CN116321274B

CN116321274B - Network access evaluation method, device, 5G micro base station and readable storage medium

Info

Publication number: CN116321274B
Application number: CN202310299850.5A
Authority: CN
Inventors: 汪昆
Original assignee: Boxin Communication Co ltd
Current assignee: Boxin Communication Co ltd
Priority date: 2023-03-25
Filing date: 2023-03-25
Publication date: 2025-05-09
Anticipated expiration: 2043-03-25
Also published as: CN116321274A

Abstract

The present application relates to the field of public network coverage, and in particular to a network access evaluation method, device, 5G micro base station and readable storage medium, the method comprising: obtaining a crowd density model based on a number of signaling data in a car obtained in real time; obtaining a target reference crowd density model based on the crowd density model and multiple reference crowd density models; obtaining preset network evaluation parameters corresponding to the target reference crowd density model based on the first corresponding relationship and the target reference crowd density model; obtaining real-time network evaluation parameters in the car; and obtaining network access evaluation results based on preset network evaluation parameters and real-time network evaluation parameters corresponding to the target reference crowd density model; judging whether the network access evaluation results meet the preset network evaluation requirements; if not, adjusting the network evaluation parameters based on the preset network evaluation parameters corresponding to the target reference crowd density model. The present application has the effect of improving the authenticity of network access evaluation results.

Description

Network access evaluation method and device, 5G micro base station and readable storage medium

Technical Field

The application relates to the technical field of public network coverage, in particular to a network access evaluation method and device, a 5G micro base station and a readable storage medium.

Background

Currently, to optimize train network quality, micro base stations may be applied to public network coverage engineering in the train cars. In the network evaluation process of the micro base station in the carriage, the network evaluation standard suitable for the carriage is generally selected based on the crowd density of the carriage.

However, the people may not be uniformly distributed in the carriage, so that the people distribution in the carriage reflected by the crowd density is compared, so that the network evaluation standard selected based on the crowd density of the carriage does not fit the requirement of the carriage on the network, and the network evaluation of the micro base station in the carriage may obtain an evaluation result with lower authenticity.

Therefore, how to provide a solution to the above technical problem is a problem that a person skilled in the art needs to solve at present.

Disclosure of Invention

In order to realize more realistic network evaluation, the application provides a network access evaluation method, a device, a 5G micro base station and a readable storage medium.

In a first aspect, the present application provides a network access evaluation method, which adopts the following technical scheme:

a network access assessment method, comprising:

acquiring a plurality of signaling data in a carriage in real time, wherein the signaling data represents communication data of user mobile equipment;

obtaining a people flow density model based on a plurality of signaling data in the carriage, wherein the people flow density model represents personnel distribution condition information in the carriage;

Obtaining a target reference people stream density model according to the people stream density model and a plurality of reference people stream density models, wherein the target reference people stream density model is the reference people stream density model with the maximum similarity with the people stream density model in the plurality of reference people stream density models;

Obtaining a preset network evaluation parameter corresponding to the target reference people stream density model according to a first corresponding relation and the target reference people stream density model, wherein the first corresponding relation is a corresponding relation between a plurality of preset reference people stream density models and a plurality of preset network evaluation parameters;

Acquiring a real-time network evaluation parameter in a carriage, and acquiring a network access evaluation result based on a preset network evaluation parameter and a real-time network evaluation parameter corresponding to a target reference people stream density model, wherein the network access evaluation result represents the difference value between the preset network evaluation parameter and the real-time network evaluation parameter corresponding to the target reference people stream density model;

and if not, adjusting the network evaluation parameters based on the preset network evaluation parameters corresponding to the target reference people stream density model.

By adopting the technical scheme, the signaling data is utilized to construct the people flow density model, the timeliness of the reflected people distribution condition can be further improved by acquiring the signaling data in real time on the basis of improving the authenticity of the people distribution condition in the carriage, the preset network evaluation parameter corresponding to the target reference people flow density model is obtained according to the corresponding relation between the preset reference people flow density model and the preset network evaluation parameter and the target reference people flow density model, the preset network evaluation parameter set based on the reference people flow density model is characterized as the network evaluation standard, the network evaluation standard can be selected based on the more reasonable personnel distribution in the carriage, the network evaluation standard can be more attached to the network demand in the carriage, the real-time network evaluation parameter is acquired, and the network access evaluation result is obtained based on the preset network evaluation parameter and the real-time network evaluation parameter, so that the authenticity of the network access evaluation result is improved.

The present application may be further configured in a preferred example to:

the real-time network assessment parameters include a plurality of parameters,

The network access evaluation result is obtained based on the preset network evaluation parameter and the real-time network evaluation parameter corresponding to the target reference people stream density model, and the method comprises the following steps:

Obtaining each sub-network access evaluation result according to each parameter and a target parameter corresponding to each parameter in preset network evaluation parameters;

And obtaining a network access evaluation result according to all the sub-network access evaluation results and the preset number of the sub-network access evaluation results.

By adopting the technical scheme, the influence of each target parameter on the network quality, which is larger than or smaller than the corresponding specific parameter in the preset network evaluation parameters, is possibly positive or negative, and the difference exists, but in the related technology, the network access evaluation result is obtained based on the numerical value and positive or negative of the specific parameter difference, and the difference between the positive or negative of the specific parameter difference and the influence on the network quality is ignored.

The present application may be further configured in a preferred example to:

the method further comprises the steps of after obtaining the network access evaluation result based on the preset network evaluation parameter and the real-time network evaluation parameter corresponding to the target reference people stream density model:

Monitoring a plurality of dynamic signaling data after a preset time interval, and predicting personnel distribution conditions at preset time by utilizing a preset personnel flow density model algorithm according to the plurality of dynamic signaling data to obtain a predicted personnel flow density model;

Obtaining a target reference people stream density model corresponding to the predicted people stream density model according to the predicted people stream density model and the plurality of reference people stream density models, and obtaining a preset network evaluation parameter corresponding to the predicted people stream density model according to the first corresponding relation and the target reference people stream density model corresponding to the predicted people stream density model;

and when the preset moment is reached, adjusting the network evaluation parameters according to the preset network evaluation parameters corresponding to the predicted people stream density model.

By adopting the technical scheme, compared with the existing signaling data to obtain the people stream density model, the real-time network evaluation parameter is adjusted according to the people stream density model, the network evaluation parameter is adjusted at the moment by obtaining the predicted people stream density model at the preset moment and utilizing the preset network evaluation parameter corresponding to the predicted people stream density model, and the process of adjusting the network evaluation parameter can be advanced from any moment to any moment so as to improve the timeliness of the network evaluation parameter adjusting process.

The present application may be further configured in a preferred example to:

and after predicting the personnel distribution condition at the preset moment by utilizing a preset people flow density model algorithm according to the plurality of dynamic signaling data to obtain a predicted people flow density model, the method further comprises the following steps:

When the time reaches the preset time, acquiring an actual people flow density model at the preset time;

Obtaining the similarity between the actual people stream density model and the predicted people stream density model according to the actual people stream density model and the predicted people stream density model, and judging whether the similarity meets the preset similarity requirement or not;

If not, acquiring the actual people stream density models corresponding to the adjacent moments of the preset moment, and correcting the predicted people stream density algorithm according to the actual people stream density models corresponding to the adjacent moments to obtain a corrected predicted people stream density model algorithm.

By adopting the technical scheme, the similarity between the actual people stream density model and the predicted people stream density model is judged to be insufficient in accuracy, and the predicted people stream density model algorithm is judged to be insufficient in accuracy.

The present application may be further configured in a preferred example to:

the first corresponding relation comprises a plurality of second corresponding relations, the second corresponding relations are corresponding relations between a plurality of preset reference people stream density models and a plurality of preset network evaluation parameters of any operation area,

After the target reference people stream density model is obtained according to the people stream density model and the plurality of reference people stream density models, the method further comprises the following steps:

Acquiring an operation area of a train;

obtaining a second corresponding relation corresponding to the operation area according to the corresponding relation between the preset operation area and the second corresponding relation and the operation area;

Correspondingly, the obtaining the preset network evaluation parameters corresponding to the target reference people stream density model according to the first corresponding relation and the target reference people stream density model comprises the following steps:

And obtaining a preset network evaluation parameter corresponding to the target reference people stream density model according to the second corresponding relation corresponding to the operating area and the target reference people stream density model.

By adopting the technical scheme, the second corresponding relation corresponding to the operating region is confirmed in the first corresponding relation, the range of the preset network evaluation parameter corresponding to the target reference people stream density model can be narrowed, the preset network evaluation parameter corresponding to the target reference people stream density model is obtained according to the second corresponding relation corresponding to the operating region and the target reference people stream density model, and the acquisition speed of the preset network evaluation parameter corresponding to the target reference people stream density model can be improved.

The present application may be further configured in a preferred example to:

Each reference people stream density model includes a plurality of reference unit people stream density models,

The obtaining a target reference people stream density model according to the people stream density model and a plurality of reference people stream density models comprises the following steps:

According to the people stream density model, a plurality of unit people stream density models are obtained through segmentation, wherein the people stream density model and a reference people stream density model are the same in segmentation mode;

According to each reference unit people stream density model and the corresponding unit people stream density model, sub-similarity between each reference unit people stream density model and the corresponding unit people stream density model of each reference unit people stream density model is obtained, and the similarity between the reference people stream density model and the people stream density model is determined according to all sub-similarities;

and determining a target reference people stream density model from all the reference people stream density models according to the similarity corresponding to each of all the reference people stream density models.

By adopting the technical scheme, compared with the reference people stream density model and the people stream density model which are integrally compared in the related art, the method and the device for obtaining the similarity between the whole reference unit people stream density model and the corresponding unit people stream density model by utilizing the whole reference unit people stream density model and the corresponding unit people stream density model aiming at each reference people stream density model can pay attention to local information in the people stream density model, and can reflect the similarity between the reference people stream density model and the people stream density model more so as to improve the reality of the similarity.

The present application may be further configured in a preferred example to:

After the multiple unit people stream density models are obtained through segmentation according to the people stream density models, the method further comprises the following steps:

Judging whether the people flow density model has any personnel position information in a car or not;

If yes, obtaining a plurality of key unit people stream density models according to the plurality of unit people stream density models, wherein the key unit people stream density models represent the unit people stream density models comprising the personnel position information in the carriage;

Correspondingly, the obtaining sub-similarity between each reference unit people stream density model and the corresponding unit people stream density model according to each reference unit people stream density model and the corresponding unit people stream density model comprises the following steps:

And obtaining sub-similarity between each key unit people stream density model and the reference unit people stream density model corresponding to each key unit people stream density model according to each key unit people stream density model and the corresponding reference unit people stream density model.

By adopting the technical scheme, the similarity between all the reference key unit people stream density models and the corresponding key unit people stream density models is obtained by utilizing all the reference key unit people stream density models and the corresponding key unit people stream density models, the process of obtaining the similarity between the key unit people stream density models which do not comprise the personnel position information in any carriage and the reference key unit people stream density models can be reduced, and the speed of obtaining the similarity process is improved.

In a second aspect, the present application provides a network access evaluation device, which adopts the following technical scheme:

a network access assessment device, comprising:

the system comprises a signaling data acquisition module, a signaling data processing module and a control module, wherein the signaling data acquisition module is used for acquiring a plurality of signaling data in a carriage in real time, wherein the signaling data represents communication data of user mobile equipment;

the traffic density model generation module is used for obtaining a traffic density model based on a plurality of signaling data in the carriage, wherein the traffic density model represents personnel distribution condition information in the carriage;

The target reference people stream density model selecting module is used for obtaining a target reference people stream density model according to the people stream density model and a plurality of reference people stream density models, wherein the target reference people stream density model is a reference people stream density model with the maximum similarity with the people stream density model in the plurality of reference people stream density models;

The preset network evaluation parameter determining module is used for obtaining preset network evaluation parameters corresponding to the target reference people stream density model according to a first corresponding relation and the target reference people stream density model, wherein the first corresponding relation is the corresponding relation between a plurality of preset reference people stream density models and a plurality of preset network evaluation parameters;

The system comprises a network access evaluation result generation module, a real-time network evaluation parameter generation module, a network access evaluation result generation module and a real-time network evaluation module, wherein the network access evaluation result generation module is used for acquiring real-time network evaluation parameters in a carriage, and obtaining a network access evaluation result based on preset network evaluation parameters and real-time network evaluation parameters corresponding to a target reference people stream density model, wherein the network access evaluation result represents the difference value between the preset network evaluation parameters and the real-time network evaluation parameters corresponding to the target reference people stream density model;

the network evaluation parameter qualification judging module is used for judging whether the network access evaluation result meets the preset network evaluation requirement, and triggering the network evaluation parameter adjusting module when the network access evaluation result does not meet the preset network evaluation requirement;

the network evaluation parameter adjustment module is used for adjusting the network evaluation parameters based on preset network evaluation parameters corresponding to the target reference people stream density model.

In a third aspect, the present application provides a 5G micro base station, which adopts the following technical scheme:

at least one processor;

A memory;

At least one application stored in memory and configured to be executed by at least one processor, the at least one application configured to perform the network access assessment method of any of the first aspects.

In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:

A computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the network access assessment method according to any one of the first aspect.

In summary, the present application includes at least one of the following beneficial technical effects:

1. The method comprises the steps of establishing a people flow density model by using signaling data, acquiring the signaling data in real time on the basis of improving and reflecting the authenticity of personnel distribution conditions in a carriage, further improving the timeliness of the reflected personnel distribution conditions, obtaining a preset network evaluation parameter corresponding to a target reference people flow density model according to the corresponding relation between the preset reference people flow density model and the preset network evaluation parameter and the target reference people flow density model, characterizing the preset network evaluation parameter set based on the reference people flow density model as a network evaluation standard, selecting the network evaluation standard more reasonably based on personnel distribution in the carriage, enabling the network evaluation standard to be more fit with the requirements of the carriage on the network, obtaining real-time network evaluation parameters, obtaining a network access evaluation result based on the preset network evaluation parameter and the real-time network evaluation parameter, and improving the authenticity of the network access evaluation result.

2. Compared with the existing signaling data, the people stream density model is obtained, and then the real-time network evaluation parameters are regulated according to the people stream density model, the scheme obtains the predicted people stream density model at the preset moment, and the network evaluation parameters are adjusted by using the preset network evaluation parameters corresponding to the predicted people flow density model at the moment, so that the process of adjusting the network evaluation parameters can be advanced to any moment from any moment so as to improve the timeliness of the network evaluation parameter adjusting process.

Drawings

Fig. 1 is a flow chart of a network access evaluation method according to an embodiment of the present application.

Fig. 2 is a schematic structural diagram of a preset coordinate plane according to an embodiment of the present application.

Fig. 3 is a schematic signal coverage diagram of a 5G micro base station in a vehicle cabin according to an embodiment of the present application.

Fig. 4 is a schematic structural diagram of a network access evaluation device according to an embodiment of the present application.

Fig. 5 is a schematic structural diagram of a 5G micro base station according to an embodiment of the present application.

Detailed Description

The present application will be described in further detail with reference to the accompanying drawings.

The present embodiment is only for explanation of the present application and is not to be construed as limiting the present application, and modifications to the present embodiment, which may not creatively contribute to the present application as required by those skilled in the art after reading the present specification, are all protected by patent laws within the scope of claims of the present application.

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application are clearly and completely described, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

In addition, the term "and/or" is merely an association relation describing the association object, and means that three kinds of relations may exist, for example, a and/or B, and that three kinds of cases where a exists alone, while a and B exist alone, exist alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.

Micro base station (also called Micro station), when the bandwidth is 20MHz, the single carrier wave transmitting power is 500mW to 10W, and the coverage radius is 50 m to 200 m.

Generally, a train has problems of poor communication signal and network quality of train passengers caused by signal attenuation and degradation due to car shielding and Doppler shift. In order to solve the problems, a railway special public network coverage system based on a vehicle-mounted micro base station is constructed, wherein the micro base station is arranged in a carriage as signal supply to enable the positions of a train and passengers to be relatively static, so that the communication signal and the network quality are improved.

However, when the number of passengers in the carriage is large, the requirements for call signals and network quality are high, and when the requirements for the number of passengers in the carriage are high, the working power of the micro base station is high, and because the mobility of personnel in the carriage is high, the parameters of the micro base station are often set according to the maximum number of passengers in the carriage in order to meet the requirements for the call signals and the network quality, so that the micro base station in the carriage often operates in an overall operation time period with high power, and when the number of the passengers in the carriage is small, the micro base station still operates with high power, and resource waste can be caused. In order to reduce the waste of resources, a method for adjusting the related parameters of the micro base station by the crowd density in the carriage is proposed in the following technology to adjust the running power of the micro base station.

However, passengers may not be uniformly distributed in the cabin, so that the passenger distribution in the cabin is reflected by the crowd density, and the network evaluation standard selected based on the crowd density of the cabin is not fit with the requirement of the cabin for the network, so that the network evaluation of the micro base station in the cabin may obtain an evaluation result with lower authenticity.

The inventor finds that the method comprises the steps of obtaining a traffic density model based on a plurality of signaling data in a carriage after obtaining a plurality of signaling data in the carriage in real time, obtaining a target reference traffic density model according to the traffic density model and a plurality of reference traffic density models, obtaining preset network evaluation parameters corresponding to the target reference traffic density model according to a first corresponding relation and the target reference traffic density model, obtaining network access evaluation results based on the preset network evaluation parameters corresponding to the target reference traffic density model and the real-time network evaluation parameters after obtaining the real-time network evaluation parameters in the carriage, and finally judging whether the network access evaluation results meet preset network evaluation requirements or not, and if not, adjusting the network evaluation parameters based on the preset network evaluation parameters corresponding to the target reference traffic density model.

Embodiments of the application are described in further detail below with reference to the drawings.

The embodiment of the application provides a network access evaluation method, which is executed by 5G micro base stations, wherein the 5G micro base stations can be installed in each car to realize the network access evaluation method, and as shown in fig. 1, the method comprises the steps of S101 to S107, wherein:

Step S101, acquiring a plurality of signaling data in a carriage in real time, wherein the signaling data represent communication data of a user mobile phone.

The signaling data may be mobile device signaling data characterizing communication data between the mobile device and the micro base station. Signaling data begins to be generated when the mobile device is powered on and any operator typeface is displayed on the device screen. In general, the signaling data of the mobile device is a control instruction in the communication system, which can instruct the terminal, the switching system and the transmission system to cooperatively operate, and establish a temporary communication channel between the designated terminals and maintain the normal operation of the network itself.

The number of signaling data in the carriage is positively correlated with the number of personnel in the carriage, so the number of signaling data can be one or a plurality of the number of the signaling data without existence.

Further, when the number of signaling data in the carriage does not exist, the 5G micro base station is adjusted to a standby state until the 5G micro base station receives any signaling data again, and then steps S102 to S107 are executed.

Step S102, a people flow density model is obtained based on a plurality of signaling data in the carriage, wherein the people flow density model represents personnel distribution information in the carriage.

Specifically, according to each signaling data, obtaining each passenger position information, wherein the passenger position information can be passenger position information and the passenger position information can be in a coordinate form, and mapping all the passenger position information on a preset coordinate plane to obtain a people stream density model.

As shown in fig. 2, the preset coordinate plane is a two-dimensional coordinate system with a 5G micro base station as an origin and limited in size. When the transverse axis is parallel to the carriage length, the longitudinal axis is perpendicular to the carriage length, the transverse axis length is the carriage length, the longitudinal axis length is the carriage width, and when the transverse axis is parallel to the carriage width, the longitudinal axis is perpendicular to the carriage width, the transverse axis is the carriage width, and the longitudinal axis is the carriage length.

Step S103, obtaining a target reference people stream density model according to the people stream density model and a plurality of reference people stream density models, wherein the target reference people stream density model is the reference people stream density model with the maximum similarity with the people stream density model in the plurality of reference people stream density models.

Specifically, the implementation manner of step S103 may specifically include a clustering-based manner or a segmentation-based manner.

In a cluster-based implementation, step S103 may specifically include steps S1031a to S1035a (not shown in the figure), where:

Step S1031a, according to the people stream Density model, obtaining the number of the passenger position information sets and the number of the passenger position information in each passenger position information set through clustering, wherein the clustering mode can be any one of DBSCAN (Density-Based Spatial Clustering of Applications with Noise, density maximum clustering algorithm of a Density-based clustering method ）、WS-DBSCAN（Weighted-Stop Density-Based Scanning Algorithm with Noise）、MDCA（Maximum Density Clustering Application, with noise).

Step S1032a, for each reference people stream density model, judges whether the number of the passenger position information sets and the reference passenger position information sets are the same.

The reference people stream density model can be stored in the 5G micro base station in advance by a technician, and the number of the reference passenger position information sets in the reference people stream density model can be calculated in advance by the technician when the reference people stream density model is set and stored in the 5G micro base station. Each reference people flow density model corresponds to each personnel distribution condition in the carriage, and the personnel distribution conditions at least comprise five conditions of passenger preparation for getting off, passenger getting on and train stable running.

If the two models are different, the similarity between the reference people stream density model and the people stream density model is 0.

Step S1033a, if the two passenger position information sets are the same, the similarity between the reference passenger flow density model and the passenger flow density model is not 0, and the corresponding relation between each passenger position information set and each reference passenger position information set is established.

Step S1034a, based on the corresponding relation between each passenger position information set and each reference passenger position information set, obtaining the similarity between the reference passenger flow density model and the passenger flow density model by using a similarity calculation formula according to the quantity of the passenger position information sets, the quantity of the passenger position information in each passenger position information set and the quantity of the passenger position information in each passenger position information set in the reference passenger flow density model.

The similarity calculation formula may be that, as the similarity, the number of passenger position information sets is the number of passenger position information in the ith passenger position information set in the reference people flow density model, and the number of passenger position information in the ith passenger position information set is the number of passenger position information.

Step S1035a, using the reference people stream density model with the maximum similarity among the similarity corresponding to all the reference people stream density models as the target reference people stream density model of the people stream density model.

In a segmentation-based implementation, step S103 may specifically include steps S1031b to S1033b (not shown in the figure), where:

Step S1031b, obtaining a plurality of unit people stream density models through segmentation according to the people stream density models, wherein the people stream density models are the same as the reference people stream density models in the segmentation mode.

Step S1032b, obtaining sub-similarity between each reference unit people stream density model and the corresponding unit people stream density model according to each reference unit people stream density model and the corresponding unit people stream density model, and determining the similarity between the reference people stream density model and the people stream density model according to all sub-similarities.

And step S1033b, determining a target reference people stream density model from all the reference people stream density models according to the similarity corresponding to each of all the reference people stream density models.

Step S104, obtaining a preset network evaluation parameter corresponding to the target reference people stream density model according to the first corresponding relation and the target reference people stream density model, wherein the first corresponding relation is the corresponding relation between the plurality of preset reference people stream density models and the plurality of preset network evaluation parameters.

The first corresponding relation can be set in advance by a technician and stored in the 5G micro base station, and further, the first corresponding relation can be periodically maintained and added and deleted by the technician. Correspondingly, the corresponding relation between each preset reference people stream density model and a plurality of preset network evaluation parameters corresponds to the number of train times one by one, the corresponding relation between the preset reference people stream density models and the plurality of preset network evaluation parameters can be set in advance by technicians and stored in the 5G micro base station, and further, the corresponding relation between the preset reference people stream density models and the plurality of preset network evaluation parameters can be maintained and increased or deleted by the technicians regularly.

The network evaluation parameters may include at least the number of radiation areas, and the signal radiation intensity and the range of radiation radii corresponding to the radiation intensity in each radiation area. For example, as shown in FIG. 3, when the number of the radiation areas is 3, the radiation areas may be 1 area, 2 area and 3 area, the signal radiation intensity of the 1 area is a, the radiation radius range is 0 to 5m, the signal radiation intensity of the 2 area is b, the radiation radius range is 6 to 15m, the signal radiation intensity of the 3 area is c, and the radiation radius range is 15 to 30 m.

Step 105, acquiring real-time network evaluation parameters in the carriage, and obtaining a network access evaluation result based on the preset network evaluation parameters and the real-time network evaluation parameters corresponding to the target reference people stream density model, wherein the network access evaluation result represents the difference value between the preset network evaluation parameters and the real-time network evaluation parameters corresponding to the target reference people stream density model.

The 5G micro base station can obtain real-time network evaluation parameters in the carriage through direct reading.

Based on the preset network evaluation parameters and the real-time network evaluation parameters corresponding to the target reference people stream density model, the implementation mode of obtaining the network access evaluation result can specifically comprise the steps of evaluating based on grades or evaluating based on scores.

In the implementation mode based on the grade evaluation, the step of obtaining the network access evaluation result based on the preset network evaluation parameter and the real-time network evaluation parameter corresponding to the target reference people stream density model specifically comprises the steps of judging whether the implementation parameter meets the preset parameter requirement according to the real-time parameter and the preset parameter for each parameter, wherein the real-time parameter is any one parameter of the real-time network evaluation parameters, the preset parameter is any one parameter of the preset network evaluation parameters, the preset parameter requirement can be prestored in the 5G micro base station by a technician, if yes, the parameters are determined to be qualified parameters, when all the parameters are qualified parameters, the network access evaluation result is determined to be qualified, and when any one parameter is unqualified, the network access evaluation result is determined to be unqualified.

In the implementation mode based on score evaluation, the step of obtaining the network access evaluation result based on the preset network evaluation parameter and the real-time network evaluation parameter corresponding to the target reference people stream density model specifically comprises the steps of obtaining each sub-network access evaluation result according to each parameter and the target parameter corresponding to each parameter in the preset network evaluation parameter, and obtaining the network access evaluation result according to all the sub-network access evaluation results and the preset sub-network access evaluation result number.

And S106, judging whether the network access evaluation result meets the preset network evaluation requirement.

Specifically, when the network access evaluation result is qualified, the preset network evaluation requirement is that the network access evaluation result is qualified, and when the network access evaluation result is that the score is not less than a preset score threshold, the preset network evaluation requirement can be prestored in the 5G micro base station by a technician according to the actual requirement.

If yes, the real-time network evaluation parameters meet the requirements of the carriage on the network, and the network evaluation parameters do not need to be adjusted.

And S107, if not, adjusting the network evaluation parameters based on the preset network evaluation parameters corresponding to the target reference people stream density model.

According to the embodiment of the application, the signaling data are acquired in real time on the basis of improving the authenticity of the personnel distribution situation in the carriage, the timeliness of the reflected personnel distribution situation can be further improved, the preset network evaluation parameters corresponding to the target reference personnel flow density model are obtained according to the corresponding relation between the preset reference personnel flow density model and the preset network evaluation parameters and the target reference personnel flow density model, the preset network evaluation parameters set based on the reference personnel flow density model are characterized as network evaluation standards, the network evaluation standards can be selected based on the personnel distribution in the carriage more reasonably, the network evaluation standards can be more fit with the network requirements in the carriage, the real-time network evaluation parameters are acquired, and the network access evaluation results are obtained based on the preset network evaluation parameters and the real-time network evaluation parameters, so that the authenticity of the network access evaluation results is improved.

Step S105 may specifically include step S1051 and step S1052 (not shown in the figure) according to one possible implementation manner of the embodiment of the present application, where:

Step S1051, obtaining each sub-network access evaluation result according to each parameter and the corresponding target parameter of each parameter in the preset network evaluation parameters.

The sub-network access evaluation result can be obtained by using a calculation formula of the sub-network access evaluation result, wherein the calculation formula of the sub-network access evaluation result can be that the sub-network access evaluation result is the ith sub-network access evaluation result, the ith parameter is the ith target parameter.

Specifically, when the sub-network access evaluation result corresponds to the number of parameter radiation areas, the number is positive. When the sub-network access evaluation result corresponds to the number of the signal radiation intensities in the parameter radiation area, the number is positive if the number is positive, and the number is negative if the number is negative. When the sub-network is accessed to the range of the radiation radius corresponding to the parameter radiation intensity corresponding to the evaluation result, the sub-network is positive, and the sub-network is negative.

Step S1052, obtaining the network access evaluation result according to all the sub-network access evaluation results and the preset number of the sub-network access evaluation results.

Specifically, the network access evaluation result can be obtained by using a calculation formula of the network access evaluation result, wherein the calculation formula of the network access evaluation result can be that the network access evaluation result is a preset number of sub-network access evaluation results and the i-th sub-network access evaluation result.

The preset number of sub-network access evaluation results can be stored in the 5G micro base station in advance by a technician.

In the embodiment of the application, the influence of each target parameter on the network quality, which is larger than or smaller than the specific parameter corresponding to each target parameter in the preset network evaluation parameters, is possibly positive or negative, and has a difference, but in the related technology, the network access evaluation result is obtained based on the numerical value and positive or negative of the specific parameter difference, and the difference between the positive or negative of the specific parameter difference and the influence on the network quality is ignored, so that the difference between the positive or negative of the specific parameter difference and the influence on the network quality can be distinguished in the process of obtaining the network quality evaluation result by adding the degree of the positive or negative of the target parameter on the network quality to the process of obtaining the network quality evaluation result, and the network access evaluation result is obtained according to the network access evaluation result, thereby improving the accuracy of the network access evaluation result.

One possible implementation manner of the embodiment of the present application may specifically further include step SA1 and step SA2 (not shown in the figure) after step S105, where:

And step SA1, monitoring a plurality of dynamic signaling data after a preset period of time, and predicting the personnel distribution condition at a preset moment by utilizing a preset personnel flow density model algorithm according to the plurality of dynamic signaling data to obtain a predicted personnel flow density model.

The preset time period and the preset time can be preset by a technician according to actual conditions and stored in the 5G micro base station in advance.

The method comprises the steps of obtaining speed information and position information of each piece of dynamic signaling data according to the detected dynamic signaling data, determining a predicted motion track according to the speed information and the speed direction, wherein the predicted motion track comprises a unique starting point which is a position corresponding to the position information, obtaining a current moment, obtaining a time length of the current moment from the preset moment according to the preset moment corresponding to the current moment and the preset moment, obtaining a predicted motion distance on the predicted motion track according to the time length and the speed direction, and obtaining the predicted position information based on the motion track and the predicted motion distance. And obtaining a predicted people flow density model at preset time according to the predicted position information corresponding to all the dynamic signaling data, wherein the preset time is any preset time in all the preset times, and the preset time can be stored in the 5G micro base station in advance by a technician.

And step SA2, obtaining a target reference people stream density model corresponding to the predicted people stream density model according to the predicted people stream density model and the plurality of reference people stream density models, and obtaining a preset network evaluation parameter corresponding to the predicted people stream density model according to the first corresponding relation and the target reference people stream density model corresponding to the predicted people stream density model.

Correspondingly, the step S106 specifically comprises the step of adjusting network evaluation parameters according to preset network evaluation parameters corresponding to the predicted people stream density model when the preset moment is reached.

In the embodiment of the application, compared with the existing signaling data to obtain the people stream density model, the real-time network evaluation parameter is adjusted according to the people stream density model, the method can advance the process of adjusting the network evaluation parameter from any moment to any moment by obtaining the predicted people stream density model at the preset moment and adjusting the network evaluation parameter by utilizing the preset network evaluation parameter corresponding to the predicted people stream density model at the moment, so that the timeliness of the network evaluation parameter adjusting process is improved.

In one possible implementation manner of the embodiment of the present application, after step SA1, step SB1 to step SB3 (not shown in the drawings) may be specifically further included, where:

And step SB1, when the time reaches the preset time, acquiring an actual people flow density model at the preset time.

The method comprises the steps of obtaining a plurality of signaling data at preset time, and obtaining an actual people stream density model based on the plurality of signaling data at the preset time.

And step SB2, obtaining the similarity between the actual people stream density model and the predicted people stream density model according to the actual people stream density model and the predicted people stream density model, and judging whether the similarity meets the preset similarity requirement.

The similarity between the actual people stream density model and the predicted people stream density model may be calculated by the content related to step S1034. The preset similarity requirement can be stored in the 5G micro base station in advance by a technician.

It can be understood that if the model algorithm is not correct, the accuracy of the model algorithm is lower, and if the model algorithm is not correct, the accuracy of the model algorithm is improved.

And step SB3, if not, acquiring actual people stream density models corresponding to a plurality of adjacent moments at preset moments, and correcting the predicted people stream density algorithm according to the actual people stream density models corresponding to the adjacent moments to obtain a corrected predicted people stream density model algorithm.

Specifically, if not, the actual people stream density models corresponding to a plurality of adjacent moments at the preset moment are used as training data, the predicted people stream density model algorithm is trained until the similarity between the predicted people stream density model at any moment and the actual people stream density at any moment obtained through the trained predicted people stream density model algorithm meets the preset similarity requirement, and the trained predicted people stream density model algorithm is used as the corrected predicted people stream density model algorithm.

In the embodiment of the application, the similarity between the actual people stream density model and the predicted people stream density model is judged to not meet the preset similarity requirement, so that the accuracy of the predicted people stream density model algorithm is not enough, and the predicted people stream density model algorithm is corrected through the acquired actual people stream density models corresponding to the adjacent times of the preset time, so that the accuracy of the predicted people stream density model algorithm is improved.

A possible implementation manner of the embodiment of the present application may specifically further include step SC1 and step SC2 (not shown in the figure) after step S103, where:

The first correspondence includes a plurality of second correspondences, and the second correspondences may be correspondences between a plurality of preset reference people stream density models and a plurality of preset network evaluation parameters in any operation area.

And step SC1, acquiring the operation area of the train.

Specifically, according to the corresponding relation between the preset train number and the operating area and the preset train number of the 5G micro base station, the operating area of the train where the 5G micro base station is located is obtained.

The corresponding relation between the preset train number and the operating area can be stored in the 5G micro base station in advance by a technician, and the preset train number of the 5G micro base station can be stored in advance when the 5G micro base station is installed.

And step SC2, obtaining a second corresponding relation corresponding to the operation area according to the corresponding relation between the preset operation area and the second corresponding relation and the operation area.

The corresponding relation between the preset operation area and the second corresponding relation can be stored in the 5G micro base station in advance by a technician.

Correspondingly, according to the first corresponding relation and the target reference people stream density model, the preset network evaluation parameters corresponding to the target reference people stream density model are obtained, and specifically the preset network evaluation parameters corresponding to the target reference people stream density model can be obtained according to the second corresponding relation corresponding to the operating region and the target reference people stream density model.

In the embodiment of the application, the range of the preset network evaluation parameters corresponding to the target reference people stream density model can be narrowed by confirming the second corresponding relation corresponding to the operating region in the first corresponding relation, the preset network evaluation parameters corresponding to the target reference people stream density model can be obtained according to the second corresponding relation corresponding to the operating region and the target reference people stream density model, and the acquisition speed of the preset network evaluation parameters corresponding to the target reference people stream density model can be improved.

In step S103, a possible implementation manner of the embodiment of the present application may specifically include step S1031b to step S1033b (not shown in the figure), where:

Each reference people stream density model includes a plurality of reference unit people stream density models.

The dividing manner of dividing the people stream density model into a plurality of unit people stream density models may be a preset dividing manner, wherein the preset dividing manner at least limits the dividing number and dividing area, and the preset dividing manner may be stored in the 5G micro base station in advance by a technician, and specifically, the dividing area is the area of each unit people stream density model.

The step of obtaining the sub-similarity between each reference unit people stream density model and the corresponding unit people stream density model according to each reference unit people stream density model and the corresponding unit people stream density model may specifically include S1032b-1 and S1032b-2 (not shown in the figure), wherein:

S1032b-1, according to the reference unit people stream density model and the corresponding unit people stream density model, obtaining the gray value corresponding to the reference unit people stream density model and the corresponding unit people stream density model respectively.

S1032b-2, aiming at each reference unit people stream density model, obtaining the sub-similarity between the reference unit people stream density model and the unit people stream density model corresponding to the reference unit people stream density model by utilizing the sub-similarity calculation formula according to the gray values corresponding to the reference unit people stream density model and the corresponding unit people stream density model.

The calculation formula of the sub-similarity can be that the sub-similarity corresponding to the i-th reference unit people stream density model is the gray value corresponding to the i-th reference unit people stream density model and the gray value corresponding to the i-th reference unit people stream density model.

The process of determining the similarity between the reference people stream density model and the people stream density model according to all the sub-similarities can be realized through a people stream density model similarity calculation formula, wherein the calculation formula specifically comprises the step of determining the number of sub-similarities of each reference people stream density model for the i-th similarity between the reference people stream density model and the people stream density model.

The method comprises the steps of judging whether any identical similarity exists in the minimum similarity according to all the similarities, determining a reference people stream density model corresponding to the minimum similarity as a target reference people stream density model if the similarity does not exist, and determining any one of a plurality of reference people stream density models corresponding to the minimum similarity as the target reference people stream density model if the similarity does not exist.

In the embodiment of the application, compared with the integral comparison of the reference people stream density model and the people stream density model in the related technology, the method and the device for the three-dimensional model of the human stream model, aiming at each reference people stream density model, utilize all the reference unit people stream density models and the corresponding unit people stream density models to obtain the similarity between all the reference unit people stream density models and the corresponding unit people stream density models, can pay attention to local information in the people stream density models, and can reflect the similarity between the reference people stream density models and the people stream density models more so as to improve the reality of the similarity.

After step S1031b, a possible implementation manner of the embodiment of the present application may specifically further include step SD1 and step SD2 (not shown in the figure), where:

And step SD1, judging whether the people flow density model has any in-car personnel position information.

It can be understood that if so, it indicates that there is a person in the car, and if not, it indicates that there is no person in the car.

And step SD2, if yes, obtaining a plurality of key unit people stream density models according to the plurality of unit people stream density models, wherein the key unit people stream density models represent the unit people stream density models comprising the personnel position information in the carriage.

Correspondingly, in step S1032b, the sub-similarity between each reference unit people stream density model and the corresponding unit people stream density model of each reference unit people stream density model is obtained according to each reference unit people stream density model and the corresponding unit people stream density model, which specifically includes obtaining the sub-similarity between each key unit people stream density model and the corresponding reference unit people stream density model of each key unit people stream density model according to each key unit people stream density model and the corresponding reference unit people stream density model of each key unit people stream density model.

In the embodiment of the application, the similarity between all the reference key unit people stream density models and the corresponding key unit people stream density models is obtained through all the reference key unit people stream density models and the corresponding key unit people stream density models, so that the process of obtaining the similarity between the key unit people stream density models which do not comprise the personnel position information in any carriage and the reference key unit people stream density models can be reduced, and the speed of obtaining the similarity process is improved.

The above embodiment describes a network access evaluation method from the viewpoint of a method flow, and the following embodiment describes a network access evaluation device from the viewpoint of a virtual module or a virtual unit, specifically the following embodiment.

The embodiment of the application provides a network access evaluation device, as shown in fig. 4, which specifically may include:

The signaling data acquisition module 201 is configured to acquire a plurality of signaling data in a carriage in real time, where the signaling data represents communication data of a user mobile device;

the people stream density model generating module 202 is configured to obtain a people stream density model based on a plurality of signaling data in the carriage, where the people stream density model characterizes personnel distribution information in the carriage;

The target reference people stream density model selecting module 203 is configured to obtain a target reference people stream density model according to a people stream density model and a plurality of reference people stream density models, where the target reference people stream density model is a reference people stream density model with the maximum similarity with the people stream density model in the plurality of reference people stream density models;

The preset network evaluation parameter determining module 204 is configured to obtain preset network evaluation parameters corresponding to the target reference people stream density model according to a first corresponding relationship and the target reference people stream density model, where the first corresponding relationship is a corresponding relationship between a plurality of preset reference people stream density models and a plurality of preset network evaluation parameters;

The network access evaluation result generation module 205 is configured to obtain a real-time network evaluation parameter in the vehicle cabin, and obtain a network access evaluation result based on the preset network evaluation parameter and the real-time network evaluation parameter corresponding to the target reference people stream density model, where the network access evaluation result represents a difference value between the preset network evaluation parameter and the real-time network evaluation parameter corresponding to the target reference people stream density model;

The network evaluation parameter qualification judging module 206 is configured to judge whether the network access evaluation result meets a preset network evaluation requirement, and trigger the network evaluation parameter adjusting module when the network access evaluation result does not meet the preset network evaluation requirement;

The network evaluation parameter adjustment module 207 is configured to adjust the network evaluation parameter based on a preset network evaluation parameter corresponding to the target reference people stream density model.

In one possible implementation of the embodiment of the present application, the real-time network evaluation parameters include a plurality of parameters,

The network access evaluation result generating module 204 is specifically configured to, when executing the preset network evaluation parameter and the real-time network evaluation parameter corresponding to the target reference people stream density model to obtain the network access evaluation result:

In one possible implementation manner of the embodiment of the present application, the network access evaluation device further includes:

the predicted people stream density model generation module is used for:

monitoring a plurality of dynamic signaling data, and predicting personnel distribution conditions at preset moments by using a preset personnel flow density model algorithm according to the plurality of dynamic signaling data to obtain a predicted personnel flow density model;

the predictive people flow density model algorithm correction module is used for:

when the moment reaches the preset moment, acquiring an actual people flow density model at the preset moment;

If not, acquiring actual people flow density models corresponding to a plurality of adjacent moments at preset moments, correcting the predicted people flow density algorithm according to the actual people flow density models corresponding to the adjacent moments, and obtaining a corrected predicted people flow density model algorithm.

In one possible implementation manner of the embodiment of the present application, the first correspondence includes a plurality of second correspondences, and the network access evaluation device further includes:

a second correspondence determining module, configured to:

Acquiring an operation area of a train;

and obtaining a second corresponding relation corresponding to the operation area according to the corresponding relation between the preset operation area and the second corresponding relation and the operation area.

Correspondingly, the preset network evaluation parameter determining module 204 is configured to, when executing the preset network evaluation parameter corresponding to the target reference people stream density model according to the first correspondence and the target reference people stream density model, perform:

In one possible implementation manner of the embodiment of the present application, each reference people stream density model includes a plurality of reference unit people stream density models, and the target reference people stream density model selecting module 203 is configured to, when executing the reference people stream density models according to the people stream density models and the plurality of reference people stream density models, obtain the target reference people stream density models:

the key unit people stream density model screening module is used for:

If so, obtaining a plurality of key unit people stream density models according to the plurality of unit people stream density models, wherein the key unit people stream density models represent the unit people stream density models comprising the personnel position information in the carriage.

Accordingly, the target reference people stream density model selection module 203 is configured to, when executing the sub-similarity between each reference unit people stream density model and the unit people stream density model corresponding to each reference unit people stream density model according to each reference unit people stream density model and the corresponding unit people stream density model,:

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, a specific working process of the network access evaluation device described above may refer to a corresponding process in the foregoing method embodiment, which is not described herein again.

In an embodiment of the present application, as shown in fig. 5, a 5G micro base station is provided, where the 5G micro base station shown in fig. 5 includes a processor 301 and a memory 303. Wherein the processor 301 is coupled to the memory 303, such as via a bus 302. Optionally, the 5G micro base station may further comprise a transceiver 304. It should be noted that, in practical applications, the transceiver 304 is not limited to one, and the structure of the 5G micro base station is not limited to the embodiment of the present application.

The Processor 301 may be a CPU (Central Processing Unit ), general purpose Processor, DSP (DIGITAL SIGNAL Processor, data signal Processor), ASIC (Application SPECIFIC INTEGRATED Circuit), FPGA (Field Programmable GATE ARRAY ) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Processor 301 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

Bus 302 may include a path to transfer information between the components. Bus 302 may be a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. Bus 302 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 5, but not only one bus or type of bus.

The Memory 303 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY ), a CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

The memory 303 is used for storing application program codes for executing the inventive arrangements and is controlled to be executed by the processor 301. The processor 301 is configured to execute the application code stored in the memory 303 to implement what is shown in the foregoing method embodiments.

The 5G micro base station shown in fig. 5 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present application.

Embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which when run on a computer, causes the computer to perform the corresponding method embodiments described above. Compared with the related art, the embodiment of the application constructs the people flow density model by utilizing the signaling data, acquires the signaling data in real time on the basis of truly improving and reflecting the authenticity of the personnel distribution situation in the carriage, further improves the timeliness of the reflected personnel distribution situation, obtains the preset network evaluation parameter corresponding to the target reference people flow density model according to the corresponding relation between the preset reference people flow density model and the preset network evaluation parameter and the target reference people flow density model, characterizes the preset network evaluation parameter set based on the reference people flow density model as the network evaluation standard, can select the network evaluation standard more reasonably based on personnel distribution in the carriage, enables the network evaluation standard to be more fit with the requirements of the carriage on the network, acquires the real-time network evaluation parameter, and obtains the network access evaluation result based on the preset network evaluation parameter and the real-time network evaluation parameter so as to improve the authenticity of the network access evaluation result.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

The foregoing is only a partial embodiment of the present application, and it should be noted that it will be apparent to those skilled in the art that modifications and adaptations can be made without departing from the principles of the present application, and such modifications and adaptations should and are intended to be comprehended within the scope of the present application.

Claims

1. A network access evaluation method, characterized by comprising:

Acquire a number of signaling data in the vehicle in real time, wherein the signaling data represents the communication data of the user's mobile device;

Based on some signaling data in the carriage, a crowd density model is obtained, wherein the crowd density model represents the distribution information of people in the carriage;

According to the crowd density model and multiple reference crowd density models, a target reference crowd density model is obtained, wherein the target reference crowd density model is a reference crowd density model with the greatest similarity to the crowd density model among the multiple reference crowd density models;

According to the first corresponding relationship and the target reference crowd density model, a preset network evaluation parameter corresponding to the target reference crowd density model is obtained, wherein the first corresponding relationship is a corresponding relationship between a plurality of preset reference crowd density models and a plurality of preset network evaluation parameters;

Acquire real-time network evaluation parameters in the carriage; and obtain network access evaluation results based on preset network evaluation parameters and real-time network evaluation parameters corresponding to the target reference passenger flow density model, wherein the network access evaluation results represent the difference between the preset network evaluation parameters and the real-time network evaluation parameters corresponding to the target reference passenger flow density model;

Determining whether the network access evaluation result meets the preset network evaluation requirements;

If not, the network evaluation parameters are adjusted based on the preset network evaluation parameters corresponding to the target reference crowd density model.

2. The network access evaluation method according to claim 1, characterized in that the real-time network evaluation parameters include multiple parameters,

The preset network evaluation parameters and real-time network evaluation parameters corresponding to the target reference traffic density model are used to obtain network access evaluation results, including:

Obtaining each sub-network access evaluation result according to each parameter and the target parameter corresponding to each parameter in the preset network evaluation parameters;

The network access evaluation result is obtained based on all sub-network access evaluation results and the preset number of sub-network access evaluation results.

3. The network access evaluation method according to claim 1 is characterized in that, after obtaining the network access evaluation result based on the preset network evaluation parameters and real-time network evaluation parameters corresponding to the target reference traffic density model, the method further comprises:

After a preset time period, multiple dynamic signaling data are monitored, and according to the multiple dynamic signaling data, a preset crowd density model algorithm is used to predict the distribution of people at a preset time to obtain a predicted crowd density model;

According to the predicted crowd density model and multiple reference crowd density models, a target reference crowd density model corresponding to the predicted crowd density model is obtained; and according to the first corresponding relationship and the target reference crowd density model corresponding to the predicted crowd density model, a preset network evaluation parameter corresponding to the predicted crowd density model is obtained;

When the preset time is reached, the network evaluation parameters are adjusted according to the preset network evaluation parameters corresponding to the predicted crowd density model.

4. The network access evaluation method according to claim 3 is characterized in that, after predicting the personnel distribution at a preset time by using a preset human flow density model algorithm based on the plurality of dynamic signaling data to obtain a predicted human flow density model, it further comprises:

When the time reaches the preset time, the actual crowd density model of the preset time is obtained;

According to the actual crowd density model and the predicted crowd density model, the similarity between the actual crowd density model and the predicted crowd density model is obtained; and whether the similarity meets the preset similarity requirement is determined;

If not, then obtain the actual crowd density models corresponding to multiple adjacent moments of the preset moment, and calibrate the predicted crowd density algorithm according to the actual crowd density models corresponding to the multiple adjacent moments to obtain a calibrated predicted crowd density model algorithm.

5. The network access evaluation method according to claim 1, characterized in that the first corresponding relationship includes a plurality of second corresponding relationships, and the second corresponding relationship is a corresponding relationship between a plurality of preset reference crowd density models in any operating area and a plurality of preset network evaluation parameters,

After obtaining the target reference crowd density model according to the crowd density model and the multiple reference crowd density models, the method further includes:

Get the operating area of the train;

According to the correspondence between the preset operating area and the second correspondence and the operating area, a second correspondence corresponding to the operating area is obtained;

Correspondingly, obtaining the preset network evaluation parameters corresponding to the target reference crowd density model according to the first corresponding relationship and the target reference crowd density model includes:

According to the second corresponding relationship corresponding to the operating area and the target reference passenger flow density model, the preset network evaluation parameters corresponding to the target reference passenger flow density model are obtained.

6. The network access evaluation method according to claim 1, characterized in that each reference crowd density model comprises a plurality of reference unit crowd density models,

The step of obtaining a target reference crowd density model according to the crowd density model and a plurality of reference crowd density models includes:

According to the crowd density model, multiple unit crowd density models are obtained through segmentation, wherein the crowd density model is segmented in the same way as the reference crowd density model;

According to each reference unit crowd density model and the corresponding unit crowd density model, a sub-similarity between each reference unit crowd density model and the unit crowd density model corresponding to each reference unit crowd density model is obtained, and the similarity between the reference crowd density model and the crowd density model is determined according to all the sub-similarity;

According to the similarities corresponding to all reference crowd density models, a target reference crowd density model is determined from all reference crowd density models.

7. The network access evaluation method according to claim 6, characterized in that after the plurality of unit crowd density models are obtained by segmentation according to the crowd density model, the method further comprises:

Determine whether there is any position information of people in any carriage in the crowd density model;

If yes, then according to the plurality of unit passenger flow density models, a plurality of key unit passenger flow density models are obtained, wherein the key unit passenger flow density model represents a unit passenger flow density model including position information of people in the carriage;

Accordingly, the sub-similarity between each reference unit crowd density model and the unit crowd density model corresponding to each reference unit crowd density model is obtained according to each reference unit crowd density model and the corresponding unit crowd density model, including:

According to each key unit crowd density model and the corresponding reference unit crowd density model, a sub-similarity between each key unit crowd density model and the reference unit crowd density model corresponding to each key unit crowd density model is obtained.

8. A network access evaluation device, comprising:

The signaling data acquisition module is used to obtain a number of signaling data in the car in real time, wherein the signaling data represents the communication data of the user's mobile device;

A crowd density model generation module is used to obtain a crowd density model based on a number of signaling data in the carriage, wherein the crowd density model represents the distribution information of people in the carriage;

A target reference crowd density model selection module is used to obtain a target reference crowd density model according to a crowd density model and multiple reference crowd density models, wherein the target reference crowd density model is a reference crowd density model with the greatest similarity to the crowd density model among multiple reference crowd density models;

A preset network evaluation parameter determination module is used to obtain the preset network evaluation parameters corresponding to the target reference crowd density model according to the first corresponding relationship and the target reference crowd density model, wherein the first corresponding relationship is the corresponding relationship between multiple preset reference crowd density models and multiple preset network evaluation parameters;

A network access evaluation result generation module is used to obtain real-time network evaluation parameters in the carriage; and based on the preset network evaluation parameters and real-time network evaluation parameters corresponding to the target reference passenger flow density model, obtain the network access evaluation result, wherein the network access evaluation result represents the difference between the preset network evaluation parameters and the real-time network evaluation parameters corresponding to the target reference passenger flow density model;

A network evaluation parameter qualification judgment module is used to judge whether the network access evaluation result meets the preset network evaluation requirements, and trigger a network evaluation parameter adjustment module when it does not meet the preset network evaluation requirements;

The network evaluation parameter adjustment module is used to adjust the network evaluation parameters based on the preset network evaluation parameters corresponding to the target reference crowd density model.

9. A 5G micro base station, comprising:

at least one processor;

Memory;

At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the network access evaluation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that a computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the network access evaluation method according to any one of claims 1 to 7.