Nbiot access signal quality prediction method, system and device, and storage medium

Abstract

The application discloses an NB-IoT access signal quality prediction method, system and device and a storage medium. The method comprises the following steps: acquiring wireless signal measurement data of a plurality of different network entity objects in a preset area and performing feature extraction to obtain wireless signal features and geographical position information of the network entity objects; the preset area is divided into a plurality of grid areas, and the wireless signal features of the network entity objects in each grid area are counted to obtain NB-IoT signal grid features and 4G signal grid features of each grid area; a grid feature correlation model of the preset area is established; the 4G signal area features of a target area are acquired, the 4G signal area features are matched, target NB-IoT signal grid features are obtained, and then the NB-IoT access signal quality of the target area is predicted. The application improves the efficiency and accuracy of the NB-IoT access signal quality prediction and can be widely applied to the technical field of Internet of Things.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to a method, system, device, and storage medium for predicting NB-IoT access signal quality. Background Technology

[0002] The domestic 4G and NB-IoT networks have accumulated a good amount of signal data. The big data center built by China Telecom Group has gathered a massive amount of MR (Wireless Measurement Report) data from the entire China Telecom network, providing a solid data foundation for network signal analysis for the network business marketing and promotion departments.

[0003] With the nationwide rollout of NB-IoT services, some service terminals connected to NB gateways have the function of reporting signal quality data, and have also accumulated a large amount of signal quality data from actual network environment measurements collected at the terminal deployment locations (covering 31 provinces across the country).

[0004] 4G and NB-IoT base stations are frequently co-located, and the two wireless signals exhibit some correlation. However, due to the differences between the two network technologies, directly using 4G network MR data from the same area to infer the wireless coverage quality of the NB-IoT network in that area may introduce significant errors. A correction parameter is needed to adjust the 4G network MR data for inferring the NB-IoT network coverage quality in that location. Even then, the inferred result may still contain discrepancies with the actual wireless signal quality.

[0005] The wireless network signal quality data collected by NB-IoT service gateways can more directly reflect the NB-IoT wireless network signal quality in the area. However, the characteristics of NB-IoT network service terminals make it difficult to conduct large-scale, continuous direct measurements through methods such as MR (Mean Offset Measurement), making it difficult for operators to obtain information on the NB-IoT network access quality over a large area. The number and geographical coverage of NB-IoT service terminals are relatively small compared to 4G network MR data, leaving many blank areas. Especially in areas where NB-IoT service terminals have not been actually deployed, it is impossible to quickly and accurately determine the distribution of NB-IoT wireless signal access quality in the target area after the deployment of NB-IoT service terminals.

[0006] Therefore, NB-IoT network operators need to find a method that can accurately and efficiently predict the NB-IoT access signal quality across the entire network (including unused areas). Summary of the Invention

[0007] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0008] Therefore, one objective of this invention is to provide an accurate and efficient method for predicting NB-IoT access signal quality.

[0009] Another objective of this invention is to provide an NB-IoT access signal quality prediction system.

[0010] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include:

[0011] In a first aspect, embodiments of the present invention provide an NB-IoT access signal quality prediction method, comprising the following steps:

[0012] The wireless signal measurement data of multiple different network entities within a preset area are acquired, and feature extraction is performed on the wireless signal measurement data to obtain the wireless signal characteristics and geographical location information of each network entity. The wireless signal characteristics include at least one of NB-IoT signal characteristics and 4G signal characteristics.

[0013] The preset area is divided into multiple grid areas based on the geographical location information, and the wireless signal characteristics of the network entity objects in each grid area are statistically analyzed to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each grid area.

[0014] A grid feature association model for the preset area is established based on the NB-IoT signal grid features and the 4G signal grid features. The grid feature association model includes the mapping relationship between the NB-IoT signal grid features and the 4G signal grid features of each grid area.

[0015] The 4G signal area features of the target area are obtained, and the 4G signal area features are matched according to the grid feature association model to obtain the matched target NB-IoT signal grid features. The NB-IoT access signal quality of the target area is predicted according to the target NB-IoT signal grid features.

[0016] Furthermore, in one embodiment of the present invention, the step of extracting features from the wireless signal measurement data to obtain the wireless signal features and geographical location information of each network entity specifically includes:

[0017] Determine the wireless signal type, wireless signal quality index, measurement location, and measurement time for each wireless signal measurement data;

[0018] The wireless signal characteristics of the corresponding network entity are determined based on the wireless signal quality index and the measurement time, and the wireless signal characteristics are determined to be NB-IoT signal characteristics or 4G signal characteristics based on the wireless signal type.

[0019] The geographical location information of each network entity object is determined based on the measured location.

[0020] Furthermore, in one embodiment of the present invention, the step of dividing the preset area into multiple grid areas based on the geographical location information, and statistically analyzing the wireless signal characteristics of the network entity objects within each grid area to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each grid area specifically includes:

[0021] The preset area is divided into multiple grid areas based on the geographic location information, such that each grid area contains at least one of the network entity objects;

[0022] Based on the measurement time, the wireless signal quality indicators of the network entities in each of the grid areas are statistically analyzed to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each of the grid areas;

[0023] The NB-IoT signal grid features include NB-IoT signal quality indicators at multiple times, and the 4G signal grid features include 4G signal quality indicators at multiple times.

[0024] Furthermore, in one embodiment of the present invention, the step of establishing a grid feature association model of the preset area based on the NB-IoT signal grid features and the 4G signal grid features specifically includes:

[0025] Determine the feature similarity of the 4G signal grid features between each grid region and the adjacent grid regions. If the feature similarity is greater than or equal to a preset first threshold, merge the grid regions with the adjacent grid regions to obtain feature grid blocks.

[0026] Determine the average NB-IoT signal quality of the NB-IoT signal quality index and the average 4G signal quality of the 4G signal quality index for each of the aforementioned feature grid blocks at each of the aforementioned times.

[0027] A first mapping relationship is established between the average NB-IoT signal quality and the average 4G signal quality at each specified time, and the grid feature association model is constructed based on the first mapping relationship.

[0028] Furthermore, in one embodiment of the present invention, the step of determining the feature similarity between the 4G signal grid features of each of the grid regions and the adjacent grid regions specifically includes:

[0029] The 4G signal feature vector of the grid region is determined based on the 4G signal quality index of the grid region at each of the stated times;

[0030] Calculate the cosine similarity between the 4G signal feature vectors of each grid region and the adjacent grid regions, and use the cosine similarity as the feature similarity.

[0031] Further, in one embodiment of the present invention, the step of obtaining the 4G signal area features of the target area, matching the 4G signal area features according to the grid feature association model to obtain the matched target NB-IoT signal grid features, and predicting the NB-IoT access signal quality of the target area based on the target NB-IoT signal grid features specifically includes:

[0032] The target area is divided into multiple target grids, and the current 4G signal quality of each target grid is determined. Based on the current 4G signal quality, the 4G signal area characteristics are determined.

[0033] Determine a first difference between the current 4G signal quality and the average of each 4G signal quality. When the first difference is less than or equal to a preset second threshold, use the average of the 4G signal quality as a candidate matching value, and obtain the time corresponding to the candidate matching value as a candidate time.

[0034] The candidate matching value corresponding to the candidate time closest to the current time is selected as the feature matching value of the current 4G signal quality, and the average NB-IoT signal quality corresponding to the feature matching value is determined as the average target NB-IoT signal quality of the target grid according to the first mapping relationship.

[0035] The target NB-IoT signal grid features are determined based on the average target NB-IoT signal quality, and the NB-IoT access signal quality of the corresponding target grid is determined based on the average target NB-IoT signal quality, thereby obtaining the distribution of the NB-IoT access signal quality in the target area.

[0036] Furthermore, in one embodiment of the present invention, the NB-IoT access signal quality prediction method further includes the following steps:

[0037] The signal measurement increment data of the preset area is obtained, and the grid feature association model is continuously corrected based on the signal measurement increment data.

[0038] In a second aspect, embodiments of the present invention provide an NB-IoT access signal quality prediction system, comprising:

[0039] The signal feature extraction module is used to acquire wireless signal measurement data of multiple different network entity objects within a preset area, and to extract features from the wireless signal measurement data to obtain the wireless signal features and geographical location information of each network entity object. The wireless signal features include at least one of NB-IoT signal features and 4G signal features.

[0040] The signal feature statistics module is used to divide the preset area into multiple grid areas according to the geographical location information, and to count the wireless signal features of the network entity objects in each grid area to obtain the NB-IoT signal grid features and 4G signal grid features of each grid area.

[0041] The association model construction module is used to establish a grid feature association model for the preset area based on the NB-IoT signal grid features and the 4G signal grid features. The grid feature association model includes the mapping relationship between the NB-IoT signal grid features and the 4G signal grid features of each grid area.

[0042] The signal quality prediction module is used to acquire the 4G signal area features of the target area, match the 4G signal area features according to the grid feature association model to obtain the matched target NB-IoT signal grid features, and predict the NB-IoT access signal quality of the target area based on the target NB-IoT signal grid features.

[0043] Thirdly, embodiments of the present invention provide an NB-IoT access signal quality prediction device, comprising:

[0044] At least one processor;

[0045] At least one memory for storing at least one program;

[0046] When the at least one program is executed by the at least one processor, the at least one processor implements the above-described NB-IoT access signal quality prediction method.

[0047] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to perform the above-described NB-IoT access signal quality prediction method.

[0048] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention:

[0049] This invention extracts and statistically analyzes wireless signal measurement data within a preset area to obtain NB-IoT signal grid features and 4G signal grid features. Then, a grid feature association model is established based on these two features. This model is used to match the 4G signal area features of the target area to obtain the target NB-IoT signal grid features. This allows for the prediction of NB-IoT access signal quality in the target area based on these target NB-IoT signal grid features. This invention establishes a mapping relationship between 4G signal grid features and NB-IoT signal grid features. By predicting NB-IoT access signal quality based on the 4G signal area features of the target area, it leverages the advantages of 4G signal measurement data—wide coverage and high update frequency—to compensate for the relatively small mobile range and limited signal quality measurement data collected by NB-IoT service terminals. This improves the efficiency and accuracy of NB-IoT access signal quality prediction. It can be used for NB-IoT access signal quality prediction before the deployment of NB-IoT service terminals, providing convenience for NB-IoT operators' network planning. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart illustrating the steps of an NB-IoT access signal quality prediction method provided in this embodiment of the invention;

[0052] Figure 2 A structural block diagram of an NB-IoT access signal quality prediction system provided in an embodiment of the present invention;

[0053] Figure 3 This is a structural block diagram of an NB-IoT access signal quality prediction device provided in an embodiment of the present invention. Detailed Implementation

[0054] The embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. The step numbers in the following embodiments are set only for ease of explanation, and there is no limitation on the order between the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0055] In the description of this invention, "multiple" means two or more. The use of "first" and "second" is for distinguishing technical features only and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or the order of the indicated technical features. Furthermore, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.

[0056] Reference Figure 1 This invention provides a method for predicting NB-IoT access signal quality, specifically including the following steps:

[0057] S101. Obtain wireless signal measurement data of multiple different network entities within a preset area, and extract features from the wireless signal measurement data to obtain the wireless signal features and geographical location information of each network entity. The wireless signal features include at least one of NB-IoT signal features and 4G signal features.

[0058] As an optional implementation, the step of extracting features from the wireless signal measurement data to obtain the wireless signal characteristics and geographical location information of each network entity specifically includes:

[0059] A1. Determine the wireless signal type, wireless signal quality index, measurement location, and measurement time for each wireless signal measurement data;

[0060] A2. Determine the wireless signal characteristics of the corresponding network entity based on the wireless signal quality index and measurement time, and determine whether the corresponding wireless signal characteristics are NB-IoT signal characteristics or 4G signal characteristics based on the wireless signal type.

[0061] A3. Determine the geographical location information of each network entity based on the measurement location.

[0062] Specifically, a feature analysis and extraction platform for wireless signal measurement data from different sources can be established. This platform aggregates and stores wireless signal measurement data collected from multiple different network entities, such as wireless signal measurement data reported by NB-IoT service terminals, 4G signal measurement data reported by 4G network devices, and base station operation data within the area. Features are extracted from the relevant signal measurement data, including indicators characterizing wireless network quality (RSRP, SNR, RSSI, TXPower, base station cell for wireless access, etc.), indicators characterizing the time and location of the measurement behavior (measurement time, measurement location latitude and longitude, etc.), and the type of wireless network (NB-IoT or 4G). Through feature extraction, the NB-IoT signal characteristics or 4G signal characteristics of each network entity are obtained, facilitating subsequent statistical analysis of the NB-IoT signal characteristics and 4G signal characteristics within each grid area.

[0063] S102. Divide the preset area into multiple grid areas according to the geographical location information, and statistically analyze the wireless signal characteristics of network entities in each grid area to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each grid area.

[0064] Specifically, in this embodiment of the invention, network entity objects are divided into grid areas corresponding to geographical location information. The NB-IoT signal characteristics and 4G signal characteristics of each grid area facilitate the subsequent establishment of a grid feature association model. Step S102 specifically includes the following steps:

[0065] S1021. Divide the preset area into multiple grid areas based on the geographical location information, so that each grid area contains at least one network entity object;

[0066] S1022. Based on the measurement time, the wireless signal quality indicators of network entities in each grid area are statistically analyzed to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each grid area.

[0067] Among them, the NB-IoT signal grid features include NB-IoT signal quality indicators at multiple times, and the 4G signal grid features include 4G signal quality indicators at multiple times.

[0068] Specifically, when performing wireless signal quality index statistics, if there are multiple network entities with NB-IoT signal characteristics within the grid area, the average value of the NB-IoT signal quality index can be taken. If there are no network entities with NB-IoT signal characteristics within the grid area (all are 4G signal characteristics), the NB-IoT signal quality index of the grid area can be represented by 0 or a preset benchmark value.

[0069] S103. Establish a grid feature association model for a preset area based on the grid features of NB-IoT signals and 4G signals. The grid feature association model includes the mapping relationship between the grid features of NB-IoT signals and 4G signals in each grid area.

[0070] Specifically, this embodiment of the invention establishes a grid feature association model for wireless signal measurement data from different sources within the same geographical area. Using geographical grids as units, it analyzes the association between the 4G signal grid features of each grid area and those of adjacent grid areas, as well as the association between the 4G signal grid features and NB-IoT signal grid features within each grid area. Furthermore, during the association analysis, the measurement time of the wireless signal measurement data is introduced as a time dimension to improve the accuracy and reliability of the association model. Step S103 specifically includes the following steps:

[0071] S1031. Determine the feature similarity of the 4G signal grid features between each grid area and the adjacent grid areas. If the feature similarity is greater than or equal to a preset first threshold, merge the grid areas with the adjacent grid areas to obtain feature grid blocks.

[0072] S1032. Determine the average NB-IoT signal quality of each feature grid block at each time point and the average 4G signal quality of the 4G signal quality index.

[0073] S1033. Establish the first mapping relationship between the average NB-IoT signal quality and the average 4G signal quality at each time point, and construct a grid feature association model based on the first mapping relationship.

[0074] As a further optional implementation, the step of determining the feature similarity of the 4G signal grid features between each grid region and adjacent grid regions specifically includes:

[0075] B1. Determine the 4G signal feature vector of the grid area based on the 4G signal quality index of the grid area at each time.

[0076] B2. Calculate the cosine similarity between the 4G signal feature vectors of each grid region and the adjacent grid regions, and use the cosine similarity as the feature similarity.

[0077] Specifically, for each grid area, multiple data dimensions are established based on the measurement time. A 4G signal feature vector is determined based on the 4G signal quality index at each measurement time (corresponding to each moment). For example, the 4G signal quality index corresponding to moment 1 is M1, the 4G signal quality index corresponding to moment 2 is M2, and the 4G signal quality index corresponding to moment n is M... n Then an n-dimensional eigenvector (M1, M2…M) can be determined. nAfter determining the 4G signal feature vector of each grid region, the grid regions are merged based on whether the cosine similarity between the 4G signal feature vector of each grid region and the 4G signal feature vector of the adjacent region is greater than or equal to a preset first threshold. Finally, multiple feature grid blocks are obtained, and each feature grid block includes at least one grid region.

[0078] For each feature grid block, calculate the average NB-IoT signal quality and the average 4G signal quality at each time point, thereby establishing the first mapping relationship between the two and obtaining the grid feature association model.

[0079] S104. Obtain the 4G signal area features of the target area, match the 4G signal area features according to the grid feature association model to obtain the matched target NB-IoT signal grid features, and predict the NB-IoT access signal quality of the target area based on the target NB-IoT signal grid features.

[0080] Specifically, the NB-IoT access signal quality in NB-IoT service-deficient areas can be predicted using a grid feature correlation model. Features of 4G signal measurement data are extracted from these areas. Grid regions with similar 4G signal features are found using the grid feature correlation model, and the corresponding NB-IoT signal grid features are matched. This allows for the prediction of the NB-IoT access signal quality in the NB-IoT service-deficient area, facilitating the assessment of the potential for promoting and developing NB-IoT service terminals in this area. Step S104 specifically includes the following steps:

[0081] S1041. Divide the target area into multiple target grids, determine the current 4G signal quality of each target grid, and determine the 4G signal area characteristics based on the current 4G signal quality.

[0082] S1042. Determine the first difference between the current 4G signal quality and the average of each 4G signal quality. When the first difference is less than or equal to a preset second threshold, use the average of the 4G signal quality as a candidate matching value, and obtain the time corresponding to the candidate matching value as a candidate time.

[0083] S1043. Select the candidate matching value corresponding to the candidate time closest to the current time as the feature matching value of the current 4G signal quality, and determine the average NB-IoT signal quality corresponding to the feature matching value as the average target NB-IoT signal quality of the target grid according to the first mapping relationship.

[0084] S1044. Determine the target NB-IoT signal grid characteristics based on the average target NB-IoT signal quality, and determine the NB-IoT access signal quality of the corresponding target grid based on the average target NB-IoT signal quality, thereby obtaining the distribution of NB-IoT access signal quality in the target area.

[0085] Specifically, in this embodiment of the invention, the target area is also divided into multiple target grids. The size of the target grids can be consistent with the size of the aforementioned grid area to facilitate matching. After determining the current 4G signal quality of the target grid, the average 4G signal quality with a difference less than or equal to a second threshold is selected as a candidate matching value. Then, based on the time dimension, the most recent candidate matching value is selected as the feature matching value with the matching degree. Thus, the corresponding target NB-IoT signal quality average can be determined according to the first mapping relationship, and this value is used as the predicted value of the NB-IoT access signal quality of the target grid. After determining the predicted value of the NB-IoT access signal quality of each target grid, the distribution of the NB-IoT access signal quality of the entire target area can be predicted.

[0086] As an optional implementation, the NB-IoT access signal quality prediction method further includes the following steps:

[0087] Acquire incremental signal measurement data for a preset area and continuously refine the raster feature association model based on the incremental signal measurement data.

[0088] Specifically, after the grid feature association model of this invention is established, it can be optimized and corrected according to the real-time updated signal measurement data, so that each time a new target area is predicted, it can be matched with newer measurement data, thereby further improving the accuracy of NB-IoT access signal quality.

[0089] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention establish a mapping relationship between 4G signal grid features and NB-IoT signal grid features. Based on the 4G signal area features of the target area, the NB-IoT access signal quality is predicted. The wide coverage and high update frequency of 4G signal measurement data compensate for the relatively small mobile range and relatively limited signal quality measurement data collected by NB-IoT service terminals, thus improving the efficiency and accuracy of NB-IoT access signal quality prediction. This method can be used for NB-IoT access signal quality prediction before the deployment of NB-IoT service terminals, providing convenience for network planning by NB-IoT operators.

[0090] Reference Figure 2 This invention provides an NB-IoT access signal quality prediction system, comprising:

[0091] The signal feature extraction module is used to acquire wireless signal measurement data of multiple different network entities within a preset area, and to extract features from the wireless signal measurement data to obtain the wireless signal features and geographical location information of each network entity. The wireless signal features include at least one of NB-IoT signal features and 4G signal features.

[0092] The signal feature statistics module is used to divide a preset area into multiple grid areas based on geographical location information, and to statistically analyze the wireless signal characteristics of network entities in each grid area to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each grid area.

[0093] The association model construction module is used to establish an association model of grid features for a preset area based on the grid features of NB-IoT signals and 4G signals. The grid feature association model includes the mapping relationship between the grid features of NB-IoT signals and 4G signals in each grid area.

[0094] The signal quality prediction module is used to acquire the 4G signal area features of the target area, match the 4G signal area features according to the grid feature association model to obtain the matched target NB-IoT signal grid features, and predict the NB-IoT access signal quality of the target area based on the target NB-IoT signal grid features.

[0095] The content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0096] Reference Figure 3 This invention provides an NB-IoT access signal quality prediction device, comprising:

[0097] At least one processor;

[0098] At least one memory for storing at least one program;

[0099] When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned NB-IoT access signal quality prediction method.

[0100] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0101] This invention also provides a computer-readable storage medium storing a processor-executable program that, when executed by a processor, performs the aforementioned NB-IoT access signal quality prediction method.

[0102] This invention provides a computer-readable storage medium that can execute an NB-IoT access signal quality prediction method provided in the method embodiments of this invention. It can execute any combination of the implementation steps of the method embodiments and has the corresponding functions and beneficial effects of the method.

[0103] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform... Figure 1 The method shown.

[0104] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0105] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0106] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0108] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or, if necessary, processing in other suitable ways, and then stored in computer memory.

[0109] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0110] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0111] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0112] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for predicting NB-IoT access signal quality, characterized in that, Includes the following steps: The wireless signal measurement data of multiple different network entities within a preset area are acquired, and feature extraction is performed on the wireless signal measurement data to obtain the wireless signal characteristics and geographical location information of each network entity. The wireless signal characteristics include at least one of NB-IoT signal characteristics and 4G signal characteristics. The preset area is divided into multiple grid areas based on the geographical location information, and the wireless signal characteristics of the network entity objects in each grid area are statistically analyzed to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each grid area. A grid feature association model for the preset area is established based on the NB-IoT signal grid features and the 4G signal grid features. The grid feature association model includes the mapping relationship between the NB-IoT signal grid features and the 4G signal grid features of each grid area. The 4G signal area features of the target area are obtained, and the 4G signal area features are matched according to the grid feature association model to obtain the matched target NB-IoT signal grid features. The NB-IoT access signal quality of the target area is predicted according to the target NB-IoT signal grid features.

2. The NB-IoT access signal quality prediction method according to claim 1, characterized in that, The step of extracting features from the wireless signal measurement data to obtain the wireless signal features and geographical location information of each network entity specifically includes: Determine the wireless signal type, wireless signal quality index, measurement location, and measurement time for each wireless signal measurement data; The wireless signal characteristics of the corresponding network entity are determined based on the wireless signal quality index and the measurement time, and the wireless signal characteristics are determined to be NB-IoT signal characteristics or 4G signal characteristics based on the wireless signal type. The geographical location information of each network entity object is determined based on the measured location.

3. The NB-IoT access signal quality prediction method according to claim 2, characterized in that, The step of dividing the preset area into multiple grid areas based on the geographical location information, and statistically analyzing the wireless signal characteristics of the network entity objects within each grid area to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each grid area, specifically includes: The preset area is divided into multiple grid areas based on the geographic location information, such that each grid area contains at least one of the network entity objects; Based on the measurement time, the wireless signal quality indicators of the network entities in each of the grid areas are statistically analyzed to obtain the NB-IoT signal grid characteristics and 4G signal grid characteristics of each of the grid areas; The NB-IoT signal grid features include NB-IoT signal quality indicators at multiple times, and the 4G signal grid features include 4G signal quality indicators at multiple times.

4. The NB-IoT access signal quality prediction method according to claim 3, characterized in that, The step of establishing a grid feature association model for the preset area based on the NB-IoT signal grid features and the 4G signal grid features specifically includes: Determine the feature similarity of the 4G signal grid features between each grid region and the adjacent grid regions. If the feature similarity is greater than or equal to a preset first threshold, merge the grid regions with the adjacent grid regions to obtain feature grid blocks. Determine the average NB-IoT signal quality of the NB-IoT signal quality index and the average 4G signal quality of the 4G signal quality index for each of the aforementioned feature grid blocks at each of the aforementioned times. A first mapping relationship is established between the average NB-IoT signal quality and the average 4G signal quality at each specified time, and the grid feature association model is constructed based on the first mapping relationship.

5. The NB-IoT access signal quality prediction method according to claim 4, characterized in that, The step of determining the feature similarity between each of the grid regions and the 4G signal grid features of adjacent grid regions specifically includes: The 4G signal feature vector of the grid region is determined based on the 4G signal quality index of the grid region at each of the stated times; Calculate the cosine similarity between the 4G signal feature vectors of each grid region and the adjacent grid regions, and use the cosine similarity as the feature similarity.

6. The NB-IoT access signal quality prediction method according to claim 4, characterized in that, The step of acquiring the 4G signal area features of the target area, matching the 4G signal area features according to the grid feature association model to obtain the matched target NB-IoT signal grid features, and predicting the NB-IoT access signal quality of the target area based on the target NB-IoT signal grid features specifically includes: The target area is divided into multiple target grids, and the current 4G signal quality of each target grid is determined. Based on the current 4G signal quality, the 4G signal area characteristics are determined. Determine a first difference between the current 4G signal quality and the average of each 4G signal quality. When the first difference is less than or equal to a preset second threshold, use the average of the 4G signal quality as a candidate matching value, and obtain the time corresponding to the candidate matching value as a candidate time. The candidate matching value corresponding to the candidate time closest to the current time is selected as the feature matching value of the current 4G signal quality, and the average NB-IoT signal quality corresponding to the feature matching value is determined as the average target NB-IoT signal quality of the target grid according to the first mapping relationship. The target NB-IoT signal grid features are determined based on the average target NB-IoT signal quality, and the NB-IoT access signal quality of the corresponding target grid is determined based on the average target NB-IoT signal quality, thereby obtaining the distribution of the NB-IoT access signal quality in the target area.

7. A method for predicting NB-IoT access signal quality according to any one of claims 1 to 6, characterized in that, The NB-IoT access signal quality prediction method further includes the following steps: The signal measurement increment data of the preset area is obtained, and the grid feature association model is continuously corrected based on the signal measurement increment data.

8. An NB-IoT access signal quality prediction system, characterized in that, include: The signal feature extraction module is used to acquire wireless signal measurement data of multiple different network entity objects within a preset area, and to extract features from the wireless signal measurement data to obtain the wireless signal features and geographical location information of each network entity object. The wireless signal features include at least one of NB-IoT signal features and 4G signal features. The signal feature statistics module is used to divide the preset area into multiple grid areas according to the geographical location information, and to count the wireless signal features of the network entity objects in each grid area to obtain the NB-IoT signal grid features and 4G signal grid features of each grid area. The association model construction module is used to establish a grid feature association model for the preset area based on the NB-IoT signal grid features and the 4G signal grid features. The grid feature association model includes the mapping relationship between the NB-IoT signal grid features and the 4G signal grid features of each grid area. The signal quality prediction module is used to acquire the 4G signal area features of the target area, match the 4G signal area features according to the grid feature association model to obtain the matched target NB-IoT signal grid features, and predict the NB-IoT access signal quality of the target area based on the target NB-IoT signal grid features.

9. An NB-IoT access signal quality prediction device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements an NB-IoT access signal quality prediction method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to perform an NB-IoT access signal quality prediction method as described in any one of claims 1 to 7.

Images