Level fingerprint-based positioning method, device and equipment, and storage medium

Abstract

The application discloses a positioning method and device based on a level fingerprint, equipment and a storage medium, relates to the technical field of communication, and comprises the following steps: starting 5G wireless measurement of a UE through a 4G base station, starting 4G wireless measurement of the UE through a 5G base station, receiving 4GMRO and 5GMRO collected by the 4G base station and the 5G base station respectively, and determining 5G outdoor wireless data under a 5G network based on the 4GMRO, 4G minimization of drive test data and the 5GMRO; dividing a region to be positioned into a plurality of grids with grid numbers according to longitude and latitude; mapping each signal parameter to each grid according to longitude and latitude information to obtain a 5G level fingerprint library. The application only needs to temporarily start the inter-system measurement function of the base station in the stage of collecting the level fingerprint library, receives the 4GMRO and the 5GMRO collected by the 4G base station and the 5G base station, does not need to start the inter-system measurement function of the base station in the stage of matching the level fingerprint library, reduces the influence on the user, the base station and OMC-R and other network equipment, and thus the load of positioning the user equipment through the 5G cellular network can be reduced.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a positioning method, apparatus, device and storage medium based on level fingerprinting. Background Technology

[0002] With the rapid development of wireless communication technology, positioning technology has been widely used in many fields, such as intelligent transportation, logistics tracking, and emergency rescue. Among them, positioning methods based on wireless signal characteristics have become a research hotspot due to their non-invasiveness and wide coverage.

[0003] Currently, common outdoor wireless positioning technologies mainly include GPS (Global Positioning System) positioning, cellular network positioning, and Wi-Fi-based positioning. GPS positioning relies on satellite signals. Although it has high accuracy, it is easily affected by obstructions in environments such as urban canyons and tunnels, leading to positioning failure or decreased accuracy. When positioning through 5G networks, the wireless characteristics of 4G are measured by 5G users through different systems. Positioning is performed using a level fingerprint database established by 4GMDT (Minimization Drive Test). However, this positioning method requires the 5G base station to keep 4G different system measurements running for a long time, which will increase the load on the UE (User Equipment). In addition, the extra collection of different system measurement data will increase the data processing overhead on both the base station side and the OMC-R (Operations and Maintenance Centre-Radio) side, leading to increased load.

[0004] Therefore, how to reduce the load on user equipment location via 5G cellular networks has become an urgent problem to be solved in this field.

[0005] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main objective of this application is to provide a positioning method, apparatus, device, and storage medium based on level fingerprinting, aiming to solve the technical problem of how to reduce the load of user equipment positioning through 5G cellular networks.

[0007] To achieve the above objectives, this application proposes a positioning method based on level fingerprinting, the method comprising:

[0008] Enable 5G wireless measurement of UE through 4G base station, and enable 4G wireless measurement of UE through 5G base station.

[0009] The system receives 4GMRO (Measurement Report of Original Type) and 5GMRO collected by 4G base stations and 5G base stations respectively, and determines 5G outdoor wireless data under the 5G network based on the 4GMRO, 4G minimized drive test data and the 5GMRO. The 5G outdoor wireless data includes latitude and longitude information and the signal parameters corresponding to the latitude and longitude information.

[0010] The area to be located is divided into multiple grids with grid numbers according to latitude and longitude;

[0011] Based on the latitude and longitude information, each of the signal parameters is mapped to each of the grids to obtain a 5G level fingerprint database, wherein the 5G level fingerprint database is used for positioning.

[0012] In one embodiment, the step of determining 5G outdoor wireless data under a 5G network based on the 4G MRO, 4G minimized drive test data, and the 5G MRO includes:

[0013] Acquire 4G wireless measurement data and 5G inter-system measurement data from the 4GMRO;

[0014] Determine the first latitude and longitude information corresponding to the 4G wireless measurement data from the acquired 4G minimized road test data;

[0015] The 5G signal parameters corresponding to the first latitude and longitude information in the 5G inter-system measurement data are used as the first 5G outdoor wireless data.

[0016] Acquire 4G heterogeneous system measurement data and 5G wireless measurement data in the 5G MRO;

[0017] Determine the second latitude and longitude information corresponding to the 4G inter-system measurement data from the 4G minimized road test data;

[0018] The 5G signal parameters corresponding to the second latitude and longitude information in the 5G wireless measurement data are used as the second 5G outdoor wireless data.

[0019] The first 5G outdoor wireless data and the second 5G outdoor wireless data are merged into 5G outdoor wireless data.

[0020] In one embodiment, the signal parameters include: network cell identifier and signal reception parameters;

[0021] After the step of mapping each of the signal parameters to each of the grids based on the latitude and longitude information to obtain the 5G level fingerprint database, the method further includes:

[0022] For each of the grids, calculate the mean and standard deviation of the signal reception parameters for each sample corresponding to each network cell identifier in the signal reception parameters;

[0023] The screening criteria are determined based on the mean and standard deviation.

[0024] Delete any abnormal signal receiving parameters in each of the sample signal receiving parameters that do not match the screening conditions in order to update the level fingerprint database.

[0025] In one embodiment, after the step of deleting abnormal signal reception parameters from each of the sample signal reception parameters that do not conform to the screening criteria to update the level fingerprint database, the method further includes:

[0026] If there are missing grids in each of the grids that do not contain signal parameters, then a data expansion model is established based on the signal parameters corresponding to each of the grids. The data expansion model is trained with the grid number as input and the signal parameters as labels.

[0027] The grid number of the missing grid is input into the data amplification model to obtain the predicted signal parameters of the missing grid, so as to complete the level fingerprint library.

[0028] In one embodiment, the step of establishing a data amplification model based on the signal parameters corresponding to each of the grids includes:

[0029] For each of the grids, the median of each signal reception parameter corresponding to each network cell identifier is determined to obtain the signal parameters of each sample.

[0030] Using the grid number as input and the sample signal parameters corresponding to each grid number as labels, the preset propagation model is trained to obtain the trained data amplification model.

[0031] In one embodiment, the method further includes:

[0032] The acquired 4G minimum road test data will be used to construct a 4G level fingerprint database;

[0033] Based on the same grid number in the 4G level fingerprint database and the 5G level fingerprint database, the 4G level fingerprint database and the 5G level fingerprint database are merged to obtain a hybrid level fingerprint database for positioning.

[0034] In one embodiment, after the step of mapping each of the signal parameters to each of the grids based on the latitude and longitude information to obtain the level fingerprint library, the method further includes:

[0035] Obtain the wireless network information of the target user, the wireless network information including: target network cell identifier and target signal reception parameters;

[0036] Multiple first target grids are obtained by filtering from the level fingerprint database, wherein the network cell identifier of the first target grid is the same as the target network cell identifier;

[0037] Calculate the similarity between the signal reception parameters of each first target grid and the target signal reception parameters;

[0038] The second target grid corresponding to the highest similarity is determined as the grid where the target user is located, in order to locate the target user.

[0039] Furthermore, to achieve the above objectives, this application also proposes a positioning device based on level fingerprinting, the positioning device based on level fingerprinting comprising:

[0040] The data acquisition module is used to enable 5G wireless measurement of the UE through a 4G base station and enable 4G wireless measurement of the UE through a 5G base station; receive 4GMRO and 5GMRO collected by the 4G base station and 5G base station respectively, and determine 5G outdoor wireless data under the 5G network based on the 4GMRO, 4G minimized drive test data and the 5GMRO, wherein the 5G outdoor wireless data includes latitude and longitude information and signal parameters corresponding to the latitude and longitude information;

[0041] The gridding module is used to divide the area to be located into multiple grids with grid numbers according to latitude and longitude;

[0042] The fingerprint database establishment module is used to map each of the signal parameters to each of the grids according to the latitude and longitude information to obtain a 5G level fingerprint database, wherein the 5G level fingerprint database is used for positioning.

[0043] In addition, to achieve the above objectives, this application also proposes an electronic device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the level fingerprint-based positioning method as described above.

[0044] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the level fingerprint-based positioning method described above.

[0045] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the level fingerprint-based positioning method described above.

[0046] This application provides a positioning method based on level fingerprinting. In the data acquisition phase, the UE's 5G wireless measurement is enabled by a 4G base station, and the UE's 4G wireless measurement is enabled by a 5G base station. The 4G GMRO and 5G GMRO collected by the 4G and 5G base stations are received. Based on the collected 4G GMRO, 4G minimum drive test data, and 5G GMRO, the 5G wireless measurement data can be determined, which includes latitude and longitude information and corresponding signal parameters. Then, when constructing the level fingerprint database, the area to be located is first divided into multiple grids with grid numbers according to latitude and longitude. Then, based on the latitude and longitude information in the 5G wireless measurement data, the signal parameters are mapped to the corresponding grids to obtain the 5G level fingerprint database. The user equipment in the area to be located can be located based on the 5G level fingerprint database.

[0047] In summary, this application only needs to briefly enable the inter-system measurement function of the base station during the stage of collecting the level fingerprint database to receive 4GMRO and 5GMRO collected by the 4G base station and 5G base station. During the stage of matching the level fingerprint database, the inter-system measurement function of the base station does not need to be enabled, which reduces the impact on users, base stations and network equipment such as OMC-R, thereby reducing the load of user equipment positioning through 5G cellular network. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart illustrating an embodiment of the positioning method based on level fingerprinting in this application.

[0051] Figure 2 This is a schematic diagram of a grid division scenario involved in an embodiment of the positioning method based on level fingerprinting in this application;

[0052] Figure 3 This is a flowchart illustrating the hybrid positioning process according to an embodiment of the positioning method based on level fingerprinting in this application.

[0053] Figure 4 This is a schematic diagram of the module structure of the positioning device based on level fingerprinting according to an embodiment of this application;

[0054] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the positioning method based on level fingerprinting in the embodiments of this application.

[0055] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0056] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0057] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0058] The main solution of this application embodiment is as follows: 5G wireless measurement of the UE is initiated through a 4G base station, and 4G wireless measurement of the UE is initiated through a 5G base station. 4GMRO and 5GMRO collected by the 4G and 5G base stations are received respectively. Based on the 4GMRO, 4G minimized drive test data, and the 5GMRO, 5G outdoor wireless data under the 5G network is determined. The 5G outdoor wireless data includes latitude and longitude information and signal parameters corresponding to the latitude and longitude information. The area to be located is divided into multiple grids with grid numbers according to latitude and longitude. Each signal parameter is mapped to each grid according to the latitude and longitude information to obtain a 5G level fingerprint database, which is used for positioning.

[0059] With the rapid development of wireless communication technology, positioning technology has been widely used in many fields, such as intelligent transportation, logistics tracking, and emergency rescue. Among them, positioning methods based on wireless signal characteristics have become a research hotspot due to their non-invasiveness and wide coverage.

[0060] Currently, common outdoor wireless positioning technologies mainly include GPS positioning, cellular network positioning, and Wi-Fi-based positioning. GPS positioning relies on satellite signals. Although it has high accuracy, it is easily affected by obstructions in environments such as cities, canyons, and tunnels, leading to positioning failure or decreased accuracy. When positioning through 5G networks, the wireless characteristics of 4G are measured by 5G users through different systems, and positioning is performed using a level fingerprint database established by 4GMDT. However, this positioning method requires the 5G base station to keep 4G different system measurements running for a long time, which will increase the load on the UE. In addition, the extra collection of different system measurement data will increase the data processing overhead on both the base station side and the OMC-R side, resulting in increased load.

[0061] Conventional indoor positioning methods based on 5G spatiotemporal big data collaboration mainly combine satellite positioning outside of the operator's mobile communication network with WIFI level fingerprinting for hybrid positioning. However, in complex environments such as high-density building clusters, tunnels, and under viaducts, satellite signals are easily blocked, resulting in a significant reduction in satellite positioning efficiency. In addition, given the high cost of WIFI network deployment and the fact that many user equipment (UE) devices do not enable WIFI, this solution is limited in its application for wide-area personnel positioning.

[0062] On the one hand, as for 5G outdoor positioning technology based on received signal strength (RSS), the challenge it faces is that the 5G radio level is affected by the adjustment of wireless parameters and is not a constant relationship with distance, which causes fluctuations in positioning accuracy.

[0063] On the other hand, 5G positioning strategies also attempt to utilize the inter-system measurement of 4G wireless characteristics by 5G user equipment, relying on the level fingerprint database built using 4G Minimum Drive Test (MDT) to complete the positioning. However, this strategy requires 5G base stations to continuously enable 4G inter-system measurement functions, which brings three adverse effects:

[0064] 1. Impaired User Experience: The UE needs to frequently perform additional inter-system measurements, which takes up data transmission time and reduces uplink and downlink rates. In areas with dynamically changing wireless environments, the system response speed slows down, which in turn affects key wireless performance indicators such as call success rate, call drop rate, handover success rate, and MR (Measurement Report) coverage, resulting in a significant decline in user experience.

[0065] 2. Decreased terminal battery life: Additional measurement tasks increase the load on the UE and shorten the device standby time, which is also detrimental to the user experience.

[0066] 3. Network efficiency is hampered: Base stations (including the Operation and Maintenance Center-R) need to process more measurement data from different systems, which increases the data processing load and the pressure on individual boards. In particular, high-load sites face operational risks, resulting in overall network efficiency being compromised.

[0067] Therefore, how to reduce the load on user equipment location via 5G cellular networks has become an urgent problem to be solved in this field.

[0068] To address the aforementioned issues, this application provides a positioning method based on level fingerprinting. In the data acquisition phase, 5G wireless measurement of the UE is initiated via a 4G base station, and 4G wireless measurement of the UE is initiated via a 5G base station. The 4GMRO and 5GMRO data collected by the 4G and 5G base stations are received. Based on the collected 4GMRO, 4G minimized drive test data, and 5GMRO, the 5G wireless measurement data can be determined, including latitude and longitude information and corresponding signal parameters. Then, when constructing the level fingerprint database, the area to be located is first divided into multiple grids with grid numbers according to latitude and longitude. Then, based on the latitude and longitude information in the 5G wireless measurement data, the signal parameters are mapped to the corresponding grids, thus obtaining the 5G level fingerprint database. The user equipment in the area to be located can be positioned using the 5G level fingerprint database.

[0069] In summary, this application only needs to briefly enable the inter-system measurement function of the base station during the stage of collecting the level fingerprint database to receive 4GMRO and 5GMRO collected by the 4G base station and 5G base station. During the stage of matching the level fingerprint database, the inter-system measurement function of the base station does not need to be enabled, which reduces the impact on users, base stations and network equipment such as OMC-R, thereby reducing the load of user equipment positioning through 5G cellular network.

[0070] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions. The following description uses an electronic device as an example to illustrate this embodiment and the subsequent embodiments.

[0071] Based on this, embodiments of this application provide a positioning method based on level fingerprinting, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the positioning method based on level fingerprinting in this application.

[0072] In this embodiment, the positioning method based on level fingerprinting includes steps S10 to S30:

[0073] Step S10: Enable 5G wireless measurement of UE through 4G base station, and enable 4G wireless measurement of UE through 5G base station. Receive 4GMRO and 5GMRO collected by 4G base station and 5G base station respectively, and determine 5G outdoor wireless data under 5G network based on 4GMRO, 4G minimized drive test data and 5GMRO. The 5G outdoor wireless data includes latitude and longitude information and signal parameters corresponding to the latitude and longitude information.

[0074] In this embodiment, when establishing the level fingerprint database, the UE's 5G wireless measurement function is first enabled through the 4G base station, and the UE's 4G wireless measurement function is enabled through the 5G base station. Then, it is necessary to collect 4GMRO and 4G minimized drive test data from the DPI (Deep Packet Inspection) system, and collect 5GMRO from the DPI system. The two collection methods are combined to simultaneously determine the 5G outdoor wireless data with latitude and longitude information and signal parameters.

[0075] Furthermore, in a feasible implementation, the step of determining the 5G outdoor wireless data under the 5G network based on the 4GMRO and the 5GMRO in step S10 above may include steps S11 to S17:

[0076] Step S11: Obtain 4G wireless measurement data and 5G inter-system measurement data from the 4GMRO;

[0077] In this embodiment, 4G wireless measurement data and 5G inter-system measurement data are separated from the MRO data collected from the 4G base station. The 4G wireless measurement data is the UE's signal measurement of the 4G network itself, while the 5G inter-system measurement data is the UE's measurement of the 5G signal.

[0078] Step S12: Determine the first latitude and longitude information corresponding to the 4G wireless measurement data from the acquired 4G minimized road test data;

[0079] It should be noted that, in this embodiment, the 4G minimized drive test data typically includes the geographical location (latitude and longitude) of the device at the time of data collection, the 4G serving cell ECI (E-UTRANCellIdentifier), the 4G neighboring cell Earfcn (E-UTRAAbsoluteRadioFrequencyChannelNumber), and the PCI (PhysicalCellIdentifier), as well as the RSRP (ReferenceSignalReceivingPower) and RSRQ (ReferenceSignalReceivingQuality) of the 4G serving cell and neighboring cells. By matching the 4G wireless measurement data with the minimized drive test data, the first latitude and longitude information corresponding to each 4G wireless measurement data is determined.

[0080] Step S13: Use the 5G signal parameters corresponding to the first latitude and longitude information in the 5G inter-system measurement data as the first 5G outdoor wireless data.

[0081] In this embodiment, using the obtained first latitude and longitude information, 5G signal parameters with the same or similar latitude and longitude are filtered from the 5G inter-system measurement data as the first 5G outdoor wireless data. Specifically, 4G wireless measurement data is compared with 4GMDT to obtain the latitude and longitude information reported by the user within the 4GMDT of the same time, the same UE, and the same 4G serving cell. The 5G level characteristics obtained by the UE from the corresponding 4GMDT data for 5G inter-system measurement are then used as the collected 5G wireless data. The first 5G outdoor wireless data includes Earfcn and PCI, RSRP and RSRQ of the 4G serving cell and neighboring cells. Matching with 4GMDT yields latitude and longitude, 5G neighboring cell NCI (NRCellIdentifier, 5G network cell identifier), RSRP, and RSRQ.

[0082] Step S14: Obtain 4G inter-system measurement data and 5G wireless measurement data in the 5G GMRO;

[0083] In this embodiment, similarly, 4G inter-system measurement data and 5G wireless measurement data are separated from the MRO data collected from the 5G base station. The 5G wireless measurement data is the UE's signal measurement of the 5G network itself, while the 4G inter-system measurement data is the UE's measurement of the 4G signal.

[0084] Step S15: Determine the second latitude and longitude information corresponding to the 4G inter-system measurement data from the 4G minimized road test data;

[0085] In this embodiment, the second latitude and longitude information corresponding to each 4G inter-system measurement data is determined by matching the 4G inter-system measurement data in 5GMRO with the 4G minimized drive test data.

[0086] Step S16: Use the 5G signal parameters corresponding to the second latitude and longitude information in the 5G wireless measurement data as the second 5G outdoor wireless data;

[0087] In this embodiment, based on the obtained second latitude and longitude information, 5G signal parameters with the same or similar latitude and longitude are selected from the 5G wireless measurement data as the second 5G outdoor wireless data. Specifically, the 4G inter-system wireless measurement data is compared with the 4GMDT to obtain the latitude and longitude information reported by the user within the 4GMDT of the same time, the same UE, and the same 4G serving cell. The 5G level characteristics obtained by the UE from the corresponding 5GMDT data are then used as the collected 5G wireless data. The second 5G outdoor wireless data includes: Earfcn and PCI, RSRP and RSRQ of the 4G neighboring cell. By matching with the 4GMDT, latitude and longitude, 5G serving cell and neighboring cell NCI, RSRP, and RSRQ are obtained.

[0088] Step S17: Combine the first 5G outdoor wireless data and the second 5G outdoor wireless data into 5G outdoor wireless data.

[0089] In this embodiment, the two sets of 5G outdoor wireless data are merged to form a complete 5G outdoor wireless dataset. Since 4GMDT is a subset of 4GMRO, 4GMDT and 4GMRO (including 5G neighbor cell level characteristics) of the same time, the same user, and the same 4G serving cell can be matched. This method can obtain 5G wireless feature data with accurate latitude and longitude information. The 5G level fingerprint database constructed using this method can achieve positioning accuracy comparable to 4GMDT.

[0090] Step S20: Divide the area to be located into multiple grids with grid numbers according to latitude and longitude;

[0091] In this embodiment, the region is divided into multiple grids according to latitude and longitude, and each grid is assigned a unique grid number to facilitate subsequent data management and analysis.

[0092] As an example, please refer to Figure 2 , Figure 2 This is a schematic diagram of a grid division scenario involved in an embodiment of the positioning method based on level fingerprinting of this application, as shown below. Figure 2 As shown, if the positioning accuracy is 10 meters, the grid size of the level fingerprint database is set to 1 / 2 of the grid side length (10 meters), that is, the size of each grid is 5*5 meters. The grid numbered 10*10 is divided into 4 5*5 grids. The area to be positioned is gridded according to latitude and longitude, assuming to be M*N grids.

[0093] Step S30: Map each of the signal parameters to each of the grids according to the latitude and longitude information to obtain a 5G level fingerprint database, wherein the 5G level fingerprint database is used for positioning.

[0094] In this embodiment, based on the range of latitude and longitude included in the grid, the grid to which each latitude and longitude information belongs is found, and then the signal parameters corresponding to the latitude and longitude information are mapped to the grid to which they belong, forming a 5G level fingerprint database. This fingerprint database contains key information such as signal strength and propagation characteristics in each grid, which is used for subsequent positioning and identification.

[0095] As an example, specifically, the collected data needs to be preprocessed to meet the field list requirements for establishing a level fingerprint library.

[0096] For outdoor scenarios, since 4GMDT does not contain 4G neighbor cell ECI information, and 4G / 5GMRO does not contain 4G / 5G serving cell and neighbor cell ECI / NCI information, it is necessary to use the Earfcn, PCI, and ECI mapping relationship in the engineering parameters (4G base station cell list) to map the Earfcn and PCI of the 4G serving cell and neighbor cell to their ECI, and the NR-Arfcn, PCI, and NCI mapping relationship in the engineering parameters (5G base station cell list) to map the NR-Arfcn and PCI of the 5G serving cell and neighbor cell to their NCI. The engineering parameters (4G base station cell list and 5G base station cell list) can be obtained from the operator's network optimization department; the 4GMDT, 4GMRO, and 5GMRO data can be collected through the operator's DPI system.

[0097] Finally, based on latitude and longitude, the area to be located is gridded according to half the side length of the grid (assuming 10 meters) (5 meters), and ECI / NCI, RSRP, RSRQ and other data are mapped into different grids.

[0098] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description and will not be repeated hereafter. In addition, the signal parameters include: network cell identifier and signal reception parameters;

[0099] Following step S30 described above, the method may further include steps A10 to A30:

[0100] Step A10: For each of the grids, calculate the mean and standard deviation of the signal reception parameters of each sample corresponding to each network cell identifier in the signal reception parameters;

[0101] In this embodiment, for each grid in the level fingerprint database, the signal reception parameters (such as RSSI, RSRP, etc.) corresponding to all network cell identifiers in the grid are traversed. Statistical analysis is performed on all sample signal reception parameters under each network cell identifier, and their mean and standard deviation are calculated. The mean reflects the average signal strength or quality of the network cell in the grid, while the standard deviation reflects the fluctuation range of the signal strength.

[0102] Step A20: Determine the screening criteria based on the mean and standard deviation;

[0103] In this embodiment, reasonable screening criteria are set based on the calculated mean and standard deviation, according to the actual situation. These criteria are usually based on statistical principles, such as setting a threshold such that the signal reception parameters falling within a certain multiple of the standard deviation of the mean are considered reasonable.

[0104] Filtering criteria may include: minimum or maximum values ​​of signal receiving parameters, or the range of deviation from the mean.

[0105] Step A30: Delete abnormal signal receiving parameters in each of the sample signal receiving parameters that do not match the screening conditions, so as to update the level fingerprint database.

[0106] In this embodiment, based on the determined filtering conditions, each grid in the level fingerprint database is traversed, and all sample signal reception parameters under each network cell identifier are checked. Abnormal signal reception parameters that do not meet the filtering conditions are deleted. These parameters may be due to measurement errors, equipment failures, or environmental factors. Finally, an updated level fingerprint database is obtained, ensuring that it contains only reliable signal reception parameters that meet the filtering conditions.

[0107] As an example, after obtaining the level fingerprint database, when cleaning the data in the level fingerprint database, data outside the RSRP / RSRQ value range and empty data within the same grid and for the same ECI / NCI are removed. Then, the standard deviation σ of the normal distribution is calculated using the following formula:

[0108]

[0109] Where N is the number of RSRP / RSRQ samples collected from the same ECI / NCI within the same grid, and X i σ is the RSRP / RSRQ value of the sample, μ is the mean of RSRP / RSRQ of the same ECI / NCI collected in the same grid, and σ is the standard deviation of RSRP / RSRQ of the same ECI / NCI collected in the same grid.

[0110] Retain sample data with RSRP / RSRQ within 3 standard deviations (±3σ), i.e. retain and remove extreme values ​​caused by random factors.

[0111] By following the steps above, setting filtering conditions and deleting abnormal signal receiving parameters, the data quality of the level fingerprint database can be significantly improved, and the positioning error caused by data abnormalities can be reduced.

[0112] Furthermore, in one feasible implementation, after step A30 described above, the method may further include steps A40 to A50:

[0113] Step A40: If there are missing grids in each of the grids that do not contain signal parameters, then a data expansion model is established based on the signal parameters corresponding to each of the grids. The data expansion model is trained with the grid number as input and the signal parameters as labels.

[0114] In this embodiment, the level fingerprint database is checked to see if each grid contains signal parameters. If a grid does not contain signal parameters, i.e., a missing grid, data augmentation is required. The data augmentation model is a machine learning-based prediction model. Its input is the grid number, and its output is the predicted signal parameters. This model is built by training on existing grid data containing signal parameters. During the training process, the model learns the mapping relationship between grid numbers and signal parameters, thereby enabling it to predict the signal parameters of missing grids.

[0115] Step A50: Input the grid number of the missing grid into the data amplification model to obtain the predicted signal parameters of the missing grid, so as to complete the level fingerprint database.

[0116] In this embodiment, for each missing grid cell, its grid number is used as input to a pre-trained data augmentation model. The model outputs predicted signal parameters based on the input grid number. These predicted signal parameters are derived from the mapping relationship between grid numbers and signal parameters learned by the model. These predicted signal parameters are added to the missing grid cells to complete the level fingerprint database. Thus, each grid cell in the level fingerprint database will contain signal parameters, providing more complete data support for subsequent localization algorithms.

[0117] Furthermore, in a feasible implementation, step A40 above may further include steps A41 to A42:

[0118] Step A41: For each of the grids, determine the median of each signal reception parameter corresponding to each network cell identifier to obtain the signal parameters of each sample.

[0119] In this embodiment, each grid in the level fingerprint database is traversed. For each network cell identifier in each grid, the median of all signal reception parameters corresponding to it is calculated. Compared with the mean, the median is more robust to outliers and can provide a more stable signal strength representation. The calculated median is used as the sample signal parameters under that grid and that network cell identifier. These medians constitute the labels required for the training data expansion model.

[0120] Step A42: Using the grid number as input and the sample signal parameters corresponding to each grid number as labels, train the preset propagation model to obtain the trained data amplification model.

[0121] In this embodiment, the grid number is used as the input feature, and the sample signal parameter (i.e., median) corresponding to each grid number is used as the label. The preset propagation model (such as a regression model based on machine learning, a neural network, etc.) is trained. During the training process, the model learns the mapping relationship between the grid number and the signal parameter. After the training is completed, the trained data expansion model is obtained. This model can predict the signal parameter of the missing grid based on the grid number.

[0122] For example, due to limitations in data collection, outdoor areas are generally on roads, so the fingerprint database cannot guarantee that all areas are tested, and the fingerprint database needs to be supplemented. Model training uses the local fingerprint database to train the propagation model to obtain a propagation model that most closely approximates the real wireless environment. Then, this model is used to calculate the RSRP and RSRQ strength of each cell in all grids.

[0123] The median of multiple RSRP and RSRQ data after data cleaning is taken to generate a training set, which is then fed into a radial basis function neural network (RBF) to expand the level fingerprint database.

[0124] Taking an indoor scene with M 5*5 meter grids and N layers of height as an example (assuming 1 main cell and 2 neighboring cells), the training set is as follows:

[0125] enter:

[0126] {Horizontal grid number ID1, Vertical height number ID1};

[0127] ...

[0128] {Horizontal grid number ID1, Vertical height number ID} n};

[0129] {Horizontal grid number ID2, vertical height number ID1};

[0130] ...

[0131] {Horizontal grid number ID} m Vertical height ID n} ;

[0132] Output:

[0133] {ECI / NCI 111 RSRP 111 RSRQ 111}, {ECI / NCI 112 RSRP 112 RSRQ 112}, {ECI / NCI 113 RSRP 113 RSRQ 113};

[0134] ...

[0135] {ECI / NCI 1n1 RSRP 1n1 RSRQ 1n1}, {ECI / NCI 1n2 RSRP 1n2 RSRQ 1n2}, {ECI / NCI 1n3 RSRP 1n3 RSRQ 1n3};

[0136] {ECI / NCI 211 RSRP 211 RSRQ 211}, {ECI / NCI 212 RSRP 212 RSRQ 212}, {ECI / NCI 213 RSRP 213 RSRQ 213};

[0137] ...

[0138] {ECI / NCI mn1 RSRP mn1 RSRQ mn1}, {ECI / NCI mn2 RSRP mn2 RSRQ mn2}, {ECI / NCI mn3 RSRP mn3 RSRQ mn3};

[0139] The data for some of the grids mentioned above may be missing. Assuming that m*n grids (m≤M, n=N) level fingerprints are actually collected, the data can be supplemented after training to form a complete M*N level fingerprint database.

[0140] 80% of the collected dataset was used for training, and 20% was used for testing.

[0141] The training algorithm for Radial Basis Function (RBF) neural networks is as follows:

[0142] The Radial Basis Functions (RBF) neural network has 2 neurons in its input layer (horizontal grid ID, vertical height ID) and 3*3 neurons in its output layer (3 sets of ECI / NCI, RSRP, and RSRQ data). The hidden layers consist of radial basis functions that transform the input space to the hidden layer space. The model is trained using m*n*80% of vectors, and its accuracy is estimated by testing the trained model on m*n*20% of vectors.

[0143] After the radial basis function (RBF) neural network is trained, the missing {horizontal grid number ID} will be... x Vertical height ID y} as input, and obtain {ECI / NCI} through a radial basis function neural network (RBF). xy1 RSRP xy1 RSRQ xy1}, {ECI / NCI xy2 RSRP xy2 RSRQ xy2}, {ECI / NCI xy3 RSRP xy3 RSRQ xy3}

[0144] Once all the missing grid data is filled in, the level fingerprint library is established.

[0145] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to the first and / or second embodiments described above can be referred to the above description and will not be repeated hereafter. Furthermore, the method may further include steps B10 to B20:

[0146] Step B10: Construct a 4G level fingerprint database from the acquired 4G minimized road test data;

[0147] In this embodiment, similar to the construction method of the 5G level fingerprint database, for 4G user positioning, 4GMDT includes latitude and longitude and 4G wireless characteristics, which can be used to build a level fingerprint database. First, 4GMDT data is collected, and the data is cleaned and expanded to build a 4G outdoor level fingerprint database. The 4G radio levels contained in the UEMR / MRO of the 4G user are matched with the 4G outdoor level fingerprint database, and the positioning result is output.

[0148] Step B20: Based on the same grid number in the 4G level fingerprint database and the 5G level fingerprint database, merge the 4G level fingerprint database and the 5G level fingerprint database to obtain a hybrid level fingerprint database for positioning.

[0149] In this embodiment, a level fingerprint database is first created for both 4G outdoor and 5G outdoor applications. Then, based on the same horizontal grid number and vertical height number, the 4G outdoor level fingerprint database and the 5G outdoor level fingerprint database are merged into a 4G / 5G hybrid level fingerprint database.

[0150] It should be understood that the methods for establishing the aforementioned 4G outdoor level fingerprint database and 5G outdoor level fingerprint database are not limited to the methods proposed in this application, but can employ any method in the prior art. By merging the 4G and 5G outdoor level fingerprint databases into a 4G / 5G hybrid level fingerprint database, more accurate positioning results can be obtained due to the significantly increased number of serving cells and neighboring cells within the 4G and 5G wireless measurement data.

[0151] As an example, specifically, please refer to Figure 3 , Figure 3 This is a flowchart illustrating the hybrid positioning process according to an embodiment of the positioning method based on level fingerprinting in this application. Figure 3 As shown, when constructing a hybrid level fingerprint database for positioning, 4G outdoor wireless data is first collected. Based on this data, a 4G outdoor level fingerprint database is constructed. Then, the 4G base station enables 5G wireless measurement of the UE, collecting 4G and 5G wireless measurement data from the DPI system's 4GMRO. The 4G wireless measurement data is compared with the 4GMDT to obtain the latitude and longitude information reported by the user within the 4GMDT for the same time, the same UE, and the same 4G serving cell. The 5G level characteristics obtained by the UE from the corresponding 4GMRO for 5G inter-system measurement are used as the collected 5G wireless data. Simultaneously, the 5G base station enables 4G wireless measurement of the UE, collecting 4G and 5G wireless measurement data from the DPI system's 5GMRO. The 4G inter-system wireless measurement data is compared with the 4GMDT to obtain the latitude and longitude information reported by the user within the 4GMDT for the same time, the same UE, and the same 4G serving cell. The 5G level characteristics obtained by the UE from the corresponding 5GMRO for 5G measurement are used as the collected 5G wireless data. Then, a 5G outdoor level fingerprint database is jointly constructed, and a 4G / 5G hybrid level fingerprint database is also constructed. During positioning, the database is matched, and the positioning result is finally output.

[0152] Based on the first to third embodiments of this application, in the fourth embodiment of this application, the content that is the same as or similar to the first to third embodiments described above can be referred to the above description and will not be repeated hereafter. Furthermore, after step S30 above, the method may further include steps C10 to C40:

[0153] Step C10: Obtain the wireless network information of the target user, wherein the wireless network information includes: target network cell identifier and target signal reception parameters;

[0154] In this embodiment, wireless network information is obtained from the target user's device (such as a smartphone, tablet, etc.). This information includes, but is not limited to, the target network cell identifier and the target signal reception parameters (such as RSSI, RSRP, etc.).

[0155] Step C20: Multiple first target grids are obtained by filtering from the level fingerprint database, wherein the network cell identifier of the first target grid is the same as the target network cell identifier;

[0156] In this embodiment, based on the target network cell identifier, all grids with the same network cell identifier are selected from the level fingerprint database and used as the first target grid set.

[0157] Step C30: Calculate the similarity between the signal reception parameters of each of the first target grids and the target signal reception parameters;

[0158] In this embodiment, for each first target grid, the similarity between its signal reception parameters (such as the stored median, mean, etc.) and the signal reception parameters reported by the target user equipment is calculated. The similarity can be calculated using various methods, such as Euclidean distance, cosine similarity, etc.

[0159] Step C40: The second target grid corresponding to the highest similarity of the target is determined as the grid where the target user is located, so as to locate the target user.

[0160] In this embodiment, among all the first target grids, the grid with the highest similarity is selected as the grid where the target user is located (i.e., the second target grid), and this grid will be used as the final location result of the target user.

[0161] Specifically, as an example, when locating a user, the wireless network in which the user is located is first determined based on the RATType. If it is a 4G network, coarse location at the base station cell level is achieved based on the ECI of the XDR of the S1-MME interface of the DPI system; if it is a 5G network, coarse location at the base station cell level is achieved based on the NCI of the XDR of the N1 / N2 interface of the DPI system.

[0162] If the UE reports UEMR / MRO during the statistical period, then based on the engineering parameters, the Earfcn / NR-ArfcnID and PCI of the DPI system UEMR / MRO are mapped to ECI / NCI.

[0163] Data containing ECI / NCI in the serving cell and neighboring cells of the level fingerprint database are filtered out to form a subset of the fingerprint database.

[0164] Based on the KNN (K-nearest neighbor), WKNN (weighted K-nearest neighbor), and EWKNN (Enhanced Weighted K-nearest Neighbors) localization algorithms, level fingerprint matching is performed on the MR to accurately locate the latitude and longitude of the MR.

[0165] Among the three algorithms, KNN, WKNN, and EWKNN, EWKNN has the best performance; the smaller the fingerprint spacing, the higher the positioning accuracy, but the greater the workload.

[0166] The fingerprint database matching principle is as follows:

[0167] (1) Fingerprint database data matching generally adopts the standard algorithm of pattern matching.

[0168] (2) Fingerprint matching principle: Select the grid that is most “similar” to the fingerprint database in MR.

[0169] (3) Similarity can be evaluated by the signal strength of the cell in MR and the LSQ (sum of square difference) of the fingerprint database. The smaller the value, the higher the similarity. The center coordinates of the K grids with the smallest LSQ are the location of the mobile phone.

[0170] (4) If the Euclidean distance between this MR and all points in the fingerprint database is greater than the preset threshold, it means that this MR cannot be found in the fingerprint database and other positioning methods need to be used.

[0171] As an example, when using the EWKNN algorithm, D is selected based on WKNN. i For reference points whose values ​​are less than the threshold R0, assuming there are G such points, we will use G Euclidean distance values ​​D. i The values ​​are sorted in ascending order, and L is defined. i If L is equal to the difference between D1 and Ds (s = 2, 3, ..., G), then L i The average value is:

[0172]

[0173] L i Compare with E(L), and put L i After removing reference points with values ​​greater than the average E(L), the remaining number of reference points is K. The WKNN algorithm is then used to calculate the coordinates of the point to be located using these K reference points, thus dynamically selecting the value of K, i.e., the number of reference points. If the Euclidean distance D between the base station signal strength of different matched reference points and the base station signal strength of the point to be located is... i If all values ​​are less than the threshold, then EWKNN is equivalent to WKNN.

[0174] The EWKNN algorithm flow is as follows:

[0175] Calculate the Euclidean distance between the fingerprint data and the location point data at each location using the following formula:

[0176]

[0177] Among them, RSRP i RSRQ i This represents the RSRP and RSRQ values ​​of the i-th base station cell collected at the location point. This represents the RSRP and RSRQ feature values ​​of the i-th base station cell in the level fingerprint database. Assuming the level fingerprint database has RSRP and RSRQ feature values ​​of 1 primary cell and 2 neighboring cells, but actually reports RSRP and RSRQ values ​​of 3 4G or 5G cells, then n = 3.

[0178] By selecting a threshold R0, we obtain the set of elements whose distance is less than R0.

[0179] Select the location fingerprint data from the final set, take the reciprocal of the distance for weighting, and calculate the location coordinates of the positioning point.

[0180] Input data example:

[0181] {{ECI1 / NCI1, RSRP1, RSRQ1}, {ECI2 / NCI2, RSRP2, RSRQ2}, {ECI3 / NCI3, RSRP3, RSRQ3}};

[0182] Output example:

[0183] {Horizontal grid number ID, Vertical height number ID};

[0184] Currently, 4G base stations typically do not enable 5G wireless measurement for UEs, and 5G base stations do not enable 4G wireless measurement for UEs. In this case, the 4G or 5G radio level within the 4G UEMR / MRO or 5G UEMR / MRO can be matched with the 4G or 5G level fingerprint features in the 4G / 5G hybrid level fingerprint database to obtain the location result. Therefore, during the level fingerprint matching stage, cross-system measurement can be performed without enabling the base station, reducing the impact on users, base stations, and network equipment such as OMC-R.

[0185] During the level fingerprint database matching stage, if the 4G base station enables UE's 5G radio measurement and the 5G base station enables UE's 4G radio measurement, the 4G / 5G UEMR / MRO will simultaneously report 4G and 5G radio measurement data. Compared to when the base station does not enable inter-system measurement, the number of serving cells and neighboring cells in the 4G and 5G radio measurement data increases exponentially. According to actual tests, the positioning error is inversely proportional to the number of serving cells and neighboring cells in the radio measurement data. Therefore, when inter-system measurement is enabled, matching the data with the 4G / 5G hybrid level fingerprint database will yield more accurate positioning results.

[0186] If multiple location results occur within a statistical period, the location result of the last time point is taken based on the TimeStamp parameter of UEMR / MRO.

[0187] Since the level fingerprint database is gridded according to half (5 meters) of the positioning accuracy (assuming 10 meters), the positioning result needs to be restored when the final output is given. That is, every 4 5*5 meter grids are mapped to 1 10*10 meter grid, and the latitude and longitude of the center point of the 10*10 meter grid is the positioning result.

[0188] To further improve positioning accuracy, the final positioning result can be corrected using a Bayesian filter. Bayesian filters are a class of methods for state estimation based on Bayes' theorem, including Kalman filtering, extended Kalman filtering, and particle filtering. By fusing prior information with current observations, positioning accuracy can be improved.

[0189] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the positioning method based on level fingerprinting in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0190] This application also provides a positioning device based on level fingerprinting, please refer to... Figure 4 The positioning device based on level fingerprinting includes:

[0191] The data acquisition module 10 is used to enable 5G wireless measurement of the UE through a 4G base station and enable 4G wireless measurement of the UE through a 5G base station; receive 4GMRO and 5GMRO collected by the 4G base station and 5G base station respectively, and determine 5G outdoor wireless data under the 5G network based on the 4GMRO, 4G minimized drive test data and the 5GMRO, wherein the 5G outdoor wireless data includes latitude and longitude information and signal parameters corresponding to the latitude and longitude information;

[0192] The gridding module 20 is used to divide the area to be located into multiple grids with grid numbers according to latitude and longitude.

[0193] The fingerprint database establishment module 30 is used to map each of the signal parameters to each of the grids according to the latitude and longitude information to obtain a 5G level fingerprint database, wherein the 5G level fingerprint database is used for positioning.

[0194] Optionally, the data acquisition module 10 is also used for:

[0195] Acquire 4G wireless measurement data and 5G inter-system measurement data from the 4GMRO;

[0196] Determine the first latitude and longitude information corresponding to the 4G wireless measurement data from the acquired 4G minimized road test data;

[0197] The 5G signal parameters corresponding to the first latitude and longitude information in the 5G inter-system measurement data are used as the first 5G outdoor wireless data.

[0198] Acquire 4G heterogeneous system measurement data and 5G wireless measurement data in the 5G MRO;

[0199] Determine the second latitude and longitude information corresponding to the 4G inter-system measurement data from the 4G minimized road test data;

[0200] The 5G signal parameters corresponding to the second latitude and longitude information in the 5G wireless measurement data are used as the second 5G outdoor wireless data.

[0201] The first 5G outdoor wireless data and the second 5G outdoor wireless data are merged into 5G outdoor wireless data.

[0202] Optionally, the signal parameters include: network cell identifier and signal reception parameters; the level fingerprint-based positioning device is also used for:

[0203] For each of the grids, calculate the mean and standard deviation of the signal reception parameters for each sample corresponding to each network cell identifier in the signal reception parameters;

[0204] The screening criteria are determined based on the mean and standard deviation.

[0205] Delete any abnormal signal receiving parameters in each of the sample signal receiving parameters that do not match the screening conditions in order to update the level fingerprint database.

[0206] Optionally, the level fingerprint-based positioning device is also used for:

[0207] If there are missing grids in each of the grids that do not contain signal parameters, then a data expansion model is established based on the signal parameters corresponding to each of the grids. The data expansion model is trained with the grid number as input and the signal parameters as labels.

[0208] The grid number of the missing grid is input into the data amplification model to obtain the predicted signal parameters of the missing grid, so as to complete the level fingerprint library.

[0209] Optionally, the level fingerprint-based positioning device is also used for:

[0210] For each of the grids, the median of each signal reception parameter corresponding to each network cell identifier is determined to obtain the signal parameters of each sample.

[0211] Using the grid number as input and the sample signal parameters corresponding to each grid number as labels, the preset propagation model is trained to obtain the trained data amplification model.

[0212] Optionally, the level fingerprint-based positioning device is also used for:

[0213] The acquired 4G minimum road test data will be used to construct a 4G level fingerprint database;

[0214] Based on the same grid number in the 4G level fingerprint database and the 5G level fingerprint database, the 4G level fingerprint database and the 5G level fingerprint database are merged to obtain a hybrid level fingerprint database for positioning.

[0215] Optionally, the level fingerprint-based positioning device is also used for:

[0216] Obtain the wireless network information of the target user, the wireless network information including: target network cell identifier and target signal reception parameters;

[0217] Multiple first target grids are obtained by filtering from the level fingerprint database, wherein the network cell identifier of the first target grid is the same as the target network cell identifier;

[0218] Calculate the similarity between the signal reception parameters of each first target grid and the target signal reception parameters;

[0219] The second target grid corresponding to the highest similarity is determined as the grid where the target user is located, in order to locate the target user.

[0220] The positioning device based on level fingerprinting provided in this application, employing the level fingerprinting-based positioning method in the above embodiments, can solve the technical problem of how to reduce the load on user equipment positioning via 5G cellular networks. Compared with the prior art, the beneficial effects of the positioning device based on level fingerprinting provided in this application are the same as those of the level fingerprinting-based positioning method provided in the above embodiments, and other technical features in the positioning device based on level fingerprinting are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0221] This application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the level fingerprint-based positioning method in Embodiment 1 above.

[0222] The following is for reference. Figure 5 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of this application. The electronic devices in these embodiments may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0223] like Figure 5 As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. While electronic devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0224] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0225] The electronic device provided in this application, employing the level fingerprint-based positioning method in the above embodiments, can solve the technical problem of how to reduce the load on user equipment positioning via 5G cellular networks. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the level fingerprint-based positioning method provided in the above embodiments, and other technical features of this electronic device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0226] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0227] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0228] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the level fingerprint-based positioning method in the above embodiments.

[0229] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0230] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0231] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to:

[0232] The system receives 4GMRO and 5GMRO collected by 4G base stations and 5G base stations respectively, and determines 5G outdoor wireless data under the 5G network based on the 4GMRO, 4G minimized drive test data and the 5GMRO. The 5G outdoor wireless data includes latitude and longitude information and signal parameters corresponding to the latitude and longitude information.

[0233] The area to be located is divided into multiple grids with grid numbers according to latitude and longitude;

[0234] Based on the latitude and longitude information, each of the signal parameters is mapped to each of the grids to obtain a 5G level fingerprint database, wherein the 5G level fingerprint database is used for positioning.

[0235] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0236] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0237] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0238] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described level fingerprint-based positioning method, thereby solving the technical problem of how to reduce the load on user equipment positioning via 5G cellular networks. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the level fingerprint-based positioning method provided in the above embodiments, and will not be repeated here.

[0239] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the level fingerprint-based positioning method described above.

[0240] The computer program product provided in this application can solve the technical problem of how to reduce the load of user equipment positioning through 5G cellular networks. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the positioning method based on level fingerprint provided in the above embodiments, and will not be repeated here.

[0241] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A positioning method based on level fingerprinting, characterized in that, The method includes: Enable 5G wireless measurement of UE through 4G base station, and enable 4G wireless measurement of UE through 5G base station. The system receives 4G MRO and 5G MRO collected by 4G base stations and 5G base stations respectively, and determines 5G outdoor wireless data under the 5G network based on the 4G MRO, 4G minimized drive test data and the 5G MRO. The 5G outdoor wireless data includes latitude and longitude information and signal parameters corresponding to the latitude and longitude information. The area to be located is divided into multiple grids with grid numbers according to latitude and longitude; Based on the latitude and longitude information, each of the signal parameters is mapped to each of the grids to obtain a 5G level fingerprint database, wherein the 5G level fingerprint database is used for positioning.

2. The positioning method based on level fingerprint as described in claim 1, characterized in that, The step of determining 5G outdoor wireless data under the 5G network based on the 4G MRO, 4G minimized drive test data and the 5G MRO includes: Acquire 4G wireless measurement data and 5G inter-system measurement data from the 4G MRO; Determine the first latitude and longitude information corresponding to the 4G wireless measurement data from the acquired 4G minimized road test data; The 5G signal parameters corresponding to the first latitude and longitude information in the 5G inter-system measurement data are used as the first 5G outdoor wireless data. Acquire 4G inter-system measurement data and 5G wireless measurement data in the 5G MRO; Determine the second latitude and longitude information corresponding to the 4G inter-system measurement data from the 4G minimized road test data; The 5G signal parameters corresponding to the second latitude and longitude information in the 5G wireless measurement data are used as the second 5G outdoor wireless data. The first 5G outdoor wireless data and the second 5G outdoor wireless data are merged into 5G outdoor wireless data.

3. The positioning method based on level fingerprint as described in claim 1, characterized in that, The signal parameters include: network cell identifier and signal reception parameters; After the step of mapping each of the signal parameters to each of the grids based on the latitude and longitude information to obtain the 5G level fingerprint database, the method further includes: For each of the grids, calculate the mean and standard deviation of the signal reception parameters for each sample corresponding to each network cell identifier in the signal reception parameters; The screening criteria are determined based on the mean and standard deviation. Delete any abnormal signal receiving parameters in each of the sample signal receiving parameters that do not match the screening conditions in order to update the level fingerprint database.

4. The positioning method based on level fingerprint as described in claim 3, characterized in that, After the step of deleting abnormal signal reception parameters from each of the sample signal reception parameters that do not meet the screening criteria to update the level fingerprint database, the method further includes: If there are missing grids in each of the grids that do not contain signal parameters, then a data expansion model is established based on the signal parameters corresponding to each of the grids. The data expansion model is trained with the grid number as input and the signal parameters as labels. The grid number of the missing grid is input into the data amplification model to obtain the predicted signal parameters of the missing grid, so as to complete the level fingerprint library.

5. The positioning method based on level fingerprint as described in claim 4, characterized in that, The step of establishing a data amplification model based on the signal parameters corresponding to each of the grids includes: For each of the grids, the median of each signal reception parameter corresponding to each network cell identifier is determined to obtain the signal parameters of each sample. Using the grid number as input and the sample signal parameters corresponding to each grid number as labels, the preset propagation model is trained to obtain the trained data amplification model.

6. The positioning method based on level fingerprint as described in claim 1, characterized in that, The method further includes: The acquired 4G minimum road test data will be used to construct a 4G level fingerprint database; Based on the same grid number in the 4G level fingerprint database and the 5G level fingerprint database, the 4G level fingerprint database and the 5G level fingerprint database are merged to obtain a hybrid level fingerprint database for positioning.

7. The positioning method based on level fingerprinting as described in any one of claims 1 to 6, characterized in that, After the step of mapping each of the signal parameters to each of the grids based on the latitude and longitude information to obtain the level fingerprint library, the method further includes: Obtain the wireless network information of the target user, the wireless network information including: target network cell identifier and target signal reception parameters; Multiple first target grids are obtained by filtering from the level fingerprint database, wherein the network cell identifier of the first target grid is the same as the target network cell identifier; Calculate the similarity between the signal reception parameters of each first target grid and the target signal reception parameters; The second target grid corresponding to the highest similarity is determined as the grid where the target user is located, in order to locate the target user.

8. A positioning device based on level fingerprinting, characterized in that, The device includes: The data acquisition module is used to enable 5G wireless measurement of the UE through a 4G base station and enable 4G wireless measurement of the UE through a 5G base station; receive 4G MRO and 5G MRO collected by the 4G base station and 5G base station respectively, and determine 5G outdoor wireless data under the 5G network based on the 4G MRO, 4G minimized drive test data and the 5G MRO, wherein the 5G outdoor wireless data includes latitude and longitude information and signal parameters corresponding to the latitude and longitude information; The gridding module is used to divide the area to be located into multiple grids with grid numbers according to latitude and longitude; The fingerprint database establishment module is used to map each of the signal parameters to each of the grids according to the latitude and longitude information to obtain a 5G level fingerprint database, wherein the 5G level fingerprint database is used for positioning.

9. An electronic device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the level fingerprint-based positioning method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the positioning method based on level fingerprint as described in any one of claims 1 to 7.

Images