Construction method of indoor 5G three-dimensional fingerprint database and related equipment

Abstract

The embodiment of the invention discloses an indoor 5G three-dimensional fingerprint database construction method and related equipment, and aims to solve the core problem that a 5G network lacks direct position reporting functions such as MDT and the like, and a traditional fingerprint database cannot be associated with a real user position. The method comprises the following steps: acquiring original MRO data of a measurement report of a 5G network and corresponding signaling data, and analyzing to obtain a user identifier and wireless signal characteristics of a serving cell and an adjacent cell; acquiring actual position information of a user, and associating the actual position information of the user with the user identifier; based on the wireless signal characteristics, distinguishing indoor and outdoor sampling points, and determining a critical point when the user enters and exits from the room according to the sudden change of the wireless signal intensity when the user enters and exits from the room; and constructing an indoor 5G three-dimensional fingerprint database corresponding to the building, the unit and the floor based on the position information of the critical point and the actual position information of the user.

Description

Technical Field

[0001] This invention relates to the field of wireless communication technology, and in particular to a method for constructing an indoor 5G three-dimensional fingerprint database and related equipment. Background Technology

[0002] With the large-scale commercial deployment of 5G networks, the need for refined assessment and positioning of indoor deep coverage is becoming increasingly urgent. Existing indoor positioning technologies mainly include solutions based on Wi-Fi, inertial navigation, magnetic fields, or fusion algorithms, but these methods have significant drawbacks when applied to 5G networks: First, it is impossible to directly associate wireless signal fingerprints with users' actual physical locations (such as residential buildings, units, and floors), resulting in positioning results that cannot reflect the true distribution of users. Second, 5G networks lack functions such as Minimization of Drive Tests (MDT) to directly report location information, making it difficult to directly obtain the precise location of indoor sampling points. Third, existing methods have insufficient positioning accuracy in the vertical dimension and are greatly affected by building structure.

[0003] Therefore, there is an urgent need for a method that can automatically associate user's actual location information and use existing 5G network data to construct a high-precision three-dimensional fingerprint library to support 5G indoor deep coverage analysis, user positioning, and network optimization. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for constructing an indoor 5G three-dimensional fingerprint database. It solves the core problems of 5G networks lacking direct location reporting functions such as MDT and traditional fingerprint databases being unable to associate with real user locations, and provides a data foundation for 5G indoor deep coverage analysis and user positioning.

[0005] In a first aspect, embodiments of this application provide a method for constructing an indoor 5G three-dimensional fingerprint database, including: Obtain the raw MRO data and corresponding signaling data from the 5G network measurement report, and parse them to obtain the user identifier, serving cell and neighboring cell wireless signal characteristics; Obtain the user's actual location information and associate the user's actual location information with the user identifier; Based on the wireless signal characteristics, indoor and outdoor sampling points are distinguished, and the critical point for the user to enter or leave the room is determined according to the sudden change in wireless signal strength when the user enters or leaves the room. Based on the location information of the critical point and the user's actual location information, an indoor 5G three-dimensional fingerprint database is constructed for the corresponding building, unit, and floor.

[0006] Optionally, obtaining the user's actual location information includes: Obtain the user's B-domain data, which includes at least the user identifier, the building, unit number, and floor information corresponding to the user's address; The data in the B domain is anonymized to protect user privacy.

[0007] Optionally, determining the critical point for a user to enter or exit the room based on the sudden change in wireless signal strength when the user enters or exits the room includes: Among consecutive sampling points for the same user, identify adjacent sampling points where the received reference signal level (RSRP) of the serving cell drops sharply; When the RSRP difference between adjacent sampling points reaches a first preset threshold, and the difference between the average RSRP of subsequent consecutive sampling points and the average RSRP of the aforementioned consecutive sampling points reaches a second preset threshold, the sampling point where the signal drops sharply is determined as the critical point.

[0008] Optionally, before constructing the indoor 5G three-dimensional fingerprint database corresponding to buildings, units, and floors, the method further includes: Obtain the BSSID of the Wi-Fi access point reported by the user at the indoor sampling point; Compare the BSSID with the address Wi-Fi BSSID recorded in the B domain data of the corresponding user; If the comparison matches, it is confirmed that the user has entered their actual residence, and the location of their indoor sampling point is confirmed accordingly.

[0009] Optionally, the construction of the indoor 5G three-dimensional fingerprint database corresponding to buildings, units, and floors includes: All indoor sampling points of users who have been confirmed to have entered their actual residences will be integrated; Generate a fingerprint record for each building, unit, and floor; The fingerprint record includes at least the following feature vectors: frequency points of the serving cell and neighboring cells, physical cell identifier (PCI), reference signal received level (RSRP), horizontal angle of arrival (HAOA), vertical angle of arrival (VAOA), time advance (TA), and the building, unit, floor, and calculated height above the ground.

[0010] Optionally, for users who cannot be associated with B-domain data, the construction of the indoor 5G three-dimensional fingerprint database corresponding to the building, unit, and floor includes: Based on the location of the critical point, it is matched with the location of the fingerprint database of existing B-domain data users to preliminarily determine the building and unit to which the user belongs; Extract the set of BSSID identifiers of surrounding Wi-Fi access points detected at the user's indoor sampling point; The BSSID set is matched with the known Wi-Fi fingerprints of adjacent units of the target unit, and the similarity of wireless signal feature vectors is combined to finally determine the floor and room where the user is located.

[0011] Optionally, the method further includes: For some floors or rooms lacking actual sampling data, spatial interpolation algorithms are used to improve the indoor 5G three-dimensional fingerprint database. The spatial interpolation algorithm is based on the spatial correlation of fingerprint feature vectors. It utilizes the known feature vector values ​​of the fingerprint database locations around the target location and calculates the interpolated estimate of the target location by assigning a weight related to spatial distance and direction to each known value.

[0012] Secondly, embodiments of this application provide an indoor 5G three-dimensional fingerprint database construction device, comprising: The data acquisition and parsing module is used to acquire the raw MRO data and corresponding signaling data of the 5G network measurement report, and parse it to obtain the user identifier, serving cell and neighboring cell wireless signal characteristics; The location acquisition module is used to acquire the user's actual location information and associate the user's actual location information with the user identifier; The critical point determination module is used to distinguish between indoor and outdoor sampling points based on the wireless signal characteristics, and to determine the critical point for the user to enter or exit the room based on the sudden change in wireless signal strength when the user enters or exits the room. The fingerprint database construction module is used to construct an indoor 5G three-dimensional fingerprint database for the corresponding building, unit, and floor based on the location information of the critical point and the actual location information of the user.

[0013] Thirdly, embodiments of this application provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the above-described indoor 5G three-dimensional fingerprint database construction method.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for constructing an indoor 5G three-dimensional fingerprint database.

[0015] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for constructing an indoor 5G three-dimensional fingerprint database.

[0016] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: This invention creatively distinguishes indoor and outdoor sampling points and locates entry and exit thresholds by analyzing existing 5G network operation and maintenance data (MRO and signaling). It then associates this data with the actual user address information (B-domain data) owned by the operator, successfully binding wireless signal fingerprints to real three-dimensional physical locations (buildings, units, floors). This solves the core problems of 5G networks lacking direct location reporting functions such as MDT (Multi-Demand Team) and traditional fingerprint databases being unable to associate with real user locations, providing a data foundation for 5G indoor deep coverage analysis and user positioning. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram illustrating the implementation process of an indoor 5G three-dimensional fingerprint database construction method provided in this application embodiment; Figure 2 A schematic diagram illustrating the implementation process of another indoor 5G three-dimensional fingerprint database construction method provided in this application embodiment; Figure 3 Building maps based on B-domain MRO data provided in this application embodiment; Figure 4 The residential space distribution and Kriging interpolation algorithm calculation diagram provided in the embodiments of this application; Figure 5 A schematic diagram of an indoor 5G three-dimensional fingerprint database construction device provided in this application embodiment; Figure 6 A schematic diagram of another indoor 5G three-dimensional fingerprint database construction device provided in this application embodiment; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] As will be known to those skilled in the art, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0020] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the description of embodiments of this application. Furthermore, the terms "comprising," "and," "having," and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements but may include other elements not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] To address the core challenges in existing technologies, such as the lack of direct location reporting functions like MDT in 5G networks and the inability of traditional fingerprint databases to be associated with real user locations, this application provides a method for constructing an indoor 5G three-dimensional fingerprint database.

[0022] The execution subject of this method can be various types of computing devices, or it can be an application or app installed on the computing device. The computing device can be a user terminal such as a mobile phone, tablet computer, or smart wearable device, or it can be a server.

[0023] For ease of description, this application uses a server as the execution subject of the method in its embodiments to illustrate the method. Those skilled in the art will understand that this embodiment uses a server as an example to describe the method, which is merely an illustrative example and does not limit the scope of protection of the corresponding claims.

[0024] Specifically, the implementation flow of the method provided in this application embodiment is as follows: Figure 1 As shown, it includes the following steps: S01: Obtain the raw MRO data and corresponding signaling data from the 5G network measurement report, and parse it to obtain the user identifier, serving cell and neighboring cell wireless signal characteristics; The Measurement Report of Original Type (MRO) data and its corresponding signaling data are obtained from the 5G network management system. MRO data contains radio signal measurement information reported by user equipment, but existing 5G MRO data does not directly report location information (such as latitude and longitude). By parsing the MRO data, key fields are extracted, including: user identifier (such as temporary Amfuengapid), Reference Signal Receiving Power (RSRP) of the serving cell, Reference Signal Receiving Quality (RSRQ), Physical Cell Identifier (PCI), frequency point (Earfcn), and corresponding radio signal characteristics of neighboring cells (RSRP, PCI, frequency point, etc.). Simultaneously, signaling data containing permanent user identifiers (such as MSISDN) and Amfuengapid is extracted from the Access Management Function (AMF) signaling, thereby establishing the association between MRO sampling points and real users.

[0025] S02: Obtain the user's actual location information and associate the user's actual location information with the user identifier; The system retrieves the user's B-domain data, which typically includes the user's MSISDN, building name, unit number, and floor corresponding to their registered address. To protect user privacy, the B-domain data is anonymized, for example, by mapping the MSISDN to an anonymous sequence number. Through the mapping between the MSISDN in the signaling data and the Amfuengapid in the MRO data, the anonymized user's actual address information (building, unit, floor) is ultimately associated with the MRO sampling points.

[0026] In some embodiments, obtaining the user's actual location information includes: Obtain the user's B-domain data, which includes at least the user identifier, the building, unit number, and floor information corresponding to the user's address; The data in the B domain is anonymized to protect user privacy.

[0027] B-domain data originates from the operator's business support system and includes at least the user identifier (MSISDN) and their registered detailed address information, which must be able to resolve to at least the building name, unit number, and floor number.

[0028] To strictly comply with data security and privacy regulations, data in Domain B must be anonymized before association and use. Specifically, the original, directly identifiable MSISDN is converted into a unique, anonymous serial number using an irreversible encryption algorithm or mapping table. Simultaneously, a mapping table is established and maintained between the MSISDN, the anonymous serial number, and the anonymized address information. This ensures that only the anonymous serial number is used in all subsequent processing steps, protecting user privacy from the outset.

[0029] By explicitly using B-domain data—a data source unique to telecom operators—users' real physical addresses can be obtained directly and accurately. This is a crucial prerequisite for achieving precise correlation between fingerprint databases and 3D locations. Mandatory anonymization procedures ensure that the entire technical solution complies with legal and regulatory requirements while creating value from sensitive data, avoiding privacy risks and enhancing the solution's compliance and practicality.

[0030] S03: Based on the wireless signal characteristics, distinguish between indoor and outdoor sampling points, and determine the critical point for the user to enter or leave the room based on the sudden change in wireless signal strength when the user enters or leaves the room. Based on the analyzed wireless signal characteristics (mainly RSRP), a logic for distinguishing indoor and outdoor sampling points is designed. This logic comprehensively considers factors such as serving cell type (indoor distributed system or outdoor macro base station), signal strength, number of neighboring cells, and time (e.g., nighttime). For example, when the serving cell is an indoor distributed system and RSRP > -95dBm, it is determined to be an indoor sampling point; when the serving cell is an outdoor base station, RSRP < -95dBm, and number of neighboring cells < 3, it is also determined to be an indoor sampling point.

[0031] Analyzing consecutive sampling point sequences for the same user is crucial. When a user moves from outdoors to indoors or vice versa, the RSRP (Residual RSRP) of the serving cell experiences a sudden drop due to obstruction from walls and other buildings. By identifying adjacent sampling points where the RSRP drops sharply and setting reasonable threshold conditions (e.g., an RSRP difference of 20 dB between adjacent points, and an average RSRP difference between multiple consecutive sampling points also reaching a certain threshold), the critical point for a user entering or exiting a building can be accurately determined. The location information of this critical point is obtained using existing positioning technologies (such as the 5GMRO location backfilling method based on 4GMDT data).

[0032] In some embodiments, determining the critical point for a user to enter or exit the room based on the sudden change in wireless signal strength when the user enters or exits the room includes: Among consecutive sampling points for the same user, identify adjacent sampling points where the received reference signal level (RSRP) of the serving cell drops sharply; When the RSRP difference between adjacent sampling points reaches a first preset threshold, and the difference between the average RSRP of subsequent consecutive sampling points and the average RSRP of the aforementioned consecutive sampling points reaches a second preset threshold, the sampling point where the signal drops sharply is determined as the critical point.

[0033] This method is specifically designed for analyzing continuous time series sampling points based on the same user.

[0034] Iterate through the user's continuous sampling points and calculate the difference in the serving cell RSRP between two adjacent sampling points. When the RSRP difference (decrease) of a certain pair of adjacent points reaches a large first preset threshold (e.g., 20dB), it is marked as a suspected critical point.

[0035] To rule out accidental signal fluctuations, further trend verification is performed. Using this suspected critical point as a boundary, the average RSRP (representing the stable outdoor or indoor state) of the preceding N (e.g., 10) sampling points is calculated, as well as the average RSRP of the following M (e.g., 10) sampling points (representing the new state after entering indoors or outdoors). The difference between these two averages is calculated. When this difference reaches a second preset threshold (e.g., also 20 dB), and the trend is consistent with the direction determined by the first threshold (e.g., both decreasing), then the suspected critical point is confirmed as the actual critical point for users entering or leaving the indoor area.

[0036] By setting dual judgment conditions of abrupt changes in adjacent points and trend changes in the preceding and following segments, this algorithm can accurately capture the instantaneous changes in wireless signals caused by passing through building walls, effectively filtering out normal signal fluctuations caused by small user movements, device swings, or short-term interference, greatly improving the accuracy and robustness of critical point identification, and providing a reliable basis for subsequent building location determination.

[0037] S04: Based on the location information of the critical point and the actual location information of the user, construct an indoor 5G three-dimensional fingerprint database corresponding to the building, unit and floor.

[0038] Based on the critical point location information determined in step S03 (i.e., the location where a user enters or exits a building), and combined with the user's actual address information (specifically down to the unit and floor) associated in step S02, all subsequent indoor sampling points collected within the building can be assigned to specific buildings, units, and floors. By integrating and statistically analyzing the wireless signal characteristics of these sampling points (e.g., taking the median), a fingerprint record is generated for each building-unit-floor combination, thereby constructing a high-precision indoor 5G three-dimensional fingerprint database.

[0039] This invention creatively distinguishes indoor and outdoor sampling points and locates entry and exit thresholds by analyzing existing 5G network operation and maintenance data (MRO and signaling). It then associates this data with the actual user address information (B-domain data) owned by the operator, successfully binding wireless signal fingerprints to real three-dimensional physical locations (buildings, units, floors). This solves the core problems of 5G networks lacking direct location reporting functions such as MDT (Multi-Demand Team) and traditional fingerprint databases being unable to associate with real user locations, providing a data foundation for 5G indoor deep coverage analysis and user positioning.

[0040] In some embodiments, before constructing the indoor 5G three-dimensional fingerprint database corresponding to buildings, units, and floors, the method further includes: Obtain the BSSID of the Wi-Fi access point reported by the user at the indoor sampling point; Compare the BSSID with the address Wi-Fi BSSID recorded in the B domain data of the corresponding user; If the comparison matches, it is confirmed that the user has entered their actual residence, and the location of their indoor sampling point is confirmed accordingly.

[0041] When a user is indoors, their mobile phone typically scans for and may connect to nearby Wi-Fi networks. The 5GMRO data can carry information about the Wi-Fi access points detected by the user's device, the most crucial of which is the Basic Service Set Identifier (BSSID), which is usually the MAC address of the Wi-Fi router and is globally unique.

[0042] Before building the fingerprint database, extract the Wi-Fi BSSID reported by the user at indoor sampling points. Compare this BSSID with the BSSID of the user's home broadband Wi-Fi that may be recorded in the corresponding user's B-domain data.

[0043] If the two match, it strongly proves that the user is currently at the physical address registered in their B-domain data. This verification step cross-validates the logical association based on network-side data (B-domain address) with the physical environment characteristics (Wi-Fi BSSID) collected on the terminal side, thus confirming that the user has entered their actual address. Based on this confirmation, all their indoor sampling points can be unambiguously attributed to that specific building, unit, and floor, significantly improving the credibility of the fingerprint database location tags.

[0044] Introducing Wi-Fi BSSID as a digital address for cross-verification resolves potential errors arising from relying solely on B-domain data association (e.g., when a user visits a neighbor). It binds the user's identity, the address registered with the carrier, and the actual wireless network environment at that address, forming a closed-loop chain of evidence. This upgrades the location confirmation of indoor sampling points from probabilistic inference to factual confirmation, significantly enhancing the accuracy and authority of the 3D fingerprint database's location information.

[0045] In some embodiments, constructing an indoor 5G three-dimensional fingerprint database corresponding to buildings, units, and floors includes: All indoor sampling points of users who have been confirmed to have entered their actual residences will be integrated; Generate a fingerprint record for each building, unit, and floor; The fingerprint record includes at least the following feature vectors: frequency points of the serving cell and neighboring cells, physical cell identifier (PCI), reference signal received level (RSRP), horizontal angle of arrival (HAOA), vertical angle of arrival (VAOA), timing advance (TA), and the building, unit, floor, and calculated height above the ground.

[0046] Indoor sampling data from all users confirmed to have entered their actual residences are integrated. A corresponding fingerprint record is generated for each unique building-unit-floor combination, based on physical space.

[0047] Each fingerprint record is a multi-dimensional feature vector, containing information in at least the following dimensions: (1) Wireless signal characteristics: Serving cell and neighboring cell information: Frequency point (FREQ), Physical cell identifier (PCI), Reference signal received level (RSRP).

[0048] Spatial channel information: The horizontal angle of arrival (HAOA) and vertical angle of arrival (VAOA) of the serving cell, obtained through signaling data parsing or from the network side. These two angles are crucial for achieving three-dimensional positioning.

[0049] Distance information: Time lead (TA) reflects the approximate distance between the user equipment and the base station.

[0050] (2) Location tag information: Building signage, unit number, floor number.

[0051] The calculated height information: The height from the ground is calculated based on the floor number. For example, height = (floor number minus one) * single-floor height (e.g., 3 meters). This is the core field for upgrading a two-dimensional planar fingerprint to a three-dimensional fingerprint.

[0052] By defining such a rich feature vector, the constructed fingerprint database not only includes traditional signal strength (RSRP) and cell identifier (PCI), but also incorporates channel angle information (HAOA / VAOA) and height labels with three-dimensional spatial resolution capabilities. When performing location matching, this fingerprint database can distinguish not only different locations on the horizontal plane, but also different floors in the vertical direction, truly achieving indoor three-dimensional positioning. The addition of TA information further constrains the distance dimension, making the positioning even more accurate.

[0053] In some embodiments, for users who cannot be associated with B-domain data, the construction of the indoor 5G three-dimensional fingerprint database corresponding to the building, unit, and floor includes: Based on the location of the critical point, it is matched with the location of the fingerprint database of existing B-domain data users to preliminarily determine the building and unit to which the user belongs; Extract the set of BSSID identifiers of surrounding Wi-Fi access points detected at the user's indoor sampling point; The BSSID set is matched with the known Wi-Fi fingerprints of adjacent units of the target unit, and the similarity of wireless signal feature vectors is combined to finally determine the floor and room where the user is located.

[0054] For users without B-domain data, the location of their entry / exit threshold is first determined. This threshold location is then spatially matched (e.g., nearest neighbor matching) with the building / unit locations recorded in the fingerprint database already built for users with existing B-domain data. If the distance is within a certain tolerance range (e.g., 20 meters), the building and unit to which the user belongs can be preliminarily inferred.

[0055] Extract the BSSIDs of all surrounding Wi-Fi access points detected by the user's mobile phone during indoor activities, forming a BSSID set. Match this set with the known Wi-Fi fingerprints (from the fingerprint records of users with BSSIDs) of the target unit and its neighboring units (e.g., upstairs, downstairs, and left / right neighbors). The matching principle is: the user's BSSID set should have a high degree of overlap with the known Wi-Fi fingerprint of the target unit (e.g., room 101), and may also contain a small number of Wi-Fi signals from neighboring units (e.g., rooms 201 and 102).

[0056] Based on Wi-Fi BSSID set matching, the similarity comparison of wireless signal feature vectors (such as SC_RSRP, SC_HAOA, NC_PCI, etc.) is further combined. The similarity (such as Euclidean distance, cosine similarity) between the feature vector of the user's indoor sampling point and the feature vector of the candidate unit fingerprint record is calculated. Finally, by combining the Wi-Fi matching results and wireless signal similarity, the most likely floor and specific apartment (e.g., Unit 1, Room 201) of the user is determined, thereby constructing a fingerprint record for them.

[0057] This method creatively utilizes critical points for coarse localization, then leverages the stable environmental feature of Wi-Fi BSSID sets for neighborhood relationship inference, and finally uses 5G signal characteristics for fine confirmation, forming a complete localization inference chain that does not rely on user registration information. It effectively expands the coverage of the fingerprint database, enabling users who are not registered in the B domain or use non-real-name cards to be included in the localization system, thus improving the completeness and usability of the fingerprint database.

[0058] In some embodiments, the method further includes: For some floors or rooms lacking actual sampling data, spatial interpolation algorithms are used to improve the indoor 5G three-dimensional fingerprint database. The spatial interpolation algorithm is based on the spatial correlation of fingerprint feature vectors. It utilizes the known feature vector values ​​of the fingerprint database locations around the target location and calculates the interpolated estimate of the target location by assigning a weight related to spatial distance and direction to each known value.

[0059] After constructing the fingerprint database using the aforementioned methods, some floors or apartments may still remain blank areas due to the lack of any user sampling data. To obtain fingerprints for these areas, a spatial interpolation algorithm is used for estimation. This invention preferably uses Kriging interpolation, a geostatistical-based optimal linear unbiased estimation method for spatial data interpolation.

[0060] This method is based on the premise that fingerprint feature vectors are spatially correlated (i.e., the closer the locations are, the more similar the signal features). For a target blank location, the method first searches for known points in the existing fingerprint database in its surrounding space (adjacent units on the same floor, corresponding units on upper and lower floors).

[0061] The algorithm assigns a weight to the feature vector value of each known point. This weight is closely related to the spatial distance and direction between the known point and the target point (calculated using a variogram model). Known points that are closer to the target point and lie in the main variogram direction receive a larger weight. Finally, the estimated fingerprint feature vector value of the target location is obtained by weighted summation of the feature vector values ​​of all known points.

[0062] By introducing spatial interpolation algorithms, fingerprints in blank areas can be scientifically inferred using existing, reliable fingerprint data, thereby generating a continuous and complete 3D fingerprint database for the entire building. This solves the problem of gaps in the fingerprint database caused by uneven user distribution or sparse data, enabling location services based on this fingerprint database to cover every corner of the building, improving the system's availability and completeness.

[0063] The following detailed description uses a specific embodiment to illustrate the above-mentioned method for constructing an indoor 5G three-dimensional fingerprint database. Figure 2 As shown: Step S11: Extract and analyze the relevant data.

[0064] Extract 5GMRO data and corresponding signaling data from the network management system.

[0065] First, the 5GMRO data needs to be analyzed. Since there is currently no 5GMDT data, and MRO data does not report latitude and longitude information, the 5GMRO sampling points need to be processed: The relevant information such as the primary serving cell RSRP, RSRQ, neighboring cell RSRP, neighboring cell PCI (physical-layer cell identity), and neighboring cell center frequency in the MRO data are parsed out. In the MRO data, MR.NRScRSRP is represented by a series of intervals, with each interval consisting of an MR.NRSS-RSRP step size of 1 dB.

[0066] RSRP = MR.NRSS - RSRP - 156 (S1.1); Based on this, MR.NRScRSRP and MR.NRNcRSRP are calculated and parsed into specific numerical values; Combining neighbor cell relationships and A3 event handover pairs in MRE, all sampling points of the same Amfuengapid are merged, and the related data is the same user data. At this time, the MRO data packet should include TimeStamp, Amfuengapid, MR.NRScEarfcn, MR.NRScPci, MR.NRncssrsrp, MR.NRncssrsrp1 (neighbor cell 1 RSRP), MR.NRncssrsrp2 (neighbor cell 2 RSRP), MR.NRncssrsrp3 (neighbor cell 3 RSRP), and MR.ltencrsrp information.

[0067] Location matching is performed on the 5G MRO data using 4G inter-frequency measurement information from the 5G MRO data. Signaling data is extracted from the AMF (Air Frequency Detection and Control). The AMF signaling includes information such as Amfuengapid, MSISDN, and TimeStamp. The MRO data includes TimeStamp and Amfuengapid. A one-to-one mapping is established between the MSISDN and Amfuengapid in the MRO data to distinguish users from the MRO sampling points. The same MSISDN corresponds to the same user.

[0068] Step S12: Desensitize the data in domain B.

[0069] Extract the B-domain data, which includes the user's MSISDN, the building and unit number and floor corresponding to the user's address.

[0070] To effectively protect user privacy, it is necessary to anonymize the data in the B domain by converting the user's MSISDN into a serial number. A mapping table between the MSISDN and the serial number is then created, which is the B domain anonymization table.

[0071] The B-domain desensitization table includes: the serial number corresponding to the MSISDN, the user's building and unit number, and the floor.

[0072] Step S13: MRO data location backfilling to establish an outdoor 5G fingerprint database for the region.

[0073] Based on 4G network coverage, the indoor deep coverage focus areas are divided as follows: First, extract the 4GMDT data to identify weak coverage sampling points in the MDT data.

[0074] Using the location information contained in the weak coverage sampling points, weak coverage areas are determined, and the above data is then differentiated between indoor and outdoor areas. The differentiation scheme is as follows: (1) The main serving cell is an indoor distributed antenna system cell, and the sampling point determination method is as follows: ① If the RSRP of the main serving cell is >-95dBm, this sampling point is an indoor user sampling point. Outdoor users usually have difficulty accessing indoor stations, and if the RSRP value is >-95dBm, it indicates that the signal received by the user from the indoor distribution system cell has not penetrated through the wall, so it is judged to be an indoor user sampling point. In special cases, this may occur when the outdoor leakage control of the indoor distribution system cell is poor, and such situations may exist at the edge of windows and at the entrance of the lobby, but the probability is small. ② If the RSRP of the primary serving cell is >-105dBm and the MR test time is 22:00-06:00 (for northwestern provinces, adjust according to the time, such as 0:00-08:00 in Xinjiang), the sampling point is determined to be an indoor user sampling point; such sampling points are located on the edge of the primary serving cell, but because they occupy indoor distributed cells and the sampling time is mostly during evening rest time, it can be determined that users are mostly active indoors at this time based on user behavior. ③ If no relevant data is collected in indoor neighboring cells where the RSRP of the primary serving cell is less than -90dBm and the RSRP of the primary serving cell differs from that of the primary serving cell by 6dBm, then the sampling point is an outdoor user sampling point. Such sampling points are mostly due to poor signal control of indoor distribution systems that leak to the outside. However, since the antennas of the relevant indoor neighboring cells are far away from this area and have greater loss, such sampling points are generated. Therefore, they can be identified as outdoor user sampling points. ④ If the neighboring cell RSRP > -105dBm and the number of outdoor signals ≤ 3, it is judged as an outdoor user sampling point; if the neighboring cell signal is strong and there are many outdoor signals in the neighboring cell, it means that the outdoor signal has not been lost through the wall, so it is judged as an outdoor user sampling point. ⑤ If the neighboring cell RSRP < -105dBm, it is determined to be an indoor user sampling point; the neighboring cell signal is weak, indicating that the outdoor signal has been lost through the wall, so it is determined to be an indoor user sampling point; (2) The main cell is an outdoor station, and the sampling point determination method is as follows: ① If the RSRP of the primary serving cell is <-95dBm and the number of neighboring cells is <3, it is judged as an indoor user sampling point. In outdoor coverage, many areas have strong RSRP values ​​and a large number of neighboring cells. However, indoors, due to the distance between different cells and the different incident angles from the window, the loss varies greatly. The RSRP difference between many other cells and the primary serving cell is >6dB, which does not meet the MR sampling neighboring cell relationship. After wall loss, the RSRP is <-95dBm. Such sampling points are judged as indoor user sampling points. ② If the primary serving cell RSRP < -90dBm, TA < 1, and the MR test time is 22:00-06:00 (for northwestern provinces, adjust according to the time, such as 0:00-08:00), then the sampling point is determined to be an indoor user sampling point; In such sampling points, the outdoor cell signal RSRP after wall loss is < -85dBm, which is relatively strong (mainly due to the proximity to the base station and the signal being mostly direct light through windows), but the sampling time is mostly during evening rest time. Based on user behavior, it can be known that users are mostly active indoors at this time, so it can be determined to be an indoor user sampling point; ③ If there is an indoor signal and RSRP>-95dBm, it is determined to be an indoor user sampling point. Such sampling points can only receive signals from indoor neighboring cells when indoors. ④ Sampling points with RSRP > -105dBm and number of neighboring cells ≥ 3 are judged as outdoor user sampling points; the RSRP of such sampling points is poor, mainly due to weak outdoor coverage, but the large number of neighboring cells indicates that the signal has not been lost through the wall, and they are judged as outdoor user sampling points.

[0075] Since users cannot receive satellite signals when they are indoors, the location of the sampling point reported by the user is usually from 10 minutes ago. However, users typically move relatively slowly after entering the community, so the reported sampling point location is usually the location of the user's residential community.

[0076] Statistics, combined with RSRP and SINR, are used to determine poor quality areas and weak coverage areas for indoor users.

[0077] By combining the location information of the backfilled 5G GMRO data, the corresponding area's 5G GMRO data is extracted, and indoor and outdoor users are distinguished. To ensure positioning accuracy, when constructing the 5G outdoor fingerprint database, it is necessary to add fingerprint database feature vectors: information is extracted from the 5G sample points after location backfilling, and the feature vectors include information such as the serving cell's frequency, PCI, RSRP, HAOA, VAOA, TA, and neighboring cell frequencies, PCI, RSRP, etc.

[0078] Step S14: Use AMFUENGAPID to distinguish users.

[0079] User data is extracted from the AMF (Agent Function File). The AMF signaling includes information such as Amfuengapid, MSISDN, and TimeStamp. The MRO (Maintenance Recovery Overhaul) data includes both TimeStamp and Amfuengapid. A one-to-one mapping between MSISDN and Amfuengapid allows for user differentiation of MRO sampling points. The same MSISDN corresponds to the same user. All AMF signaling is anonymized; the anonymized MSISDN should match the anonymized sequence number of the MSISDN in the B-domain anonymized data.

[0080] User differentiation is achieved using the anonymized MSISDN (Mean Information Function Name) from the AMF signaling protocol, with each MSISDN representing the same user. Based on the mapping between MSISDN and AMF, the corresponding user is located in the MRO (Management Recovery Equipment) database, and the MSISDN is entered into the MRO data. This MSISDN serves as the identifier for user differentiation.

[0081] Step S15: Perform user location matching to determine whether the user has entered the indoor area.

[0082] Using the indoor fingerprint database identified in step S13, the sampling points are matched to determine whether they enter the indoor deep coverage area of ​​interest. All outdoor sampling points entering this area are extracted, along with the corresponding user's (amfuengapid) ID. Using the correspondence between user MSISDN and Amfuengapid obtained in step S14, the sampling points are divided by user, yielding sampling point information for all users in this area.

[0083] Using the indoor and outdoor sampling points distinguished in step S13, determine the critical point for each user entering indoors or exiting outdoors. At this critical point, the user's RSRP will drop sharply; that is, the RSRP difference between this critical point and the next adjacent sampling point is approximately 20 dB, and the average RSRP of the subsequent 10 sampling points differs from the average RSRP of the 10 sampling points before the critical point by 20 dB. This is used to find the critical point. If a user enters indoors from outdoors, the critical point for entering indoors is obtained; if they exit outdoors from indoors, the first critical point for exiting outdoors is obtained. This critical point is the outdoor sampling point.

[0084] The building information entered by the user is obtained by backfilling the results of the user's critical point location.

[0085] However, the accuracy of the user information at this point is significantly inaccurate due to location backfilling issues. Therefore, it is necessary to utilize other data to further improve positioning accuracy.

[0086] Step S16: Use B-domain information in combination with Wi-Fi information to determine the location of the user's indoor sampling point.

[0087] Data from domain B is extracted to obtain the user's residential floor and unit information. The mapping between MSISDN and Amfuengapid yields the residential floor and unit information corresponding to the user's sampling point. Since users may not necessarily enter their own residence within the relevant area, further matching is required.

[0088] The sampling points are analyzed on a user-by-user basis, extracting all indoor sampling points for that user. Since users typically use home Wi-Fi for data access when indoors, when they enter areas far from the Wi-Fi source, such as bathrooms, the attenuated Wi-Fi signal may cause them to disconnect from Wi-Fi and connect to the mobile communication network. When a user connects to Wi-Fi, it causes the user's RRCconnect to be released, resulting in the cessation of MRO data reporting. However, when a user connects to a 5G network, they will report the Wi-Fi signal to the network. At this time, there will be more than one received Wi-Fi signal, and the serving Wi-Fi network will provide a BSSID. A BSSID is a Basic Service Set Identifier in a wireless LAN, a unique identifier used to identify each Basic Service Set (BSS) in a wireless network. BSSIDs are usually generated from the MAC address of a router or access point, so each BSSID is unique. The purpose of the BSSID is to distinguish different Basic Service Sets in a wireless network, allowing devices to connect to the correct network. When scanning for wireless networks, the device collects the BSSIDs of all nearby Basic Service Sets and compares them with known networks stored in the device to determine which network is available. Since BSSIDs are generated based on MAC addresses, they are very useful for network administrators to identify devices connected to the network and monitor network usage. Furthermore, some security policies can also be implemented based on BSSIDs, such as restricting wireless network connections to only specific BSSIDs.

[0089] By comparing the BSSID with the BSSID information in the B domain data, if they match, it means that the user has entered the information recorded in the B domain. At this time, all sampling points of the user in the room are extracted and an indoor three-dimensional fingerprint database is established.

[0090] Step S17: Construct an indoor 5G three-dimensional fingerprint database for residential communities.

[0091] The RSRP of the sampling points obtained in step S16 is statistically analyzed. The window sampling points have the strongest RSRP, at which point at least three (including three) neighboring cell signals can be received. The bathroom sampling points have the weakest RSRP, with virtually no neighboring cell signals. The living room and bedroom have relatively strong RSRP. The median value of all sampling points is taken as the feature value, at which point one to two neighboring cell signals can be received. Based on this, an indoor 3D fingerprint database is established. The specific feature vectors include: Wi-Fi_BSSID\Wi-Fi1_SSID\Wi-Fi2_SSID\Wi-Fi3_SSID\SC_RSRP \SC_RSRQ\SC_sinr\SC_TA\SC_HAOA\SC_VAOA\SC_FREQ\SC_PCI\NC_RSRP\NC_FREQ\NC_PCI\Window (Living Room & Bedroom, Bathroom)\Floor\Unit Number\Building\Residential Community Name\Height from Ground. Where height from ground = (Number of Floors - 1) * 3.

[0092] The user's building and unit information is extracted and imported into GPS software to extract the GPS information of the user's building and unit. The unit location information is compared with the data information in step S15. If the difference between the two is within 20 meters, the critical point location information obtained in step S15 is used as the location information of the indoor 3D fingerprint database. Otherwise, the location information extracted by the GPS software is directly used as the fingerprint database location information.

[0093] Construct a 5G 3D fingerprint database of the corresponding unit and floor of a building by using all sampling points that can be matched with B-domain data.

[0094] Extract the critical points of all users with B-domain data, determine the location of the critical points, and use this as the fingerprint database for that building unit.

[0095] S18: Build a fingerprint database for users without B-domain data using Wi-Fi data.

[0096] However, some users did not find the corresponding B-domain data. In this case, it is necessary to combine Wi-Fi data to build a fingerprint database.

[0097] First, for user MRO data that did not match corresponding B-domain data (hereinafter referred to as B-domain MRO data), critical points are extracted on a user-by-user basis. These critical points are then matched against the building unit fingerprint database obtained in step S17, based on the critical points obtained in step S15, to determine the building where the user's indoor sampling point is located. The critical point is the sampling point where the user enters or exits the building; therefore, this point represents the location information of the user's indoor sampling point. Using this as the location information of the building unit is the most accurate method.

[0098] Map all user MRO data that did not match the corresponding B-domain data (referred to as B-domain non-B-domain MRO data) to the relevant buildings and units.

[0099] The fingerprint database is constructed using the above data in the following manner: Extract the MRO data from the B field mentioned above, and create building drawings accordingly, such as... Figure 3 As shown, Figure 3 The building map based on B-domain MRO data provided in this application embodiment.

[0100] like Figure 3As shown, green represents users with B-domain MRO data, and yellow represents users without B-domain MRO data. At this time, the Wi-Fi information of all green users is extracted. Taking Unit 1, Room 102 as an example, this user can receive Wi-Fi signals from Unit 1, Room 101, Unit 1, Room 201, Unit 1, Room 202, Unit 1, Room 203, and Unit 1, Room 103. Users who meet the above conditions can be defined as users of Unit 1, Room 102. The user data that meets this requirement is extracted as the candidate data for users of Unit 1, Room 102.

[0101] Using the preliminary fingerprint database constructed in step S17, feature vector comparison was performed. The feature values ​​of user SC_RSRP\SC_RSRQ\SC_sinr\SC_TA\SC_HAOA\SC_VAOA\SC_FREQ\SC_PCI\NC_RSRP\NC_FREQ\NC_PCI in unit 1, room 102, are basically consistent with those of users in unit 1, room 101, and unit 1, room 103. Using the fingerprint database matching scheme, the candidate data of user 102 in unit 1 were matched to obtain the MRO data of user 102 in unit 1. This completes the construction of an indoor fingerprint database with partial B-domain MRO data.

[0102] S19: Improve the fingerprint database using the Kriging interpolation algorithm.

[0103] Since the availability of mobile broadband is currently limited, fingerprint databases cannot be established in some indoor areas. Therefore, Kriging interpolation algorithms are needed to further improve the fingerprint database.

[0104] Kriging interpolation is applicable when regionalized variables exhibit spatial correlation. Specifically, if the results of variogram and structural analysis indicate spatial correlation among regionalized variables, Kriging interpolation can be used for interpolation or extrapolation. Essentially, it utilizes the original data of the regionalized variables and the structural characteristics of the variogram to perform a linear, unbiased, and optimal estimate of unknown sample points. Unbiased means the expected value of the deviation is zero, and optimal means the sum of the squares of the differences between the estimated and actual values ​​is minimized. Therefore, Kriging interpolation is a linear, unbiased, and optimal estimate of unknown sample points based on data from several known sample points within a finite neighborhood of the unknown sample point, considering the shape, size, and spatial orientation of the sample points, their spatial relationship with the unknown sample point, and the structural information provided by the variogram.

[0105] First, for all floors and residences where the fingerprint database has been completed, create building-specific blueprints. For example... Figure 4 As shown, Figure 4 The diagram shows the residential space distribution and Kriging interpolation algorithm calculation provided in the embodiments of this application.

[0106] Assuming the study area is Figure 4The yellow area represents the feature vector value of the fingerprint database, Z(x). Since the matching of all user thresholds was completed in step S18, if the SC_FREQ\SC_PCI values ​​of users on the same floor and in the same unit remain essentially unchanged, the focus now is on constructing the user's SC_RSRP\SC_RSRQ\SC_sinr\SC_TA\SC_HAOA\SC_VAOA\NC_RSRP\NC_FREQ\NC_PCI values, using the green user residence as x. The attribute value at location A(i=1,2,...,n) is... Then the yellow house x to be inserted Kriging interpolation result of attribute value Z() at point A The known sampling point attribute value Z( The weighted sum of (=1, 2, n), that is: (1) In the formula These are undetermined weighting coefficients.

[0107] in There is a certain correlation between them. This correlation is related not only to distance but also to changes in their relative direction. The Kriging interpolation method refers to the studied objects as regionalized variables. Under the unbiased and minimum variance conditions of the Kriging method, the unbiased conditions can be obtained, and the undetermined weighting coefficients can be obtained. (i=1,2,……,n) satisfy the following relation: (2) Assuming unbiasedness, minimizing the Kriging variance yields the system of equations for solving the undetermined weighting coefficients:

[0108] By importing the coefficients obtained above into (1), the Kriging interpolation result can be obtained. .

[0109] Will Figure 4 Centered on the yellow residential building, the RSRP of the horizontal green residential building (taking unit 1, room 803 as an example) is taken as known data, and the RSRP of the vertical building is also taken as known data (see the red box). The undetermined weighting coefficients are calculated separately. Thus, RSRP data for Unit 1, Room 803 of the Yellow Residential Building was obtained.

[0110] Similarly, import SC_RSRQ\SC_sinr\SC_TA\SC_HAOA\SC_VAOA\ into the above formula for calculation.

[0111] For NC_RSRP, NC_FREQ, and NC_PCI, the data is analyzed with reference to the residential community corresponding to the red box. If the same data exists on both the left and right sides, the data is added to the data corresponding to Room 803, Unit 1 of the yellow residential building. Otherwise, the data is analyzed based on the vertical data, with the nearest residential building as a reference for data addition.

[0112] This will complete the construction of the indoor fingerprint database for the remaining B-domain MRO data.

[0113] Because data calibration and fingerprint database improvement were performed using 5G MRO data combined with Wi-Fi and GPS data, a complete three-dimensional fingerprint database for the entire building was obtained. This database allows for comprehensive indoor depth coverage analysis of all buildings within a target area, and also enables user tracking and location services, providing precise positioning support for epidemic prevention and control, and the detection of telecom fraud.

[0114] In summary, compared with existing technologies, the embodiments of this application calculate using MRO data and accurately locate user sampling points using B-domain data, effectively solving the problem of needing to use related algorithms to estimate user location. Simultaneously, this algorithm is associated with the user's actual residential information, ensuring the accuracy of the user's location and effectively avoiding the problem of insufficient positioning accuracy caused by electromagnetic wave reflections due to building obstruction.

[0115] This application embodiment utilizes existing 5G data: The fingerprint database is constructed using the SC_RSRP\SC_RSRQ\SC_sinr\SC_TA\SC_HAOA\SC_VAOA\SC_FREQ\SC_PCI\NC_RSRP\NC_FREQ\NC_PCI domains. The B-domain data is used for positioning, and the outdoor fingerprint database is used to determine whether the residence entered by the user is consistent with the B-domain. Therefore, the accuracy of the 5G three-dimensional fingerprint database construction is guaranteed from multiple dimensions.

[0116] This application utilizes Wi-Fi data as a supplement. Based on the positioning data from MRO and B-domain data, it combines the tested Wi-Fi data to extract the BSSID for indoor user positioning. This effectively avoids the problem of using user Wi-Fi signals for positioning, where user Wi-Fi data and user data cannot be directly correlated. Therefore, the positioning accuracy is not affected by the user turning off their Wi-Fi device.

[0117] This application embodiment utilizes the Kriging interpolation algorithm to supplement the residential fingerprint database without B-domain data, and makes full use of 5G network data information for indoor user positioning, solving the current problem of checkpoints without 5G MDT functionality, and making the positioning scheme more accurate and reliable.

[0118] By constructing a 5G 3D fingerprint database solution, precise 3D positioning of 5G indoor users can be achieved without conducting on-site testing. Ultimately, even without MDT (Multi-Targeted Theory) functionality in 5G, this solution utilizes B-domain data, critical point positioning, Kriging interpolation algorithms, and Wi-Fi data-assisted positioning to achieve refined 3D positioning analysis of 5G users indoors. This provides sophisticated data support for refined PCI planning of wireless networks, refined simulation of wireless networks, location tracking of telecom fraud, and deep coverage analysis of wireless networks indoors. Furthermore, this application's embodiments reduce on-site testing labor costs and improve the efficiency of 5G indoor deep coverage analysis.

[0119] Figure 5 This application provides a schematic diagram of the structure of an indoor 5G three-dimensional fingerprint database construction device; the indoor 5G three-dimensional fingerprint database construction device includes: The data acquisition and parsing module 301 is used to acquire the original MRO data of the 5G network measurement report and the corresponding signaling data, and to parse the user identifier, serving cell and neighboring cell wireless signal characteristics. The location acquisition module 302 is used to acquire the user's actual location information and associate the user's actual location information with the user identifier; The critical point determination module 303 is used to distinguish between indoor and outdoor sampling points based on the wireless signal characteristics, and to determine the critical point for the user to enter or leave the room based on the sudden change in wireless signal strength when the user enters or leaves the room. The fingerprint database construction module 304 is used to construct an indoor 5G three-dimensional fingerprint database corresponding to buildings, units and floors based on the location information of the critical point and the actual location information of the user.

[0120] Figure 6 This is a schematic diagram of another indoor 5G three-dimensional fingerprint database construction device provided in an embodiment of this application.

[0121] like Figure 6 As shown, the data parsing module 20 mainly includes a 5G MRO data processing module 201 and a 5G signaling processing module 202. It extracts MRO data through the network management platform and extracts 5G signaling data from the AMF. According to the process in step S11, it converts MRO and signaling data into relevant databases, maps MSISDN in MRO to Amfuengapid one by one, and distinguishes MRO sampling points by user.

[0122] The data desensitization module 21 mainly includes a B-domain data desensitization module 211 and a signaling data desensitization module 212. According to the process in step S12, the MSISDN and the serial number are made into a corresponding relationship table, namely the B-domain desensitization table.

[0123] The outdoor fingerprint database user differentiation module 22 mainly includes an outdoor fingerprint database construction module 221 and a user differentiation module 222. It differentiates indoor and outdoor users according to steps S13 and S14, and constructs an outdoor fingerprint database in conjunction with the outdoor fingerprint database construction scheme, providing a basis for determining whether a user has entered the building in the area.

[0124] The user entering indoor judgment module 23 mainly includes a critical point judgment module 231 and a user entering indoor judgment module 232. It mainly determines the critical point for entering indoors or exiting outdoors for the same user as a unit based on step S15 and judges whether the user has entered indoors.

[0125] The user indoor sampling point positioning module 24 mainly includes a BSSID processing module 241 and a BSSID information comparison module 242. It mainly determines the location of the user's residence by comparing the BSSID in the MRO data with the B domain data in step S16.

[0126] The initial three-dimensional fingerprint database construction module 25 mainly includes a user building and unit GPS extraction module 251 and a 5G three-dimensional fingerprint database construction module 252. It extracts user building and unit information, imports it into GPS software, and extracts the GPS information of user buildings and units. It constructs a 5G three-dimensional fingerprint database of a certain building, corresponding unit and corresponding floor of a certain building by using all sampling points that can be matched with B domain data.

[0127] The fingerprint database improvement module 26 mainly includes a fingerprint database improvement module 261 using Wi-Fi data and a fingerprint database improvement module 262 using Kriging interpolation algorithm. It uses the constructed preliminary fingerprint database to perform feature vector matching to complete the construction of an indoor fingerprint database with some B-domain MRO data; and uses Kriging interpolation algorithm to improve the indoor fingerprint database with the remaining MRO data.

[0128] Figure 7 To illustrate the hardware structure of an electronic device according to various embodiments of this application, the electronic device 400 includes, but is not limited to, components such as: a radio frequency unit 401, a network module 402, an audio output unit 403, an input unit 404, a sensor 405, a display unit 406, a user input unit 407, an interface unit 408, a memory 409, a processor 410, and a power supply 411. Those skilled in the art will understand that... Figure 7 The electronic device structures shown are not intended to limit the electronic device. An electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements. In the embodiments of this application, the electronic device includes, but is not limited to, mobile phones, tablets, laptops, PDAs, in-vehicle terminals, wearable devices, and pedometers.

[0129] The processor 410 is used to implement the steps of the above-mentioned indoor 5G three-dimensional fingerprint database construction method.

[0130] The memory 409 is used to store a computer program that can run on the processor 410, which, when executed by the processor 410, implements the functions described above by the processor 410.

[0131] It should be understood that, in this embodiment, the radio frequency unit 401 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink data from the base station and processes it with the processor 410; additionally, it transmits uplink data to the base station. Typically, the radio frequency unit 401 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc. Furthermore, the radio frequency unit 401 can also communicate with networks and other devices through a wireless communication system.

[0132] The electronic device provides users with wireless broadband internet access through the network module 402, such as helping users send and receive emails, browse web pages, and access streaming media.

[0133] The audio output unit 403 can convert audio data received by the radio frequency unit 401 or the network module 402 or stored in the memory 409 into audio signals and output them as sound. Furthermore, the audio output unit 403 can also provide audio output related to specific functions performed by the electronic device 400 (e.g., call signal reception sound, message reception sound, etc.). The audio output unit 403 includes a speaker, a buzzer, and a receiver, etc.

[0134] Input unit 404 is used to receive audio or video signals. Input unit 404 may include a graphics processing unit (GPU) 4041 and a microphone 4042. The GPU 4041 processes image data of still images or videos acquired by an image capture device (such as a camera) in video capture mode or image capture mode. The processed image frames can be displayed on display unit 406. The image frames processed by GPU 4041 can be stored in memory 409 (or other storage medium) or transmitted via radio frequency unit 401 or network module 402. Microphone 4042 can receive sound and process such sound into audio data. The processed audio data can be converted into a format that can be transmitted to a mobile communication base station via radio frequency unit 401 in telephone call mode.

[0135] The electronic device 400 also includes at least one sensor 405, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 4061 according to the ambient light level, and the proximity sensor can turn off the display panel 4061 and / or backlight when the electronic device 400 is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used to identify the posture of the electronic device (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc. The sensor 405 may also include a fingerprint sensor, pressure sensor, iris sensor, molecular sensor, gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., which will not be described in detail here.

[0136] The display unit 406 is used to display information input by the user or information provided to the user. The display unit 406 may include a display panel 4061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0137] User input unit 407 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of electronic devices. Specifically, user input unit 407 includes a touch panel 4071 and other input devices 4072. Touch panel 4071, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near touch panel 4071). Touch panel 4071 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 410, which receives and executes commands from the processor 410. In addition, touch panel 4071 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides touch panel 4071, user input unit 407 may also include other input devices 4072. Specifically, other input devices 4072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here.

[0138] Furthermore, the touch panel 4071 can cover the display panel 4061. When the touch panel 4071 detects a touch operation on or near it, it transmits the information to the processor 410 to determine the type of touch event. Subsequently, the processor 410 provides corresponding visual output on the display panel 4061 based on the type of touch event. Although in Figure 7 In this embodiment, the touch panel 4071 and the display panel 4061 are two independent components to realize the input and output functions of the electronic device. However, in some embodiments, the touch panel 4071 and the display panel 4061 can be integrated to realize the input and output functions of the electronic device. The specific implementation is not limited here.

[0139] Interface unit 408 serves as an interface for connecting external devices to electronic device 400. For example, external devices may include a wired or wireless headphone port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 408 can be used to receive input (e.g., data, power, etc.) from external devices and transmit the received input to one or more components within electronic device 400, or it can be used to transmit data between electronic device 400 and external devices.

[0140] The memory 409 can be used to store software programs and various data. The memory 409 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback, image playback, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory 409 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0141] The processor 410 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 409, and by calling data stored in the memory 409, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 410 may include one or more processing units; preferably, the processor 410 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 410.

[0142] The electronic device 400 may also include a power supply 411 (such as a battery) that supplies power to various components. Preferably, the power supply 411 can be logically connected to the processor 410 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system.

[0143] In addition, electronic device 400 includes some functional modules not listed, which will not be described in detail here.

[0144] Preferably, this application embodiment also provides an electronic device, including a processor 410, a memory 409, and a computer program stored in the memory 409 and executable on the processor 410. When the computer program is executed by the processor 410, it implements the various processes of the above-described indoor 5G three-dimensional fingerprint database construction method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0145] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, this computer program implements the various processes of the above-described indoor 5G three-dimensional fingerprint database construction method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0146] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0148] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0149] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0150] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0151] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0152] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0153] It should also be noted that the terms "include," "comprise," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "includes a…" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0154] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for constructing an indoor 5G three-dimensional fingerprint database, characterized in that, include: Obtain the raw MRO data and corresponding signaling data from the 5G network measurement report, and parse them to obtain the user identifier, serving cell and neighboring cell wireless signal characteristics; Obtain the user's actual location information and associate the user's actual location information with the user identifier; Based on the wireless signal characteristics, indoor and outdoor sampling points are distinguished, and the critical point for the user to enter or leave the room is determined according to the sudden change in wireless signal strength when the user enters or leaves the room. Based on the location information of the critical point and the user's actual location information, an indoor 5G three-dimensional fingerprint database is constructed for the corresponding building, unit, and floor.

2. The method for constructing an indoor 5G three-dimensional fingerprint database according to claim 1, characterized in that, The process of obtaining the user's actual location information includes: Obtain the user's B-domain data, which includes at least the user identifier, the building, unit number, and floor information corresponding to the user's address; The data in the B domain is anonymized to protect user privacy.

3. The method for constructing an indoor 5G three-dimensional fingerprint database according to claim 1 or 2, characterized in that, The method of determining the critical point for a user to enter or exit the room based on the sudden change in wireless signal strength when the user enters or exits the room includes: Among consecutive sampling points for the same user, identify adjacent sampling points where the received reference signal level (RSRP) of the serving cell drops sharply; When the RSRP difference between adjacent sampling points reaches a first preset threshold, and the difference between the average RSRP of subsequent consecutive sampling points and the average RSRP of the aforementioned consecutive sampling points reaches a second preset threshold, the sampling point where the signal drops sharply is determined as the critical point.

4. The method for constructing an indoor 5G three-dimensional fingerprint database according to claim 2, characterized in that, Before constructing the indoor 5G three-dimensional fingerprint database corresponding to buildings, units, and floors, the method further includes: Obtain the BSSID of the Wi-Fi access point reported by the user at the indoor sampling point; Compare the BSSID with the address Wi-Fi BSSID recorded in the B domain data of the corresponding user; If the comparison matches, it is confirmed that the user has entered their actual residence, and the location of their indoor sampling point is confirmed accordingly.

5. The method for constructing an indoor 5G three-dimensional fingerprint database according to claim 4, characterized in that, The construction of the indoor 5G three-dimensional fingerprint database corresponding to buildings, units, and floors includes: All indoor sampling points of users who have been confirmed to have entered their actual residences will be integrated; Generate a fingerprint record for each building, unit, and floor; The fingerprint record includes at least the following feature vectors: frequency points of the serving cell and neighboring cells, physical cell identifier (PCI), reference signal received level (RSRP), horizontal angle of arrival (HAOA), vertical angle of arrival (VAOA), time advance (TA), and the building, unit, floor, and calculated height above the ground.

6. The method for constructing an indoor 5G three-dimensional fingerprint database according to claim 1, characterized in that, For users who cannot be associated with B-domain data, the construction of the corresponding indoor 5G three-dimensional fingerprint database for buildings, units, and floors includes: Based on the location of the critical point, it is matched with the location of the fingerprint database of existing B-domain data users to preliminarily determine the building and unit to which the user belongs; Extract the set of BSSID identifiers of surrounding Wi-Fi access points detected at the user's indoor sampling point; The BSSID set is matched with the known Wi-Fi fingerprints of adjacent units of the target unit, and the similarity of wireless signal feature vectors is combined to finally determine the floor and room where the user is located.

7. An indoor 5G three-dimensional fingerprint database construction device, characterized in that, include: The data acquisition and parsing module is used to acquire the raw MRO data and corresponding signaling data of the 5G network measurement report, and parse it to obtain the user identifier, serving cell and neighboring cell wireless signal characteristics; The location acquisition module is used to acquire the user's actual location information and associate the user's actual location information with the user identifier; The critical point determination module is used to distinguish between indoor and outdoor sampling points based on the wireless signal characteristics, and to determine the critical point for the user to enter or exit the room based on the sudden change in wireless signal strength when the user enters or exits the room. The fingerprint database construction module is used to construct an indoor 5G three-dimensional fingerprint database for the corresponding building, unit, and floor based on the location information of the critical point and the actual location information of the user.

8. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored on the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the indoor 5G three-dimensional fingerprint database construction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the indoor 5G three-dimensional fingerprint database construction method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The method includes a computer program that, when executed by a processor, implements the steps of the indoor 5G three-dimensional fingerprint database construction method according to any one of claims 1 to 6.

Images