CN-122027468-A - Network resource pre-coverage method and computer program product

CN122027468ACN 122027468 ACN122027468 ACN 122027468ACN-122027468-A

Abstract

The present disclosure provides a network resource pre-overlay method and computer program product by obtaining data of a first enterprise that has been subject to an address change within a preset time. And generating a network resource coverage prediction model for predicting the port variation by using the user data, the network variation index, the port demand number, the port margin and the port variation of the first enterprise. The network resource coverage prediction model can predict the port variation of the target building when an enterprise moves into the target building, so as to provide a guiding basis for the target building to perform network resource coverage. Compared with manual experience, the method can provide more accurate data support, ensure that the back-end resources can meet the requirements of the front end, and achieve efficient utilization of the resources.

Inventors

DANG ZHIJUN
Nie Jianya
ZHU TINGHUI
ZHANG HAOJIE
LAN WANSHUN
LIU FUSHENG
ZHU JIAN
WU WEI
Cai Tieguang

Assignees

中国移动通信集团广东有限公司
中国移动通信集团有限公司

Dates

Publication Date: 20260512
Application Date: 20260107

Claims (15)

1. A method for pre-coverage of network resources, comprising: Acquiring user data of a first enterprise, first network resource data of a first building, second network resource data of a second building and third network resource data of the first enterprise, wherein the first building is a building where the first enterprise is located before changing an address, and the second building is a building where the first enterprise is located after changing the address; And determining a network resource coverage prediction model based on the user data, the first network resource data, the second network resource data and the third network resource data, so as to perform network resource pre-coverage construction on the target building by using the network resource coverage prediction model.
2. The network resource pre-overlay method of claim 1, wherein the first enterprise is configured as an enterprise that has changed address within a preset time, and the user data includes at least one or more of enterprise industry, enterprise scale, broadband tariffs.
3. The network resource pre-coverage method of claim 2, wherein the first network resource data comprises at least network access information of the first building.
4. The network resource pre-overlay method of claim 3, wherein the second network resource data includes at least the network access information of the second building, a port margin of the second building when the first enterprise enters the second building but does not occupy the second building port, and a port variation of the second building when the first enterprise enters the second building.
5. The network resource pre-coverage method of claim 4, wherein the third network resource data comprises at least a number of port requirements occupied by the first enterprise at the first building.
6. The network resource pre-overlay method of claim 5, wherein the obtaining user data of a first enterprise, first network resource data of a first building, second network resource data of a second building, and third network resource data of the first enterprise comprises: Determining a plurality of first enterprises with address change in the preset time; Determining the first building and the second building corresponding to each first enterprise, and And acquiring the user data and the third network resource data of each first enterprise, the first network resource data of each first building and the second network resource data of each second building.
7. The network resource pre-coverage method of claim 6, wherein said determining a network resource coverage prediction model based on said user data, said first network resource data, said second network resource data, and said third network resource data comprises: Determining a training set, wherein the training set at least comprises input data and output data; Building a predictive model, and The predictive model is trained based on the training set to determine the network resource coverage predictive model.
8. The network resource pre-coverage method of claim 7, wherein said determining a training set, said training set comprising at least input data and output data, comprises: determining the user data, the network change index of the first enterprise, the port allowance and the port demand quantity as input variables; Determining the port variation as an output variable, and The training set is determined from a plurality of the user data, a plurality of the first network resource data, a plurality of the second network resource data, and a plurality of the third network resource data based on input variables and output variables.
9. The network resource pre-coverage method of claim 8, wherein determining the network variation index comprises: Determining a network access variation of the first enterprise based on the network access information of the first building and the network access information of the second building corresponding to the first enterprise, wherein the network access information at least comprises a network access sum of the buildings; Determining network access variation of a plurality of first enterprises and A network variation index of the first enterprise is determined based on a minimum of the network access variations among the plurality of buildings, a maximum of the network access variations among the plurality of buildings, and the network access variations of the first enterprise.
10. The network resource pre-coverage method of claim 7, wherein the constructing a predictive model comprises determining a structure, a training function, and a training number of the predictive model, the structure of the predictive model comprising at least a number of input layer neurons, a number of output layer neurons, and a number of hidden layer neurons, the number of hidden layer neurons being determined based at least on the number of input layer neurons and the number of output layer neurons.
11. The network resource pre-coverage method of claim 8, further comprising: determining a test set from a plurality of the user data, a plurality of the first network resource data, a plurality of the second network resource data, and a plurality of the third network resource data based on the input variable and the output variable, and And verifying the network resource coverage prediction model based on the test set.
12. The network resource pre-coverage method of claim 11, wherein said validating the network resource coverage prediction model based on the test set comprises: dividing the test set into a plurality of test groups based on the difference value of the port numbers of the building occupied before and after the address change of the first enterprise; training the network resource coverage prediction model to obtain a predicted port variation of the second building corresponding to the first enterprise using the user data, the network variation index, the port margin, and the port demand quantity in the test set, and And verifying the network resource coverage prediction model based on the predicted port variation and the port variation of the second building in the test group.
13. The network resource pre-coverage method of claim 9, further comprising: determining a second enterprise newly migrated to the target building; Judging whether the second enterprise is a new registered enterprise or not based on the data information of the second enterprise; Determining a third enterprise proximate to the second enterprise in response to the second enterprise being the new registered enterprise, and And training the network resource coverage prediction model based on the user data of the third enterprise, the network change index, the port demand number and the port allowance of the second building corresponding to the third enterprise so as to perform network resource pre-coverage construction on the target building.
14. The network resource pre-coverage method of claim 13, further comprising: determining user data of the second enterprise, the network change index, the port demand quantity, the port margin of the second building corresponding to the second enterprise, and And training the network resource coverage prediction model based on the user data of the second enterprise, the network change index, the port allowance and the port demand number so as to perform network resource pre-coverage construction on the target building.
15. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the network resource pre-coverage method according to any of claims 1 to 14.

Description

Network resource pre-coverage method and computer program product Technical Field The present disclosure relates to the field of wireless communication technologies, and in particular, to a network resource pre-coverage method and a computer program product. Background Under the background of digital transformation, intelligent upgrading and fusion innovation of various industries in the whole society, the optical communication network has the advantages of large bandwidth, long distance, low cost and the like, and is a preferred scheme for high-speed data transmission at a fixed position. At present, when a communication network has a new access requirement, the experience of a network side personnel is often relied on to judge how to plan network resources, the process often lacks powerful data support, has larger errors compared with the actual network use condition, and cannot accurately determine the network resource pre-coverage requirement of a building. Disclosure of Invention The present disclosure provides a network resource pre-coverage method and computer program product. And constructing a network resource coverage prediction model through historical data, so that an accurate theoretical basis is provided for the construction of the network resource pre-coverage of the target building. In one aspect, the embodiment provides a network resource pre-coverage method, which comprises the steps of obtaining user data of a first enterprise, first network resource data of a first building, second network resource data of a second building and third network resource data of the first enterprise, wherein the first building is a building where the first enterprise is located before an address is changed, the second building is a building where the first enterprise is located after the address is changed, and determining a network resource coverage prediction model based on the user data, the first network resource data, the second network resource data and the third network resource data so as to perform network resource pre-coverage construction on a target building by using the network resource coverage prediction model. In an embodiment of the present disclosure, the first enterprise is configured as an enterprise that has been subject to address changes within a preset time, and the user data includes at least one or more of an enterprise industry, an enterprise scale, and a broadband tariff. In an embodiment of the disclosure, the first network resource data includes at least network access information of the first building. In an embodiment of the disclosure, the second network resource data at least includes network access information of the second building, a port allowance of the second building when the first enterprise enters the second building but does not occupy a port of the second building, and a port variation of the second building when the first enterprise enters the second building. In an embodiment of the present disclosure, the third network resource data includes at least a port demand number occupied by the first enterprise at the first building. In an embodiment of the disclosure, acquiring user data of a first enterprise, first network resource data of a first building, second network resource data of a second building, and third network resource data of the first enterprise includes determining a plurality of first enterprises that have undergone address change within a preset time, determining a first building and a second building corresponding to each first enterprise, and acquiring user data and third network resource data of each first enterprise, first network resource data of each first building, and second network resource data of each second building. In an embodiment of the present disclosure, determining a network resource coverage prediction model based on user data, first network resource data, second network resource data, and third network resource data includes determining a training set, the training set including at least input data and output data, constructing a prediction model, and training the prediction model based on the training set to determine the network resource coverage prediction model. In an embodiment of the present disclosure, determining a training set including at least input data and output data includes determining user data, a network variation index of a first enterprise, a port margin, and a port demand number as input variables, determining a port variation as output variables, and determining the training set from among a plurality of user data, a plurality of first network resource data, a plurality of second network resource data, and a plurality of third network resource data based on the input variables and the output variables. In an embodiment of the disclosure, determining a network variation index includes determining a network access variation of a first enterprise based on network access information of the first building and