WO2024040836A1 - Private network planning method and apparatus, electronic device, and storage medium - Google Patents

Abstract

The present disclosure provides a private network planning method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring a site parameter and a service parameter of a port to be planned, the service parameter being determined on the basis of a selected service mode; inputting the site parameter and the service parameter into a device quantity prediction model to obtain a device quantity prediction result outputted by the device quantity prediction model; and on the basis of the device quantity prediction result, determining a private network planning result of said port.

Description

Private network planning method, device, electronic equipment and storage medium

Cross-references to related applications

This application claims priority to Chinese Patent Application No. 202211007539.0 filed in China on August 22, 2022, the entire content of which is incorporated herein by reference.

Technical field

The present disclosure relates to the field of communication technology, and in particular to a private network planning method, device, electronic equipment and storage medium.

Background technique

With the rapid development of the fifth generation mobile communication technology (5G), vertical industry projects are growing rapidly, especially for port business. Based on this, it is necessary to provide a private network planning solution for port business to meet the network needs of port customers.

Currently, private network planning and configuration are manually performed based on customer business needs. However, relying on manual planning and configuration of private network requires manual analysis of business requirements, which is inefficient; and it relies too much on expert experience, so the accuracy of private network planning and configuration is low.

Contents of the invention

The present disclosure provides a private network planning method, device, electronic equipment and storage medium to solve the defects of low efficiency and low accuracy of private network planning and configuration in related technologies, and to realize a high-efficiency and high-accuracy private network. Network planning and configuration.

The present disclosure provides a private network planning method, including:

Obtain the site parameters and business parameters of the port to be planned, the business parameters are determined based on the selected business model, and the port to be planned is the port of the private network to be planned;

Input the site parameters and the business parameters into the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the equipment quantity prediction model;

Based on the equipment quantity prediction result, the private network planning result of the port to be planned is determined.

According to a private network planning method provided by the present disclosure, inputting the site parameters and the service parameters into a device quantity prediction model to obtain a device quantity prediction result output by the device quantity prediction model includes:

Input the site parameters and the business parameters into the feature mapping layer of the equipment quantity prediction model, and obtain the site characteristics and business characteristics output by the feature mapping layer;

Input the site characteristics and the business characteristics into the classification layer of the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the classification layer;

Wherein, the classification layer is trained based on sample site parameters and sample service parameters, and the number of sample devices corresponding to the sample site parameters and the sample service parameters.

According to a private network planning method provided by the present disclosure, the classification layer includes a communication equipment classification layer, and the site characteristics and the business characteristics are input into the classification layer of the equipment quantity prediction model to obtain the The prediction results of the number of devices output by the classification layer include:

Input the site characteristics and the business characteristics into the communication equipment classification layer, and obtain the prediction result of the number of communication equipment output by the communication equipment classification layer;

Wherein, the communication equipment classification layer includes an active antenna unit AAU classification layer and/or a baseband board classification layer;

In the case where the communication device classification layer includes an AAU classification layer, the communication device number prediction result includes an AAU number prediction result;

In the case where the communication equipment classification layer includes a baseband board classification layer, the communication equipment quantity prediction result includes a baseband board quantity prediction result.

According to a private network planning method provided by the present disclosure, the classification layer includes a service equipment classification layer, and the site characteristics and the service characteristics are input into the classification layer of the equipment quantity prediction model to obtain the The prediction results of the number of devices output by the classification layer include:

Input the site characteristics and the service characteristics into the service equipment classification layer, and obtain the service equipment quantity prediction result output by the service equipment classification layer;

Wherein, the business equipment classification layer includes at least one of a crane classification layer, an unmanned card collection classification layer, and an intelligent tally classification layer;

In the case where the business equipment classification layer includes a crane classification layer, the business equipment quantity prediction results include a crane quantity prediction result;

In the case where the business equipment classification layer includes an unmanned card collection classification layer, the business equipment quantity prediction result includes an unmanned card collection quantity prediction result;

In the case where the business equipment classification layer includes an intelligent tally classification layer, the business equipment quantity prediction results include intelligent tally quantity prediction results.

According to a private network planning method provided by the present disclosure, the private network planning results include at least one of equipment quantity prediction results, equipment cost results, maintenance cost results, service fee results, network capacity results, and total quotation results. ;

Determining the private network planning results of the port to be planned based on the equipment quantity prediction results includes:

When the private network planning results include equipment cost results, determine the equipment cost results based on the equipment quantity prediction results and the preset equipment cost unit price;

If the private network planning result includes a maintenance cost result, determine the maintenance cost result based on the equipment quantity prediction result and the preset maintenance cost unit price;

When the private network planning result includes a service fee result, determine the service fee result based on the device quantity prediction result and the preset service fee unit price;

When the private network planning result includes a network capacity result, determine the network capacity result based on the device quantity prediction result and the preset single device capability;

In the case where the private network planning result includes a total quotation result, based on at least one of the equipment cost result, the maintenance cost result, the service fee result, and the contract period indicated by the service parameters, Determine the total quote result.

According to a private network planning method provided by the present disclosure, the site parameters include offshore depth and/or berth shoreline length.

According to a private network planning method provided by the present disclosure, the service parameters include at least one of contract period, package mode, and yard service;

The yard business includes at least one of yard crane, unmanned card collection, smart tally, first combined business, second combined business, third combined business and fourth combined business;

The first combined business includes yard crane and unmanned card collection, the second combined business includes unmanned card collection and smart tally, the third combined business includes yard crane and smart tally, and the third combined business includes yard crane and smart tally. The four integrated businesses include yard cranes, unmanned card collection and smart tallying.

The present disclosure also provides a private network planning device, including:

The acquisition module is used to obtain the site parameters and business parameters of the port to be planned. The business parameters are determined based on the selected business model. The port to be planned is the port of the private network to be planned;

A prediction module, configured to input the site parameters and the business parameters into the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the equipment quantity prediction model;

A determination module, configured to determine the private network planning results of the port to be planned based on the equipment quantity prediction results.

The present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements any one of the above private network networks. planning methods.

The present disclosure also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements any one of the above private network planning methods.

The private network planning method, device, electronic equipment and storage medium provided by the disclosure obtain the site parameters and business parameters of the port to be planned; input the site parameters and business parameters into the equipment quantity prediction model, and obtain the equipment output by the equipment quantity prediction model Quantity prediction results; based on the equipment quantity prediction results, determine the private network planning results of the port to be planned. Through the above method, the present disclosure can use the equipment quantity prediction model to predict the number of equipment for the site parameters and business parameters of the port to be planned, automatically obtain the equipment quantity prediction results, and then determine the private network planning results based on the equipment quantity prediction results, improving the private network planning results. The efficiency of the network planning and configuration of the network is improved; and by predicting the number of devices based on the device number prediction model, compared with manual planning and configuration of the private network, the present disclosure can improve the accuracy of the planning and configuration of the private network.

Description of drawings

In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, a brief introduction will be given below to the drawings that need to be used in the description of the embodiments or related technologies. Obviously, the drawings in the following description are of the present disclosure. For some embodiments, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.

Figure 1 is one of the flow diagrams of the private network planning method provided by the present disclosure;

Figure 2 is a schematic flowchart 2 of the private network planning method provided by the present disclosure;

Figure 3 is a schematic structural diagram of a private network planning device provided by the present disclosure;

Figure 4 is a schematic structural diagram of an electronic device provided by the present disclosure.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions in the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure. , not all examples. Based on the embodiments in this disclosure, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of this disclosure.

With the rapid development of 5G, vertical industry projects have grown rapidly, especially port business. Based on this, in order to respond to customers' real-time understanding of the private network planning and configuration solutions for port businesses, it is necessary to provide private network planning solutions for port businesses to meet the network needs of port customers.

Currently, private network planning and configuration are manually performed based on customer business needs. However, relying on manual network planning and configuration for private networks requires many days from receiving customer requirements to analyzing and outputting private network planning solutions, which is inefficient; and relying too much on expert experience may lead to incomplete private network planning solutions and cannot Problems in meeting customer needs, which in turn lead to low accuracy in private network planning and configuration; and over-reliance on expert experience, which results in unstable configurations of private network planning solutions, which cannot improve customer satisfaction, which in turn leads to private network The accuracy of network planning and configuration is low.

In response to the above problems, the present disclosure proposes the following embodiments. Figure 1 is one of the flow diagrams of the private network planning method provided by the present disclosure. As shown in Figure 1, the private network planning method includes:

Step 110: Obtain the site parameters and service parameters of the port to be planned. The service parameters are determined based on the selected business model. The port to be planned is the port of the private network to be planned.

Here, the port to be planned is a port that requires private network planning. The site parameters of the port to be planned may include but are not limited to at least one of the following: offshore depth, berth shoreline length, etc. For example, the offshore depth is 350 meters and the berth shoreline length is 500 meters. The business parameters of the port to be planned may include but are not limited to one or more of the following: contract period, package model, yard business, etc. For example, the contract period includes 3 years, 5 years, etc., the package model includes activation fee + monthly package, activation fee, etc., and the yard business includes yard crane, unmanned card collection, smart tally, yard crane + unmanned card collection , unmanned card collection + smart tally, yard crane + smart tally, yard crane + unmanned card collection + smart tally, etc.

Site parameters can be determined based on the user's business needs. Specifically, it can be determined based on the on-site inspection results of the port to be planned, or the site parameters determined by the port customer can be directly obtained.

Business parameters are determined based on the business model selected by the user. Specifically, it can be selected by the port customer or the operator. Among them, the business model may include but is not limited to one or more of the following: contract period, package model, storage yard business, etc.

Step 120: Input the site parameters and the service parameters into the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the equipment quantity prediction model.

Here, the equipment quantity prediction model is used to predict the equipment quantity based on site parameters and business parameters, and obtain the equipment quantity prediction results.

Here, the equipment quantity prediction results may include but are not limited to at least one of the following: communication equipment quantity prediction results, business equipment quantity prediction results, etc. The communication equipment quantity prediction results may include but are not limited to at least one of the following: active antenna unit (Active Antenna Unit, AAU) quantity prediction results, baseband board quantity prediction results, baseband unit (Base band Unit, BBU) quantity prediction results, etc. The business equipment quantity prediction results may include but are not limited to at least one of the following: yard crane quantity prediction results, unmanned truck collection quantity prediction results, intelligent tally quantity prediction results, etc.

The types of communication devices corresponding to the prediction results of the number of communication devices can be set according to actual needs, and this is not specifically limited in the embodiments of the present disclosure. For example, the embodiment of the present disclosure is aimed at private network planning for 5G networks, and the communication equipment may include AAU, baseband board, BBU, etc.

Among them, the type of service equipment corresponding to the prediction result of the number of service equipment can be set according to actual needs, and this is not specifically limited in the embodiment of the present disclosure. For example, if the yard business in the business parameters includes cranes, then the prediction result of the number of business equipment includes the prediction result of the number of cranes; if the yard business in the business parameters includes unmanned truck collection, then The prediction results of the quantity of business equipment include the prediction results of the quantity of unmanned collection cards; when the yard business in the business parameters includes intelligent tally, the prediction results of the quantity of business equipment include the prediction results of the quantity of intelligent tallying; If the yard business includes yard cranes + unmanned truck collection, the business equipment quantity prediction results include the yard crane quantity prediction results and the unmanned truck collection forecast results; the yard business in the business parameters includes yard cranes + In the case of smart tally, the business equipment quantity forecast results include the yard crane quantity forecast results and the smart tally quantity forecast results; in the case of the yard business in the business parameters including unmanned card collection + smart tally, then The prediction results of the number of business equipment include the prediction results of the quantity of unmanned card collection and the prediction results of the number of smart tally; when the yard business in the business parameters includes yard crane + unmanned card collection + smart tally, the number of business equipment The prediction results include the prediction results of the quantity of cranes on the yard, the prediction results of the quantity of unmanned trucks and the prediction results of the quantity of intelligent tally.

The device quantity prediction model may include a feature mapping layer and a classification layer, or may include a feature extraction layer and a classification layer. Among them, the feature mapping layer is used to perform feature mapping to obtain site characteristics and business characteristics based on site parameters and business parameters; the classification layer is used to predict the number of equipment based on site characteristics and business characteristics to obtain equipment number prediction results; feature extraction is used to predict the number of equipment based on site characteristics and business characteristics. Site parameters and business parameters, feature extraction is performed to obtain site characteristics and business characteristics. The feature mapping layer or feature extraction layer may be a convolutional layer or a mapping layer set based on preset rules, which is not specifically limited in this embodiment of the disclosure. The classification layer can be constructed by a classifier. The classifier can include but is not limited to: a classifier corresponding to the random forest algorithm, a naive Bayes classifier, a support vector machine classifier, etc. This is not specified in the embodiment of the present disclosure. limited.

The equipment quantity prediction model is trained based on sample site parameters and sample business parameters, as well as the sample equipment quantity corresponding to the sample site parameters and sample business parameters.

Step 130: Determine the private network planning results of the port to be planned based on the equipment quantity prediction results.

Here, the private network planning results may include but are not limited to at least one of the following: equipment quantity results, equipment cost results, maintenance cost results, service fee results, network capacity results, total quotation results, etc.

The equipment quantity results may include but are not limited to at least one of the following: AAU quantity results, baseband board quantity results, BBU quantity results, yard crane quantity results, unmanned card collection quantity results, smart tally quantity results, etc.

In one embodiment, the equipment quantity prediction result is determined as the equipment quantity result.

In another embodiment, the device quantity result is determined based on the device quantity prediction result and the device quantity parameter. The device quantity parameter is determined based on the number of devices selected by the user. The equipment quantity parameters may include but are not limited to at least one of the following: AAU quantity results, baseband board quantity results, BBU quantity results, yard crane quantity results, unmanned card collection quantity results, smart tally quantity results, etc.

More specifically, the equipment quantity prediction results and the equipment quantity parameters are aggregated to obtain the equipment quantity results. The aggregation process can be weighted average, average, or other processing methods. For example, if the device quantity prediction result is that the number of AAUs is 10, and the device quantity parameter is that the AAU quantity is 6, then average processing is performed to obtain the device quantity result as 8; the weight of the device quantity prediction result is 80%, and the weight of the device quantity parameter is 20%. , then the weighted average processing is performed and the result of the number of devices is 9.

In another embodiment, the device quantity result is determined based on the device quantity prediction result and the device quantity analysis result. The equipment quantity analysis results are determined based on the site parameters of the port to be planned. The equipment quantity analysis results may include but are not limited to at least one of the following: AAU quantity results, baseband board quantity results, BBU quantity results, yard crane quantity results, unmanned collection card quantity results, smart tally quantity results, etc.

More specifically, the equipment quantity prediction results and the equipment quantity analysis results are aggregated to obtain the equipment quantity results. The aggregation process can be weighted average, average, or other processing methods. For example, if the device quantity prediction result is that the number of AAUs is 10, and the device quantity analysis result is that the AAU number is 6, then average processing is performed to obtain the device quantity result as 8; the weight of the device quantity prediction result is 80%, and the weight of the device quantity analysis result is 20%, then the weighted average processing is performed and the result of the number of equipment is 9.

Among them, the equipment quantity analysis result can be the starting quantity for sale or the maximum quantity for sale, or the average of the starting quantity for sale and the maximum quantity for sale.

For example, the minimum sales quantity of a bridge crane = round up (((offshore depth-50)/50)*2); the maximum sellable quantity of a bridge crane = round up ((offshore depth-50)/ 100) + the minimum sales quantity of the bridge crane; the minimum sales quantity of the unmanned truck collecting truck = round up (((offshore depth-50)/50)*4); the maximum sellable quantity of the unmanned truck collecting truck = upward Rounding ((offshore depth-50)/50) + the minimum sales quantity of unmanned card collection; the minimum sales quantity of smart tally = rounding up (offshore depth/100); the maximum sellable quantity of smart tally =Round up (offshore depth/80). For example, if the offshore depth in the site parameters is 350 meters, the minimum sales quantity of the yard crane is 12, the maximum sellable quantity of the yard crane is 15, the minimum quantity of the unmanned truck collection is 24, and the minimum quantity of the unmanned truck collection is 24. The maximum sellable quantity is 30, the starting quantity for smart tally is 4, and the maximum sellable quantity for smart tally is 5.

In a specific embodiment, the BBU number result can be determined based on the AAU number result, that is, there is a mapping relationship between the AAU number and the BBU number. For example, one AAU corresponds to one BBU, or two AAUs correspond to one BBU. The number of baseband boards can also be determined based on the number of AAUs. That is, there is a mapping relationship between the number of AAUs and the number of baseband boards. For example, one AAU corresponds to one baseband board, or two AAUs correspond to one baseband board.

The private network planning method provided by the embodiment of the present disclosure obtains the site parameters and business parameters of the port to be planned; inputs the site parameters and business parameters into the equipment quantity prediction model, and obtains the equipment quantity prediction results output by the equipment quantity prediction model; based on the equipment Quantity prediction results determine the private network planning results of the port to be planned. Through the above method, the present disclosure can use the equipment quantity prediction model to predict the number of equipment for the site parameters and business parameters of the port to be planned, automatically obtain the equipment quantity prediction results, and then determine the private network planning results based on the equipment quantity prediction results, improving the private network planning results. The efficiency of the network planning and configuration of the network is improved; and by predicting the number of devices based on the device number prediction model, compared with manual planning and configuration of the private network, the present disclosure can improve the accuracy of the planning and configuration of the private network.

Based on the above embodiments, Figure 2 is a flow diagram 2 of the private network planning method provided by the present disclosure. As shown in Figure 2, the above step 120 includes:

Step 121: Input the site parameters and the service parameters into the feature mapping layer of the device quantity prediction model to obtain the site characteristics and service characteristics output by the feature mapping layer.

Here, the feature mapping layer is used to map site parameters and business parameters into site characteristics and business characteristics. In a specific embodiment, the venue parameters and service parameters can be mapped into venue characteristics and service characteristics in digital format.

In one embodiment, the feature mapping layer includes a first mapping layer corresponding to the offshore depth. The offshore depth is input to the first mapping layer to obtain the first site characteristics corresponding to the offshore depth output by the first mapping layer. That is, digital mapping of offshore depth of site parameters. For example, 300 meters of offshore depth is mapped to 1, 350 meters of offshore depth is mapped to 2, 400 meters of offshore depth is mapped to 3, 450 meters of offshore depth is mapped to 4, and 500 meters of offshore depth is mapped to 4. The offshore depth is mapped to 5, the 550-meter offshore depth is mapped to 6, the 600-meter offshore depth is mapped to 7, the 650-meter offshore depth is mapped to 8, and the 700-meter offshore depth is mapped to 9 .

In one embodiment, the feature mapping layer includes a second mapping layer corresponding to the berth shoreline length. The berth shoreline length is input to the second mapping layer to obtain the second site characteristics corresponding to the berth shoreline length output by the second mapping layer. . That is to digitally map the berth shoreline length of the site parameters. For example, the berth shoreline length of 300 meters is mapped to 1, the berth shoreline length of 350 meters is mapped to 2, the berth shoreline length of 400 meters is mapped to 3, and the berth shoreline length of 450 meters is mapped to 4. The 500-meter berth shoreline length is mapped to 5, the 550-meter berth shoreline length is mapped to 6, the 600-meter berth shoreline length is mapped to 7, the 650-meter berth shoreline length is mapped to 8, and the 700-meter berth shoreline length is mapped to 8. The berth shoreline length is mapped to 9 meters.

In one embodiment, the feature mapping layer includes a third mapping layer corresponding to the package mode. The package mode is input to the third mapping layer to obtain the first service feature corresponding to the package mode output by the third mapping layer. That is, digital mapping of the package model of business parameters. For example, map the package mode of monthly package to 0, and map the package mode of monthly package + activation fee to 1.

In one embodiment, the feature mapping layer includes a fourth mapping layer corresponding to the contract period, and the contract period is input to the fourth mapping layer to obtain the second business characteristics corresponding to the contract period output by the fourth mapping layer. That is, digital mapping of the contract period of business parameters. For example, a 3-year contract period is mapped to 0, and a 5-year contract period is mapped to 1.

In one embodiment, the feature mapping layer includes a fifth mapping layer corresponding to the storage yard business. The storage yard business is input to the fifth mapping layer to obtain the third business feature corresponding to the storage yard business output by the fifth mapping layer. That is, digital mapping of the yard business of business parameters. For example, map the yard business of the yard crane to 1, map the yard business of unmanned card collection to 2, map the yard business of smart tally to 3, map the yard business of yard crane + unmanned card collection to 3. The yard business is mapped to 4, the yard business of unmanned card collection + smart tally is mapped to 5, the yard business of yard crane + intelligent tally is mapped to 6, the yard business of yard crane + unmanned card collection + intelligence is mapped The tally yard business is mapped to 7.

Step 122: Input the site characteristics and the business characteristics into the classification layer of the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the classification layer.

Here, the classification layer includes a communication device classification layer and/or a service device classification layer; the device quantity prediction result includes a communication device quantity prediction result and/or a service device quantity prediction result.

In one embodiment, the site characteristics and business characteristics are input to the communication equipment classification layer, and the communication equipment quantity prediction result output by the communication equipment classification layer is obtained.

In one embodiment, the site characteristics and service characteristics are input to the service equipment classification layer, and the service equipment quantity prediction result output by the service equipment classification layer is obtained.

Wherein, the classification layer is trained based on sample site parameters and sample service parameters, and the number of sample devices corresponding to the sample site parameters and the sample service parameters.

Here, the sample site parameters, sample business parameters, and sample equipment quantity are determined based on historical data. The sample site parameters, sample business parameters and sample equipment quantity can be obtained by data cleaning of historical data in advance. Among them, the number of sample equipment is used to label sample site parameters and sample business parameters.

The sample site parameters may include but are not limited to at least one of the following: offshore depth, berth shoreline length, etc. The sample business parameters may include but are not limited to at least one of the following: contract period, package mode, storage yard business, etc.

In one embodiment, the communication device classification layer is trained based on sample site parameters and sample service parameters, and the number of sample communication devices corresponding to the sample site parameters and sample service parameters.

In one embodiment, the service equipment classification layer is trained based on sample site parameters and sample service parameters, and the number of sample service equipment corresponding to the sample site parameters and sample service parameters.

In a specific embodiment, the classification layer is a random forest classification layer, that is, a random forest machine learning algorithm is used to establish the classification layer. For ease of understanding, the AAU classification layer of the communication equipment classification layer is used as an example for description here.

During the training process of the classification layer, first, sample data is established based on historical data. The sample data includes sample site parameters and sample business parameters, as well as the number of sample devices corresponding to the sample site parameters and sample business parameters. For example, it includes 100 sample data. Each sample data includes offshore depth, berth coastline length, contract period, package model, yard business, and the corresponding number of labeled AAUs. Afterwards, feature mapping is performed on the above sample site parameters and sample business parameters to obtain sample site characteristics and sample business characteristics. After that, a preset number of training samples (for example, 60 training samples) are randomly selected from the 100 sample data with replacement, a classification regression tree (sub-decision tree) is constructed in parallel, and the sub-decision is repeated a preset number of times (for example, 80 times). The number of trees is the number corresponding to the preset time (for example, 80 sub-decision trees). After that, the training samples included in each sub-decision tree can include five feature subsets of offshore depth, berth coastline length, contract period, package mode, and yard business. After that, you can arbitrarily select a preset from the five feature subsets. (for example, 4) feature subsets for subsequent classification training based on the preset feature subsets. After that, the obtained preset sub-decision trees are used to form a random forest, and the sub-decision trees of each lesson are guaranteed to grow to the maximum extent without pruning process, and then the training of the classification layer is completed. Among them, the random forest splitting method can include but is not limited to: CART algorithm (using the Gini index minimization criterion for feature selection), ID3 (using the feature with the largest information gain) algorithm, C4.5 (using the information gain ratio to select features) algorithm one of them.

In addition, the specific execution processes of the crane classification layer, unmanned card collection classification layer, intelligent tally classification layer, BBU classification layer, and baseband board classification layer are basically similar to the above-mentioned AAU classification layer, and will not be repeated here.

The private network planning method provided by the embodiment of the present disclosure maps site parameters and service parameters into site characteristics and service characteristics through the feature mapping layer, and then predicts the number of devices for the site characteristics and service characteristics through the classification layer, and automatically obtains the equipment The quantity prediction results are then used to determine the private network planning results based on the device quantity prediction results, which improves the efficiency of private network planning and configuration; and the device quantity prediction is based on the classification layer. Compared with manual private network planning and configuration, the classification layer is based on The sample site parameters and sample service parameters, as well as the number of sample devices corresponding to the sample site parameters and sample service parameters, are obtained through training, which can improve the accuracy of private network planning and configuration.

Based on any of the above embodiments, in this method, the classification layer includes a communication device classification layer, and the above step 122 includes:

Input the site characteristics and the business characteristics into the communication equipment classification layer, and obtain the prediction result of the number of communication equipment output by the communication equipment classification layer;

Wherein, the communication equipment classification layer includes an active antenna unit AAU classification layer and/or a baseband board classification layer;

In the case where the communication device classification layer includes an AAU classification layer, the communication device number prediction result includes an AAU number prediction result;

In the case where the communication equipment classification layer includes a baseband board classification layer, the communication equipment quantity prediction result includes a baseband board quantity prediction result.

In one embodiment, site characteristics and business characteristics are input to the AAU classification layer to obtain the AAU number prediction result output by the AAU classification layer.

Among them, the AAU classification layer is trained based on the sample site parameters and sample service parameters, as well as the number of sample AAUs corresponding to the sample site parameters and sample service parameters.

In one embodiment, the site characteristics and service characteristics are input to the baseband board classification layer, and the baseband board quantity prediction result output by the baseband board classification layer is obtained.

Among them, the baseband board classification layer is trained based on sample site parameters and sample service parameters, as well as the number of sample baseband boards corresponding to the sample site parameters and sample service parameters.

The private network planning method provided by the embodiment of the present disclosure uses the AAU classification layer and the baseband board classification layer to predict the number of AAUs and the number of baseband boards based on site characteristics and business characteristics, and automatically obtains the prediction results of the number of AAUs and the number of baseband boards. , and then determine the private network planning results based on the equipment quantity prediction results, which improves the efficiency of private network planning and configuration; and the equipment quantity prediction based on the AAU classification layer and the baseband board classification layer can be compared with manual private network planning and configuration. Improve the accuracy of private network planning and configuration.

Based on any of the above embodiments, in this method, the classification layer includes a service equipment classification layer, and the above step 122 includes:

Input the site characteristics and the service characteristics into the service equipment classification layer, and obtain the service equipment quantity prediction result output by the service equipment classification layer;

Wherein, the business equipment classification layer includes at least one of a crane classification layer, an unmanned card collection classification layer, and an intelligent tally classification layer;

In the case where the business equipment classification layer includes a crane classification layer, the business equipment quantity prediction results include a crane quantity prediction result;

In the case where the business equipment classification layer includes an unmanned card collection classification layer, the business equipment quantity prediction result includes an unmanned card collection quantity prediction result;

In the case where the business equipment classification layer includes an intelligent tally classification layer, the business equipment quantity prediction results include intelligent tally quantity prediction results.

In one embodiment, the site characteristics and business characteristics are input to the crane classification layer, and the prediction result of the crane quantity output by the crane classification layer is obtained.

Among them, the crane classification layer is trained based on the sample site parameters and sample business parameters, as well as the number of sample cranes corresponding to the sample site parameters and sample business parameters.

In one embodiment, site characteristics and business characteristics are input to the unmanned card collection classification layer to obtain the unmanned card collection quantity prediction result output by the unmanned card collection classification layer.

Among them, the unmanned collection card classification layer is trained based on the sample site parameters and sample business parameters, as well as the number of sample unmanned collection cards corresponding to the sample site parameters and sample business parameters.

In one embodiment, the site characteristics and business characteristics are input to the intelligent tally classification layer to obtain the intelligent tally quantity prediction result output by the intelligent tally classification layer.

Among them, the intelligent tally classification layer is trained based on the sample site parameters and sample business parameters, as well as the sample intelligent tally quantity corresponding to the sample site parameters and sample business parameters.

The private network planning method provided by the embodiment of the present disclosure uses the crane classification layer, the unmanned card collection classification layer and the intelligent tally classification layer to predict the number of cranes and the number of unmanned card collections based on the site characteristics and business characteristics. Forecasting and intelligent tally quantity prediction, automatically obtain the forecast results of the number of cranes, unmanned trucks, and intelligent tally quantity, and then determine the private network planning results based on the equipment quantity prediction results, improving the private network The efficiency of planning and configuration; and the prediction of the number of equipment based on the crane classification layer, the unmanned card collection classification layer and the intelligent tally classification layer can improve the accuracy of the private network planning and configuration compared to manual private network planning and configuration. .

Based on any of the above embodiments, in this method, the private network planning results include at least one of equipment quantity prediction results, equipment cost results, maintenance cost results, service fee results, network capacity results, and total quotation results; the above Step 130 includes:

When the private network planning results include equipment cost results, determine the equipment cost results based on the equipment quantity prediction results and the preset equipment cost unit price;

If the private network planning result includes a maintenance cost result, determine the maintenance cost result based on the equipment quantity prediction result and the preset maintenance cost unit price;

When the private network planning result includes a service fee result, determine the service fee result based on the device quantity prediction result and the preset service fee unit price;

When the private network planning result includes a network capacity result, determine the network capacity result based on the device quantity prediction result and the preset single device capability;

In the case where the private network planning result includes a total quotation result, based on at least one of the equipment cost result, the maintenance cost result, the service fee result, and the contract period indicated by the service parameters, Determine the total quote result.

Here, the preset equipment cost unit price is set according to the actual situation. For example, the cost unit price of a bridge crane is 100,000 yuan/unit, or 2,700 yuan/unit per month, or 30,000 yuan/unit per year, etc.

In one embodiment, when the preset equipment cost unit price is the buyout unit price (for example, 100,000/unit), the equipment quantity prediction result is multiplied by the preset equipment cost unit price to obtain the equipment cost result.

In another embodiment, when the preset equipment cost unit price is the rental period unit price (for example, 2,700 yuan/unit per month), the equipment quantity prediction results, the preset equipment cost unit price and the contract period in the business parameters are multiplied. Get equipment cost results.

It can be understood that if multiple equipment cost results are included, the multiple equipment cost results will be added to determine the final equipment cost result.

Here, the preset maintenance cost unit price is set according to the actual situation. For example, the maintenance unit price of a bridge crane is 80,000 yuan/unit, or 2,000 yuan/unit per month, or 30,000 yuan/unit per year, etc.

In one embodiment, when the preset maintenance cost unit price is the buyout unit price (for example, 80,000/unit), the equipment quantity prediction result is multiplied by the preset maintenance cost unit price to obtain the maintenance cost result.

In another embodiment, when the preset maintenance cost unit price is the rental period unit price (for example, 2,000 yuan/unit per month), the equipment quantity prediction result, the preset maintenance cost unit price and the contract period in the business parameters are multiplied. Get maintenance cost results.

It can be understood that if multiple maintenance cost results are included, the multiple maintenance cost results are added together to determine the final maintenance cost result.

Here, the default service fee unit price is set according to the actual situation. For example, the service fee unit price of AAU is 50,000 yuan/unit, or 1,500 yuan/unit per month, or 20,000 yuan/unit per year, etc.

In one embodiment, when the preset service fee unit price is the buyout unit price (for example, 50,000/unit), the device quantity prediction result is multiplied by the preset service fee unit price to obtain the service fee result.

In another embodiment, when the preset service fee unit price is the rental period unit price (for example, 1,500 yuan/unit per month), the equipment quantity prediction result, the preset service fee unit price and the contract period in the business parameters are multiplied. Get service fee results.

It can be understood that if multiple service fee results are included, the multiple service fee results will be added together to determine the final service fee result.

Here, the preset single device capability is set based on the actual situation, for example, single cell capability, single device bandwidth requirement, etc. For example, the total network bandwidth in the network capacity result = single cell capability * total number of baseband boards.

Specifically, the total quotation result is determined based on at least one of the equipment cost result, the maintenance cost result, the service fee result, and the contract period indicated by the preset profit margin and business parameters.

In a specific embodiment, the total equipment cost is determined based on the contract period, equipment cost results and maintenance cost results indicated by the business parameters, the cost quotation is determined based on the total equipment cost and the preset profit margin, and the cost quotation, service fee results, and business parameters are determined. The indicated contract period determines the total quote result. For example, the total quotation result for a three-year contract period = (total equipment cost for a three-year contract period)/(1-preset profit rate) + service fee result for a three-year contract period; the total quotation result for a five-year contract period Quotation result = (total equipment cost with a five-year contract period)/(1-preset profit margin) + service fee result with a five-year contract period.

In addition, the private network profit can also be determined based on the total equipment cost and the preset profit rate, for example, private network profit = total equipment cost * (1/(1-profit rate)-1)).

The private network planning method provided by the embodiment of the present disclosure determines the private network planning results of the equipment quantity prediction results, equipment cost results, maintenance cost results, service fee results, network capacity results, and total quotation results based on the equipment quantity prediction results, thereby A more complete configuration of the private network planning solution further improves the accuracy of private network planning.

Based on any of the above embodiments, the site parameters include offshore depth and/or berth shoreline length.

Based on any of the above embodiments, the business parameters include at least one of contract period, package mode, and yard business; the yard business includes yard bridge crane, unmanned card collection, smart tally, and first combination business , at least one of the second combined service, the third combined service, and the fourth combined service; the first combined service includes a bridge crane and an unmanned card collection, and the second combined service includes an unmanned card collection and an intelligent For tallying, the third combined business includes yard crane and smart tally, and the fourth combined business includes yard crane, unmanned card collection and smart tally.

In the actual application process, by analyzing and summarizing the port business characteristics, deeply exploring the correlation between the port business private network planning and configuration scheme and construction costs, establishing a port business private network planning and configuration model, and matching the private network planning and configuration through the random forest algorithm model, automatically output private network planning and configuration plans, cost assessments, etc., which solves the uncertainty of manual design in related technologies, makes up for the shortcomings of insufficient manual analysis solutions in related technologies, and optimizes the time-consuming manual processing of operation processes. Long and low efficiency.

The private network planning device provided by the present disclosure will be described below. The private network planning device described below and the private network planning method described above can correspond to each other.

Figure 3 is a schematic structural diagram of a private network planning device provided by the present disclosure. As shown in Figure 3, the private network planning device includes:

The acquisition module 310 is used to obtain the site parameters and service parameters of the port to be planned, where the service parameters are determined based on the selected business model, and the port to be planned is the port of the private network to be planned;

The prediction module 320 is used to input the site parameters and the business parameters into the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the equipment quantity prediction model;

The determination module 330 is configured to determine the private network planning result of the port to be planned based on the equipment quantity prediction result.

The private network planning device provided by the embodiment of the present disclosure obtains the site parameters and business parameters of the port to be planned; inputs the site parameters and business parameters into the equipment quantity prediction model, and obtains the equipment quantity prediction results output by the equipment quantity prediction model; based on the equipment Quantity prediction results determine the private network planning results of the port to be planned. Through the above method, the present disclosure can use the equipment quantity prediction model to predict the number of equipment for the site parameters and business parameters of the port to be planned, automatically obtain the equipment quantity prediction results, and then determine the private network planning results based on the equipment quantity prediction results, improving the private network planning results. The efficiency of the network planning and configuration of the network is improved; and by predicting the number of devices based on the device number prediction model, compared with manual planning and configuration of the private network, the present disclosure can improve the accuracy of the planning and configuration of the private network.

Based on any of the above embodiments, the prediction module 320 includes:

A feature mapping unit, configured to input the site parameters and the business parameters into the feature mapping layer of the equipment quantity prediction model, and obtain the site characteristics and business characteristics output by the feature mapping layer;

A quantity prediction unit, configured to input the site characteristics and the business characteristics into the classification layer of the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the classification layer;

Wherein, the classification layer is trained based on sample site parameters and sample service parameters, and the number of sample devices corresponding to the sample site parameters and the sample service parameters.

Based on any of the above embodiments, the classification layer includes a communication device classification layer, and the quantity prediction unit is also used for:

Input the site characteristics and the business characteristics into the communication equipment classification layer, and obtain the prediction result of the number of communication equipment output by the communication equipment classification layer;

Wherein, the communication equipment classification layer includes an active antenna unit AAU classification layer and/or a baseband board classification layer;

In the case where the communication device classification layer includes an AAU classification layer, the communication device number prediction result includes an AAU number prediction result;

In the case where the communication equipment classification layer includes a baseband board classification layer, the communication equipment quantity prediction result includes a baseband board quantity prediction result.

Based on any of the above embodiments, the classification layer includes a service equipment classification layer, and the quantity prediction unit is also used to:

Input the site characteristics and the service characteristics into the service equipment classification layer, and obtain the service equipment quantity prediction result output by the service equipment classification layer;

Wherein, the business equipment classification layer includes at least one of a crane classification layer, an unmanned card collection classification layer, and an intelligent tally classification layer;

In the case where the business equipment classification layer includes a crane classification layer, the business equipment quantity prediction results include a crane quantity prediction result;

In the case where the business equipment classification layer includes an unmanned card collection classification layer, the business equipment quantity prediction result includes an unmanned card collection quantity prediction result;

In the case where the business equipment classification layer includes an intelligent tally classification layer, the business equipment quantity prediction results include intelligent tally quantity prediction results.

Based on any of the above embodiments, the private network planning results include at least one of equipment quantity prediction results, equipment cost results, maintenance cost results, service fee results, network capacity results, and total quotation results; the determination module 330 also Used for:

When the private network planning results include equipment cost results, determine the equipment cost results based on the equipment quantity prediction results and the preset equipment cost unit price;

If the private network planning result includes a maintenance cost result, determine the maintenance cost result based on the equipment quantity prediction result and the preset maintenance cost unit price;

When the private network planning result includes a service fee result, determine the service fee result based on the device quantity prediction result and the preset service fee unit price;

When the private network planning result includes a network capacity result, determine the network capacity result based on the device quantity prediction result and the preset single device capability;

In the case where the private network planning result includes a total quotation result, based on at least one of the equipment cost result, the maintenance cost result, the service fee result, and the contract period indicated by the service parameters, Determine the total quote result.

Based on any of the above embodiments, the site parameters include offshore depth and/or berth shoreline length.

Based on any of the above embodiments, the service parameters include at least one of contract period, package mode, and yard service;

The yard business includes at least one of yard crane, unmanned card collection, smart tally, first combined business, second combined business, third combined business and fourth combined business;

The first combined business includes yard crane and unmanned card collection, the second combined business includes unmanned card collection and smart tally, the third combined business includes yard crane and smart tally, and the third combined business includes yard crane and smart tally. The four integrated businesses include yard cranes, unmanned card collection and smart tallying.

Figure 4 illustrates a schematic diagram of the physical structure of an electronic device. As shown in Figure 4, the electronic device may include: a processor (processor) 410, a communications interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440. Among them, the processor 410, the communication interface 420, and the memory 430 complete communication with each other through the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a private network planning method. The method includes: obtaining the site parameters and service parameters of the port to be planned, the service parameters are determined based on the selected business model, the The port to be planned is the port of the private network to be planned; the site parameters and the business parameters are input into the equipment quantity prediction model, and the equipment quantity prediction results output by the equipment quantity prediction model are obtained; based on the equipment quantity prediction results, Determine the private network planning results of the port to be planned.

In addition, the above-mentioned logical instructions in the memory 430 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the relevant technology or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several The instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code. .

On the other hand, the present disclosure also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can Execute the private network planning method provided by the above methods. The method includes: obtaining the site parameters and business parameters of the port to be planned. The business parameters are determined based on the selected business model. The port to be planned is the private network to be planned. port of the network; input the site parameters and the business parameters into the equipment quantity prediction model to obtain the equipment quantity prediction results output by the equipment quantity prediction model; determine the port to be planned based on the equipment quantity prediction results Private network planning results.

In another aspect, the present disclosure also provides a non-transitory computer-readable storage medium on which a computer program is stored. The computer program is implemented when executed by a processor to execute the private network planning method provided by each of the above methods. The method The method includes: obtaining the site parameters and business parameters of the port to be planned, the business parameters are determined based on the selected business model, and the port to be planned is the port of the private network to be planned; inputting the site parameters and the business parameters Go to the equipment quantity prediction model to obtain the equipment quantity prediction result output by the equipment quantity prediction model; based on the equipment quantity prediction result, determine the private network planning result of the port to be planned.

The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in One location, or it can be distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Persons of ordinary skill in the art can understand and implement the method without any creative effort.

Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions can be embodied in the form of software products in essence or in part that contribute to related technologies. The computer software products can be stored in computer-readable storage media, such as ROM/RAM, disks. , optical disk, etc., including a number of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present disclosure, but not to limit it; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still be Modifications may be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions may be made to some of the technical features; however, these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims (10)

1. A private network planning method, including:

   Obtain the site parameters and business parameters of the port to be planned, the business parameters are determined based on the selected business model, and the port to be planned is the port of the private network to be planned;

   Input the site parameters and the business parameters into the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the equipment quantity prediction model;

   Based on the equipment quantity prediction result, the private network planning result of the port to be planned is determined.
2. The private network planning method according to claim 1, wherein the input of the site parameters and the service parameters into the equipment quantity prediction model to obtain the equipment quantity prediction result output by the equipment quantity prediction model includes:

   Input the site parameters and the business parameters into the feature mapping layer of the equipment quantity prediction model, and obtain the site characteristics and business characteristics output by the feature mapping layer;

   Input the site characteristics and the business characteristics into the classification layer of the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the classification layer;

   Wherein, the classification layer is trained based on sample site parameters and sample service parameters, and the number of sample devices corresponding to the sample site parameters and the sample service parameters.
3. The private network planning method according to claim 2, wherein the classification layer includes a communication equipment classification layer, and the site characteristics and the business characteristics are input into the classification layer of the equipment quantity prediction model, and we obtain The prediction results of the number of devices output by the classification layer include:

   Input the site characteristics and the business characteristics into the communication equipment classification layer, and obtain the prediction result of the number of communication equipment output by the communication equipment classification layer;

   Wherein, the communication equipment classification layer includes an active antenna unit AAU classification layer and/or a baseband board classification layer;

   In the case where the communication device classification layer includes an AAU classification layer, the communication device number prediction result includes an AAU number prediction result;

   In the case where the communication equipment classification layer includes a baseband board classification layer, the communication equipment quantity prediction result includes a baseband board quantity prediction result.
4. The private network planning method according to claim 2, wherein the classification layer includes a service equipment classification layer, and the site characteristics and the service characteristics are input into the classification layer of the equipment quantity prediction model to obtain The prediction results of the number of devices output by the classification layer include:

   Input the site characteristics and the service characteristics into the service equipment classification layer, and obtain the service equipment quantity prediction result output by the service equipment classification layer;

   Wherein, the business equipment classification layer includes at least one of a crane classification layer, an unmanned card collection classification layer, and an intelligent tally classification layer;

   In the case where the business equipment classification layer includes a crane classification layer, the business equipment quantity prediction results include a crane quantity prediction result;

   In the case where the business equipment classification layer includes an unmanned card collection classification layer, the business equipment quantity prediction result includes an unmanned card collection quantity prediction result;

   In the case where the business equipment classification layer includes an intelligent tally classification layer, the business equipment quantity prediction results include intelligent tally quantity prediction results.
5. The private network planning method according to claim 1, wherein the private network planning results include at least one of equipment quantity prediction results, equipment cost results, maintenance cost results, service fee results, network capacity results, and total quotation results. A sort of;

   Determining the private network planning results of the port to be planned based on the equipment quantity prediction results includes:

   When the private network planning results include equipment cost results, determine the equipment cost results based on the equipment quantity prediction results and the preset equipment cost unit price;

   If the private network planning result includes a maintenance cost result, determine the maintenance cost result based on the equipment quantity prediction result and the preset maintenance cost unit price;

   When the private network planning result includes a service fee result, determine the service fee result based on the device quantity prediction result and the preset service fee unit price;

   When the private network planning result includes a network capacity result, determine the network capacity result based on the device quantity prediction result and the preset single device capability;

   In the case where the private network planning result includes a total quotation result, based on at least one of the equipment cost result, the maintenance cost result, the service fee result, and the contract period indicated by the service parameters, Determine the total quote result.
6. The private network planning method according to any one of claims 1 to 5, wherein the site parameters include offshore depth and/or berth shoreline length.
7. The private network planning method according to any one of claims 1 to 5, wherein the service parameters include at least one of contract period, package mode, and yard service;

   The yard business includes at least one of yard crane, unmanned card collection, smart tally, first combined business, second combined business, third combined business and fourth combined business;

   The first combined business includes yard crane and unmanned card collection, the second combined business includes unmanned card collection and smart tally, the third combined business includes yard crane and smart tally, and the third combined business includes yard crane and smart tally. The four integrated businesses include yard cranes, unmanned card collection and smart tallying.
8. A private network planning device, including:

   The acquisition module is used to obtain the site parameters and business parameters of the port to be planned. The business parameters are determined based on the selected business model. The port to be planned is the port of the private network to be planned;

   A prediction module, configured to input the site parameters and the business parameters into the equipment quantity prediction model, and obtain the equipment quantity prediction results output by the equipment quantity prediction model;

   A determination module, configured to determine the private network planning results of the port to be planned based on the equipment quantity prediction results.
9. An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the computer program as claimed in any one of claims 1 to 7 is implemented. Describe the private network planning method.
10. A non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the private network planning method according to any one of claims 1 to 7 is implemented.

Images