Proximity base station location association calibration method fusing user trajectory lbs data

Abstract

The present application relates to the technical field of base station coordinate calibration, and particularly relates to a near base station position association calibration method fusing user trajectory LBS data, which can specifically include obtaining user trajectory LBS data of a target base station and a near base station; based on the relative position relationship between the target base station and the near base station and the user trajectory LBS data, respectively determining an association degree index of the near base station relative to the target base station, geographical features of the near base station and the target base station, and a calibration contribution index of the near base station relative to the target base station, and then calculating to obtain a calibration weight of the near base station relative to the target base station, and calibrating the position information of the target base station according to the calibration weight. The technical scheme provided by the present application can obtain a near base station with higher calibration contribution to the target base station, avoid the deviation interference influence of complex terrain environments such as cities on the position calibration of the target base station, and improve the accuracy and stability of the position calibration of the target base station.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of base station coordinate calibration, and in particular to a method for calibrating the position of a nearby base station by fusing user trajectory LBS data. BACKGROUND

[0002] Location-Based Service (LBS) is a system and service that uses the geographic location information of a terminal to provide functions such as information push, navigation guidance, trajectory analysis, and location-related advertising. Common LBS technologies include cellular network base station positioning, wireless local area network positioning, satellite navigation positioning (such as GPS and Beidou), and multi-source fusion positioning. Among them, in a cellular network environment, using the spatial position information of base stations in the communication network for positioning is an important way, especially in indoor, large urban high-rise dense, or satellite signal blocked scenarios, base station positioning can often provide basic location information support.

[0003] In the base station positioning mode, a terminal measures signal parameters (such as received signal strength RSSI, timing advance TA, time difference of arrival TDOA, etc.) with several base stations, and combines the known spatial coordinates of the base stations to calculate the position of the terminal in the geographic space. The positioning accuracy of this method depends largely on the accuracy of the base station coordinates and the update degree of the network topology. However, in actual operation and maintenance, the base station coordinate data stored in the operator database may have various error sources, including coordinate offset, labeling error, and position information change not updated in time, and the position information of the base station needs to be calibrated in a timely and accurate manner. The existing base station position calibration method mainly relies on the network detection data of the operator or the field survey means, although the accuracy is high, but the cost is large, the coverage is limited, and it is difficult to update in real time. Therefore, how to efficiently, accurately and timely calibrate the position information of the target base station has become a practical application problem to be solved. SUMMARY

[0004] In order to solve the technical problems proposed in the background art, the purpose of the present disclosure is to provide a method for calibrating the position of a nearby base station by fusing user trajectory LBS data, and the technical solution adopted is as follows:

[0005] The first aspect of the present disclosure provides a method for calibrating the position of a nearby base station by fusing user trajectory LBS data, which can specifically include:

[0006] Based on the position information of the target base station, determine the nearby base station associated with the target base station;

[0007] Obtain user trajectory LBS data of the target base station and the nearby base station;

[0008] determine the correlation degree index of the neighboring base station relative to the target base station based on the relative position relationship between the target base station and the neighboring base station and the user trajectory LBS data associated with both the target base station and the neighboring base station;

[0009] determine the geographical features of the neighboring base station and the target base station based on the user trajectory LBS data, and determine the calibration contribution index of the neighboring base station relative to the target base station according to the geographical features;

[0010] determine the calibration weight of the neighboring base station relative to the target base station based on the correlation degree index and the calibration contribution index;

[0011] calibrate the location information of the target base station based on the calibration weight and the accurate location information of the neighboring base station.

[0012] In a possible implementation of the first aspect, in the process of determining the neighboring base station associated with the target base station based on the location information of the target base station, the following steps are included:

[0013] continuously acquire, based on the location information of the target base station, access base stations with a distance less than or equal to a preset threshold from the target base station as preliminary neighboring base stations;

[0014] in a case where the location information of the preliminary neighboring base station is an accurate position coordinate, the preliminary neighboring base station is taken as the neighboring base station.

[0015] In a possible implementation of the first aspect, the user trajectory LBS data includes at least one or a combination of any multiple of user identity data, user behavior data, user movement process space-time record data, and user access base station data.

[0016] In a possible implementation of the first aspect, in the process of determining the correlation degree index of the neighboring base station relative to the target base station, the following steps are included:

[0017] based on the user trajectory LBS data associated with both the target base station and the neighboring base station, acquire the movement time of a single user moving from the neighboring base station to the target base station within a preset period of time, and acquire the occurrence number of a single user directly moving from the neighboring base station to the target base station or directly moving from the target base station to the neighboring base station within the preset period of time;

[0018] determine the movement proximity index corresponding to the single user based on the relative distance between the target base station and the neighboring base station and the movement time;

[0019] determine the correlation degree index based on the product of the average value of the movement proximity index of all users within the preset period of time and the occurrence number.

[0020] In a possible implementation of the first aspect, in the process of determining the geographical features of the target base station and the neighboring base station based on the user trajectory LBS data, the following steps are included:

[0021] Based on the user trajectory LBS data, the user activity of the target base station and the neighboring base station in a preset time period is obtained.

[0022] Based on the user activity and the mean of the user activity of all users, the geographical prosperity index of the target base station and the neighboring base station is determined, wherein the geographical features include the geographical prosperity index.

[0023] In a possible implementation of the first aspect, in the process of obtaining the user activity of the target base station and the neighboring base station in a preset time period, the following steps are included:

[0024] Based on the user trajectory LBS data, the user quantity distribution of the target base station and the neighboring base station in a preset time period is obtained.

[0025] Based on the base station data of the target base station and the neighboring base station, the base station coverage area of the target base station and the neighboring base station and the base station load rate distribution of the target base station and the neighboring base station in a preset time period are obtained.

[0026] Based on the base station coverage area, the user quantity distribution in a preset time period and the base station load rate distribution in a preset time period, the user activity in a preset time period is determined.

[0027] In a possible implementation of the first aspect, in the process of determining the geographical features of the target base station and the neighboring base station based on the user trajectory LBS data, the following steps are included:

[0028] Based on the difference between the geographical prosperity index of the target base station and the geographical prosperity index of the neighboring base station, the user distribution similarity index of the neighboring base station relative to the target base station is determined, wherein the geographical features include the user distribution similarity index.

[0029] In a possible implementation of the first aspect, in the process of determining the geographical features of the target base station and the neighboring base station based on the user trajectory LBS data, the following steps are included:

[0030] Based on the user trajectory LBS data, the first user quantity of the neighboring base station in a preset time period and the second user quantity of the neighboring base station moving to the target base station or moving from the target base station to the neighboring base station in a preset time period are obtained.

[0031] Based on the first user quantity, the second user quantity and the user distribution similarity index, the user behavior similarity index of the neighboring base station relative to the target base station is determined, wherein the geographical features include the user behavior similarity index.

[0032] In a possible implementation of the first aspect, in the process of determining the calibration contribution indicator of the neighboring base station relative to the target base station according to the geographical feature, the following step is included:

[0033] The calibration contribution indicator of the neighboring base station relative to the target base station is determined based on the product of the user behavior similarity indicator, the user distribution similarity indicator, and the geographical prosperity indicator.

[0034] In a possible implementation of the first aspect, in the process of calibrating the location information of the target base station based on the calibration weight and the accurate location information of the neighboring base station, the following step is included:

[0035] The initial calibration location information of the target base station is obtained by weighted averaging according to the calibration weight based on the accurate location information of the neighboring base station and the movement of the user between the neighboring base station and the target base station;

[0036] The initial calibration location information is corrected based on the historical calibration data set to obtain the accurate calibration location information of the target base station.

[0037] Compared with the background art, the present disclosure has the following beneficial effects:

[0038] The technical solution provided by the present disclosure introduces user trajectory LBS data in the process of calibrating the location of the target base station, can analyze the geographical prosperity of the coverage area of each neighboring base station of the target base station based on the user trajectory LBS data, identify the area with rich user activity and trajectory data, and select the neighboring base station with higher contribution to the location estimation of the target base station according to the set correlation degree indicator and calibration contribution indicator of the neighboring base station relative to the target base station, so that the location calibration process of the target base station is no longer dependent on the fixed neighbor relation, but the different calibration weights of each neighboring base station are dynamically determined according to the real movement behavior of the user, realizing data-driven adaptive optimization, avoiding the deviation and interference of complex terrain environment such as city on the location calibration of the target base station, reducing the noise interference caused by the participation of redundant or invalid neighboring base stations in the calculation, realizing the location calibration of the neighboring base station based on the fusion of user trajectory LBS data, improving the accuracy and stability of the location calibration of the target base station, and having promotional value. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0040] Figure 1 For the embodiment according to the present disclosure, a flowchart of a method for calibrating the location of a nearby base station in association with a target base station is provided.

[0041] Figure 2 For the embodiment according to the present disclosure, a flowchart of a method for determining the nearby base station associated with the target base station based on the location information of the target base station is provided.

[0042] Figure 3 For the embodiment according to the present disclosure, a flowchart of a method for determining the degree of association of the nearby base station relative to the target base station is provided.

[0043] Figure 4 For the embodiment according to the present disclosure, a flowchart of a method for determining the geographical features of the nearby base station and the target base station based on the user trajectory LBS data is provided.

[0044] Figure 5 For the embodiment according to the present disclosure, a flowchart of a method for obtaining the user activity of the nearby base station and the target base station within a preset time period is provided.

[0045] Figure 6 For the embodiment according to the present disclosure, a flowchart of a method for calibrating the location information of the target base station based on the calibration weight and the accurate location information of the nearby base station is provided. DETAILED DESCRIPTION

[0046] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined object, the specific embodiments, structures, features and effects of a method for calibrating the location of a nearby base station in association with a target base station by fusing user trajectory LBS data according to the present application are described in detail below. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0048] To solve the problems raised in the background art, the present disclosure provides a method for calibrating the location of a nearby base station in association with a target base station by fusing user trajectory LBS data, which can calibrate the location of a nearby base station by fusing user trajectory LBS data and improve the accuracy and stability of the calibration of the location of a target base station. Specifically, in some embodiments of the present disclosure, Figure 1 a flowchart of a method for calibrating the location of a nearby base station in association with a target base station by fusing user trajectory LBS data is shown, as Figure 1As shown, the method can specifically include the following steps:

[0049] Step 100: Based on the location information of the target base station, determine the neighboring base stations associated with the target base station. In some embodiments, in the process of acquiring the target base station and the neighboring base stations, the base station data of the target base station and the neighboring base stations can also be acquired synchronously, wherein the base station data can specifically include the base station code, the load rate, the coverage, the number of access users, and other related information, which are not limited herein. The specific acquisition of the neighboring base stations will be described in detail later, which is not repeated here.

[0050] Step 200: Acquire the user trajectory LBS data of the target base station and the neighboring base stations. In some embodiments, the user trajectory LBS data can specifically include at least one or any combination of a plurality of the user identity data, the user behavior data, the user movement process space-time record data, and the user access base station data. In some embodiments, the user trajectory LBS data can come from two levels of LBS public service providers (mobile communication and Internet location services) and government departments. In some embodiments, the IMSI information, the IMEI information, the user network ID, the GPS longitude and latitude information, the base station information (LAC, CID), the Wi-Fi information, the motion state information, and other related data of the mobile terminal can be parsed from the LBS data stream, which can specifically include the space-time data (the longitude and latitude coordinates of the user on the earth, the residence time of the user at a specific location, or the time difference between two position updates, etc.), the base station data (the unique identifier Cell ID of the access mobile network base station, the received signal strength indication (RSSI), the time advance (TA), etc.), the user data (the user identity data, the user behavior data, etc.), which are not limited herein.

[0051] Step 300: determining the correlation degree index of the neighboring base station relative to the target base station based on the relative position relationship between the target base station and the neighboring base station, and the user trajectory LBS data associated with the target base station and the neighboring base station at the same time. It can be understood that the sequence of base stations connected by the user in the moving process can truly reflect the spatial proximity relationship between different base stations. The traditional base station neighborhood relationship is often established based on theoretical planning or signal strength model, but in complex urban environment, due to building shielding, electromagnetic interference, terrain undulation and other factors, the actual coverage range of the base station may deviate from the planned area, and it is difficult to accurately describe its spatial relationship by relying on static geographic coordinates only; while the user trajectory LBS data contains a large number of real connection records of users at different times and in different scenes. These trajectories can reflect the frequency and time continuity of the base stations being accessed together. By analyzing the trajectory transfer law of the user in the target base station and its surrounding area, the correlation degree index between each neighboring base station and the target base station can be obtained, providing a more reliable spatial correlation basis for the position calibration of the target base station. The specific acquisition of the correlation degree index will be described in detail in the following, which will not be repeated here.

[0052] Step 400: determining the geographic features of the neighboring base station and the target base station based on the user trajectory LBS data, and determining the calibration contribution index of the neighboring base station relative to the target base station according to the geographic features. In some embodiments, the above steps 300 and 400 can be executed synchronously or asynchronously, and the execution order of steps 300 and 400 is not limited when steps 300 and 400 are executed asynchronously. It can be understood that the geographic features of the area where the base station is located will directly affect the distribution density and representativeness of the user trajectory data: for example, in urban or commercial prosperous areas, the user activity is frequent, the LBS data is dense, and the trajectory sample is more abundant, which can provide higher reference value in the calibration process; by analyzing the spatio-temporal distribution characteristics of the user trajectory in the coverage range of each base station, the geographic prosperity of the base station can be analyzed, and then the geographic features of the neighboring base station and the target base station are compared, which can effectively identify the most similar and representative neighborhood base station to the target base station in terms of spatial structure and user behavior mode, and assign different calibration contribution indexes to these neighboring base stations, so that the position calibration process is more in line with the real geographic environment and population distribution characteristics, thereby improving the accuracy of calibration. The specific acquisition of the geographic features and the calibration contribution index will be described in detail in the following, which will not be repeated here.

[0053] Step 500: determining the calibration weight of the neighboring base station relative to the target base station based on the correlation degree index and the calibration contribution index. It can be understood that different neighboring base stations and target base stations differ in spatial distance, signal coverage overlap, user trajectory intersection frequency, and geographical prosperity, etc. The reference value in the process of target base station position calibration is also different. If all neighboring base stations are given the same weight in calibration, it is easy to cause interference to the result of the far distance or sparse data base station, thereby reducing the calibration accuracy. In order to reasonably allocate the influence degree of different neighboring base stations on the position correction of the target base station in the position calibration process, the correlation degree index and the calibration contribution index obtained in the foregoing steps can be used to make the neighboring base station with closer position correlation, higher similarity and greater calibration contribution occupy a greater proportion in the position calibration, so as to weaken the influence of noise data and improve the accuracy of the target base station position calibration. The specific acquisition process of the calibration weight will be described in detail in the following, and will not be repeated here.

[0054] Step 600: calibrating the position information of the target base station based on the calibration weight and the accurate position information of the neighboring base station. In some embodiments, the specific implementation of calibrating the position information of the target base station will be described in detail in the following, and will not be repeated here. It can be understood that based on the above steps 100 to 600, the correlation degree index of the neighboring base station and the target base station can be determined based on the geographical feature information of the neighboring base station and the target base station, the calibration contribution index of the neighboring base station relative to the target base station can be calculated, the neighboring base station with higher calibration contribution to the target base station can be obtained, the deviation interference of the complex terrain environment such as city on the target base station position calibration can be avoided, the position calibration of the neighboring base station of the fusion user trajectory LBS data can be realized, and the accuracy and stability of the target base station position calibration are improved. The specific implementation of the above steps 100 to 600 will be further described in combination with specific embodiments.

[0055] In some embodiments, Figure 2 A flowchart for determining the neighboring base station associated with the target base station based on the position information of the target base station is shown, as shown in Figure 2 The specific implementation of the above steps 100 to 600 will be further described in combination with specific embodiments.

[0056] Step 210: Based on the location information of the target base station, continuously acquire the access base station within the preset threshold distance from the target base station as the preliminary adjacent base station. In some embodiments, the location information of the target base station refers to the current known location information of the target base station, and does not represent the real location information of the target base station in the actual environment. It can be understood that in complex environmental scenarios such as urban high-rise dense areas or underground spaces, in order to meet the stable communication quality of users in the region, there are various base station setting forms such as fixed base stations and mobile base stations, among which the mobile base station can be freely increased or reduced according to the actual needs of users in the region, that is, the number of access base stations within the preset threshold range of the target base station can be dynamically changed, which is not limited here.

[0057] Step 220: In the case that the location information of the preliminary adjacent base station is the known accurate position coordinate, the preliminary adjacent base station is taken as the adjacent base station. In some embodiments, the location information of part of the preliminary adjacent base station can be obtained at the time of setting the corresponding accurate position coordinate, and the accurate position coordinate of part of the preliminary adjacent base station can be obtained based on the position calibration update in the use process, which is not limited here. It can be understood that in the process of position calibration of the target base station, the required adjacent base station has known and accurate position coordinate information, only the preliminary adjacent base station with known and accurate position coordinate can be used as the adjacent base station in the embodiments of the present disclosure.

[0058] In some embodiments, Figure 3 A flowchart for determining the correlation degree index of the adjacent base station relative to the target base station is shown, as shown in Figure 3 The specific steps can include the following steps:

[0059] Step 310: Based on the user trajectory LBS data associated with the target base station and the adjacent base station at the same time, the moving time of a single user moving from the adjacent base station to the target base station within a preset period is acquired. In some embodiments, the preset period can be 12 hours, 24 hours, 48 hours, etc. By acquiring user trajectory LBS data in a longer period of time, the use characteristics of users in the coverage range of the adjacent base station and the target base station can be reflected, which is not limited here. In some embodiments, the moving time can be the time of any user moving from the selected adjacent base station to the target base station, that is, the interval time between the starting time points of entering the adjacent base station and the target base station, which can reflect the spatio-temporal correlation degree between the adjacent base station and the target base station, which is not limited here.

[0060] Step 320: Obtain the number of times a single user moves directly from a nearby base station to a target base station or from a target base station to a nearby base station within a preset time period. In some embodiments, steps 310 and 320 can be executed synchronously or asynchronously. When steps 310 and 320 are executed asynchronously, the order of execution of steps 310 and 320 is not limited. In some embodiments, the number of times a single user moves directly from a nearby base station to a target base station or from a target base station to a nearby base station can be determined according to the order in which the user accesses the base stations, i.e., from a nearby base station to the target base station or from the target base station to a nearby base station. This can reflect the movement trajectory pattern of the user between the nearby base station and the target base station to a certain extent. The more times this occurs, the closer the user correlation between the nearby base station and the target base station is, which is not limited here.

[0061] Step 330: Based on the relative distance and travel time between the target base station and neighboring base stations, determine the mobile proximity index for a single user. In some embodiments, the mobile proximity index for a single user can be obtained based on the following mathematical expression:

[0062] ;

[0063] in, For the first Among the nearest base stations, the first Mobile proximity metrics for each user For the first The relative distance between a nearby base station and the target base station For the first Among the nearest base stations, the first Mobile time for each user For the natural constant The equation is an exponential function with base 0. Based on the above mathematical expression, it can be understood that the smaller the relative distance between the theoretical locations of the nearby base station and the target base station, and the shorter the user's movement time between the nearby and target base stations, the closer their actual coverage areas are, and the larger the mobility proximity index becomes. In other words, the mobility proximity index is inversely correlated with both the relative distance between the target and nearby base stations and the movement time. It should be noted that the relative distance and movement time used in the calculations in this embodiment are normalized values ​​to avoid the influence of dimensions. The normalization method uses a minimum-maximum normalization function, and the normalization method can be adjusted according to the specific implementation environment, which will not be further elaborated here.

[0064] Step 340: Determine the correlation index based on the product of the mean and the frequency of occurrence of the mobile proximity index for all users within a preset time period. In some embodiments, the correlation index can be obtained based on the following mathematical expression:

[0065] ;

[0066] wherein, is an association degree indicator of the th adjacent base station relative to the target base station, is the number of all users in a preset period, is a moving proximity indicator of the th user in the th adjacent base station, is the number of times that a single user directly moves from the th adjacent base station to the target base station or directly moves from the target base station to the th adjacent base station in a preset period. Based on the above mathematical expression, it can be understood that in the case of inaccurate positioning of the target base station, the association degree between the adjacent base station and the target base station can be determined by the moving behavior of the user between the adjacent base station and the target base station in the user trajectory LBS data: if most users successively pass through the adjacent base station and the target base station in a preset period, and the communication access switching speed between the adjacent base station and the target base station is fast, i.e. the moving proximity indicator is large, then the association degree indicator between the adjacent base station and the target base station is also larger.

[0067] In some embodiments, Figure 4 a flowchart for determining the geographical features of the adjacent base station and the target base station based on the user trajectory LBS data is shown, as shown in Figure 4 , which can specifically include the following steps:

[0068] Step 410: Based on the user trajectory LBS data, the user activity of the adjacent base station and the target base station in a preset period is obtained. It can be understood that in order to be able to select the adjacent base station which has more reference significance for the position calibration of the target base station from multiple adjacent base stations, the adjacent base station with stronger association can be judged from the perspective of user activity: the more the number of users in the coverage range of a base station, and the more time in the busy state, the higher the user activity of the base station. In some embodiments, further, Figure 5 a flowchart for obtaining the user activity of the adjacent base station and the target base station in a preset period is shown, as shown in Figure 5 , which can specifically include the following steps:

[0069] Step 510: Based on the user trajectory LBS data, the user number distribution of the adjacent base station and the target base station in a preset period is obtained. In some embodiments, the user number distribution can specifically include the number of users accessing the adjacent base station and the target base station at a certain time in a preset period, which is not limited herein.

[0070] Step 520: Based on the base station data of neighboring base stations and the target base station, obtain the base station coverage area of ​​the neighboring base stations and the base station load rate distribution within a preset time period. In some embodiments, the base station coverage area of ​​the neighboring base stations and the base station load rate distribution within a preset time period can be obtained through statistical analysis of the base station data of the target base station and neighboring base stations. Those skilled in the art can choose appropriate methods for obtaining the above data according to actual needs, and no limitation is made here.

[0071] Step 530: Determine the user activity level within the preset time period based on the base station coverage area, the user number distribution within the preset time period, and the base station load rate distribution within the preset time period. In some embodiments, user activity level can be obtained based on the following mathematical expression:

[0072] ;

[0073] in, For the first User activity at each base station This refers to the number of monitoring times corresponding to the base station monitoring data within a preset time period. For the first The first base station within the preset time period Number of users at each monitoring time For the first The coverage area of ​​each base station For the first The first base station within the preset time period The base station load rate at each monitoring time. It should be noted that the base station coverage area is usually not 0. If the base station coverage area is 0, it indicates that the corresponding base station has experienced operational abnormalities such as damage or paralysis, which is not within the scope of analysis of this embodiment of the invention and will not be further elaborated here.

[0074] Step 420: Based on the user activity level and the average activity level of all users, determine the geographic prosperity index of neighboring base stations and the target base station, wherein geographic features include the geographic prosperity index. In some embodiments, when the user activity level corresponding to a base station is determined, the geographic prosperity index of the current base station can be evaluated by comparing the user activity levels of each base station. In some embodiments, the geographic prosperity index can be obtained based on the following mathematical expression:

[0075] ;

[0076] in, For the first Geographical prosperity indicators for each base station. For the first User activity at each base station This represents the average user activity level across all base stations. Based on the above mathematical expression, it can be understood that when the user activity level of a base station is higher than the average, it indicates dense user activity and abundant trajectory data, thus resulting in a higher geographical activity index. Here, "all base stations" includes the target base station and all neighboring base stations. It should be noted that the average user activity level of all base stations is usually not 0. If the average user activity level of all base stations is 0, it indicates that all base stations are experiencing operational abnormalities such as damage or paralysis, which is outside the scope of analysis in this embodiment and will not be further elaborated upon here.

[0077] In some embodiments, further, in such Figure 4 The process of determining the geographical features of neighboring base stations and the target base station based on user trajectory LBS data may further include the following step 430: determining the user distribution similarity index of the neighboring base station relative to the target base station based on the difference between the geographical prosperity index of the target base station and the geographical prosperity index of the neighboring base station, wherein the geographical features include the user distribution similarity index. In some embodiments, the user distribution similarity index can be obtained based on the following mathematical expression:

[0078] ;

[0079] in, For the first Similarity index of user distribution between neighboring base stations and the target base station For the first Geographical prosperity indicators of a nearby base station. This refers to the geographical prosperity indicators of the target base station. For the natural constant It is an exponential function with base 0. Based on the above mathematical expression, it can be understood that the closer the relationship between a neighboring base station and the target base station, the more similar the distribution of users in these two base stations should be. Therefore, the closer the geographical prosperity indicators of neighboring and target base stations are, the higher the similarity index of user distribution between the two base stations.

[0080] In some embodiments, further, in such Figure 4 The process of determining the geographical features of nearby base stations and target base stations based on user trajectory LBS data may also include the following steps:

[0081] Step 440: Based on the user trajectory LBS data, the first user quantity of the adjacent base station in the preset period is obtained, and the second user quantity moving from the adjacent base station to the target base station or moving from the target base station to the adjacent base station in the preset period is obtained. In some specific examples, if the users of the target base station mostly flow to the first adjacent base station and a small part flow to the second adjacent base station, even if the distance between the target base station and the first adjacent base station is far away before calibration, but because the user behavior of the first adjacent base station is more similar to the user behavior of the target base station, the actual target base station position is closer to the first adjacent base station, so the user flow direction of the target base station can be characterized by the first user quantity and the second user quantity, which is not limited here.

[0082] Step 450: Based on the first user quantity, the second user quantity, and the user distribution similarity index, the user behavior similarity index of the adjacent base station relative to the target base station is determined, and the geographical feature includes the user behavior similarity index. In some embodiments, the user behavior similarity index can be obtained based on the following mathematical expression:

[0083] ;

[0084] Wherein, is the user behavior similarity index of the i-th adjacent base station relative to the target base station, is the user distribution similarity index of the i-th adjacent base station relative to the target base station, is the first user quantity of the i-th adjacent base station in the preset period, is the second user quantity moving from the adjacent base station to the target base station or moving from the target base station to the adjacent base station in the preset period, is the natural constant e, is the exponential function with base e. Based on the above mathematical expression, it can be understood that when the user trajectory flows between the adjacent base station and the target base station, and the user distribution similarity index between the two base stations is synchronized, then the user behavior similarity index of the adjacent base station and the target base station is also higher. In order to avoid the case that the denominator is 0, when e is 0, the present embodiment replaces the corresponding denominator participating in the calculation with 0.5, which can be adjusted by itself, and will not be described further here. In some embodiments, based on the specific index content of each geographical feature obtained in the foregoing steps 410 to 450, the calibration contribution index of the adjacent base station relative to the target base station can be determined based on the product of the user behavior similarity index, the user distribution similarity index, and the geographical prosperity index. In some embodiments, the calibration contribution index can be obtained based on the following mathematical expression:

[0085] In some embodiments, based on the specific index content of each geographical feature obtained in the foregoing steps 410 to 450, the calibration contribution index of the adjacent base station relative to the target base station can be determined based on the product of the user behavior similarity index, the user distribution similarity index, and the geographical prosperity index. In some embodiments, the calibration contribution index can be obtained based on the following mathematical expression: ​​​

[0086] ;

[0087] in, For the first The calibration contribution index of each neighboring base station relative to the target base station. For the first Similarity index of user distribution between neighboring base stations and the target base station For the first Similarity index of user behavior between neighboring base stations and the target base station. For the first The geographical prosperity index of neighboring base stations. Based on the above mathematical expression, it can be understood that in geographically prosperous scenarios with higher population flow density, the density of communication base station deployment is relatively higher. When the geographical prosperity index of neighboring base stations is large, and the user distribution similarity index of neighboring base stations relative to the target base station is high, it indicates that the user density of neighboring base stations and the target base station is similar, both located in relatively prosperous geographical scenarios. The stronger the reference value of the neighboring base station for the location calibration of the target base station, the stronger the reference value of the neighboring base station for the location calibration of the target base station. At the same time, the higher user behavior similarity index of neighboring base stations relative to the target base station, it indicates that the user behavior patterns within the coverage area of ​​the neighboring base station are more similar to the user behavior patterns within the target base station. The stronger the reference value of the neighboring base station for the location calibration of the target base station, the stronger the reference value of the neighboring base station for the location calibration of the target base station. That is, the calibration contribution index of neighboring base stations relative to the target base station is positively correlated with the user behavior similarity index, the user distribution similarity index, and the geographical prosperity index.

[0088] In some embodiments, when the calibration contribution index and the correlation index are obtained separately, the calibration weight of the neighboring base station relative to the target base station can be obtained based on the following mathematical expression:

[0089] ;

[0090] in, For the first The calibration weights of each neighboring base station relative to the target base station. For the first The calibration contribution index of each neighboring base station relative to the target base station. For the first The correlation index between a neighboring base station and the target base station. Based on the above mathematical expression, it can be understood that if the correlation index between a neighboring base station and the target base station is high, and the calibration contribution index relative to the target base station is also in a high range, it indicates that the calibration weight of the neighboring base station relative to the target base station is large. That is, the calibration weight of the neighboring base station relative to the target base station is positively correlated with both the calibration contribution index and the correlation index.

[0091] In some embodiments, Figure 6A flowchart of a process for calibrating the location information of a target base station based on calibration weights and accurate location information of neighboring base stations is shown, as shown in Figure 6 which can specifically include the following steps:

[0092] Step 610: Based on the accurate location information of the neighboring base stations and the movement of the user between the neighboring base stations and the target base station, the initial calibration location information of the target base station is obtained by weighted average according to the calibration weights. In some embodiments, specifically, in the case of obtaining the calibration contribution weights of the neighboring base stations relative to the target base station, the target base station can be calibrated by the neighboring base stations with higher calibration contribution weights, or the target base station can be calibrated by weighted average of all neighboring base stations with accurate location information, which is not limited herein. In some embodiments, specifically, the communication distance between base stations can be estimated based on the actual movement time of the user between the neighboring base stations and the target base station and the base station communication parameters such as timing advance (TA), and the location coordinates of the target base station are corrected by using the weighted average algorithm to integrate the accurate location information of multiple neighboring base stations to obtain the initial calibration location information. Compared with the prior art, the introduction of the calibration contribution index in the above step 610 makes the obtained initial calibration location information avoid the influence of the deviation of the complex terrain environment such as city on the calibration of the target base station, and the obtained initial calibration location information can better reflect the real location information of the target base station, and has better calibration accuracy.

[0093] Step 620: The initial calibration location information is corrected based on the historical calibration data set to obtain the accurate calibration location information of the target base station. In some embodiments, further, after obtaining the initial calibration location information of the target base station, the error can be further corrected by introducing the historical calibration data set to improve the accuracy and stability of the calibration of the target base station, wherein the historical calibration data set can include the real base station coordinates and their calibration residual information verified in different times and different regions. By comparing the differences between the initial calibration results and these historical samples, a target function reflecting the system error and environmental deviation can be constructed, and then the least square method or other algorithms are used to iteratively optimize the above target function, the calibration location information of the target base station is adjusted continuously, so that the error square sum between the calculated calibration location and the historical data is minimized, thereby gradually approaching the optimal solution to obtain the accurate calibration location information of the target base station; the skilled in the art can also obtain the above accurate calibration location information by using other suitable algorithms, models or machine learning methods according to actual needs, which is not limited herein.

[0094] In summary, the technical scheme provided by the present disclosure introduces user trajectory LBS data in the process of position calibration of the target base station, can analyze the geographical prosperity degree of the coverage area of each adjacent base station of the target base station based on the user trajectory LBS data, identify the area where the user activity is dense and the trajectory data is rich, and select the adjacent base station with higher contribution to the position estimation of the target base station according to the set correlation degree index and the calibration contribution index of the adjacent base station relative to the target base station, so that the position calibration process of the target base station is no longer dependent on the fixed adjacent area relationship, but dynamically determines the calibration weights of each adjacent base station according to the real mobile behavior of the user, realizes the data-driven adaptive optimization, avoids the deviation interference of complex terrain environment such as city on the position calibration of the target base station, reduces the noise interference caused by the participation of redundant or invalid adjacent base stations in the calculation, realizes the position calibration of the adjacent base station based on the fusion of user trajectory LBS data, improves the accuracy and stability of the position calibration of the target base station, and has a popularization value.

[0095] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0096] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A method for calibrating the location association of proximate base stations by fusing user trajectory LBS data, characterized in that, The method comprises the following steps: determining a nearby base station associated with the target base station based on the location information of the target base station; obtaining user trajectory LBS data of the target base station and the nearby base station; determining an association degree index of the nearby base station relative to the target base station based on the relative position relationship between the target base station and the nearby base station and the user trajectory LBS data associated with both the target base station and the nearby base station; determining geographical features of the target base station and the nearby base station based on the user trajectory LBS data and determining a calibration contribution index of the nearby base station relative to the target base station according to the geographical features; determining a calibration weight of the nearby base station relative to the target base station based on the association degree index and the calibration contribution index; calibrating the location information of the target base station based on the calibration weight and the accurate location information of the nearby base station; In the process of determining the association degree index of the nearby base station relative to the target base station, the following steps are included: obtaining the moving time of a single user from the nearby base station to the target base station within a preset period based on the user trajectory LBS data associated with both the target base station and the nearby base station; and obtaining the number of times that a single user directly moves from the nearby base station to the target base station or directly moves from the target base station to the nearby base station within the preset period based on the user trajectory LBS data associated with both the target base station and the nearby base station; determining a moving proximity index corresponding to a single user based on the relative distance between the target base station and the nearby base station and the moving time; determining the association degree index based on the product of the average of the moving proximity indexes of all users within the preset period and the number of times; In the process of determining the geographical features of the target base station and the nearby base station based on the user trajectory LBS data, the following steps are included: obtaining user activity of the target base station and the nearby base station within a preset period based on the user trajectory LBS data; determining a geographical prosperity index of the target base station and the nearby base station based on the user activity and the average of all the user activities, wherein the geographical features include the geographical prosperity index; In the process of determining the geographical features of the target base station and the nearby base station based on the user trajectory LBS data, the following steps are included: determining a user distribution similarity index of the nearby base station relative to the target base station based on the difference between the geographical prosperity index of the target base station and the geographical prosperity index of the nearby base station, wherein the geographical features include the user distribution similarity index; In the process of determining the geographical features of the target base station and the nearby base station based on the user trajectory LBS data, the following steps are included: obtaining a first number of users of the nearby base station within a preset period and a second number of users moving from the nearby base station to the target base station or moving from the target base station to the nearby base station within the preset period based on the user trajectory LBS data; determining a user behavior similarity index of the neighboring base station relative to the target base station based on the first user number, the second user number, and the user distribution similarity index, wherein the geographic feature comprises the user behavior similarity index; in a process of determining a calibration contribution index of the neighboring base station relative to the target base station according to the geographic feature, comprising the following steps: determining the calibration contribution index of the neighboring base station relative to the target base station based on a product of the user behavior similarity index, the user distribution similarity index, and the geographic prosperity index; in a process of calibrating the location information of the target base station based on the calibration weight and the accurate location information of the neighboring base station, comprising the following steps: obtaining initial calibration location information of the target base station by weighted average according to the calibration weight based on the accurate location information of the neighboring base station and the movement of users between the neighboring base station and the target base station; correcting the initial calibration location information based on a historical calibration data set to obtain accurate calibration location information of the target base station.

2. The method of claim 1, wherein the method of calibrating the location association of the adjacent base stations by fusing the user trajectory LBS data comprises: in a process of determining the neighboring base station associated with the target base station based on the location information of the target base station, comprising the following steps: continuously obtaining access base stations with a distance less than or equal to a preset threshold from the target base station as preliminary neighboring base stations based on the location information of the target base station; in a case where the location information of the preliminary neighboring base station is a known accurate position coordinate, taking the preliminary neighboring base station as the neighboring base station. 3.The method of claim 1, wherein, The user trajectory LBS data comprises at least one or any combination of user identity data, user behavior data, user movement process space-time record data, and user access base station data.

4. The method of claim 1, wherein the method of calibrating the location association of the neighboring base stations fused with the user trajectory LBS data comprises: in a process of obtaining user activity of the neighboring base station and the target base station within a preset time period, comprising the following steps: obtaining user number distribution of the neighboring base station and the target base station within the preset time period based on the user trajectory LBS data; obtaining base station coverage area of the neighboring base station and the target base station and base station load rate distribution within the preset time period based on base station data of the neighboring base station and the target base station; determining the user activity within the preset time period based on the base station coverage area, the user number distribution within the preset time period, and the base station load rate distribution within the preset time period.

Images