Positioning service networking method, device, equipment, storage medium and product

Abstract

The invention provides a positioning service networking method and device, equipment, a storage medium and a product. The method is applied to a cloud server, and comprises the steps that terminal fingerprint information sent by a plurality of user terminal devices is received, the terminal fingerprint information is state information data based on the user terminal devices, and a state information data set of the user terminal devices is constructed, extracting key information in the state information data set to directly obtain the state information, or processing the key information through a time sequence aggregation algorithm to obtain the state information; identifying multi-dimensional data features of each piece of terminal fingerprint information; calculating a terminal score corresponding to each user terminal device according to the multi-dimensional data features; selecting a target user terminal device of which the terminal score meets a preset condition from the plurality of user terminal devices; and fusing the target user terminal equipment with a ground base station to generate a positioning service network.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a positioning service networking method, device, equipment, storage medium and product. Background Art

[0002] Networked Real-Time Kinematic (NRTK) is a high-precision positioning technology that relies on a network of ground reference stations to provide positioning correction data to achieve centimeter-level positioning accuracy. This service usually requires a large number of reference physical sites to cover a specific area to ensure the accuracy and reliability of positioning data.

[0003] Traditional NRTK networking requires a large number of ground-based base stations, which leads to a significant increase in the cost of station construction and subsequent maintenance. In some areas, due to the insufficient number of base stations, the service coverage and quality are limited. At the same time, the coverage density is insufficient during the active phase of the ionosphere, which further affects the modeling accuracy and leads to a decrease in positioning accuracy. Summary of the invention

[0004] The embodiments of the present application provide a positioning service networking method, apparatus, device, storage medium and product, which can improve positioning accuracy.

[0005] In a first aspect, the present application provides a positioning service networking method, which is applied to a cloud server and includes:

[0006] Receiving terminal fingerprint information respectively sent by a plurality of user terminal devices, the terminal fingerprint information is obtained by constructing a state information data set of the user terminal device based on state information data of the user terminal device, and extracting key information from the state information data set directly, or by processing the key information through a time series aggregation algorithm;

[0007] Identify the multi-dimensional data features of each terminal fingerprint information;

[0008] Calculating a terminal score corresponding to each of the user terminal devices according to the multidimensional data features;

[0009] Selecting a target user terminal device whose terminal score meets a preset condition from multiple user terminal devices;

[0010] By integrating the target user terminal equipment with the ground base station, a positioning service network is generated.

[0011] In some possible implementations, calculating the terminal score corresponding to each of the user terminal devices according to the multidimensional data features includes:

[0012] Extracting basic operating condition features from the multidimensional data features to obtain first-level data, where the first-level data indicates whether the user terminal device can operate normally;

[0013] Extracting timeliness features from the multidimensional data features to obtain second-level data, where the second-level data represents current performance and data validity of the user terminal device;

[0014] Extracting the observation positioning feature from the multidimensional data feature to obtain third-level data, wherein the third-level data represents the specific observation data and positioning data quality of the user terminal device;

[0015] The terminal score corresponding to each of the user terminal devices is calculated according to the first-level data, the second-level data and the third-level data of each of the user terminal devices.

[0016] In some possible implementations, calculating a terminal score corresponding to each of the user terminal devices according to the first-level data, the second-level data, and the third-level data of each of the user terminal devices includes:

[0017] For each of the user terminal devices, the following steps are performed respectively:

[0018] Determining corresponding hierarchical data parameters according to the first hierarchical data, the second hierarchical data and the third hierarchical data respectively;

[0019] According to each of the hierarchical data parameters and the corresponding parameter weights, a terminal score corresponding to the user terminal device is obtained.

[0020] In some possible implementations, determining corresponding hierarchical data parameters according to the first hierarchical data, the second hierarchical data, and the third hierarchical data respectively includes:

[0021] normalizing at least one of the first-level data, the second-level data, and the third-level data;

[0022] According to the preset weights, the normalized hierarchical data are weighted and summed to determine the corresponding hierarchical data parameters.

[0023] In some possible implementations, selecting a target user terminal device whose terminal score satisfies a preset condition from a plurality of user terminal devices includes:

[0024] Sorting the user terminal devices according to the terminal scores;

[0025] Based on a preset required number of user terminal devices, target user terminal devices whose number corresponds to the preset required number are selected according to the ranking.

[0026] In a second aspect, the present application provides a positioning service networking method, which is applied to a user terminal device, and the method includes:

[0027] Acquire status information data of a user terminal device and construct a status information data set of the user terminal device;

[0028] Extract key information from the status information data set to obtain terminal fingerprint information;

[0029] The terminal fingerprint information is sent to a cloud server so that the cloud server can identify the multi-dimensional data features of each terminal fingerprint information, calculate the terminal score corresponding to each user terminal device according to the multi-dimensional data features, select the corresponding target user terminal device according to the terminal score, and generate a positioning service network by integrating the target user terminal device with the ground base station.

[0030] In some possible implementations, after extracting the key information in the status information data set to obtain the terminal fingerprint information, the method further includes:

[0031] Determine the original sampling frequency corresponding to the terminal fingerprint information;

[0032] According to the original sampling frequency, down-sampling the terminal fingerprint information according to the target sampling frequency to obtain down-sampled terminal fingerprint information;

[0033] The sending the terminal fingerprint information to the cloud server includes:

[0034] The downsampled terminal fingerprint information is sent to the cloud server.

[0035] In some possible implementations, downsampling the terminal fingerprint information according to the original sampling frequency and the target sampling frequency to obtain the downsampled terminal fingerprint information includes:

[0036] Determine the corresponding sliding window size according to the original sampling frequency;

[0037] According to the size of the sliding window and a preset aggregation formula, the terminal fingerprint information in the sliding window is aggregated to obtain the down-sampled terminal fingerprint information.

[0038] In some possible implementations, the preset aggregation formula is:

[0039]

[0040] Where n represents the number of sliding times of the window, represents the current window mean, represents the historical window mean, x n Represents the current value in the window.

[0041] In some possible implementations, the acquiring the status information data of the user terminal device and constructing the status information data set of the user terminal device includes:

[0042] Obtain basic hardware configuration information of user terminal equipment and obtain a data set of general equipment information;

[0043] Obtain real-time status information of user terminal equipment during operation and obtain a data set of equipment status information;

[0044] Acquire the data collected by the user terminal device during observation to obtain a statistical information data set of the observation data;

[0045] Acquire the data generated by the user terminal device when performing positioning solution, and obtain a statistical information data set of the positioning solution;

[0046] A status information data set of the user terminal device is constructed according to the device general information data set, the device status information data set, the observation data statistical information data set and the solved positioning statistical information data set.

[0047] In a third aspect, the present application provides a positioning service networking device, the device comprising:

[0048] A receiving module, used to receive terminal fingerprint information respectively sent by multiple user terminal devices, wherein the terminal fingerprint information is obtained by constructing a state information data set of the user terminal device based on the state information data of the user terminal device, and extracting key information from the state information data set directly, or by processing the key information through a time series aggregation algorithm;

[0049] An identification module, used to identify the multi-dimensional data features of each terminal fingerprint information;

[0050] A calculation module, used for calculating a terminal score corresponding to each of the user terminal devices according to the multi-dimensional data features;

[0051] A selection module, used to select a target user terminal device whose terminal score meets a preset condition from multiple user terminal devices;

[0052] The fusion module is used to generate a positioning service network by fusing the target user terminal device with the ground base station.

[0053] In a fourth aspect, the present application provides a positioning service networking device, the device comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the positioning service networking method as described above.

[0054] In a fifth aspect, the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the positioning service networking method as described above is implemented.

[0055] In a sixth aspect, the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the positioning service networking method described above.

[0056] The positioning service networking method, apparatus, equipment, storage medium and product provided in the embodiments of the present application are networked by integrating the target terminal whose score meets the conditions selected from multiple user terminals and the ground base station. By introducing user terminal equipment when positioning the service group in real-time dynamic network, the effective number of base stations is increased, so that in areas where base stations are scarce, the positioning needs can be met without the need for new base stations, reducing the number of new base stations. At the same time, the terminal score of each user terminal device is calculated, and the corresponding user terminal network is selected according to the score. Therefore, the user terminal devices selected as base stations are all terminals selected based on the actual positioning performance, so the efficiency is improved, the resource consumption caused by too many terminals is avoided, the efficiency of data screening can be improved, and the positioning accuracy can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present application can be better understood from the following description of the specific embodiments of the present application in conjunction with the accompanying drawings, in which:

[0058] Other features, objects and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, in which the same or similar reference numerals represent the same or similar features.

[0059] Figure 1 This is a flow chart of a positioning service networking method provided by an embodiment of the present application;

[0060] Figure 2 is a flowchart of a positioning service networking method provided by another embodiment of the present application;

[0061] Figure 3 It is a schematic diagram of a system architecture corresponding to a positioning service networking method provided by an embodiment of the present application;

[0062] Figure 4It is a schematic diagram of a terminal device status information data set in a positioning service networking method provided by an embodiment of the present application;

[0063] Figure 5 It is a schematic diagram of a time series downsampling process in a positioning service networking method provided by an embodiment of the present application;

[0064] Figure 6 This is a schematic diagram of parameter value distribution characteristics provided by an embodiment of the present application;

[0065] Figure 7 It is a structural diagram of a positioning service networking device provided by an embodiment of the present application;

[0066] Figure 8 It is a schematic diagram of the hardware structure of the positioning service networking device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0067] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0068] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0069] Traditional NRTK networking requires a large number of physical reference sites. In some areas, due to the insufficient number of base stations, service coverage and quality are limited. If the data of user terminal devices is used as base stations, the insufficient number of base stations can be compensated. However, when processing a large amount of base station data, it is impossible to efficiently extract the data generated by massive terminal devices, especially in the face of different device characteristics and complex environments. It is impossible to filter out effective data and high-quality devices. The service interaction process has a large amount of data, resource consumption is under pressure, and positioning accuracy is reduced.

[0070] In order to solve the problems of the prior art, the embodiments of the present application provide a positioning service networking method, device, equipment, storage medium and product. The positioning service networking method provided by the embodiments of the present application is first introduced below.

[0071] Figure 1 The figure shows a flow chart of a positioning service networking method provided by an embodiment of the present application. The above method is applied to a cloud server, such as Figure 1 As shown, the method includes the following steps: S101 to S105.

[0072] S101: receiving terminal fingerprint information respectively sent by a plurality of user terminal devices, wherein the terminal fingerprint information is based on status information data of the user terminal devices, constructing a status information data set of the user terminal devices, and extracting key information in the status information data set directly, or obtaining the key information by processing the key information through a time series aggregation algorithm.

[0073] In the specific implementation, the cloud server receives requests from various user terminals through the network interface. Each user terminal will send its "fingerprint information", which contains the status information data of the terminal device. The cloud server stores the received terminal fingerprint information in the database and builds a "terminal status information data set". This data set is dynamic, and as new data is continuously added, the status information of the terminal device will be continuously updated.

[0074] As another example of S101, the received original terminal information will undergo certain preprocessing, such as noise removal, formatting and verification, to ensure the accuracy and consistency of the data. If there is packet loss or the data format does not meet the requirements, the system will correct or discard the erroneous data through the error handling mechanism.

[0075] As another example of S101, a time series aggregation algorithm may be used to analyze and process historical data to extract key information, which is based on statistical data of the terminal device status.

[0076] S102: Identify the multi-dimensional data features of each of the above terminal fingerprint information.

[0077] In a specific implementation, meaningful features are extracted from the terminal fingerprint information. For example, based on the status information of the device, device health features, environmental features, and behavioral features can be selected to obtain multi-dimensional data features.

[0078] As another example of S102, in multidimensional data, the value ranges of various features may vary greatly, and therefore, the data needs to be normalized to convert data of different features to a unified scale for subsequent comparison and analysis.

[0079] As another example of S102, in order to improve computational efficiency and reduce redundant information, principal component analysis or other dimensionality reduction algorithms may be used to compress the original multi-dimensional feature vector into a feature set in a low-dimensional space while maintaining key information of the data.

[0080] S103: Calculate the terminal score corresponding to each of the user terminal devices according to the multi-dimensional data features.

[0081] In the specific implementation, a scoring model is designed in advance to calculate the terminal score for each device based on machine learning or rule engines. The model may be a weighted scoring function that scores each device based on different features and calculates the terminal score corresponding to each of the above user terminal devices. The scoring criteria are set according to the actual application, such as the response speed, location accuracy, health status, etc. of the device. The calculated terminal score can be used as the "trustworthiness" or "priority" indicator of the device. A device with a high score represents that it performs better in the task or is more suitable for the positioning task.

[0082] As another example of S103, the terminal score is dynamic and will be updated in real time as the device status changes. When the device status changes, the score will be recalculated.

[0083] S104: Selecting a target user terminal device whose terminal score meets a preset condition from multiple user terminal devices.

[0084] In a specific implementation, based on a preset score threshold or ranking condition, devices with terminal scores that meet the requirements are screened out. For example, a minimum score threshold can be set, and only devices with scores higher than this value can be selected as target user terminal devices.

[0085] S105: Generate a positioning service network by integrating the above-mentioned target user terminal equipment with the ground base station.

[0086] In the specific implementation, the cloud communicates with the target user terminal device in real time through a network connection, combines the target user terminal device with the ground base station, establishes a real-time communication channel, and generates a positioning service network.

[0087] The positioning service networking method provided in the embodiment of the present application is networked by fusing the target terminal whose score meets the conditions selected from multiple user terminals and the ground base station. By introducing user terminal equipment when positioning the service group in real-time dynamic network, the effective number of base stations is increased, so that in areas where base stations are scarce, the positioning needs can be met without the need for new base stations, reducing the number of new base stations. At the same time, the terminal score of each user terminal device is calculated, and the corresponding user terminal networking is selected according to the score. Therefore, the user terminal devices selected as base stations are all terminals selected based on the actual positioning performance, so the efficiency is improved, the resource consumption caused by too many terminals is avoided, the efficiency of data screening can be improved, and the positioning accuracy can be improved.

[0088] In order to comprehensively evaluate the operating status of the user terminal device, in some implementations, the above S103 may include the following steps: S1031 to S1034.

[0089] S1031: Extracting basic operating condition features from the multi-dimensional data features to obtain first-level data, where the first-level data indicates whether the user terminal device can operate normally.

[0090] In the specific implementation, the hardware resource status of the terminal device is collected, such as CPU usage, memory usage, disk space, network bandwidth, etc. These are the basic conditions for reflecting whether the device has normal operation. Check whether the key services and processes have been started normally to ensure that the device can perform subsequent work in an available state. By analyzing the above information, a data set representing the "basic operating conditions" is generated, which is the "first-level data". If any key resource has a problem, the device is considered to be unable to operate normally, otherwise it is considered normal.

[0091] S1032: Extracting timeliness features from the multi-dimensional data features to obtain second-level data, where the second-level data represents the current performance and data validity of the user terminal device.

[0092] In the specific implementation, monitor the response time of the device when processing requests. A long response time indicates that the performance of the device may be affected and it cannot respond to user requests in time. Analyze changes in system load in different time periods. Analyze the timeliness of resource usage. For example, the cached data in the system may become less effective over time, and it is necessary to determine whether the data is still valid based on timeliness. By analyzing the timeliness characteristics of the device's current operating status, response speed, data validity and other dimensions, we can obtain "second-level data", which represents whether the device's current performance is qualified and whether the data is reliable.

[0093] S1033: Extract the observation positioning features from the multi-dimensional data features to obtain third-level data, where the third-level data represents the specific observation data and positioning data quality of the user terminal device.

[0094] In the specific implementation, the positioning data quality and observation data quality in the above multi-dimensional data features are extracted, and the device's observation data quality is evaluated based on factors such as the device's positioning accuracy, signal strength, and reliability of observation data. This information constitutes the "third level data", which directly reflects the device's observation and positioning capabilities.

[0095] S1034: Calculate a terminal score corresponding to each of the user terminal devices according to the first-level data, the second-level data and the third-level data of each of the user terminal devices.

[0096] In the specific implementation, the importance of each level of data is determined according to the application scenario, and different weights can be assigned to different levels of data. The first level data, the second level data, and the third level data are combined and weighted averaged to perform a comprehensive score. Based on the comprehensive score, the final score of each terminal device is generated.

[0097] The above implementation method of the embodiment of the present application obtains the first-level data by extracting the basic operating condition features in the above-mentioned multi-dimensional data features, and the above-mentioned first-level data indicates whether the user terminal device can operate normally, and extracts the timeliness features in the above-mentioned multi-dimensional data features to obtain the second-level data, and the above-mentioned second-level data indicates the current performance and data validity of the user terminal device; and then extracts the observation positioning features in the above-mentioned multi-dimensional data features to obtain the third-level data, and the above-mentioned third-level data indicates the specific observation data and positioning data quality of the user terminal device, and then calculates the terminal score corresponding to each of the above-mentioned user terminal devices according to the above-mentioned first-level data, the above-mentioned second-level data and the above-mentioned third-level data of each of the above-mentioned user terminal devices, and extracts features from multiple dimensions such as device hardware, performance, data validity and positioning accuracy in turn, and finally generates a comprehensive "terminal score", so as to comprehensively evaluate the operating status of the user terminal device.

[0098] In order to accurately obtain a score that reflects the overall status of the device, in some embodiments, the above S1034 may include the following steps: S10341 to S10342.

[0099] For each of the above user terminal devices, perform the following steps respectively:

[0100] S10341: Determine corresponding hierarchical data parameters according to the first hierarchical data, the second hierarchical data and the third hierarchical data respectively.

[0101] In the specific implementation, the key parameters of the first-level data are extracted based on the hardware status and operating system status of the device; the key parameters of the second-level data are extracted based on the timeliness characteristics of the device, such as the response time of the device, load change trend, time dimension evaluation of resource usage, etc.; the key parameters of the third-level data are extracted based on the observation data characteristics such as the positioning accuracy, signal strength and sensor data validity of the device, and the corresponding level data parameters are determined.

[0102] S10342: Obtain a terminal score corresponding to the user terminal device according to each of the above-mentioned hierarchical data parameters and the corresponding parameter weights.

[0103] In the specific implementation, the weights of the hierarchical data parameters are determined, and the corresponding weights are assigned to each hierarchical data parameter, and the data parameters of each hierarchical level are weighted. The data parameters of each hierarchical level are adjusted by the corresponding weights to obtain a weighted score. The final terminal score is obtained by comprehensively calculating the weighted scores of each level.

[0104] The above implementation of the embodiment of the present application determines the corresponding hierarchical data parameters according to the above first hierarchical data, the above second hierarchical data and the above third hierarchical data respectively, and then obtains the terminal score corresponding to the above user terminal device and the comprehensive terminal score of each device according to each of the above hierarchical data parameters and the corresponding parameter weights. Through weighted calculation and standardized processing, an accurate score reflecting the overall status of the device is finally obtained.

[0105] In order to obtain an accurate equipment evaluation, in some implementations, the above S10341 may include the following steps: S103411 to S103412.

[0106] S103411: Normalize at least one of the first-level data, the second-level data, and the third-level data.

[0107] In a specific implementation, the value ranges of data at each level may be different. Through normalization, these data can be converted into the same standard scale. According to specific needs and the nature of the data, at least one of the above-mentioned first-level data, the above-mentioned second-level data and the above-mentioned third-level data is selected for normalization processing.

[0108] S103412: Perform weighted summation on the normalized hierarchical data according to preset weights to determine corresponding hierarchical data parameters.

[0109] In the specific implementation, each data item has different importance in the terminal scoring, and different weights may need to be assigned to each level of data items according to actual needs. By weighted summation, it can ensure that data items with higher importance contribute more to the final result. Define the weight of each data item, calculate the normalized weighted score, and determine the corresponding level data parameters.

[0110] The above-mentioned implementation method of the embodiment of the present application normalizes at least one of the above-mentioned first-level data, the above-mentioned second-level data and the above-mentioned third-level data, and then performs weighted summation on the normalized level data according to preset weights to determine the corresponding level data parameters, and performs weighted summation on the normalized level data according to preset weights to determine the corresponding level data parameters, and performs weighted summation on the normalized data according to preset weights to finally obtain a comprehensive level score for each device. This process ensures that data at different levels can have different impacts on the scoring results according to their importance, and finally obtains an accurate device evaluation.

[0111] In order to screen out devices that meet the requirements, in some implementations, the above S104 may include the following steps: S1041 to S1042.

[0112] S1041: Sort the user terminal devices according to the terminal scores.

[0113] In a specific implementation, a terminal score is calculated on each terminal device, and the devices are sorted in a descending order based on the above device score data.

[0114] S1042: Based on a preset required number of user terminal devices, select target user terminal devices whose number corresponds to the preset required number according to the above ranking.

[0115] In a specific implementation, the user's preset demand quantity is obtained, and based on the sorted device list, the first n devices are selected, where n is the demand quantity set by the user, so as to select target user terminal devices whose quantity corresponds to the preset demand quantity according to the above sorting.

[0116] The above implementation method of the embodiment of the present application sorts each user terminal device according to the above terminal score, and then based on the preset required number of user terminal devices, selects the target user terminal devices corresponding to the preset required number according to the above sorting, which can effectively screen out the devices that meet the requirements from a large number of terminal devices.

[0117] As another implementation of the positioning service networking method, the above method is applied to a user terminal device, such as Figure 2 As shown, the method includes the following steps: S201 to S203.

[0118] S201: Acquire status information data of a user terminal device and construct a status information data set of the user terminal device.

[0119] In the specific implementation, it is necessary to first obtain the status information of each user terminal device. This status information can come from multiple sources such as the device's hardware monitoring, operating system, network connection, etc. Common status information includes hardware status, network status, device health status, and location information. All the acquired device status information will be organized into a status information data set.

[0120] S202: Extract key information from the above status information data set to obtain terminal fingerprint information.

[0121] In the specific implementation, relevant features are selected to extract important features related to device performance and network services from the status information data set, and the extracted key information will be combined into a terminal fingerprint.

[0122] S203: Send the terminal fingerprint information to the cloud server so that the cloud server can identify the multi-dimensional data features of each terminal fingerprint information, calculate the terminal score corresponding to each user terminal device according to the multi-dimensional data features, select the corresponding target user terminal device according to the terminal score, and generate a positioning service network by integrating the target user terminal device with the ground base station.

[0123] In the specific implementation, the terminal fingerprint information needs to be sent to the cloud server through the network interface, so that the cloud server can generate a positioning service network.

[0124] In order to effectively reduce the volume of data, in some implementations, after the above S202, the above method may further include the following steps: S2021 to S2022.

[0125] S2021: Determine the original sampling frequency corresponding to the above terminal fingerprint information.

[0126] In a specific implementation, fingerprint information is extracted from the terminal device, and the original sampling frequency of these data is determined.

[0127] S2022: According to the original sampling frequency, downsample the terminal fingerprint information according to the target sampling frequency to obtain downsampled terminal fingerprint information.

[0128] In the specific implementation, the target sampling frequency is determined and the downsampling ratio is calculated. The downsampling ratio refers to the ratio between the target sampling frequency and the original sampling frequency. For example, if the original sampling frequency is 50Hz and the target sampling frequency is 10Hz, then the downsampling ratio is 5. Then the downsampling operation is performed to obtain the terminal fingerprint information after downsampling. Downsampling usually selects to retain data points within certain time intervals. For example, if the downsampling ratio is 5, you can select a data point every 5 data points, or select data through other techniques such as averaging and interpolation.

[0129] The above S203 includes:

[0130] The terminal fingerprint information after the above downsampling is sent to the cloud server.

[0131] The above-mentioned implementation method of the embodiment of the present application, after determining the original sampling frequency corresponding to the above-mentioned terminal fingerprint information, downsamples the above-mentioned terminal fingerprint information according to the target sampling frequency based on the above-mentioned original sampling frequency to obtain the downsampled terminal fingerprint information, and then sends the above-mentioned downsampled terminal fingerprint information to the cloud server, which can effectively reduce the data volume.

[0132] In order to retain key information of the data, in some implementations, the above S2022 may include the following steps: S20221 to S20222.

[0133] S20221: Determine the corresponding sliding window size according to the above original sampling frequency.

[0134] In a specific implementation, the size of the corresponding sliding window is determined according to the original sampling frequency and the target sampling frequency. The window size is determined according to the ratio of the original sampling frequency to the target sampling frequency.

[0135] S20222: According to the size of the sliding window and a preset aggregation formula, the terminal fingerprint information in the sliding window is aggregated to obtain downsampled terminal fingerprint information.

[0136] In the specific implementation, once the window size and aggregation formula are determined, the data can be aggregated and the aggregation method can be adjusted according to the needs. After the aggregation is completed, a downsampled data sequence is obtained, and the downsampled terminal fingerprint information is obtained.

[0137] The above implementation of the embodiment of the present application determines the corresponding sliding window size according to the above original sampling frequency, and then according to the above sliding window size and a preset aggregation formula, aggregates the terminal fingerprint information in the above sliding window to obtain the downsampled terminal fingerprint information, which can compress the original high-frequency data into low-frequency data while retaining the key information of the data.

[0138] In some implementations, the above preset aggregation formula is:

[0139]

[0140] Among them, n represents the number of sliding times of the window. represents the current window mean, represents the historical window mean, x n Represents the current value in the window.

[0141] In order to accurately construct the state information data set, in some implementations, the above S201 may include the following steps: S2011 to S2015.

[0142] S2011: Obtain basic hardware configuration information of the user terminal device and obtain a data set of general device information.

[0143] S2012: Acquire real-time status information of the user terminal device during operation to obtain a device status information data set.

[0144] S2013: Acquire data collected by the user terminal device during observation to obtain an observation data statistical information data set.

[0145] S2014: Acquire data generated by the user terminal device when performing positioning solution, and obtain a solved positioning statistical information data set.

[0146] S2015: Constructing a status information data set of the user terminal device according to the device general information data set, the device status information data set, the observation data statistical information data set and the calculated positioning statistical information data set.

[0147] As another implementation, you can refer to Figure 3 The overall architecture is divided into two modules: terminal device 301 and cloud management 303. In the terminal management 302 in the terminal module, the following steps are performed for each device: information construction data set 3021, fingerprint data collection 3022, and time series aggregation operation 3023; then real-time data return 3024, and the processed data is returned to the cloud in real time. The cloud uses a dynamic weighted algorithm to evaluate the quality of the device fingerprint portrait, and ranks the fingerprint portrait 3031, from which high-quality terminals are selected to improve the stability of device data return, improve the accuracy of ionosphere modeling, and perform service networking 3032.

[0148] In order to ensure the stability of NRTK service networking modeling for massive enterprise terminal devices, it is necessary to verify and analyze the effectiveness of the data source provided; to grasp the status information of the terminal equipment in real time, and to perform access permission and shielding operations for equipment models of varying quality during the service process, which is a necessary prerequisite for ensuring high-quality data return; in addition, accurately identify the real-time status information of user terminal devices to ensure that the power consumption, traffic and bandwidth information occupancy conditions involved in data return will not have a significant impact on terminal use.

[0149] Based on the hardware and software features of the terminal device and the operation process, this patent comprehensively evaluates that each terminal device will have a terminal information data set consisting of four dimensions: device general information, device status information, observation data statistical information, and solution positioning statistical information, as follows Figure 4 The terminal status information 401 specifically includes device general information 4011 , device status information 4012 , observation data statistical information 4013 and solution positioning statistical information 4014 .

[0150] First, the general information of the equipment is composed of the basic firmware of the equipment, the equipment board, the equipment network, etc.; in the use of a large number of terminals, there are multi-platform mixed networking models of enterprise self-developed and third-party terminals. For the models, boards and equipment networks of different equipment manufacturers, a full amount of unified general status identification is required. Devices with old hardware board models, abnormal antennas or low power, and poor networks will be marked in the data analysis stage to ensure the stable startup and information registration capabilities of the equipment; secondly, the terminal's operating status information is also an important data consideration construction element (power status, network rate, network delay). The power consumption and network delay status information during the operation of the equipment are transmitted back in real time, which helps the service to quickly determine the reliability of the data source of the equipment; in addition, the observation data statistics and solution positioning statistics of the terminal equipment are important indicators to measure whether the equipment can output a stable and available data source. In the process of equipment observation, the frequency differentiation of the observation interval, the stability of the number of observed satellites, and the signal-to-noise ratio (SNR) value distribution characteristics of the frequency band reference signal are important data quality indicators; the statistical information of the equipment solution positioning status includes the epoch fixation rate and the differential age.

[0151] When the terminal completes the construction of the device status information data set, the data can be used for persistent storage, data quality analysis, and fault regression. To further form a stable data source for networking services and push it back in real time, the data set needs to be processed in batches, and object fingerprint modeling is performed in four dimensions: device general information, status information, observation data statistics, and solution positioning statistics. The basic structure definition is shown in the following table.

[0152] Table 1

[0153]

[0154]

[0155] Fingerprint data completes object-oriented collection and has the channel protocol transmission conditions, that is, it has Figure 3 The real-time path return of Path1 provides all the data to the service cloud platform.

[0156] In the process of real-time transmission of terminal fingerprint information to the cloud for service networking, due to the high frequency of real-time data transmission and the huge nature of the massive terminal data set constructed, the required bandwidth resources and network speed are relatively large, and the interactive communication between the cloud and the terminal faces transmission pressure. In addition, the high-frequency transmission of massive data, which is mixed with redundant information without state bits, is not conducive to the cloud's screening and use of valid data.

[0157] Therefore, we further propose an effective time series aggregation algorithm for massive terminal data. In the original data set, the real-time feedback of device network status, observation data and positioning data is based on high-frequency time series data sets, so the algorithm uses downsampling to convert the original data from a higher frequency (such as 1 second interval) to a lower frequency (1 minute or 15 minutes) data. For example, Figure 5 As shown, during the downsampling process, the original data 501 includes 60 1-second interval data from Ts0 to Ts59, that is, one minute of data. The original data 501 is aggregated to obtain the first downsampling data 502. The first downsampling data 502 includes A-Tm0 to A-Tm4, a total of 5 minutes of data. Downsampling is performed again to obtain the second downsampling data 503. The second downsampling data 503 includes three A-Tm5 containing 5 minutes of data. Downsampling is continued to obtain the third downsampling data 504. The third downsampling data 504 includes A-Tm15 containing 15 minutes of data. In this way, the original data is converted from a higher frequency (1-second interval) to a low frequency (15 minutes) data.

[0158] In the process of downsampling, in order to dynamically track the changes in time series, a sliding window is introduced to achieve real-time update capabilities with a specified window span, such as 5 minutes, and the aggregation results are dynamically updated in each time period, thereby maintaining data variability while also ensuring data freshness. In addition, in order to achieve average / extreme aggregation of parameter information on terminal data status, observation data statistics, and positioning data quality statistics, the following formula is shown:

[0159]

[0160] max(x1,x2,…,x n )=max(max(x1,x2,…,xn-1 ),x n )

[0161] min(x1,x2,…,x n )=min(min(x1,x2,…,x n-1 ),x n )

[0162] Considering the multi-dimensional characteristics of parameter information, during the smoothing process, the stored state quantity that slides with the window is only the result value calculated in the previous historical window. For example, the extreme value of the current state N is the latest extreme value compared with the extreme value of the previous N-1 sliding window and the current value; and the mean is calculated in a weighted manner, with the window mean accounting for a weight of , and the current value accounting for a weight of . Taking the number of observable satellites in a single epoch as an example, the fingerprint parameters of the data set can realize dynamic statistics of the number of satellites in the aggregated state of the time series dimension (such as the average / maximum / minimum number of satellites per single epoch in 5 minutes).

[0163] Once the fingerprint data is aggregated, the terminal data can be Figure 3 The Path2 path in the network is transmitted back to the cloud in real time for service networking.

[0164] Based on the construction of the above terminal data set, fingerprint collection and time series aggregation, the terminal management module realizes the efficient processing of the entire massive data flow. Through the cloud service platform, the real-time aggregated data can support the centralized monitoring and analysis capabilities of a series of terminal devices and meet the business needs of regional modeling. This centralized management not only improves the efficiency of data processing, but also enhances the real-time insight into the status of terminal devices.

[0165] Based on this framework, a portrait description and intelligent ranking algorithm for massive available terminals is further proposed. The algorithm uses multi-dimensional data features and introduces machine learning normalization functions to perform comprehensive feature extraction and analysis of terminal devices. The algorithm model combines the user's customized weights for terminal parameters to generate highly recognizable portrait descriptions based on the behavioral patterns of various terminals during use, and then intelligently ranks the devices to identify high-priority terminal devices and provide data support for subsequent decisions. The user portrait scoring principle is shown in the following formula:

[0166]

[0167] in, Indicates the final score of the device data, s j is the jth parameter in the parameter set of the i-th layer, w jIndicates the custom weight corresponding to the jth parameter in the i-th layer parameter. Therefore, it can be understood that the total terminal data set constructed above is further divided into multiple layers according to the characteristics of the device status information. In each layer of parameters, there are also weighted comprehensive statistical parameters of multiple dimensions. It is equal to the cumulative value of the multi-level parameters. The basic characteristics of the equipment are evaluated based on the following formula:

[0168] S1=x online &x power &x network = = 1? 1.0: 0

[0169] S2=x load_loss <0.5?0∶x load_loss <0.9?x load_loss ∶1

[0170] S3=x age >5?0∶x age >3?0.5∶1.0

[0171] where x online 、x power With x network They respectively indicate whether the device is turned on, whether it has power, and the network conditions. As the first-level parameter layer, S1 describes the basic information of the device, which has the characteristics of either 0 or 1, and plays a decisive role in the final ranking score weight. As the second-level parameter layer division, it is a metric analysis of data parameters, where x load_loss Indicates the uplink and downlink speed of network loading, x age The characteristics of this type of parameters are variable, and the occasional difference in data (such as poor network speed, data delay, low battery, etc.) will not have a great impact on the terminal data usage. As different users have different focuses on terminal devices, the second-level parameter layer is configurable.

[0172] The observation data and positioning data of the terminal are classified into the third-level parameter layer. The activation function sigmod(x) in the neural network is introduced here to normalize the parameters, as shown in the following formula:

[0173]

[0174] Among them, a i represents the normalized center value, b i Represents the slope. For different parameters, users can customize their normalized numerical distribution characteristics, as shown in the following formula:

[0175] S snr =SIG(35,10)

[0176] Ssats =SIG(35,10)

[0177] S integrity =SIG(0.85,0.15)

[0178] S distance =SIG(10,5)

[0179] S DOP =SIG(20,-20)

[0180] Among them, S snr is the signal-to-noise ratio of the observed signal, S sats is the number of observed satellites, S integrity is the data integrity, S distance is the positioning distance deviation value, S DOP is the average positioning precision factor, for example S snr / S sats The parameter characteristic distribution of Figure 6 As shown, if the user needs to increase the sample parameters, further parameters such as epoch fixation rate and average difference age can be considered. The weight configuration is shown in the following formula:

[0181]

[0182] Among them, S4 is the score of the third-layer data parameter set, and finally it can be concluded that:

[0183]

[0184] The device ranking algorithm for available terminals not only improves the level of intelligence in terminal management, facilitates the cloud platform to enable massive terminal selections and enhances the stability of regional networking, but also provides strong data support for enterprises in equipment optimization, resource allocation and business decision-making.

[0185] Based on the positioning service networking method provided in the above embodiment, the present application also provides a specific implementation of the positioning service networking device. Please refer to the following embodiment.

[0186] See first Figure 7 The positioning service networking device 600 provided in the embodiment of the present application includes the following modules:

[0187] The receiving module 601 is used to receive terminal fingerprint information sent by multiple user terminal devices respectively. The above-mentioned terminal fingerprint information is based on the status information data of the user terminal device, constructs a status information data set of the above-mentioned user terminal device, and extracts key information in the above-mentioned status information data set directly, or obtains the above-mentioned key information by processing the above-mentioned key information through a time series aggregation algorithm.

[0188] The identification module 602 is used to identify the multi-dimensional data features of each of the above terminal fingerprint information.

[0189] The calculation module 603 is used to calculate the terminal score corresponding to each of the user terminal devices according to the multi-dimensional data characteristics.

[0190] The selection module 604 is used to select a target user terminal device whose terminal score meets a preset condition from multiple user terminal devices.

[0191] The fusion module 605 is used to generate a positioning service network by fusing the above-mentioned target user terminal equipment with the ground base station.

[0192] The positioning service networking device provided in the embodiment of the present application is networked by fusing the target terminal whose score meets the conditions selected from multiple user terminals and the ground base station. By introducing user terminal equipment when positioning the service group in real-time dynamic network, the effective number of base stations is increased, so that in areas where base stations are scarce, the positioning needs can be met without the need for new base stations, reducing the number of new base stations. At the same time, the terminal score of each user terminal device is calculated, and the corresponding user terminal networking is selected according to the score. Therefore, the user terminal devices selected as base stations are all terminals selected based on the actual positioning performance, so the efficiency is improved, the resource consumption caused by too many terminals is avoided, the efficiency of data screening can be improved, and the positioning accuracy can be improved.

[0193] As an implementation of the present application, the calculation module 603 includes:

[0194] The extraction unit is used to extract the basic operating condition features from the multi-dimensional data features to obtain the first level data, wherein the first level data indicates whether the user terminal device can operate normally.

[0195] The extraction unit is further used to extract the timeliness features in the above-mentioned multidimensional data features to obtain second-level data, and the above-mentioned second-level data represents the current performance and data validity of the user terminal device.

[0196] The extraction unit is also used to extract the observation positioning features in the above-mentioned multidimensional data features to obtain third-level data, and the above-mentioned third-level data represents the specific observation data and positioning data quality of the user terminal device.

[0197] The calculation unit is used to calculate the terminal score corresponding to each of the above-mentioned user terminal devices according to the above-mentioned first-level data, the above-mentioned second-level data and the above-mentioned third-level data of each of the above-mentioned user terminal devices.

[0198] As an implementation of the present application, a computing unit includes:

[0199] The determination subunit is used to determine corresponding hierarchical data parameters according to the first hierarchical data, the second hierarchical data and the third hierarchical data respectively.

[0200] The calculation subunit is used to obtain the terminal score corresponding to the above-mentioned user terminal device according to each of the above-mentioned hierarchical data parameters and the corresponding parameter weights.

[0201] As an implementation of the present application, determining a subunit includes:

[0202] The normalization subunit is used to normalize at least one of the first-level data, the second-level data, and the third-level data.

[0203] The summing subunit is used to perform weighted summation on the normalized hierarchical data according to preset weights to determine the corresponding hierarchical data parameters.

[0204] As an implementation of the present application, the selection module 604 includes:

[0205] The sorting unit is used to sort the user terminal devices according to the terminal scores.

[0206] The selection unit is used to select target user terminal devices whose number corresponds to the preset required number according to the above ranking based on the preset required number of user terminal devices.

[0207] As an implementation of the present application, a positioning service networking device includes:

[0208] The construction module is used to obtain the status information data of the user terminal device and construct the status information data set of the user terminal device.

[0209] The extraction module is used to extract key information from the above status information data set to obtain terminal fingerprint information.

[0210] The sending module is used to send the above-mentioned terminal fingerprint information to the cloud server so that the above-mentioned cloud server can identify the multi-dimensional data characteristics of each of the above-mentioned terminal fingerprint information, calculate the terminal score corresponding to each of the above-mentioned user terminal devices according to the above-mentioned multi-dimensional data characteristics, select the corresponding target user terminal device according to the above-mentioned terminal score, and generate a positioning service network by integrating the above-mentioned target user terminal device with the ground base station.

[0211] As an implementation of the present application, the positioning service networking device also includes:

[0212] The determination module is used to determine the original sampling frequency corresponding to the above terminal fingerprint information.

[0213] The sampling module is used to downsample the terminal fingerprint information according to the target sampling frequency based on the original sampling frequency to obtain the downsampled terminal fingerprint information.

[0214] The sending module is used to send the terminal fingerprint information to the cloud server, including:

[0215] The sending module is also used to send the terminal fingerprint information after the downsampling to the cloud server.

[0216] As an implementation of the present application, the sampling module includes:

[0217] The determining unit is used to determine the corresponding sliding window size according to the original sampling frequency.

[0218] The aggregation unit is used to aggregate the terminal fingerprint information in the above sliding window according to the size of the above sliding window and a preset aggregation formula to obtain the down-sampled terminal fingerprint information.

[0219] As an implementation of the present application, a building block includes:

[0220] The acquisition unit is used to acquire basic hardware configuration information of the user terminal device and obtain a device general information data set.

[0221] The acquisition unit is also used to acquire the real-time status information of the user terminal device during operation to obtain a device status information data set.

[0222] The acquisition unit is also used to acquire data collected by the user terminal device during observation to obtain an observation data statistical information data set.

[0223] The acquisition unit is also used to acquire data generated by the user terminal device when performing positioning solution, and obtain a data set of solved positioning statistical information.

[0224] The construction unit is used to construct the status information data set of the user terminal device according to the above-mentioned device general information data set, the above-mentioned device status information data set, the above-mentioned observation data statistical information data set and the above-mentioned solution positioning statistical information data set.

[0225] Each module in the data processing device provided in the embodiment of the present application can implement each step in the above-mentioned data processing method and achieve the corresponding effect. For the sake of concise description, it will not be repeated here.

[0226] Figure 8 A schematic diagram of the structure of the data processing hardware provided in an embodiment of the present application is shown.

[0227] The data processing device may include a processor 701 and a memory 702 storing computer program instructions.

[0228] Specifically, the processor 701 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0229] The memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 702 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 702 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 702 is a non-volatile solid-state memory.

[0230] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the data processing method according to any one embodiment of the present disclosure.

[0231] The processor 701 implements any one of the data processing methods in the above embodiments by reading and executing computer program instructions stored in the memory 702 .

[0232] In one example, the data processing device may further include a communication interface 703 and a bus 710. Figure 7 As shown, the processor 701, the memory 702, and the communication interface 703 are connected via a bus 710 and communicate with each other.

[0233] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0234] Bus 710 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 710 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0235] In addition, in combination with the method for positioning service networking in the above embodiments, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the positioning service networking methods in the above embodiments is implemented.

[0236] An embodiment of the present application further provides a computer program product, including a computer program, which, when executed, implements any one of the positioning service networking methods in the above embodiments.

[0237] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0238] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0239] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0240] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0241] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A positioning service networking method, characterized in that: The method is applied to a cloud server, and the method includes: Receiving terminal fingerprint information respectively sent by a plurality of user terminal devices, the terminal fingerprint information is obtained by constructing a state information data set of the user terminal device based on state information data of the user terminal device, and extracting key information from the state information data set directly, or by processing the key information through a time series aggregation algorithm; Identify the multi-dimensional data features of each terminal fingerprint information; Calculating a terminal score corresponding to each of the user terminal devices according to the multidimensional data features; Selecting a target user terminal device whose terminal score meets a preset condition from multiple user terminal devices; By integrating the target user terminal equipment with the ground base station, a positioning service network is generated.

2. The positioning service networking method according to claim 1, characterized in that: The calculating, according to the multi-dimensional data features, a terminal score corresponding to each of the user terminal devices, comprises: Extracting basic operating condition features from the multidimensional data features to obtain first-level data, where the first-level data indicates whether the user terminal device can operate normally; Extracting timeliness features from the multidimensional data features to obtain second-level data, where the second-level data represents current performance and data validity of the user terminal device; Extracting the observation positioning feature from the multidimensional data feature to obtain third-level data, wherein the third-level data represents the specific observation data and positioning data quality of the user terminal device; The terminal score corresponding to each of the user terminal devices is calculated according to the first-level data, the second-level data and the third-level data of each of the user terminal devices.

3. The positioning service networking method according to claim 2, characterized in that: The calculating, according to the first-level data, the second-level data and the third-level data of each of the user terminal devices, a terminal score corresponding to each of the user terminal devices comprises: For each of the user terminal devices, the following steps are performed respectively: Determining corresponding hierarchical data parameters according to the first hierarchical data, the second hierarchical data and the third hierarchical data respectively; According to each of the hierarchical data parameters and the corresponding parameter weights, a terminal score corresponding to the user terminal device is obtained.

4. The positioning service networking method according to claim 3, characterized in that: The determining corresponding hierarchical data parameters according to the first hierarchical data, the second hierarchical data and the third hierarchical data respectively includes: normalizing at least one of the first-level data, the second-level data, and the third-level data; According to the preset weights, the normalized hierarchical data are weighted and summed to determine the corresponding hierarchical data parameters.

5. The positioning service networking method according to any one of claims 1 to 4, characterized in that: The step of selecting a target user terminal device whose terminal score satisfies a preset condition from a plurality of user terminal devices comprises: Sorting the user terminal devices according to the terminal scores; Based on a preset required number of user terminal devices, target user terminal devices whose number corresponds to the preset required number are selected according to the ranking.

6. A positioning service networking method, characterized in that: The method is applied to a user terminal device, and the method comprises: Acquire status information data of a user terminal device and construct a status information data set of the user terminal device; Extract key information from the status information data set to obtain terminal fingerprint information; The terminal fingerprint information is sent to a cloud server so that the cloud server can identify the multi-dimensional data features of each terminal fingerprint information, calculate the terminal score corresponding to each user terminal device according to the multi-dimensional data features, select the corresponding target user terminal device according to the terminal score, and generate a positioning service network by integrating the target user terminal device with the ground base station.

7. The positioning service networking method according to claim 6, characterized in that: After extracting the key information in the status information data set to obtain the terminal fingerprint information, the method further includes: Determine the original sampling frequency corresponding to the terminal fingerprint information; According to the original sampling frequency, down-sampling the terminal fingerprint information according to the target sampling frequency to obtain down-sampled terminal fingerprint information; The sending the terminal fingerprint information to the cloud server includes: The downsampled terminal fingerprint information is sent to the cloud server.

8. The positioning service networking method according to claim 7, characterized in that: The downsampling the terminal fingerprint information according to the original sampling frequency and the target sampling frequency to obtain the downsampled terminal fingerprint information includes: Determine the corresponding sliding window size according to the original sampling frequency; According to the size of the sliding window and a preset aggregation formula, the terminal fingerprint information in the sliding window is aggregated to obtain the down-sampled terminal fingerprint information.

9. The positioning service networking method according to claim 8, characterized in that: The preset aggregation formula is: Where n represents the number of sliding times of the window, represents the current window mean, represents the historical window mean, x n Represents the current value in the window.

10. The positioning service networking method according to any one of claims 6 to 9, characterized in that: The acquiring of status information data of the user terminal device and constructing a status information data set of the user terminal device includes: Obtain basic hardware configuration information of user terminal equipment and obtain a data set of general equipment information; Obtain real-time status information of user terminal equipment during operation and obtain a data set of equipment status information; Acquire the data collected by the user terminal device during observation to obtain a statistical information data set of the observation data; Acquire the data generated by the user terminal device when performing positioning solution, and obtain a statistical information data set of the positioning solution; A status information data set of the user terminal device is constructed according to the device general information data set, the device status information data set, the observation data statistical information data set and the solved positioning statistical information data set.

11. A positioning service networking device, characterized in that: The device comprises: A receiving module, used to receive terminal fingerprint information respectively sent by multiple user terminal devices, wherein the terminal fingerprint information is obtained by constructing a state information data set of the user terminal device based on the state information data of the user terminal device, and extracting key information from the state information data set directly, or by processing the key information through a time series aggregation algorithm; An identification module, used to identify the multi-dimensional data features of each terminal fingerprint information; A calculation module, used for calculating a terminal score corresponding to each of the user terminal devices according to the multi-dimensional data features; A selection module, used to select a target user terminal device whose terminal score meets a preset condition from multiple user terminal devices; The fusion module is used to generate a positioning service network by fusing the target user terminal device with the ground base station.

12. A positioning service networking device, characterized in that: The device comprises: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the positioning service networking method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the positioning service networking method according to any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the positioning service networking method as described in any one of claims 1 to 10.

Images