processor filters noise from call behavior in the behavior record table of users on this network by: determining whether the call duration and signal strength fluctuation value of the call behavior both fall within a preset threshold range; if not, it is determined to be noise and the call behavior is filtered out. The processor filters noise from traffic session behavior in the behavior record table of users on this network by: determining whether the transmission rate, continuous transmission duration, and data packet interaction frequency of the traffic session behavior all fall within a preset threshold range; if not, it is determined to be noise and the traffic session behavior is filtered out.

[0052] Furthermore, the radio frequency signal characteristics of call behavior of users on different networks include signal duration, fluctuation range, and the time of radio frequency signal appearance and disappearance; the radio frequency signal characteristics of traffic session behavior include signal transmission duration, data packet exchange frequency, and the time of radio frequency signal appearance and disappearance. The processor filters noise from call behavior records of users on other networks by: determining whether the duration of the radio frequency signal, the signal strength fluctuation value, and the signal spectrum stability fall within a preset threshold range; if not, it is determined to be noise and the call behavior is filtered out. The processor filters noise from traffic session behavior in the behavior log table of users on other networks by: determining whether the duration of continuous transmission of radio frequency signals, data packet interaction frequency, and signal strength all fall within a preset threshold range; if not, it is determined to be noise and the traffic session behavior is filtered out.

[0053] Furthermore, the processor filters noise from the behavior log table of users on other networks, including: Typical rural noise was sampled and modeled to establish a noise model; Input the call and data session records of users from other networks into the noise model, calculate the matching degree between the record and the noise model, and mark the record as a suspicious record if the matching degree is greater than or equal to the preset threshold. The designated area is divided into core area and non-core area according to the geographic information system. The regional attributes of the core area include villages, markets and roads; the regional attributes of the non-core area include field operation areas, mountains and forests and rivers. If the location corresponding to a suspicious behavior record falls into a non-core area, the suspicious behavior record is determined to be noise and filtered out. If the location corresponding to a suspicious behavior record falls within the core area, compare the radio frequency model characteristics in the suspicious behavior record with a preset threshold range. If the radio frequency model characteristics in the suspicious behavior record fall within the preset threshold range, the suspicious behavior record is retained; otherwise, the suspicious behavior record is filtered out.

[0054] Furthermore, the processor is also configured to sample and model typical rural noises to establish a noise model; The collected call and data session behavior records of users on different networks are input into the noise model. The matching degree between the behavior record and the noise model is calculated. If the matching degree is greater than or equal to the preset matching degree threshold, the preset filtering threshold is adjusted to improve the filtering effect.

[0055] Furthermore, the processor is also configured to: preset a period of high population density, identify the duration of the behavior records of users on other networks, determine whether it intersects with the preset period of high population density, and if so, reduce the maximum value of the preset threshold range corresponding to the signal strength.

[0056] Furthermore, the processor is configured to filter noise from call behavior records in the behavior log table of users on other networks, and then perform a secondary verification on the filtered behavior records, including: Construct an effective signal model. Input each behavior record from the filtered behavior record table of users from other networks into the effective signal model and output a matching value. If the matching value is greater than or equal to the preset effective threshold, the behavior record is retained. If the matching value is less than the preset effective threshold, the behavior record is filtered.

[0057] Furthermore, when the processor divides a specified area into grids, it divides the specified area according to a scene, which includes fields, villages, towns, and markets. The grid density of the areas corresponding to fields and villages is lower than that of the areas corresponding to towns and markets.

[0058] Furthermore, the radio frequency signal characteristics of traffic session behavior and call behavior of users from other networks collected by the base station also include frequency bands and standards. The processor analyzes the operators corresponding to the radio frequency signals based on the frequency bands and standards. The behavior records in the behavior record table of users from other networks also include operators. The processor generates a hotspot distribution map and counts the number of users from different operators in the hotspot areas.

[0059] Furthermore, the radio frequency signal characteristics of traffic session behavior and call behavior of users from other networks collected by the base station also include frequency band and standard, respectively. The processor is configured to analyze the operator corresponding to the radio frequency signal based on the frequency band and standard, and generate a behavior record table of users from other networks including the operator. The processor is also configured to count the number of users of different operators in hotspot areas.

[0060] Furthermore, if the frequency bands of traffic session behavior and call behavior of users on different networks correspond to two different operators, the signal frame structure of the corresponding radio frequency signals is analyzed to determine the operator.

[0061] Furthermore, after the processor embeds the behavior records into the grid where the corresponding location falls, the processor is configured to: for users on the same network, deduplicate call behavior and data traffic behavior generated simultaneously by the same user on the same network within the grid; for users on different networks, based on the call behavior and data traffic session behavior generated simultaneously within the grid, use signal trajectory matching degree to determine whether the call behavior and data traffic session behavior generated simultaneously belong to the same user on different networks, and if so, deduplicate the call behavior and data traffic behavior generated simultaneously.

[0062] Furthermore, the user identifiers of users on this website are anonymous.

[0063] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method.

[0064] Another technical solution of the present invention to solve the above-mentioned technical problem is as follows: a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned method is implemented.

[0065] The beneficial effects of the call and data traffic hotspot acquisition method, system, device, and medium described in this invention include: This technology enables simultaneous collection and analysis of call and data traffic data from both local and external network users in rural settings. It overcomes the limitations of traditional base stations that can only process data from their own network, fills the gap in analyzing the behavior of users on different networks in rural areas, and provides data support for operators' precision marketing and network optimization.

[0066] By using radio frequency signal characteristics and positioning, the behavior of users on other networks can be identified and counted. This can be done without demodulating the protocols of other networks or obtaining user identification. Under the premise of technical feasibility, the number of users on other networks can be counted, while meeting privacy compliance requirements.

[0067] By using grid partitioning and behavior embedding to achieve spatialized statistics of user behavior, we can intuitively reflect the distribution patterns of users in different areas of rural areas, providing an accurate data foundation for hotspot identification.

[0068] The algorithm uses density clustering to automatically identify call hotspots and data traffic hotspots, and outputs a visual hotspot distribution map, making the identification of hotspot areas in rural areas more objective and efficient. This can directly provide data support for package promotion, marketing, and efficient allocation of network resources. Attached Figure Description

[0069] Figure 1 This is a flowchart of the method for obtaining call and data hotspot areas according to the present invention; Figure 2 This is a schematic diagram of the structure of the electronic device described in this invention. Detailed Implementation

[0070] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0071] Example 1 See attached document Figure 1 As shown, Embodiment 1 of this application is proposed. Embodiment 1 describes a method for obtaining call and data hotspot areas, including: Step 1: During the collection period, use the base station in conjunction with the core network to obtain the signaling data of the user identifier, call behavior and traffic session behavior of the network users in the designated area, calculate the location corresponding to the call behavior and traffic session behavior, and generate the behavior record table of the network users based on the user identifier, call behavior and traffic session behavior and the corresponding signaling data. Signaling data for call behavior of users on this network includes anonymized user identifier, call start time, access base station identifier, AOA and RSSI signal reception strength; signaling data for traffic session behavior of users on this network includes anonymized user identifier, traffic transmission start time and end time, data transmission rate, access base station identifier, AOA and RSSI signal reception strength.

[0072] Our users are identified using encrypted Temporary Mobile Subscriber Identity (TMSI) codes, with all personally identifiable information such as International Mobile Subscriber Identity (IMSI) codes and phone numbers removed throughout the entire process. This real-time anonymization process from the data collection source prevents the storage of user privacy information and eliminates the possibility of reverse-engineering personal information, complying with the requirements of the Personal Information Protection Law.

[0073] When calculating the location of a user's communication behavior or traffic session behavior, if the user's communication behavior or traffic session behavior is connected to at least two base stations at the same time, the TDOA (Time Difference of Arrival) and AOA fusion technology is used to calculate the location of the user's communication behavior or traffic session behavior; if the user's communication behavior or traffic session behavior is connected to a single base station, the AOA and signal received strength fusion technology is used to calculate the location of the user's communication behavior or traffic session behavior.

[0074] In response to the situation in rural areas where single-base station coverage is the primary method and multiple base stations are used as supplementary methods, a differentiated positioning strategy is adopted to make full use of existing base station resources and improve positioning accuracy without additional hardware investment.

[0075] When using AOA and signal reception strength fusion technology to locate communication behavior or traffic session behavior, terrain correction parameters are introduced to correct the positioning results based on the terrain features of the specified area. Specifically, the terrain correction parameters are set as follows: 1.0 for plains, 1.3 for hills, and 1.5 for mountains. This corrects the attenuation effect of terrain on signal transmission, solving the problem of excessive errors in traditional single-base station positioning in hilly and mountainous terrains. The positioning accuracy of single base stations is improved from the traditional 500-1000 meters to 100-500 meters, making it suitable for rural settlements.

[0076] Each record in the final user behavior log table includes an anonymized user identifier, behavior type (call / data usage), start and end time, access base station identifier, location, and signaling data.

[0077] Step 1: During the collection period, all base stations in the designated area collect radio frequency signals within their respective coverage areas, identify call behavior and traffic session behavior and obtain the corresponding radio frequency signal characteristics, calculate the location of the corresponding call behavior and traffic session behavior based on the radio frequency signal characteristics, and generate a behavior record table of the users on different networks based on the call behavior and traffic session behavior and the corresponding radio frequency signal characteristics of the users on different networks. Utilizing the wideband receiving capability of the base station's RF front-end, the RF signal characteristics of users on different networks within the coverage area are collected without demodulating the content of the different network protocols. The collected call signal characteristics include: frequency band, RSSI, AOA, signal duration, and fluctuation range; the collected traffic signal characteristics include: frequency band, RSSI, AOA, signal transmission duration, data packet exchange frequency, and modulation method. Simultaneously, the signal appearance / disappearance time is recorded and correlated with the time characteristics of rural scenarios.

[0078] The radio frequency signal characteristics of inter-network users' call and data traffic session behaviors include AOA (Aspect-Oriented Analysis) and Received Signal Strength (RSS). AOA and SRS fusion technology is used to locate the communication or data traffic session behaviors of inter-network users. Similarly, when using AOA and SRS fusion technology to locate communication or data traffic session behaviors, terrain correction parameters are introduced based on the terrain features of the specified area to correct the location results.

[0079] The radio frequency signal characteristics of traffic session behavior and call behavior of users from other networks collected in step 1 also include frequency bands and modulation methods. The operators corresponding to the radio frequency signals are analyzed based on the frequency bands and modulation methods in step 1. The behavior records in the behavior record table of users from other networks also include operators.

[0080] In the pre-defined rural mainstream frequency band mapping table, China Mobile's cross-network signals cover 4G bands B38 / B39 / B40 / B41 and 5G bands n41 / n79; China Telecom's cross-network signals cover 4G bands B1 / B3 / B5 and 5G band n78; and China Unicom's cross-network signals cover 4G bands B1 / B3 / B8 and 5G band n78. During analysis, the signal frequency band and modulation method are first extracted, and the mapping table is matched to determine the operator affiliation. This allows for quick and accurate differentiation of cross-network operators, providing data support for cross-network user proportion statistics and targeted penetration marketing.

[0081] If the frequency bands of traffic session behavior or call behavior of users on different networks correspond to two operators, analyze the signal frame structure of the corresponding radio frequency signals and determine the operator to resolve the problem of operator affiliation caused by frequency band overlap.

[0082] Each record in the inter-network user behavior record table obtained in Step 1 includes the operator affiliation, behavior type (call / data usage), start and end time of the behavior, and radio frequency signal characteristics. Inter-network users are counted based on their radio frequency signal characteristics and the signal source represented by their location; the same signal source is counted as one user.

[0083] In step 1, the collection period can be adjusted according to the scenario. For example, the designated area can be divided according to the scenario, including fields, villages, towns, and markets. The collection period for fields and villages is longer than that for towns and markets. For example, the default collection period is 30 minutes for villages and fields, and shortened to 15 minutes for towns and markets. During the busy farming season, it can be adjusted to 20 minutes as needed. Different collection periods adapt to the signal density characteristics of different rural areas in different scenarios, improving statistical accuracy in densely populated towns and markets, and reducing base station computing power consumption in sparsely populated fields and villages, thus achieving a balance between accuracy and resources.

[0084] Step 2: Filter noise from the behavior record tables of users on this network and users on other networks.

[0085] In this embodiment, the call behavior filtering method for users of this network is as follows: the call duration is ≥2 seconds, the voice channel occupancy is stable, and the signal strength fluctuation is ≤±5dBm. If the call does not meet the above preset threshold range, the corresponding call behavior is excluded, including abnormal calls caused by immediate hanging up after dialing or signal interruption. The traffic behavior filtering method for users of this network is as follows: the data transmission rate is ≥1Mbps, the continuous transmission duration is ≥5 seconds, and the data packet exchange frequency is ≥2 data packets per second. If the traffic behavior does not meet the above preset threshold range, the corresponding traffic session behavior is excluded. This distinguishes between low-rate signaling exchanges and effective traffic behavior, thereby adapting to the behavioral characteristics of short-duration greeting calls and intermittent traffic usage of rural users and reducing the false positive rate.

[0086] In this embodiment, the method for filtering inter-network user call behavior is as follows: signal duration ≥ 3 seconds, signal strength fluctuation ≤ ±6dBm, and simultaneously satisfying signal spectrum stability and a signal occurrence time matching the peak rural call time period ≥ 60%. If it does not meet the preset threshold range, the corresponding call behavior is filtered. The method for filtering inter-network user traffic behavior is as follows: signal transmission duration ≥ 6 seconds, data packet exchange frequency 3-10 data packets per second, signal strength ≥ -105dBm. If it does not meet the preset threshold range, the corresponding call behavior is filtered.

[0087] When filtering noise from the behavior records of users on other networks using a preset threshold range, an adaptive threshold algorithm is employed, including: Typical noise signals in rural areas were sampled and modeled to establish a noise model. The core noise in rural areas includes two types: field electromagnetic interference and agricultural machinery wireless signals. Field electromagnetic interference is characterized by low intensity, wide spectrum, and irregular fluctuations, with signal strength ≤ -110dBm and fluctuation frequency > 10Hz. Agricultural machinery wireless signals are characterized by bursty, short-duration, and narrow spectrum signals with a duration of < 2 seconds and the spectrum is concentrated in the industrial wireless frequency band.

[0088] The collected call and data session behavior records of users on different networks are input into the noise model. The matching degree between the behavior record and the noise model is calculated. If the matching degree is greater than or equal to a preset threshold, the preset filtering threshold is adjusted to improve the filtering effect. For example, during busy farming seasons, the judgment duration threshold for agricultural machinery signals is automatically reduced from 2 seconds to 1.5 seconds; during market seasons, the filtering threshold for low-intensity fluctuating signals is increased, thereby dynamically adapting to noise changes in rural areas at different times and solving the problem of poor filtering effect of traditional fixed thresholds in special scenarios such as busy farming seasons and market seasons.

[0089] As a preferred embodiment, in another embodiment, filtering noise in the behavior record table of users on other networks includes: inputting the collected behavior records of users on other networks into a noise model, calculating the matching degree between the behavior record and the noise model, and if the matching degree is greater than or equal to a preset threshold, marking the behavior record as a suspicious behavior record. The designated area is divided into core and non-core areas according to the Geographic Information System (GIS). The regional attributes of the core area include villages, markets, and roads, while the regional attributes of the non-core area include field work areas, forests, and rivers. If the location corresponding to a suspicious behavior record falls into the non-core area, the suspicious behavior record is determined to be noise and filtered. If the location corresponding to a suspicious behavior record falls into the core area, the radio frequency signal characteristics in the suspicious behavior record are compared with a preset threshold range. If it falls into the preset threshold range, it is retained; otherwise, it is filtered.

[0090] As a preferred approach, the behavior records of filtered users from other networks are further validated by a second step. This includes constructing an effective signal model, inputting each behavior record from the behavior record table of filtered users from other networks into the effective signal model, and outputting a matching value. If the matching value is greater than or equal to a preset effective threshold, the behavior record is retained; otherwise, it is filtered.

[0091] The effective signal model is constructed based on the typical effective signal characteristics of different rural areas. It is based on the characteristics that village users' call signals are mostly medium intensity and continuous and stable, while road users' signals are mostly medium duration and linear movement. The noise filtering effect is ensured through secondary verification.

[0092] Step 3: Divide the specified area into grids. Based on the location of each behavior record in the behavior record tables of users in this network and users in other networks, embed the behavior record into the grid where the corresponding location falls, and output the behavior distribution matrix. Specifically, designated areas are divided according to scenarios, including fields, villages, towns, and markets. When dividing these areas into grids, the grid density for fields and villages is lower than that for towns and markets. Specifically, villages and fields use a 200m x 200m grid, while towns and markets use a 100m x 100m grid. This ensures statistical granularity for villages while accurately capturing the dense user distribution in markets, resulting in lower statistical errors compared to traditional uniform grid division.

[0093] After embedding the behavior records into the corresponding grid where the location falls, duplicate call and data traffic behaviors generated simultaneously by the same user in each grid are deduplicated. Specifically, for users within the same network, user identifiers are used to deduplicate call and data traffic behaviors generated simultaneously by the same user in the same grid; simultaneous call and data traffic behaviors by the same user in the same grid are counted as one person. For users from other networks, if call and data traffic sessions of users from other networks occur simultaneously in a grid, signal trajectory matching is used to determine whether the simultaneous call and data traffic sessions belong to the same user from other networks. If so, the simultaneous call and data traffic behaviors are deduplicated.

[0094] The generated behavior distribution matrix includes the number of local network call users, local network traffic users, inter-network call users, and inter-network traffic users within the corresponding grid.

[0095] Step 4: Use density clustering algorithm to perform cluster analysis on call behavior and traffic session behavior in the behavior distribution matrix, identify hotspot areas of call behavior and traffic session behavior within the collection period, and output a hotspot area distribution map.

[0096] A density-based noise application spatial clustering algorithm (DBSCAN) optimized for rural scenarios is used, with call user density and data traffic user density as core indicators, combined with the geographical continuity characteristics of rural areas for clustering. In the density clustering algorithm, specified areas are divided according to scenarios, including fields, villages, towns, and markets. The hotspot thresholds in field and village scenarios are lower than those in town and market scenarios. For example, the hotspot thresholds are set as follows: ≥5 people per grid in villages, ≥15 people per grid in markets, and ≥3 people per grid in field work areas.

[0097] After clustering is completed, adjacent grids that meet the threshold are divided into call hotspot areas and traffic hotspot areas, and hotspot levels are marked respectively, including primary hotspots such as markets, secondary hotspots such as central villages, and hotspot area distribution maps are output.

[0098] The hotspot distribution map can also simultaneously mark the geographical identifiers of each grid, such as villages, markets, and field roads.

[0099] As a preferred option, the hotspot distribution map can also show the percentage of users from the local network / other networks in the marked hotspot areas.

[0100] As a preferred option, the hotspot distribution map also simultaneously marks the number of users from different operators in the hotspot areas.

[0101] As a preferred option, the hotspot distribution map also simultaneously marks areas where call hotspots and data traffic hotspots overlap.

[0102] In this embodiment, preferably, step 5 is also included. Step 5 includes: presetting multiple time periods, each preset time period including at least two collection cycles, based on the hotspot areas determined by all collection cycles in each preset time period, statistically analyzing the change relationship of the number of users in the hotspot areas over time, and extracting the hotspot areas corresponding to the peak of the number of users according to the change relationship and using them as the hotspot areas of the preset time period.

[0103] The preset time periods can be set according to general hourly intervals or according to rural-specific time periods, such as the pre-farming period in the morning (7-8 am), market period (9-11 am), midday rest period (12-2 pm), afternoon farming period (3-5 pm), and evening leisure period (7-9 pm). Step 5 identifies the call activity hotspots and data traffic hotspots within each preset time period. Based on the results, the differences in peak call / data traffic times for each hotspot area can be accurately extracted. For example, peak call times in markets are identified as 9-11 am, and peak data traffic times as 10-12 pm; peak call times in villages are identified as 7-9 pm, and peak data traffic times as 8-10 pm. These peak times can directly guide operators in developing time-sharing marketing strategies.

[0104] In this embodiment, the condition that needs to be met during peak user numbers is that the number of users in the hotspot area is in the top 30% for at least two consecutive collection periods, which is suitable for the concentrated characteristics of rural time periods.

[0105] Example 2 This embodiment proposes a call and data traffic hotspot area acquisition system, including at least one base station deployed in a designated area, the base station being connected to a processor; The base station is configured to acquire signaling data of user identifiers, call behavior, and traffic session behavior of users in a designated area by combining the core network during the acquisition period; and to acquire radio frequency signals within the coverage area during the acquisition period, identify call behavior and traffic session behavior, and acquire corresponding radio frequency signal characteristics.

[0106] The base station includes an antenna, radio frequency unit, and BBU baseband processing unit. The base station collects signaling data from users of the network through a standard interface with the core network and transmits it to the processor. This signaling data includes: anonymized user identifier, call start / end time, traffic transmission start / end time, data transmission rate, access base station identifier, AOA (Angle of Arrival), and RSSI (Received Signal Strength Indicator). Preferably, the user identifiers of the network users are anonymized, with privacy information such as IMSI and mobile phone numbers completely removed throughout the process.

[0107] The base station utilizes a wide-band RF front-end to collect RF signals from all users on different networks within its coverage area and transmits them to the processor without demodulating the different network protocols. The collected data includes: frequency band, modulation scheme, AOA, RSSI, signal duration, data packet exchange frequency, and signal appearance / disappearance time.

[0108] The processor is configured to calculate the location corresponding to call behavior and data traffic session behavior using signaling data of users on the local network; and generate a behavior record table for users on the local network based on the user identifier, call behavior, data traffic session behavior and corresponding signaling data of users on the local network; the processor is also configured to calculate the location corresponding to call behavior and data traffic session behavior using radio frequency signal characteristics of users on other networks, and generate a behavior record table for users on other networks based on the call behavior and data traffic session behavior and corresponding radio frequency signal characteristics of users on other networks.

[0109] When calculating the location of a user's communication behavior or traffic session behavior, if the user's communication behavior or traffic session behavior is connected to at least two base stations at the same time, the TDOA (Time Difference of Arrival) and AOA fusion technology is used to calculate the location of the user's communication behavior or traffic session behavior; if the user's communication behavior or traffic session behavior is connected to a single base station, the AOA and signal received strength fusion technology is used to calculate the location of the user's communication behavior or traffic session behavior.

[0110] In response to the situation in rural areas where single-base station coverage is the primary method and multiple base stations are used as supplementary methods, a differentiated positioning strategy is adopted to make full use of existing base station resources and improve positioning accuracy without additional hardware investment.

[0111] When using AOA and signal reception strength fusion technology to locate communication behavior or traffic session behavior, terrain correction parameters are introduced to correct the positioning results based on the terrain features of the specified area. Specifically, the terrain correction parameters are set as follows: 1.0 for plains, 1.3 for hills, and 1.5 for mountains. This corrects the attenuation effect of terrain on signal transmission, solving the problem of excessive errors in traditional single-base station positioning in hilly and mountainous terrains. The positioning accuracy of single base stations is improved from the traditional 500-1000 meters to 100-500 meters, making it suitable for rural settlements.

[0112] Each record in the final user behavior log table includes an anonymized user identifier, behavior type (call / data usage), start and end time, access base station identifier, location, and signaling data.

[0113] The characteristics of inter-network user call signals include: frequency band, RSSI, AOA, signal duration, and fluctuation range; the characteristics of traffic signals include: frequency band, RSSI, AOA, signal transmission duration, data packet exchange frequency, and modulation method. The signal appearance / disappearance time is also recorded and correlated with the time characteristics of rural scenarios.

[0114] The radio frequency signal characteristics of inter-network users' call and data traffic session behaviors include AOA (Aspect-Oriented Analysis) and Received Signal Strength (RSS). AOA and SRS fusion technology is used to locate the communication or data traffic session behaviors of inter-network users. Similarly, when using AOA and SRS fusion technology to locate communication or data traffic session behaviors, terrain correction parameters are introduced based on the terrain features of the specified area to correct the location results.

[0115] The radio frequency signal features of traffic session behavior and call behavior of users on different networks collected by the base station also include frequency bands and modulation methods. The processor is also configured to parse the operator corresponding to the radio frequency signal based on the frequency band and modulation method. The behavior records in the generated inter-network user behavior record table also include the operator.

[0116] In the pre-defined rural mainstream frequency band mapping table, China Mobile's cross-network signals cover 4G bands B38 / B39 / B40 / B41 and 5G bands n41 / n79; China Telecom's cross-network signals cover 4G bands B1 / B3 / B5 and 5G band n78; and China Unicom's cross-network signals cover 4G bands B1 / B3 / B8 and 5G band n78. During analysis, the signal frequency band and modulation method are first extracted, and the mapping table is matched to determine the operator affiliation. This allows for quick and accurate differentiation of cross-network operators, providing data support for cross-network user proportion statistics and targeted penetration marketing.

[0117] If the frequency bands of traffic session behavior or call behavior of users on different networks correspond to two operators, analyze the signal frame structure of the corresponding radio frequency signals and determine the operator to resolve the problem of operator affiliation caused by frequency band overlap.

[0118] Each record in the final cross-network user behavior log includes the carrier affiliation, behavior type (call / data usage), start and end time of the behavior, and radio frequency signal characteristics. Cross-network users are counted based on their radio frequency signal characteristics and the signal source represented by their location; the same signal source is counted as one user.

[0119] The duration of base station data collection can be adjusted according to the specific scenario. For example, a designated area can be divided into scenarios such as fields, villages, towns, and markets. The data collection period for fields and villages is longer than that for towns and markets. For instance, the default collection period is 30 minutes for villages and fields, shortened to 15 minutes for towns and markets, and can be adjusted to 20 minutes during the busy farming season. This differentiated collection period adapts to the signal density characteristics of different rural areas, improving statistical accuracy in densely populated towns and markets, and reducing base station computing power consumption in sparsely populated fields and villages, thus achieving a balance between accuracy and resources.

[0120] The processor is further configured to filter noise from the behavior log tables of users on the local network and users on other networks, specifically: In this embodiment, the call behavior filtering logic for users of this network is as follows: the call duration is ≥2 seconds, the voice channel occupancy is stable, and the signal strength fluctuation is ≤±5dBm. If the call does not meet the above preset threshold range, the corresponding call behavior is excluded, as are abnormal calls caused by immediate hanging up after dialing or signal interruption. The data traffic behavior filtering logic for users of this network is as follows: the data transmission rate is ≥1Mbps, the continuous transmission duration is ≥5 seconds, and the data packet exchange frequency is ≥2 data packets per second. If the data traffic does not meet the above preset threshold range, the corresponding data traffic session behavior is excluded. This distinguishes between low-rate signaling exchanges and effective data traffic behavior, thereby adapting to the behavioral characteristics of short-duration greeting calls and intermittent data traffic usage of rural users and reducing the false positive rate.

[0121] In this embodiment, the filtering logic for inter-network user call behavior is as follows: signal duration ≥ 3 seconds, signal strength fluctuation ≤ ±6dBm, and simultaneously satisfying signal spectrum stability and a signal occurrence time matching the peak rural call time period ≥ 60%. If it does not meet the preset range, the corresponding call behavior is filtered. The filtering logic for inter-network user traffic behavior is as follows: signal transmission duration ≥ 6 seconds, data packet exchange frequency 3-10 data packets per second, signal strength ≥ -105dBm. If it does not meet the preset threshold range, the corresponding call behavior is filtered.

[0122] When filtering noise from behavior records using a preset threshold range, an adaptive threshold algorithm is employed, including: Typical noise signals in rural areas were sampled and modeled to establish a noise model. The core noise in rural areas includes two types: field electromagnetic interference and agricultural machinery wireless signals. Field electromagnetic interference is characterized by low intensity, wide spectrum, and irregular fluctuations, with signal strength ≤ -110dBm and fluctuation frequency > 10Hz. Agricultural machinery wireless signals are characterized by bursty, short-duration, and narrow spectrum signals with a duration of < 2 seconds and the spectrum is concentrated in the industrial wireless frequency band.

[0123] The collected call and data session behavior records of users on different networks are input into the noise model. The matching degree between the behavior record and the noise model is calculated. If the matching degree is greater than or equal to a preset threshold, the preset filtering threshold is adjusted to improve the filtering effect. For example, during busy farming seasons, the judgment duration threshold for agricultural machinery signals is automatically reduced from 2 seconds to 1.5 seconds; during market seasons, the filtering threshold for low-intensity fluctuating signals is increased, thereby dynamically adapting to noise changes in rural areas at different times and solving the problem of poor filtering effect of traditional fixed thresholds in special scenarios such as busy farming seasons and market seasons.

[0124] Preferably, in another embodiment, the processor filters noise in the behavior record table of users on other networks by: inputting the collected behavior records of users on other networks into a noise model, calculating the matching degree between the behavior record and the noise model, and marking the behavior record as a suspicious behavior record if the matching degree is greater than or equal to a preset threshold. The designated area is divided into core and non-core areas according to the Geographic Information System (GIS). The regional attributes of the core area include villages, markets, and roads, while the regional attributes of the non-core area include field work areas, forests, and rivers. If the location corresponding to a suspicious behavior record falls into the non-core area, the suspicious behavior record is determined to be noise and filtered. If the location corresponding to a suspicious behavior record falls into the core area, the radio frequency signal characteristics in the suspicious behavior record are compared with a preset threshold range. If it falls into the preset threshold range, it is retained; otherwise, it is filtered.

[0125] Preferably, the processor is further configured to perform secondary verification on the behavior records of filtered users from other networks, the secondary verification including: This includes constructing an effective signal model, inputting each behavior record from the filtered behavior record table of users from other networks into the effective signal model, outputting a matching value, and retaining the behavior record if the matching value is greater than or equal to a preset effective threshold, otherwise filtering it.

[0126] The effective signal model is constructed based on the typical effective signal characteristics of different rural areas. It is based on the characteristics that village users' call signals are mostly medium intensity and continuous and stable, while road users' signals are mostly medium duration and linear movement. The noise filtering effect is ensured through secondary verification.

[0127] The processor is also configured to divide the specified area into grids, embed the behavior records into the grids where the corresponding locations fall, and output a behavior distribution matrix based on the location of each behavior record in the behavior record tables of users on the local network and users on other networks.

[0128] Specifically, designated areas are divided according to scenarios, including fields, villages, towns, and markets. When dividing these areas into grids, the grid density for fields and villages is lower than that for towns and markets. Specifically, villages and fields use a 200m x 200m grid, while towns and markets use a 100m x 100m grid. This ensures statistical granularity for villages while accurately capturing the dense user distribution in markets, resulting in lower statistical errors compared to traditional uniform grid division.

[0129] After embedding the behavior records into the corresponding location's grid, duplicate call and data usage behaviors of the same user within the grid are deduplicated. Specifically, for users within the same network, user identifiers are used to deduplicate call and data usage behaviors of the same user within the same grid; simultaneous call and data usage behaviors of the same user within the same network within the same grid are counted as one person. For users from other networks, if call and data usage behaviors of users from other networks occur simultaneously within the same grid, signal trajectory matching is used to determine whether the simultaneous call and data usage behaviors belong to the same user from other networks. If so, the simultaneous call and data usage behaviors are deduplicated and counted as one person.

[0130] The generated behavior distribution matrix includes the number of local network call users, local network traffic users, inter-network call users, and inter-network traffic users within the corresponding grid.

[0131] The processor is also configured to use a density clustering algorithm to perform cluster analysis on call behavior and traffic session behavior in the behavior distribution matrix, respectively, to identify hotspot areas for call behavior and traffic session behavior within the collection period, and output a hotspot area distribution map. Specifically, A density-based noise application spatial clustering algorithm (DBSCAN) optimized for rural scenarios is used, with call user density and data traffic user density as core indicators, combined with the geographical continuity characteristics of rural areas for clustering. In the density clustering algorithm, specified areas are divided according to scenarios, including fields, villages, towns, and markets. The hotspot thresholds in field and village scenarios are lower than those in town and market scenarios. For example, the hotspot thresholds are set as follows: ≥5 people per grid in villages, ≥15 people per grid in markets, and ≥3 people per grid in field work areas.

[0132] After clustering is completed, adjacent grids that meet the threshold are divided into call hotspot areas and traffic hotspot areas, and hotspot levels are marked respectively, including primary hotspots such as markets, secondary hotspots such as central villages, and hotspot area distribution maps are output.

[0133] The hotspot distribution map can also simultaneously mark the geographical markers of each grid (such as villages, markets, field roads, etc.); Preferably, the processor is also configured to statistically analyze and label the proportion of local network users and external network users in the call behavior hotspot areas and traffic session behavior hotspot areas in the hotspot area distribution map.

[0134] Preferably, the processor is also configured to count and label the number of users from different network operators in the call behavior hotspot areas and traffic session behavior hotspot areas in the hotspot area distribution map.

[0135] Preferably, the processor is also configured to mark the overlapping area of ​​call hotspots and data traffic hotspots in the hotspot area distribution map.

[0136] Preferably, the processor is further configured to: preset multiple time periods, each preset time period including at least two collection cycles; based on the hotspot areas determined by all collection cycles in each preset time period, statistically analyze the change relationship of the number of users in the hotspot areas over time; and extract the hotspot areas corresponding to the peak of the number of users and use them as the hotspot areas of the preset time period according to the change relationship.

[0137] In addition to using general hourly intervals, preset time periods can also be set according to rural-specific time periods, such as the pre-farming period (7-8 am), market period (9-11 am), midday rest period (12-2 pm), afternoon farming period (3-5 pm), and evening leisure period (7-9 pm). By identifying call and data traffic hotspots within each preset time period, and based on the analysis results, the differences in peak call / data traffic times for each hotspot area can be accurately extracted. For example, peak call times in markets are identified as 9-11 am, and peak data traffic times as 10-12 pm; peak call times in villages are 7-9 pm, and peak data traffic times are 8-10 pm. This information can directly guide operators in developing time-segmented marketing strategies.

[0138] In this embodiment, the condition that needs to be met during peak user numbers is that the number of users in the hotspot area is in the top 30% for at least two consecutive collection periods, which is suitable for the concentrated characteristics of rural time periods.

[0139] In some embodiments, the call and data traffic hotspot acquisition system of the present invention can be implemented in a combination of hardware and software. As an example, the call and data traffic hotspot acquisition system of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the call and data traffic hotspot acquisition method of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0140] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0141] Example 3 Embodiment 3 of the present invention relates to an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned method for obtaining call and data traffic hotspot areas. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the method for obtaining call and data traffic hotspot areas shown in Embodiment 1 of the present invention by calling the computer program.

[0142] In one alternative embodiment, an electronic device is provided, such as Figure 2 As shown, Figure 2 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0143] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0144] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 2 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0145] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0146] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0147] Among them, electronic devices can also be terminal devices, which can be any device that can install applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0148] It should be noted that, Figure 2 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0149] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for obtaining call and data hotspot areas.

[0150] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0151] In exemplary embodiment 4, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned method for obtaining call and data hotspot areas.

[0152] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0153] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0154] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EEPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0155] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0156] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0157] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0158] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0159] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for obtaining call and data traffic hotspot areas, characterized in that, include: Step 1: During the collection period, use base stations to acquire signaling data of user identifiers, call behavior and data traffic session behavior of users in the designated area, calculate the location corresponding to the call behavior and data traffic session behavior, and generate a behavior record table of users in the network based on the user identifiers, call behavior and data traffic session behavior and the corresponding signaling data. During the collection period, all base stations in the designated area collect radio frequency signals within their respective coverage areas, identify call behavior and traffic session behavior and obtain corresponding radio frequency signal characteristics, calculate the location of the corresponding call behavior and traffic session behavior based on the radio frequency signal characteristics, and generate a behavior record table of the users on different networks based on the call behavior and traffic session behavior and the corresponding radio frequency signal characteristics of the users on different networks. Step 2: Filter noise from the behavior log tables of users on this network and users on other networks; Step 3: Divide the specified area into grids. Based on the location of each behavior record in the behavior record tables of users in this network and users in other networks, embed the behavior record into the grid where the corresponding location falls, and output the behavior distribution matrix. Step 4: Use density clustering algorithm to perform cluster analysis on call behavior and traffic session behavior in the behavior distribution matrix, identify hotspot areas of call behavior and traffic session behavior within the collection period, and output a hotspot area distribution map.

2. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, It also includes step 5, which includes: presetting multiple time periods, each of which includes at least two collection cycles; Based on the hotspot areas determined by all collection cycles in each preset time period, the relationship between the number of users in each hotspot area and time is statistically analyzed. Based on this relationship, the hotspot area corresponding to the peak number of users is extracted and used as the hotspot area for that preset time period.

3. The method for obtaining call and data traffic hotspot areas according to claim 2, characterized in that, Step 4 also includes: calculating the proportion of users from the local network and users from other networks in the call behavior hotspot areas and traffic session behavior hotspot areas.

4. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, The designated areas are divided according to the scenario, which includes fields, villages, towns and markets; in the density clustering algorithm in step 4, the hotspot threshold in the field and village scenarios is lower than that in the town and market scenarios.

5. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, The designated areas are divided according to scenarios, including fields, villages, towns, and markets; in step 1, the data collection period of the base station in the fields and villages is longer than that in the towns and markets.

6. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, Step 4 outputs a hotspot distribution map with overlaid geographic identifiers.

7. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, In step 1, the signaling data for the call behavior and data traffic session behavior of users on this network include start time, AOA, and signal reception strength, respectively. If a user's communication behavior or traffic session behavior is simultaneously accessed by at least two base stations, the TDOA and AOA fusion technology is used to calculate and locate the user's communication behavior or traffic session behavior. If the communication behavior or traffic session behavior of a user on this network is connected to a single base station, the communication behavior or traffic session behavior of the user on this network is calculated and located using AOA and signal received strength fusion technology.

8. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, In step 1, the radio frequency signal characteristics of the call behavior and traffic session behavior of users on different networks include AOA and signal reception strength. The communication behavior or traffic session behavior of users on different networks is located by using AOA and signal reception strength fusion technology.

9. The method for obtaining call and data traffic hotspot areas according to claim 7 or 8, characterized in that, When using AOA and signal reception strength fusion technology to locate communication behavior or traffic session behavior, terrain correction parameters are introduced to correct the location results based on the terrain features of the specified area.

10. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, Signaling data for users' call behavior includes call start time and access base station identifier; signaling data for traffic session behavior includes traffic transmission start time and end time, data transmission rate, and access base station identifier. The step 2 of filtering noise in the call behavior record table of users of this network includes: determining whether the call duration and signal strength fluctuation value of the call behavior both fall within the preset threshold range; if not, it is determined to be noise and the call behavior is filtered out. The step 2 of filtering noise in the traffic session behavior of users on this network includes: determining whether the transmission rate, continuous transmission duration, and data packet interaction frequency of the traffic session behavior all fall within the preset threshold range; if not, it is determined to be noise and the traffic session behavior is filtered out.

11. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, The radio frequency (RF) signal characteristics of call behavior of users on different networks include signal duration, fluctuation range, and the time of RF signal appearance and disappearance; the RF signal characteristics of traffic session behavior include signal transmission duration, data packet exchange frequency, and the time of RF signal appearance and disappearance. The step 2 of filtering noise from call behavior in the behavior record table of users on other networks includes: determining whether the duration of the radio frequency signal, the signal strength fluctuation value, and the signal spectrum stability all fall within the preset threshold range; if not, it is determined to be noise and the call behavior is filtered out. The step 2 of filtering noise in the traffic session behavior of users on other networks includes: determining whether the continuous transmission duration of the radio frequency signal, the data packet interaction frequency, and the signal strength all fall within the preset threshold range; if not, it is determined to be noise and the traffic session behavior is filtered out.

12. The method for obtaining call and data traffic hotspot areas according to claim 11, characterized in that, The noise filtering in step 2 of the user behavior record table from other networks includes: Typical rural noise was sampled and modeled to establish a noise model; The collected behavioral records of users from other networks are input into the noise model. The matching degree between the behavioral record and the noise model is calculated. If the matching degree is greater than or equal to the preset matching degree threshold, the behavioral record is marked as a suspicious behavioral record. The designated area is divided into core area and non-core area according to the geographic information system. The regional attributes of the core area include villages, markets and roads; the regional attributes of the non-core area include field operation areas, mountains and forests and rivers. If the location corresponding to a suspicious behavior record falls into a non-core area, the suspicious behavior record is determined to be noise and filtered out. If the location corresponding to a suspicious behavior record falls within the core area, compare the radio frequency model characteristics in the suspicious behavior record with a preset threshold range. If the radio frequency model characteristics in the suspicious behavior record fall within the preset threshold range, the suspicious behavior record is retained; otherwise, the suspicious behavior record is filtered out.

13. The method for obtaining call and data traffic hotspot areas according to claim 11, characterized in that, Also includes: Typical rural noise was sampled and modeled to establish a noise model; In step 1, the collected behavior records of users from other networks are input into the noise model, and the matching degree between the behavior record and the noise model is calculated. If the matching degree is greater than or equal to the preset threshold, the preset threshold range is adjusted to improve the filtering effect in step 2.

14. The method for obtaining call and data traffic hotspot areas according to claim 11, characterized in that, If the duration of a user's behavior record from another network intersects with the preset peak hours for crowds, the maximum value of the preset threshold range corresponding to the signal strength will be reduced.

15. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, Step 2 further includes: performing secondary verification on the behavior records of the filtered users from other networks, including: Construct an effective signal model. Input each behavior record from the filtered behavior record table of users from other networks into the effective signal model and output a matching value. If the matching value is greater than or equal to the preset effective threshold, the behavior record is retained. If the matching value is less than the preset effective threshold, the behavior record is filtered.

16. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, Step 3, dividing the specified area into grids, includes: The designated areas are divided according to scenes, which include fields, villages, towns, and markets; When dividing a specified area into grids, the grid density of the areas corresponding to fields and villages is less than that of the areas corresponding to towns and markets.

17. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, The radio frequency signal features of traffic session behavior and call behavior of users from other networks collected in step 1 also include frequency bands and standards. The corresponding operators are analyzed based on frequency bands and standards in step 1. The behavior records in the behavior record table of users from other networks also include operators. Step 4 also counts the number of users from different operators in hotspot areas.

18. The method for obtaining call and data traffic hotspot areas according to claim 17, characterized in that, If the frequency bands of traffic session behavior and call behavior of users on different networks correspond to two different operators, analyze the signal frame structure of the corresponding radio frequency signals and determine the operators.

19. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, Step 3: After embedding the behavior records into the grid where the corresponding location falls, for users of this network, deduplicate the call behavior and data traffic behavior generated simultaneously by the same user of this network in the grid. For users on different networks, based on the call behavior and data traffic session behavior generated simultaneously within the network, the signal trajectory matching degree is used to determine whether the call behavior and data traffic session behavior generated simultaneously belong to the same user on different networks. If so, the call behavior and data traffic behavior generated simultaneously are deduplicated.

20. The method for obtaining call and data traffic hotspot areas according to claim 1, characterized in that, The user identifiers of users on this website are anonymous.

21. A system for obtaining call and data traffic hotspot areas, characterized in that, Includes at least one base station deployed in a designated area, the base station being connected to the processor; The base station is configured to acquire, within a collection period, signaling data of user identifiers, call behavior, and traffic session behavior of users in a designated area, in conjunction with the core network. It also collects radio frequency signals within the coverage area during the collection period, identifies call behavior and traffic session behavior, and obtains the corresponding radio frequency signal characteristics; The processor is configured to calculate the location corresponding to call behavior and traffic session behavior using the signaling data of the network user, and generate a behavior record table of the network user based on the user identifier, call behavior and traffic session behavior and the corresponding signaling data of the network user; The processor is also configured to calculate the location of the corresponding call behavior and data traffic session behavior using the radio frequency signal characteristics of the user on the other network, and generate a behavior record table of the user on the other network based on the call behavior and data traffic session behavior and the corresponding radio frequency signal characteristics. The processor is also configured to filter noise from the behavior record tables of users on the local network and users on other networks, divide the specified area into grids, embed the behavior record into the grid where the corresponding location falls according to the location of each behavior record in the behavior record tables of users on the local network and users on other networks, and output a behavior distribution matrix. The processor is also configured to use a density clustering algorithm to perform cluster analysis on call behavior and traffic session behavior in the behavior distribution matrix, identify hotspot areas of call behavior and traffic session behavior within the collection period, and output a hotspot area distribution map.

22. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The processor is further configured to: preset multiple time periods, each preset time period including at least two collection cycles; based on the hotspot areas determined by all collection cycles in each preset time period, statistically analyze the change relationship of the number of users in the hotspot areas over time; and extract the hotspot areas corresponding to the peak number of users and use them as the hotspot areas of the preset time period based on the change relationship.

23. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The processor is also configured to calculate the percentage of local and external network users in call behavior hotspots and traffic session behavior hotspots in the hotspot distribution map.

24. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The designated area is divided into scenarios, including fields, villages, towns, and markets. The hotspot threshold of the density clustering algorithm in the field and village scenarios is lower than that in the town and market scenarios.

25. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The designated area is divided into scenarios, and the base station collects data on scenarios in fields and villages for a longer period than it collects data on scenarios in towns and markets.

26. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The processor outputs a hotspot distribution map overlaid with geographic identifiers.

27. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The signaling data for users' call behavior and data usage session behavior on this network includes start time, AOA, and signal reception strength, respectively. The processor uses signaling data from users of this network to calculate the location corresponding to call behavior and data session behavior, including: If a user's communication behavior or traffic session behavior is simultaneously accessed by at least two base stations, the TDOA and AOA fusion technology is used to calculate and locate the user's communication behavior or traffic session behavior. If the communication behavior or traffic session behavior of a user on this network is connected to a single base station, the communication behavior or traffic session behavior of the user on this network is calculated and located using AOA and signal received strength fusion technology.

28. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The radio frequency signal characteristics of inter-network users' call behavior and data traffic session behavior include AOA and signal reception strength. The processor uses the radio frequency signal characteristics of inter-network users to calculate the localization corresponding to call behavior and data traffic session behavior, including: The communication behavior or traffic session behavior of users on different networks is located by using AOA and signal reception strength fusion technology.

29. The call and data traffic hotspot area acquisition system according to claim 27 or 28, characterized in that, When the processor uses AOA and signal reception strength fusion technology to locate communication behavior or traffic session behavior, it introduces terrain correction parameters to correct the location results based on the terrain features of the specified area.

30. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, Signaling data for users' call behavior includes call start time and access base station identifier; signaling data for traffic session behavior includes traffic transmission start time and end time, data transmission rate, and access base station identifier. The processor filters noise from call behavior in the behavior record table of users on this network by: determining whether the call duration and signal strength fluctuation value of the call behavior both fall within a preset threshold range; if not, it is determined to be noise and the call behavior is filtered out. The processor filters noise from traffic session behavior in the behavior record table of users on this network by: determining whether the transmission rate, continuous transmission duration, and data packet interaction frequency of the traffic session behavior all fall within a preset threshold range; if not, it is determined to be noise and the traffic session behavior is filtered out.

31. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The radio frequency (RF) signal characteristics of call behavior of users on different networks include signal duration, fluctuation range, and the time of RF signal appearance and disappearance; the RF signal characteristics of traffic session behavior include signal transmission duration, data packet exchange frequency, and the time of RF signal appearance and disappearance. The processor filters noise from call behavior records of users on other networks by: determining whether the duration of the radio frequency signal, the signal strength fluctuation value, and the signal spectrum stability fall within a preset threshold range; if not, it is determined to be noise and the call behavior is filtered out. The processor filters noise from traffic session behavior in the behavior log table of users on other networks by: determining whether the duration of continuous transmission of radio frequency signals, data packet interaction frequency, and signal strength all fall within a preset threshold range; if not, it is determined to be noise and the traffic session behavior is filtered out.

32. The system for obtaining dual hotspot areas of voice calls and data traffic for rural local and inter-network users based on communication base stations according to claim 31, characterized in that, The processor filters noise from the behavior logs of users on other networks, including: Typical rural noise was sampled and modeled to establish a noise model; Input the behavior records of users from other networks into the noise model, calculate the matching degree between the behavior record and the noise model, and if the matching degree is greater than or equal to the preset matching degree threshold, mark the behavior record as a suspicious behavior record. The designated area is divided into core area and non-core area according to the geographic information system. The regional attributes of the core area include villages, markets and roads; the regional attributes of the non-core area include field operation areas, mountains and forests and rivers. If the location corresponding to a suspicious behavior record falls into a non-core area, the suspicious behavior record is determined to be noise and filtered out. If the location corresponding to a suspicious behavior record falls within the core area, compare the radio frequency model characteristics in the suspicious behavior record with a preset threshold range. If the radio frequency model characteristics in the suspicious behavior record fall within the preset threshold range, the suspicious behavior record is retained; otherwise, the suspicious behavior record is filtered out.

33. The call and data traffic hotspot area acquisition system according to claim 31, characterized in that, The processor is also configured to: Typical rural noise was sampled and modeled to establish a noise model; The collected call and data session behavior records of users on different networks are input into the noise model. The matching degree between the behavior record and the noise model is calculated. If the matching degree is greater than or equal to the preset matching degree threshold, the preset filtering threshold is adjusted to improve the filtering effect.

34. The call and data traffic hotspot area acquisition system according to claim 31, characterized in that, The processor is also configured to: preset a period of high population density, identify the duration of the behavior records of users on other networks, determine whether it intersects with the preset period of high population density, and if so, reduce the maximum value of the preset threshold range corresponding to the signal strength.

35. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The processor is configured to filter noise from the behavior logs of users on other networks, and then perform a secondary verification on the filtered behavior logs of those users, including: Construct an effective signal model. Input each behavior record from the filtered behavior record table of users from other networks into the effective signal model and output a matching value. If the matching value is greater than or equal to the preset effective threshold, the behavior record is retained. If the matching value is less than the preset effective threshold, the behavior record is filtered.

36. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, When the processor divides a specified area into grids, it divides the specified area according to a scene, which includes fields, villages, towns and markets. The grid density in fields and villages is lower than that in towns and markets.

37. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The radio frequency signal features of traffic session behavior and call behavior of users on different networks collected by the base station also include frequency bands and standards. The processor is configured to parse the corresponding operators based on frequency bands and standards, and generate a behavior record table of users on different networks including operators. The processor is also configured to count the number of users of different operators in hotspot areas.

38. The call and data traffic hotspot area acquisition system according to claim 37, characterized in that, If the frequency bands of traffic session behavior and call behavior of users on different networks correspond to two different operators, the processor analyzes the signal frame structure of the corresponding radio frequency signals and determines the operator.

39. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, After the processor embeds the behavior record into the grid where the corresponding location falls, the processor is configured to: for users of this network, deduplicate call behavior and data traffic behavior generated simultaneously by the same user of this network in the grid; For users on different networks, based on the call behavior and data traffic session behavior generated simultaneously within the network, the signal trajectory matching degree is used to determine whether the call behavior and data traffic session behavior generated simultaneously belong to the same user on different networks. If so, the call behavior and data traffic behavior generated simultaneously are deduplicated.

40. The call and data traffic hotspot area acquisition system according to claim 21, characterized in that, The user identifiers of users on this website are anonymous.

41. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of claims 1-20.

42. A computer-readable storage medium, characterized in that, A computer-readable storage medium stores a computer program that, when executed by a processor, implements the method according to any one of claims 1-20.

Images